diff --git a/Dockerfile.cpu b/Dockerfile.cpu
new file mode 100644
index 0000000000000000000000000000000000000000..dceffbfc595003c75680694d24e4de72536559c7
--- /dev/null
+++ b/Dockerfile.cpu
@@ -0,0 +1,35 @@
+FROM python:3.9
+
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends \
+        ffmpeg
+
+RUN python3 -m pip install --upgrade pip
+
+# Python installation
+WORKDIR /usr/src/app
+
+# Force CPU versions of torch
+RUN pip3 install \
+    torch==1.13.1+cpu \
+    torchaudio==0.13.1+cpu \
+    -f https://download.pytorch.org/whl/torch_stable.html
+
+# Note: First installing the python requirements permits to save time when re-building after a source change.
+COPY requirements.txt /usr/src/app/requirements.txt
+RUN cd /usr/src/app/ && pip3 install -r requirements.txt
+
+# Copy source
+COPY setup.py /usr/src/app/setup.py
+COPY whisper_timestamped /usr/src/app/whisper_timestamped
+
+# Install
+RUN cd /usr/src/app/ && pip3 install ".[dev]"
+
+# Cleanup
+RUN rm -R /usr/src/app/requirements.txt /usr/src/app/setup.py /usr/src/app/whisper_timestamped
+
+# Copy tests
+COPY tests /usr/src/app/tests
+
+ENTRYPOINT ["/bin/bash"]
\ No newline at end of file
diff --git a/LICENCE b/LICENCE
new file mode 100644
index 0000000000000000000000000000000000000000..0ad25db4bd1d86c452db3f9602ccdbe172438f52
--- /dev/null
+++ b/LICENCE
@@ -0,0 +1,661 @@
+                    GNU AFFERO GENERAL PUBLIC LICENSE
+                       Version 3, 19 November 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The GNU Affero General Public License is a free, copyleft license for
+software and other kinds of works, specifically designed to ensure
+cooperation with the community in the case of network server software.
+
+  The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works.  By contrast,
+our General Public Licenses are intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
+
+  Developers that use our General Public Licenses protect your rights
+with two steps: (1) assert copyright on the software, and (2) offer
+you this License which gives you legal permission to copy, distribute
+and/or modify the software.
+
+  A secondary benefit of defending all users' freedom is that
+improvements made in alternate versions of the program, if they
+receive widespread use, become available for other developers to
+incorporate.  Many developers of free software are heartened and
+encouraged by the resulting cooperation.  However, in the case of
+software used on network servers, this result may fail to come about.
+The GNU General Public License permits making a modified version and
+letting the public access it on a server without ever releasing its
+source code to the public.
+
+  The GNU Affero General Public License is designed specifically to
+ensure that, in such cases, the modified source code becomes available
+to the community.  It requires the operator of a network server to
+provide the source code of the modified version running there to the
+users of that server.  Therefore, public use of a modified version, on
+a publicly accessible server, gives the public access to the source
+code of the modified version.
+
+  An older license, called the Affero General Public License and
+published by Affero, was designed to accomplish similar goals.  This is
+a different license, not a version of the Affero GPL, but Affero has
+released a new version of the Affero GPL which permits relicensing under
+this license.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                       TERMS AND CONDITIONS
+
+  0. Definitions.
+
+  "This License" refers to version 3 of the GNU Affero General Public License.
+
+  "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
+
+  "The Program" refers to any copyrightable work licensed under this
+License.  Each licensee is addressed as "you".  "Licensees" and
+"recipients" may be individuals or organizations.
+
+  To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy.  The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
+
+  A "covered work" means either the unmodified Program or a work based
+on the Program.
+
+  To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy.  Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
+
+  To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies.  Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
+
+  An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License.  If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
+
+  1. Source Code.
+
+  The "source code" for a work means the preferred form of the work
+for making modifications to it.  "Object code" means any non-source
+form of a work.
+
+  A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
+
+  The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form.  A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
+
+  The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities.  However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work.  For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+  The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
+
+  The Corresponding Source for a work in source code form is that
+same work.
+
+  2. Basic Permissions.
+
+  All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met.  This License explicitly affirms your unlimited
+permission to run the unmodified Program.  The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work.  This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
+
+  You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force.  You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright.  Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
+
+  Conveying under any other circumstances is permitted solely under
+the conditions stated below.  Sublicensing is not allowed; section 10
+makes it unnecessary.
+
+  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+
+  No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
+
+  When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+  4. Conveying Verbatim Copies.
+
+  You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+  You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+  5. Conveying Modified Source Versions.
+
+  You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+    a) The work must carry prominent notices stating that you modified
+    it, and giving a relevant date.
+
+    b) The work must carry prominent notices stating that it is
+    released under this License and any conditions added under section
+    7.  This requirement modifies the requirement in section 4 to
+    "keep intact all notices".
+
+    c) You must license the entire work, as a whole, under this
+    License to anyone who comes into possession of a copy.  This
+    License will therefore apply, along with any applicable section 7
+    additional terms, to the whole of the work, and all its parts,
+    regardless of how they are packaged.  This License gives no
+    permission to license the work in any other way, but it does not
+    invalidate such permission if you have separately received it.
+
+    d) If the work has interactive user interfaces, each must display
+    Appropriate Legal Notices; however, if the Program has interactive
+    interfaces that do not display Appropriate Legal Notices, your
+    work need not make them do so.
+
+  A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit.  Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+  6. Conveying Non-Source Forms.
+
+  You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+    a) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by the
+    Corresponding Source fixed on a durable physical medium
+    customarily used for software interchange.
+
+    b) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by a
+    written offer, valid for at least three years and valid for as
+    long as you offer spare parts or customer support for that product
+    model, to give anyone who possesses the object code either (1) a
+    copy of the Corresponding Source for all the software in the
+    product that is covered by this License, on a durable physical
+    medium customarily used for software interchange, for a price no
+    more than your reasonable cost of physically performing this
+    conveying of source, or (2) access to copy the
+    Corresponding Source from a network server at no charge.
+
+    c) Convey individual copies of the object code with a copy of the
+    written offer to provide the Corresponding Source.  This
+    alternative is allowed only occasionally and noncommercially, and
+    only if you received the object code with such an offer, in accord
+    with subsection 6b.
+
+    d) Convey the object code by offering access from a designated
+    place (gratis or for a charge), and offer equivalent access to the
+    Corresponding Source in the same way through the same place at no
+    further charge.  You need not require recipients to copy the
+    Corresponding Source along with the object code.  If the place to
+    copy the object code is a network server, the Corresponding Source
+    may be on a different server (operated by you or a third party)
+    that supports equivalent copying facilities, provided you maintain
+    clear directions next to the object code saying where to find the
+    Corresponding Source.  Regardless of what server hosts the
+    Corresponding Source, you remain obligated to ensure that it is
+    available for as long as needed to satisfy these requirements.
+
+    e) Convey the object code using peer-to-peer transmission, provided
+    you inform other peers where the object code and Corresponding
+    Source of the work are being offered to the general public at no
+    charge under subsection 6d.
+
+  A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+  A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling.  In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage.  For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product.  A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+  "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source.  The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+  If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information.  But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+  The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed.  Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+  Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+  7. Additional Terms.
+
+  "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law.  If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+  When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it.  (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.)  You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+  Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+    a) Disclaiming warranty or limiting liability differently from the
+    terms of sections 15 and 16 of this License; or
+
+    b) Requiring preservation of specified reasonable legal notices or
+    author attributions in that material or in the Appropriate Legal
+    Notices displayed by works containing it; or
+
+    c) Prohibiting misrepresentation of the origin of that material, or
+    requiring that modified versions of such material be marked in
+    reasonable ways as different from the original version; or
+
+    d) Limiting the use for publicity purposes of names of licensors or
+    authors of the material; or
+
+    e) Declining to grant rights under trademark law for use of some
+    trade names, trademarks, or service marks; or
+
+    f) Requiring indemnification of licensors and authors of that
+    material by anyone who conveys the material (or modified versions of
+    it) with contractual assumptions of liability to the recipient, for
+    any liability that these contractual assumptions directly impose on
+    those licensors and authors.
+
+  All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10.  If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term.  If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+  If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+  Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+  8. Termination.
+
+  You may not propagate or modify a covered work except as expressly
+provided under this License.  Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+  However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+  Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+  Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License.  If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+  9. Acceptance Not Required for Having Copies.
+
+  You are not required to accept this License in order to receive or
+run a copy of the Program.  Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance.  However,
+nothing other than this License grants you permission to propagate or
+modify any covered work.  These actions infringe copyright if you do
+not accept this License.  Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+  10. Automatic Licensing of Downstream Recipients.
+
+  Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License.  You are not responsible
+for enforcing compliance by third parties with this License.
+
+  An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations.  If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+  You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License.  For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+  11. Patents.
+
+  A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based.  The
+work thus licensed is called the contributor's "contributor version".
+
+  A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version.  For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+  Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+  In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement).  To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+  If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients.  "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+  If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+  A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License.  You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+  Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+  12. No Surrender of Others' Freedom.
+
+  If conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all.  For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+  13. Remote Network Interaction; Use with the GNU General Public License.
+
+  Notwithstanding any other provision of this License, if you modify the
+Program, your modified version must prominently offer all users
+interacting with it remotely through a computer network (if your version
+supports such interaction) an opportunity to receive the Corresponding
+Source of your version by providing access to the Corresponding Source
+from a network server at no charge, through some standard or customary
+means of facilitating copying of software.  This Corresponding Source
+shall include the Corresponding Source for any work covered by version 3
+of the GNU General Public License that is incorporated pursuant to the
+following paragraph.
+
+  Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU General Public License into a single
+combined work, and to convey the resulting work.  The terms of this
+License will continue to apply to the part which is the covered work,
+but the work with which it is combined will remain governed by version
+3 of the GNU General Public License.
+
+  14. Revised Versions of this License.
+
+  The Free Software Foundation may publish revised and/or new versions of
+the GNU Affero General Public License from time to time.  Such new versions
+will be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+  Each version is given a distinguishing version number.  If the
+Program specifies that a certain numbered version of the GNU Affero General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation.  If the Program does not specify a version number of the
+GNU Affero General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+  If the Program specifies that a proxy can decide which future
+versions of the GNU Affero General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+  Later license versions may give you additional or different
+permissions.  However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+  15. Disclaimer of Warranty.
+
+  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. Limitation of Liability.
+
+  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGES.
+
+  17. Interpretation of Sections 15 and 16.
+
+  If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU Affero General Public License as published
+    by the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Affero General Public License for more details.
+
+    You should have received a copy of the GNU Affero General Public License
+    along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+  If your software can interact with users remotely through a computer
+network, you should also make sure that it provides a way for users to
+get its source.  For example, if your program is a web application, its
+interface could display a "Source" link that leads users to an archive
+of the code.  There are many ways you could offer source, and different
+solutions will be better for different programs; see section 13 for the
+specific requirements.
+
+  You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU AGPL, see
+<https://www.gnu.org/licenses/>.
diff --git a/figs/VAD_auditok.png b/figs/VAD_auditok.png
new file mode 100644
index 0000000000000000000000000000000000000000..9dbaa4adc16a3082df4a6b17ddb3e4dbc0d4c227
Binary files /dev/null and b/figs/VAD_auditok.png differ
diff --git a/figs/VAD_silero_v3.1.png b/figs/VAD_silero_v3.1.png
new file mode 100644
index 0000000000000000000000000000000000000000..5216ef11328b5437fe715c63f66c0b095e0442d8
Binary files /dev/null and b/figs/VAD_silero_v3.1.png differ
diff --git a/figs/VAD_silero_v4.0.png b/figs/VAD_silero_v4.0.png
new file mode 100644
index 0000000000000000000000000000000000000000..3b516f9a5ac8eebf05688f7689ae49ae0dc4f24b
Binary files /dev/null and b/figs/VAD_silero_v4.0.png differ
diff --git a/figs/example_alignement_plot.png b/figs/example_alignement_plot.png
new file mode 100644
index 0000000000000000000000000000000000000000..504528ece2e36b2cec4990ccdfcdc1d771a14beb
Binary files /dev/null and b/figs/example_alignement_plot.png differ
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000000000000000000000000000000000000..f5a15670950a2dca208b867d00ff408e2cd577f3
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,3 @@
+Cython
+dtw-python
+openai-whisper
\ No newline at end of file
diff --git a/setup.py b/setup.py
new file mode 100644
index 0000000000000000000000000000000000000000..e49e71edb8ef44278a78b9cdc4bdb88ef6eb0512
--- /dev/null
+++ b/setup.py
@@ -0,0 +1,58 @@
+import os
+
+from setuptools import setup, find_packages
+
+install_requires = [
+    "Cython",
+    "dtw-python",
+    "openai-whisper",
+]
+
+required_packages_filename = os.path.join(os.path.dirname(__file__), "requirements.txt")
+if os.path.exists(required_packages_filename):
+    install_requires2 = [l.strip() for l in open(required_packages_filename).readlines()]
+    assert install_requires == install_requires2, f"requirements.txt is not up-to-date: {install_requires} != {install_requires2}"
+
+version = None
+license = None
+with open(os.path.join(os.path.dirname(__file__), "whisper_timestamped", "transcribe.py")) as f:
+    for line in f:
+        if line.strip().startswith("__version__"):
+            version = line.split("=")[1].strip().strip("\"'")
+            if version and license:
+                break
+        if line.strip().startswith("__license__"):
+            license = line.split("=")[1].strip().strip("\"'")
+            if version and license:
+                break
+assert version and license
+
+description="Multi-lingual Automatic Speech Recognition (ASR) based on Whisper models, with accurate word timestamps, access to language detection confidence, several options for Voice Activity Detection (VAD), and more."
+
+setup(
+    name="whisper-timestamped",
+    py_modules=["whisper_timestamped"],
+    version=version,
+    description=description,
+    long_description=description+"\nSee https://github.com/linto-ai/whisper-timestamped for more information.",
+    long_description_content_type='text/markdown',
+    python_requires=">=3.7",
+    author="Jeronymous",
+    url="https://github.com/linto-ai/whisper-timestamped",
+    license=license,
+    packages=find_packages(exclude=["tests*"]),
+    install_requires=install_requires,
+    entry_points = {
+        'console_scripts': [
+            'whisper_timestamped=whisper_timestamped.transcribe:cli',
+            'whisper_timestamped_make_subtitles=whisper_timestamped.make_subtitles:cli'
+        ],
+    },
+    include_package_data=True,
+    extras_require={
+        'dev': ['matplotlib', 'transformers'],
+        'vad_silero': ['onnxruntime', 'torchaudio'],
+        'vad_auditok': ['auditok'],
+        'test': ['jsonschema'],
+    },
+)
diff --git a/tests/__init__.py b/tests/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..8b137891791fe96927ad78e64b0aad7bded08bdc
--- /dev/null
+++ b/tests/__init__.py
@@ -0,0 +1 @@
+
diff --git a/tests/data/apollo11.mp3 b/tests/data/apollo11.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..d9246ca9f73701df5270dd342bdca2d316eda5b3
Binary files /dev/null and b/tests/data/apollo11.mp3 differ
diff --git a/tests/data/bonjour.wav b/tests/data/bonjour.wav
new file mode 100644
index 0000000000000000000000000000000000000000..f03944e35c448f2226923356f7208d0234a6419a
Binary files /dev/null and b/tests/data/bonjour.wav differ
diff --git a/tests/data/bonjour_vous_allez_bien.mp3 b/tests/data/bonjour_vous_allez_bien.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..53bd078e6610cca0bddf7dbcaff2b2a991028c51
Binary files /dev/null and b/tests/data/bonjour_vous_allez_bien.mp3 differ
diff --git a/tests/data/empty.mp3 b/tests/data/empty.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..a73b2f2f14d2f33beb872041f64abc0208eee70b
Binary files /dev/null and b/tests/data/empty.mp3 differ
diff --git a/tests/data/empty.wav b/tests/data/empty.wav
new file mode 100644
index 0000000000000000000000000000000000000000..a15eb0580e1a5cd7cd4b4d3e610155a3a967c81b
Binary files /dev/null and b/tests/data/empty.wav differ
diff --git a/tests/data/gaenswein15.mp3 b/tests/data/gaenswein15.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..48689cfe8af4a3873f7c988793bd48ab12523094
Binary files /dev/null and b/tests/data/gaenswein15.mp3 differ
diff --git a/tests/data/gloria.mp3 b/tests/data/gloria.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..8289f3989deb8bccd19b102b9530974600791798
Binary files /dev/null and b/tests/data/gloria.mp3 differ
diff --git a/tests/data/japanese.mp3 b/tests/data/japanese.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..10337faea507f73c0add491837ad997e5656741a
Binary files /dev/null and b/tests/data/japanese.mp3 differ
diff --git a/tests/data/laugh1.mp3 b/tests/data/laugh1.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..c564abe8c4f87cbaa1ee1998f17a36a1592f5c61
Binary files /dev/null and b/tests/data/laugh1.mp3 differ
diff --git a/tests/data/laugh2.mp3 b/tests/data/laugh2.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..b8fb8840f31d416eab241969a1b5f2da067a6acf
Binary files /dev/null and b/tests/data/laugh2.mp3 differ
diff --git a/tests/data/no_punctuations.mp3.words.json b/tests/data/no_punctuations.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..46d20abcf33869ed2f4eda32988e19619cfaf7b4
--- /dev/null
+++ b/tests/data/no_punctuations.mp3.words.json
@@ -0,0 +1,68 @@
+{
+  "text": " Dis-moi, est-ce que l'avion vole?",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.4,
+      "end": 2.34,
+      "text": " Dis-moi, est-ce que l'avion vole?",
+      "tokens": [
+        50364,
+        4208,
+        12,
+        29292,
+        11,
+        871,
+        12,
+        384,
+        631,
+        287,
+        6,
+        706,
+        313,
+        49877,
+        2506,
+        50494
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3014036907869227,
+      "compression_ratio": 0.8048780487804879,
+      "no_speech_prob": 0.05134102329611778,
+      "confidence": 0.925,
+      "words": [
+        {
+          "text": "Dis-moi",
+          "start": 0.4,
+          "end": 1.36,
+          "confidence": 0.801
+        },
+        {
+          "text": "est-ce",
+          "start": 1.36,
+          "end": 1.52,
+          "confidence": 0.966
+        },
+        {
+          "text": "que",
+          "start": 1.52,
+          "end": 1.64,
+          "confidence": 0.977
+        },
+        {
+          "text": "l'avion",
+          "start": 1.64,
+          "end": 2.02,
+          "confidence": 0.994
+        },
+        {
+          "text": "vole",
+          "start": 2.02,
+          "end": 2.34,
+          "confidence": 0.891
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/data/punctuations.mp3 b/tests/data/punctuations.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..b797032d15a7fc9cd575f79bd6ec43e37e66e555
Binary files /dev/null and b/tests/data/punctuations.mp3 differ
diff --git a/tests/data/radio_short.mp3 b/tests/data/radio_short.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..1772d945c050cb88948fb3b4d7f84657e06a90d7
Binary files /dev/null and b/tests/data/radio_short.mp3 differ
diff --git a/tests/data/smartphone.mp3 b/tests/data/smartphone.mp3
new file mode 100644
index 0000000000000000000000000000000000000000..9c1c12473bf6c5485426a4f563b1385fd039f243
Binary files /dev/null and b/tests/data/smartphone.mp3 differ
diff --git a/tests/data/smartphone.mp3.words.json b/tests/data/smartphone.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..8cf211f5b9abc1b522e115e190503add6af20a12
--- /dev/null
+++ b/tests/data/smartphone.mp3.words.json
@@ -0,0 +1,4802 @@
+{
+  "text": " C'est évident ce que dit Nicolas, mais je ne me l'étais jamais formulé comme ça. Ce qui fait la force du smartphone, c'est pas seulement l'accumulation des fonctions, mais la manière dont elles interagissent entre elles. Ce qui dit d'ailleurs sur la photo, c'est hyper convaincant. Alors évidemment, il faudrait ajouter les interfaces. L'écran tactile a été beaucoup très souvent mentionné. Mais bon, il faut dire qu'il profite aussi de 20 ans pendant lesquels les ordinateurs nous ont appris à cliquer sur des icônes. Sauf que le smartphone ajoute le toucher, ce qui rend le contact plus direct, plus sensible. Et puis évidemment, il faudrait parler aussi des applications qui permettent de contourner le côté touffu de la navigation web pour aller directement au but. Bref, tout ça, ce sont les conditions qui permettent de créer cet objet dont Nicolas dit qu'il est vraisemblablement inédit dans l'histoire de l'humanité. Mais ça, ça soulève une autre interrogation. Est-ce que le fait que cet objet soit inédit induit que notre rapport à lui est aussi un rapport inédit? Je veux dire, est-ce que le rapport qu'on a au smartphone est comparable à celui qu'on entretenait à d'autres objets techniques comme la voiture ou le téléphone? Il n'y a pas d'équivalent en fait. Et donc cette espèce de nouveauté dans la relation à l'objet, c'est fascinant et terrifiant. Parce qu'on a l'impression, comme le disent les utilisateurs et les services, d'être dépendants de cet objet, d'induire en fait une espèce de relation, de médiation avec le monde qui rend de l'ampleur et qui amène aussi à des formes de rejet. Donc, à objet inédit, rapport inédit. Et ce rapport, si j'en crois Nicolas, serait caractérisé par un mélange de dépendance et de rejet. Bon, en vrai, il faudrait remonter très très finement toute l'histoire des objets techniques et de leur insertion dans nos vies pour déterminer si ce rapport est totalement inédit. Mais j'ai l'impression comme ça que Nicolas ne se trompe pas vraiment. Pour autant que je sache, il y a eu plein de discussions autour de la voiture ou même du téléphone. Mais la dépendance n'était pas du même ordre. Donc le rejet non plus n'était pas du même ordre. On peut adorer sa bagnole, en avoir besoin pour plein de choses. Et bien, le soir, quand on va se coucher, on la laisse. On ne l'a pas dans la main quand on est au lit, on ne l'emmène pas au chiottes. On pouvait être énervé par son môme qui occupait la ligne de téléphone pendant une heure chaque soir pour discuter avec un copain. Mais ça ne ressemblait pas à ce qu'on peut ressentir à voir ce même môme aujourd'hui, continuellement avec son smartphone dans la main, comme si c'était une sorte de pacemaker externe, comme si le lâcher allait entraîner sa mort immédiate. Bon, je dis ça pour le môme, mais c'est évidemment valable pour nous aussi. Donc, rapport inédit. D'accord. Mais pourquoi a-t-on l'impression qu'on n'en sortira jamais? Est-ce qu'il faut en remettre la faute sur les gens qui ont créé cet outil merveilleux et diabolique, et diabolique parce que merveilleux? Les économistes parlent de dépendance du sentier. C'est l'idée qu'on est sur un sentier qui a été établi, soit volontairement en marchant dessus, soit en définissant des bornes, en définissant une signalétique.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.38,
+      "end": 3.62,
+      "text": " C'est évident ce que dit Nicolas, mais je ne me l'étais jamais formulé comme ça.",
+      "tokens": [
+        383,
+        6,
+        377,
+        20090,
+        1078,
+        1769,
+        631,
+        6176,
+        38268,
+        11,
+        2420,
+        1506,
+        408,
+        385,
+        287,
+        6,
+        22824,
+        14540,
+        49990,
+        526,
+        5173,
+        2788,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2362671656324374,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.15368737280368805,
+      "confidence": 0.935,
+      "words": [
+        {
+          "text": "C'est",
+          "start": 0.38,
+          "end": 0.58,
+          "confidence": 0.961
+        },
+        {
+          "text": "évident",
+          "start": 0.58,
+          "end": 0.88,
+          "confidence": 0.984
+        },
+        {
+          "text": "ce",
+          "start": 0.88,
+          "end": 1.02,
+          "confidence": 0.663
+        },
+        {
+          "text": "que",
+          "start": 1.02,
+          "end": 1.08,
+          "confidence": 0.989
+        },
+        {
+          "text": "dit",
+          "start": 1.08,
+          "end": 1.2,
+          "confidence": 0.994
+        },
+        {
+          "text": "Nicolas,",
+          "start": 1.2,
+          "end": 1.78,
+          "confidence": 0.91
+        },
+        {
+          "text": "mais",
+          "start": 1.78,
+          "end": 1.9,
+          "confidence": 0.979
+        },
+        {
+          "text": "je",
+          "start": 1.9,
+          "end": 2.24,
+          "confidence": 0.981
+        },
+        {
+          "text": "ne",
+          "start": 2.24,
+          "end": 2.34,
+          "confidence": 0.837
+        },
+        {
+          "text": "me",
+          "start": 2.34,
+          "end": 2.38,
+          "confidence": 0.821
+        },
+        {
+          "text": "l'étais",
+          "start": 2.38,
+          "end": 2.58,
+          "confidence": 0.971
+        },
+        {
+          "text": "jamais",
+          "start": 2.58,
+          "end": 2.84,
+          "confidence": 0.989
+        },
+        {
+          "text": "formulé",
+          "start": 2.84,
+          "end": 3.26,
+          "confidence": 0.908
+        },
+        {
+          "text": "comme",
+          "start": 3.26,
+          "end": 3.42,
+          "confidence": 0.993
+        },
+        {
+          "text": "ça.",
+          "start": 3.42,
+          "end": 3.62,
+          "confidence": 0.975
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 4.08,
+      "end": 7.92,
+      "text": " Ce qui fait la force du smartphone, c'est pas seulement l'accumulation des fonctions,",
+      "tokens": [
+        8257,
+        1956,
+        3887,
+        635,
+        3464,
+        1581,
+        13307,
+        11,
+        269,
+        6,
+        377,
+        1736,
+        27772,
+        287,
+        6,
+        8476,
+        449,
+        2776,
+        730,
+        17290,
+        3916,
+        11
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2362671656324374,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.15368737280368805,
+      "confidence": 0.93,
+      "words": [
+        {
+          "text": "Ce",
+          "start": 4.08,
+          "end": 4.26,
+          "confidence": 0.952
+        },
+        {
+          "text": "qui",
+          "start": 4.26,
+          "end": 4.34,
+          "confidence": 0.958
+        },
+        {
+          "text": "fait",
+          "start": 4.34,
+          "end": 4.48,
+          "confidence": 0.567
+        },
+        {
+          "text": "la",
+          "start": 4.48,
+          "end": 4.66,
+          "confidence": 0.972
+        },
+        {
+          "text": "force",
+          "start": 4.66,
+          "end": 5.0,
+          "confidence": 0.999
+        },
+        {
+          "text": "du",
+          "start": 5.0,
+          "end": 5.2,
+          "confidence": 0.996
+        },
+        {
+          "text": "smartphone,",
+          "start": 5.2,
+          "end": 5.88,
+          "confidence": 0.912
+        },
+        {
+          "text": "c'est",
+          "start": 5.88,
+          "end": 6.12,
+          "confidence": 0.879
+        },
+        {
+          "text": "pas",
+          "start": 6.12,
+          "end": 6.26,
+          "confidence": 0.991
+        },
+        {
+          "text": "seulement",
+          "start": 6.26,
+          "end": 6.52,
+          "confidence": 0.999
+        },
+        {
+          "text": "l'accumulation",
+          "start": 6.52,
+          "end": 7.38,
+          "confidence": 0.958
+        },
+        {
+          "text": "des",
+          "start": 7.38,
+          "end": 7.56,
+          "confidence": 0.983
+        },
+        {
+          "text": "fonctions,",
+          "start": 7.56,
+          "end": 7.92,
+          "confidence": 0.987
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 8.32,
+      "end": 10.88,
+      "text": " mais la manière dont elles interagissent entre elles.",
+      "tokens": [
+        2420,
+        635,
+        22267,
+        9400,
+        23576,
+        728,
+        559,
+        25450,
+        3962,
+        23576,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2362671656324374,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.15368737280368805,
+      "confidence": 0.977,
+      "words": [
+        {
+          "text": "mais",
+          "start": 8.32,
+          "end": 8.44,
+          "confidence": 0.992
+        },
+        {
+          "text": "la",
+          "start": 8.44,
+          "end": 8.6,
+          "confidence": 0.995
+        },
+        {
+          "text": "manière",
+          "start": 8.6,
+          "end": 8.9,
+          "confidence": 0.999
+        },
+        {
+          "text": "dont",
+          "start": 8.9,
+          "end": 9.1,
+          "confidence": 0.978
+        },
+        {
+          "text": "elles",
+          "start": 9.1,
+          "end": 9.48,
+          "confidence": 0.967
+        },
+        {
+          "text": "interagissent",
+          "start": 9.48,
+          "end": 10.32,
+          "confidence": 0.964
+        },
+        {
+          "text": "entre",
+          "start": 10.32,
+          "end": 10.58,
+          "confidence": 0.955
+        },
+        {
+          "text": "elles.",
+          "start": 10.58,
+          "end": 10.88,
+          "confidence": 0.989
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 10.96,
+      "end": 13.0,
+      "text": " Ce qui dit d'ailleurs sur la photo, c'est hyper convaincant.",
+      "tokens": [
+        8257,
+        1956,
+        6176,
+        274,
+        6,
+        19400,
+        1022,
+        635,
+        5052,
+        11,
+        269,
+        6,
+        377,
+        9848,
+        3754,
+        491,
+        66,
+        394,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2362671656324374,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.15368737280368805,
+      "confidence": 0.906,
+      "words": [
+        {
+          "text": "Ce",
+          "start": 10.96,
+          "end": 11.16,
+          "confidence": 0.608
+        },
+        {
+          "text": "qui",
+          "start": 11.16,
+          "end": 11.22,
+          "confidence": 0.769
+        },
+        {
+          "text": "dit",
+          "start": 11.22,
+          "end": 11.4,
+          "confidence": 0.983
+        },
+        {
+          "text": "d'ailleurs",
+          "start": 11.4,
+          "end": 11.56,
+          "confidence": 0.985
+        },
+        {
+          "text": "sur",
+          "start": 11.56,
+          "end": 11.72,
+          "confidence": 0.48
+        },
+        {
+          "text": "la",
+          "start": 11.72,
+          "end": 11.78,
+          "confidence": 0.984
+        },
+        {
+          "text": "photo,",
+          "start": 11.78,
+          "end": 12.12,
+          "confidence": 0.994
+        },
+        {
+          "text": "c'est",
+          "start": 12.12,
+          "end": 12.2,
+          "confidence": 0.997
+        },
+        {
+          "text": "hyper",
+          "start": 12.2,
+          "end": 12.42,
+          "confidence": 0.993
+        },
+        {
+          "text": "convaincant.",
+          "start": 12.42,
+          "end": 13.0,
+          "confidence": 0.982
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 13.34,
+      "end": 16.02,
+      "text": " Alors évidemment, il faudrait ajouter les interfaces.",
+      "tokens": [
+        9946,
+        24724,
+        11,
+        1930,
+        38694,
+        8645,
+        17680,
+        23985,
+        1512,
+        28416,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2362671656324374,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.15368737280368805,
+      "confidence": 0.912,
+      "words": [
+        {
+          "text": "Alors",
+          "start": 13.34,
+          "end": 13.62,
+          "confidence": 0.584
+        },
+        {
+          "text": "évidemment,",
+          "start": 13.62,
+          "end": 14.34,
+          "confidence": 0.832
+        },
+        {
+          "text": "il",
+          "start": 14.34,
+          "end": 14.38,
+          "confidence": 0.953
+        },
+        {
+          "text": "faudrait",
+          "start": 14.38,
+          "end": 14.74,
+          "confidence": 0.996
+        },
+        {
+          "text": "ajouter",
+          "start": 14.74,
+          "end": 15.16,
+          "confidence": 0.992
+        },
+        {
+          "text": "les",
+          "start": 15.16,
+          "end": 15.52,
+          "confidence": 0.985
+        },
+        {
+          "text": "interfaces.",
+          "start": 15.52,
+          "end": 16.02,
+          "confidence": 0.984
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 0,
+      "start": 16.22,
+      "end": 19.36,
+      "text": " L'écran tactile a été beaucoup très souvent mentionné.",
+      "tokens": [
+        441,
+        6,
+        9062,
+        4257,
+        47319,
+        257,
+        8862,
+        8796,
+        5732,
+        20847,
+        2152,
+        15055,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2362671656324374,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.15368737280368805,
+      "confidence": 0.923,
+      "words": [
+        {
+          "text": "L'écran",
+          "start": 16.22,
+          "end": 16.7,
+          "confidence": 0.996
+        },
+        {
+          "text": "tactile",
+          "start": 16.7,
+          "end": 17.06,
+          "confidence": 0.986
+        },
+        {
+          "text": "a",
+          "start": 17.06,
+          "end": 17.26,
+          "confidence": 0.98
+        },
+        {
+          "text": "été",
+          "start": 17.26,
+          "end": 17.88,
+          "confidence": 0.974
+        },
+        {
+          "text": "beaucoup",
+          "start": 17.88,
+          "end": 18.28,
+          "confidence": 0.976
+        },
+        {
+          "text": "très",
+          "start": 18.28,
+          "end": 18.62,
+          "confidence": 0.447
+        },
+        {
+          "text": "souvent",
+          "start": 18.62,
+          "end": 18.9,
+          "confidence": 0.996
+        },
+        {
+          "text": "mentionné.",
+          "start": 18.9,
+          "end": 19.36,
+          "confidence": 0.978
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 0,
+      "start": 19.84,
+      "end": 25.26,
+      "text": " Mais bon, il faut dire qu'il profite aussi de 20 ans pendant lesquels les ordinateurs nous ont appris à cliquer sur des icônes.",
+      "tokens": [
+        6313,
+        4428,
+        11,
+        1930,
+        8487,
+        1264,
+        421,
+        6,
+        388,
+        1740,
+        642,
+        6212,
+        368,
+        945,
+        1567,
+        17338,
+        1512,
+        358,
+        1625,
+        1512,
+        4792,
+        13923,
+        2156,
+        4666,
+        6592,
+        724,
+        5714,
+        1531,
+        596,
+        23909,
+        1022,
+        730,
+        4376,
+        2851,
+        4081,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2362671656324374,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.15368737280368805,
+      "confidence": 0.92,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 19.84,
+          "end": 20.22,
+          "confidence": 0.943
+        },
+        {
+          "text": "bon,",
+          "start": 20.22,
+          "end": 20.52,
+          "confidence": 0.666
+        },
+        {
+          "text": "il",
+          "start": 20.52,
+          "end": 20.6,
+          "confidence": 0.99
+        },
+        {
+          "text": "faut",
+          "start": 20.6,
+          "end": 20.7,
+          "confidence": 0.99
+        },
+        {
+          "text": "dire",
+          "start": 20.7,
+          "end": 20.84,
+          "confidence": 0.995
+        },
+        {
+          "text": "qu'il",
+          "start": 20.84,
+          "end": 20.96,
+          "confidence": 0.88
+        },
+        {
+          "text": "profite",
+          "start": 20.96,
+          "end": 21.26,
+          "confidence": 0.995
+        },
+        {
+          "text": "aussi",
+          "start": 21.26,
+          "end": 21.68,
+          "confidence": 0.972
+        },
+        {
+          "text": "de",
+          "start": 21.68,
+          "end": 21.9,
+          "confidence": 0.97
+        },
+        {
+          "text": "20",
+          "start": 21.9,
+          "end": 22.1,
+          "confidence": 0.812
+        },
+        {
+          "text": "ans",
+          "start": 22.1,
+          "end": 22.32,
+          "confidence": 0.997
+        },
+        {
+          "text": "pendant",
+          "start": 22.32,
+          "end": 22.48,
+          "confidence": 0.723
+        },
+        {
+          "text": "lesquels",
+          "start": 22.48,
+          "end": 22.92,
+          "confidence": 0.98
+        },
+        {
+          "text": "les",
+          "start": 22.92,
+          "end": 23.04,
+          "confidence": 0.71
+        },
+        {
+          "text": "ordinateurs",
+          "start": 23.04,
+          "end": 23.54,
+          "confidence": 0.966
+        },
+        {
+          "text": "nous",
+          "start": 23.54,
+          "end": 23.72,
+          "confidence": 0.602
+        },
+        {
+          "text": "ont",
+          "start": 23.72,
+          "end": 23.82,
+          "confidence": 0.974
+        },
+        {
+          "text": "appris",
+          "start": 23.82,
+          "end": 24.1,
+          "confidence": 0.991
+        },
+        {
+          "text": "à",
+          "start": 24.1,
+          "end": 24.24,
+          "confidence": 0.828
+        },
+        {
+          "text": "cliquer",
+          "start": 24.24,
+          "end": 24.5,
+          "confidence": 0.989
+        },
+        {
+          "text": "sur",
+          "start": 24.5,
+          "end": 24.66,
+          "confidence": 0.984
+        },
+        {
+          "text": "des",
+          "start": 24.66,
+          "end": 24.94,
+          "confidence": 0.971
+        },
+        {
+          "text": "icônes.",
+          "start": 24.94,
+          "end": 25.26,
+          "confidence": 0.992
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 2534,
+      "start": 25.42,
+      "end": 30.64,
+      "text": " Sauf que le smartphone ajoute le toucher, ce qui rend le contact plus direct, plus sensible.",
+      "tokens": [
+        318,
+        9507,
+        631,
+        476,
+        13307,
+        17680,
+        14040,
+        476,
+        2557,
+        260,
+        11,
+        1769,
+        1956,
+        6125,
+        476,
+        3385,
+        1804,
+        2047,
+        11,
+        1804,
+        25380,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07923513396173461,
+      "compression_ratio": 1.6254416961130742,
+      "no_speech_prob": 3.4465685985196615e-06,
+      "confidence": 0.969,
+      "words": [
+        {
+          "text": "Sauf",
+          "start": 25.42,
+          "end": 25.76,
+          "confidence": 0.99
+        },
+        {
+          "text": "que",
+          "start": 25.76,
+          "end": 26.26,
+          "confidence": 0.996
+        },
+        {
+          "text": "le",
+          "start": 26.26,
+          "end": 26.66,
+          "confidence": 0.632
+        },
+        {
+          "text": "smartphone",
+          "start": 26.66,
+          "end": 27.06,
+          "confidence": 0.996
+        },
+        {
+          "text": "ajoute",
+          "start": 27.06,
+          "end": 27.44,
+          "confidence": 0.991
+        },
+        {
+          "text": "le",
+          "start": 27.44,
+          "end": 27.62,
+          "confidence": 0.992
+        },
+        {
+          "text": "toucher,",
+          "start": 27.62,
+          "end": 28.18,
+          "confidence": 0.988
+        },
+        {
+          "text": "ce",
+          "start": 28.18,
+          "end": 28.22,
+          "confidence": 0.989
+        },
+        {
+          "text": "qui",
+          "start": 28.22,
+          "end": 28.28,
+          "confidence": 1.0
+        },
+        {
+          "text": "rend",
+          "start": 28.28,
+          "end": 28.48,
+          "confidence": 0.994
+        },
+        {
+          "text": "le",
+          "start": 28.48,
+          "end": 28.68,
+          "confidence": 0.993
+        },
+        {
+          "text": "contact",
+          "start": 28.68,
+          "end": 29.1,
+          "confidence": 0.999
+        },
+        {
+          "text": "plus",
+          "start": 29.1,
+          "end": 29.46,
+          "confidence": 0.985
+        },
+        {
+          "text": "direct,",
+          "start": 29.46,
+          "end": 30.22,
+          "confidence": 0.995
+        },
+        {
+          "text": "plus",
+          "start": 30.22,
+          "end": 30.26,
+          "confidence": 0.994
+        },
+        {
+          "text": "sensible.",
+          "start": 30.26,
+          "end": 30.64,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 2534,
+      "start": 31.04,
+      "end": 37.82,
+      "text": " Et puis évidemment, il faudrait parler aussi des applications qui permettent de contourner le côté touffu de la navigation web pour aller directement au but.",
+      "tokens": [
+        3790,
+        9093,
+        24724,
+        11,
+        1930,
+        38694,
+        8645,
+        16421,
+        6212,
+        730,
+        5821,
+        1956,
+        21540,
+        317,
+        368,
+        21234,
+        1193,
+        476,
+        18437,
+        10095,
+        602,
+        84,
+        368,
+        635,
+        17346,
+        3670,
+        2016,
+        8722,
+        37297,
+        1609,
+        457,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07923513396173461,
+      "compression_ratio": 1.6254416961130742,
+      "no_speech_prob": 3.4465685985196615e-06,
+      "confidence": 0.892,
+      "words": [
+        {
+          "text": "Et",
+          "start": 31.04,
+          "end": 31.22,
+          "confidence": 0.97
+        },
+        {
+          "text": "puis",
+          "start": 31.22,
+          "end": 31.36,
+          "confidence": 0.971
+        },
+        {
+          "text": "évidemment,",
+          "start": 31.36,
+          "end": 31.7,
+          "confidence": 0.875
+        },
+        {
+          "text": "il",
+          "start": 31.7,
+          "end": 31.74,
+          "confidence": 0.993
+        },
+        {
+          "text": "faudrait",
+          "start": 31.74,
+          "end": 31.94,
+          "confidence": 0.995
+        },
+        {
+          "text": "parler",
+          "start": 31.94,
+          "end": 32.12,
+          "confidence": 0.839
+        },
+        {
+          "text": "aussi",
+          "start": 32.12,
+          "end": 32.34,
+          "confidence": 0.977
+        },
+        {
+          "text": "des",
+          "start": 32.34,
+          "end": 32.48,
+          "confidence": 0.994
+        },
+        {
+          "text": "applications",
+          "start": 32.48,
+          "end": 32.9,
+          "confidence": 0.993
+        },
+        {
+          "text": "qui",
+          "start": 32.9,
+          "end": 33.18,
+          "confidence": 0.482
+        },
+        {
+          "text": "permettent",
+          "start": 33.18,
+          "end": 33.74,
+          "confidence": 0.992
+        },
+        {
+          "text": "de",
+          "start": 33.74,
+          "end": 33.96,
+          "confidence": 0.884
+        },
+        {
+          "text": "contourner",
+          "start": 33.96,
+          "end": 34.42,
+          "confidence": 0.959
+        },
+        {
+          "text": "le",
+          "start": 34.42,
+          "end": 34.52,
+          "confidence": 0.777
+        },
+        {
+          "text": "côté",
+          "start": 34.52,
+          "end": 34.8,
+          "confidence": 0.984
+        },
+        {
+          "text": "touffu",
+          "start": 34.8,
+          "end": 35.32,
+          "confidence": 0.741
+        },
+        {
+          "text": "de",
+          "start": 35.32,
+          "end": 35.72,
+          "confidence": 0.882
+        },
+        {
+          "text": "la",
+          "start": 35.72,
+          "end": 35.78,
+          "confidence": 0.992
+        },
+        {
+          "text": "navigation",
+          "start": 35.78,
+          "end": 36.24,
+          "confidence": 0.994
+        },
+        {
+          "text": "web",
+          "start": 36.24,
+          "end": 36.6,
+          "confidence": 0.854
+        },
+        {
+          "text": "pour",
+          "start": 36.6,
+          "end": 36.78,
+          "confidence": 0.583
+        },
+        {
+          "text": "aller",
+          "start": 36.78,
+          "end": 36.98,
+          "confidence": 0.987
+        },
+        {
+          "text": "directement",
+          "start": 36.98,
+          "end": 37.52,
+          "confidence": 0.997
+        },
+        {
+          "text": "au",
+          "start": 37.52,
+          "end": 37.68,
+          "confidence": 0.967
+        },
+        {
+          "text": "but.",
+          "start": 37.68,
+          "end": 37.82,
+          "confidence": 0.995
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 2534,
+      "start": 37.82,
+      "end": 46.58,
+      "text": " Bref, tout ça, ce sont les conditions qui permettent de créer cet objet dont Nicolas dit qu'il est vraisemblablement inédit dans l'histoire de l'humanité.",
+      "tokens": [
+        49957,
+        11,
+        3486,
+        2788,
+        11,
+        1769,
+        4900,
+        1512,
+        4487,
+        1956,
+        21540,
+        317,
+        368,
+        32062,
+        8603,
+        14964,
+        9400,
+        38268,
+        6176,
+        421,
+        6,
+        388,
+        871,
+        6070,
+        271,
+        443,
+        5199,
+        712,
+        518,
+        294,
+        7811,
+        270,
+        2680,
+        287,
+        6,
+        29093,
+        368,
+        287,
+        6,
+        18796,
+        5066,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07923513396173461,
+      "compression_ratio": 1.6254416961130742,
+      "no_speech_prob": 3.4465685985196615e-06,
+      "confidence": 0.974,
+      "words": [
+        {
+          "text": "Bref,",
+          "start": 37.82,
+          "end": 38.76,
+          "confidence": 0.987
+        },
+        {
+          "text": "tout",
+          "start": 38.76,
+          "end": 38.98,
+          "confidence": 0.711
+        },
+        {
+          "text": "ça,",
+          "start": 38.98,
+          "end": 39.42,
+          "confidence": 0.995
+        },
+        {
+          "text": "ce",
+          "start": 39.42,
+          "end": 39.7,
+          "confidence": 0.993
+        },
+        {
+          "text": "sont",
+          "start": 39.7,
+          "end": 39.88,
+          "confidence": 0.999
+        },
+        {
+          "text": "les",
+          "start": 39.88,
+          "end": 40.16,
+          "confidence": 0.991
+        },
+        {
+          "text": "conditions",
+          "start": 40.16,
+          "end": 40.68,
+          "confidence": 0.995
+        },
+        {
+          "text": "qui",
+          "start": 40.68,
+          "end": 40.96,
+          "confidence": 0.997
+        },
+        {
+          "text": "permettent",
+          "start": 40.96,
+          "end": 41.46,
+          "confidence": 0.997
+        },
+        {
+          "text": "de",
+          "start": 41.46,
+          "end": 41.6,
+          "confidence": 0.998
+        },
+        {
+          "text": "créer",
+          "start": 41.6,
+          "end": 42.06,
+          "confidence": 0.998
+        },
+        {
+          "text": "cet",
+          "start": 42.06,
+          "end": 42.38,
+          "confidence": 0.998
+        },
+        {
+          "text": "objet",
+          "start": 42.38,
+          "end": 42.6,
+          "confidence": 0.994
+        },
+        {
+          "text": "dont",
+          "start": 42.6,
+          "end": 42.8,
+          "confidence": 0.78
+        },
+        {
+          "text": "Nicolas",
+          "start": 42.8,
+          "end": 43.26,
+          "confidence": 0.989
+        },
+        {
+          "text": "dit",
+          "start": 43.26,
+          "end": 43.5,
+          "confidence": 0.986
+        },
+        {
+          "text": "qu'il",
+          "start": 43.5,
+          "end": 43.7,
+          "confidence": 0.983
+        },
+        {
+          "text": "est",
+          "start": 43.7,
+          "end": 43.88,
+          "confidence": 0.991
+        },
+        {
+          "text": "vraisemblablement",
+          "start": 43.88,
+          "end": 44.98,
+          "confidence": 0.991
+        },
+        {
+          "text": "inédit",
+          "start": 44.98,
+          "end": 45.38,
+          "confidence": 0.981
+        },
+        {
+          "text": "dans",
+          "start": 45.38,
+          "end": 45.7,
+          "confidence": 0.969
+        },
+        {
+          "text": "l'histoire",
+          "start": 45.7,
+          "end": 45.98,
+          "confidence": 0.957
+        },
+        {
+          "text": "de",
+          "start": 45.98,
+          "end": 46.18,
+          "confidence": 0.999
+        },
+        {
+          "text": "l'humanité.",
+          "start": 46.18,
+          "end": 46.58,
+          "confidence": 0.992
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 2534,
+      "start": 46.6,
+      "end": 48.82,
+      "text": " Mais ça, ça soulève une autre interrogation.",
+      "tokens": [
+        6313,
+        2788,
+        11,
+        2788,
+        5133,
+        31397,
+        2251,
+        15081,
+        24871,
+        399,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07923513396173461,
+      "compression_ratio": 1.6254416961130742,
+      "no_speech_prob": 3.4465685985196615e-06,
+      "confidence": 0.969,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 46.6,
+          "end": 47.24,
+          "confidence": 0.845
+        },
+        {
+          "text": "ça,",
+          "start": 47.24,
+          "end": 47.72,
+          "confidence": 0.934
+        },
+        {
+          "text": "ça",
+          "start": 47.72,
+          "end": 47.76,
+          "confidence": 0.977
+        },
+        {
+          "text": "soulève",
+          "start": 47.76,
+          "end": 47.84,
+          "confidence": 0.993
+        },
+        {
+          "text": "une",
+          "start": 47.84,
+          "end": 48.02,
+          "confidence": 0.998
+        },
+        {
+          "text": "autre",
+          "start": 48.02,
+          "end": 48.26,
+          "confidence": 0.999
+        },
+        {
+          "text": "interrogation.",
+          "start": 48.26,
+          "end": 48.82,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 4884,
+      "start": 49.22,
+      "end": 55.46,
+      "text": " Est-ce que le fait que cet objet soit inédit induit que notre rapport à lui est aussi un rapport inédit?",
+      "tokens": [
+        4410,
+        12,
+        384,
+        631,
+        476,
+        3887,
+        631,
+        8603,
+        14964,
+        12703,
+        294,
+        7811,
+        270,
+        13716,
+        270,
+        631,
+        10349,
+        18018,
+        1531,
+        8783,
+        871,
+        6212,
+        517,
+        18018,
+        294,
+        7811,
+        270,
+        2506
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10683460109281225,
+      "compression_ratio": 1.662379421221865,
+      "no_speech_prob": 1.2805365258827806e-05,
+      "confidence": 0.988,
+      "words": [
+        {
+          "text": "Est-ce",
+          "start": 49.22,
+          "end": 49.62,
+          "confidence": 0.982
+        },
+        {
+          "text": "que",
+          "start": 49.62,
+          "end": 49.72,
+          "confidence": 0.991
+        },
+        {
+          "text": "le",
+          "start": 49.72,
+          "end": 49.82,
+          "confidence": 0.993
+        },
+        {
+          "text": "fait",
+          "start": 49.82,
+          "end": 49.98,
+          "confidence": 0.999
+        },
+        {
+          "text": "que",
+          "start": 49.98,
+          "end": 50.14,
+          "confidence": 0.991
+        },
+        {
+          "text": "cet",
+          "start": 50.14,
+          "end": 50.32,
+          "confidence": 0.991
+        },
+        {
+          "text": "objet",
+          "start": 50.32,
+          "end": 50.66,
+          "confidence": 0.997
+        },
+        {
+          "text": "soit",
+          "start": 50.66,
+          "end": 51.12,
+          "confidence": 0.995
+        },
+        {
+          "text": "inédit",
+          "start": 51.12,
+          "end": 51.8,
+          "confidence": 0.995
+        },
+        {
+          "text": "induit",
+          "start": 51.8,
+          "end": 52.32,
+          "confidence": 0.976
+        },
+        {
+          "text": "que",
+          "start": 52.32,
+          "end": 52.42,
+          "confidence": 0.983
+        },
+        {
+          "text": "notre",
+          "start": 52.42,
+          "end": 52.72,
+          "confidence": 0.996
+        },
+        {
+          "text": "rapport",
+          "start": 52.72,
+          "end": 53.28,
+          "confidence": 0.997
+        },
+        {
+          "text": "à",
+          "start": 53.28,
+          "end": 53.44,
+          "confidence": 0.978
+        },
+        {
+          "text": "lui",
+          "start": 53.44,
+          "end": 53.66,
+          "confidence": 0.999
+        },
+        {
+          "text": "est",
+          "start": 53.66,
+          "end": 54.02,
+          "confidence": 0.915
+        },
+        {
+          "text": "aussi",
+          "start": 54.02,
+          "end": 54.54,
+          "confidence": 0.995
+        },
+        {
+          "text": "un",
+          "start": 54.54,
+          "end": 54.7,
+          "confidence": 0.995
+        },
+        {
+          "text": "rapport",
+          "start": 54.7,
+          "end": 55.0,
+          "confidence": 0.996
+        },
+        {
+          "text": "inédit?",
+          "start": 55.0,
+          "end": 55.46,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 4884,
+      "start": 55.46,
+      "end": 63.12,
+      "text": " Je veux dire, est-ce que le rapport qu'on a au smartphone est comparable à celui qu'on entretenait à d'autres objets techniques comme la voiture ou le téléphone?",
+      "tokens": [
+        2588,
+        16389,
+        1264,
+        11,
+        871,
+        12,
+        384,
+        631,
+        476,
+        18018,
+        421,
+        6,
+        266,
+        257,
+        1609,
+        13307,
+        871,
+        25323,
+        1531,
+        22829,
+        421,
+        6,
+        266,
+        3962,
+        1147,
+        1001,
+        1531,
+        274,
+        6,
+        16752,
+        1111,
+        25349,
+        7512,
+        5173,
+        635,
+        38859,
+        2820,
+        476,
+        47159,
+        2506
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10683460109281225,
+      "compression_ratio": 1.662379421221865,
+      "no_speech_prob": 1.2805365258827806e-05,
+      "confidence": 0.965,
+      "words": [
+        {
+          "text": "Je",
+          "start": 55.46,
+          "end": 55.9,
+          "confidence": 0.879
+        },
+        {
+          "text": "veux",
+          "start": 55.9,
+          "end": 56.0,
+          "confidence": 0.988
+        },
+        {
+          "text": "dire,",
+          "start": 56.0,
+          "end": 56.24,
+          "confidence": 0.997
+        },
+        {
+          "text": "est-ce",
+          "start": 56.24,
+          "end": 56.36,
+          "confidence": 0.99
+        },
+        {
+          "text": "que",
+          "start": 56.36,
+          "end": 56.42,
+          "confidence": 0.99
+        },
+        {
+          "text": "le",
+          "start": 56.42,
+          "end": 56.58,
+          "confidence": 0.995
+        },
+        {
+          "text": "rapport",
+          "start": 56.58,
+          "end": 56.88,
+          "confidence": 0.998
+        },
+        {
+          "text": "qu'on",
+          "start": 56.88,
+          "end": 57.04,
+          "confidence": 0.985
+        },
+        {
+          "text": "a",
+          "start": 57.04,
+          "end": 57.18,
+          "confidence": 0.989
+        },
+        {
+          "text": "au",
+          "start": 57.18,
+          "end": 57.28,
+          "confidence": 0.967
+        },
+        {
+          "text": "smartphone",
+          "start": 57.28,
+          "end": 57.6,
+          "confidence": 0.994
+        },
+        {
+          "text": "est",
+          "start": 57.6,
+          "end": 57.92,
+          "confidence": 0.949
+        },
+        {
+          "text": "comparable",
+          "start": 57.92,
+          "end": 58.24,
+          "confidence": 0.997
+        },
+        {
+          "text": "à",
+          "start": 58.24,
+          "end": 58.48,
+          "confidence": 0.95
+        },
+        {
+          "text": "celui",
+          "start": 58.48,
+          "end": 58.66,
+          "confidence": 0.998
+        },
+        {
+          "text": "qu'on",
+          "start": 58.66,
+          "end": 58.9,
+          "confidence": 0.989
+        },
+        {
+          "text": "entretenait",
+          "start": 58.9,
+          "end": 59.32,
+          "confidence": 0.929
+        },
+        {
+          "text": "à",
+          "start": 59.32,
+          "end": 59.46,
+          "confidence": 0.959
+        },
+        {
+          "text": "d'autres",
+          "start": 59.46,
+          "end": 59.7,
+          "confidence": 0.997
+        },
+        {
+          "text": "objets",
+          "start": 59.7,
+          "end": 59.96,
+          "confidence": 0.991
+        },
+        {
+          "text": "techniques",
+          "start": 59.96,
+          "end": 60.46,
+          "confidence": 0.983
+        },
+        {
+          "text": "comme",
+          "start": 60.46,
+          "end": 60.88,
+          "confidence": 0.586
+        },
+        {
+          "text": "la",
+          "start": 60.88,
+          "end": 61.5,
+          "confidence": 0.987
+        },
+        {
+          "text": "voiture",
+          "start": 61.5,
+          "end": 62.06,
+          "confidence": 1.0
+        },
+        {
+          "text": "ou",
+          "start": 62.06,
+          "end": 62.36,
+          "confidence": 0.946
+        },
+        {
+          "text": "le",
+          "start": 62.36,
+          "end": 62.68,
+          "confidence": 0.998
+        },
+        {
+          "text": "téléphone?",
+          "start": 62.68,
+          "end": 63.12,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 4884,
+      "start": 63.36,
+      "end": 66.66,
+      "text": " Il n'y a pas d'équivalent en fait.",
+      "tokens": [
+        4416,
+        297,
+        6,
+        88,
+        257,
+        1736,
+        274,
+        6,
+        20183,
+        3576,
+        317,
+        465,
+        3887,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10683460109281225,
+      "compression_ratio": 1.662379421221865,
+      "no_speech_prob": 1.2805365258827806e-05,
+      "confidence": 0.936,
+      "words": [
+        {
+          "text": "Il",
+          "start": 63.36,
+          "end": 65.42,
+          "confidence": 0.778
+        },
+        {
+          "text": "n'y",
+          "start": 65.42,
+          "end": 65.48,
+          "confidence": 0.978
+        },
+        {
+          "text": "a",
+          "start": 65.48,
+          "end": 65.54,
+          "confidence": 0.992
+        },
+        {
+          "text": "pas",
+          "start": 65.54,
+          "end": 65.66,
+          "confidence": 0.999
+        },
+        {
+          "text": "d'équivalent",
+          "start": 65.66,
+          "end": 66.22,
+          "confidence": 0.995
+        },
+        {
+          "text": "en",
+          "start": 66.22,
+          "end": 66.42,
+          "confidence": 0.601
+        },
+        {
+          "text": "fait.",
+          "start": 66.42,
+          "end": 66.66,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 4884,
+      "start": 66.88,
+      "end": 71.52,
+      "text": " Et donc cette espèce de nouveauté dans la relation à l'objet, c'est fascinant et terrifiant.",
+      "tokens": [
+        3790,
+        5926,
+        5550,
+        7089,
+        30236,
+        368,
+        11456,
+        1375,
+        526,
+        2680,
+        635,
+        9721,
+        1531,
+        287,
+        6,
+        996,
+        7108,
+        11,
+        269,
+        6,
+        377,
+        7184,
+        259,
+        394,
+        1030,
+        7245,
+        351,
+        5798,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10683460109281225,
+      "compression_ratio": 1.662379421221865,
+      "no_speech_prob": 1.2805365258827806e-05,
+      "confidence": 0.953,
+      "words": [
+        {
+          "text": "Et",
+          "start": 66.88,
+          "end": 66.98,
+          "confidence": 0.599
+        },
+        {
+          "text": "donc",
+          "start": 66.98,
+          "end": 67.08,
+          "confidence": 0.902
+        },
+        {
+          "text": "cette",
+          "start": 67.08,
+          "end": 67.28,
+          "confidence": 0.712
+        },
+        {
+          "text": "espèce",
+          "start": 67.28,
+          "end": 67.54,
+          "confidence": 0.996
+        },
+        {
+          "text": "de",
+          "start": 67.54,
+          "end": 67.68,
+          "confidence": 0.999
+        },
+        {
+          "text": "nouveauté",
+          "start": 67.68,
+          "end": 68.48,
+          "confidence": 0.979
+        },
+        {
+          "text": "dans",
+          "start": 68.48,
+          "end": 68.66,
+          "confidence": 0.98
+        },
+        {
+          "text": "la",
+          "start": 68.66,
+          "end": 68.94,
+          "confidence": 0.995
+        },
+        {
+          "text": "relation",
+          "start": 68.94,
+          "end": 69.22,
+          "confidence": 0.998
+        },
+        {
+          "text": "à",
+          "start": 69.22,
+          "end": 69.38,
+          "confidence": 0.997
+        },
+        {
+          "text": "l'objet,",
+          "start": 69.38,
+          "end": 70.24,
+          "confidence": 0.997
+        },
+        {
+          "text": "c'est",
+          "start": 70.24,
+          "end": 70.38,
+          "confidence": 0.98
+        },
+        {
+          "text": "fascinant",
+          "start": 70.38,
+          "end": 70.64,
+          "confidence": 0.978
+        },
+        {
+          "text": "et",
+          "start": 70.64,
+          "end": 70.76,
+          "confidence": 0.965
+        },
+        {
+          "text": "terrifiant.",
+          "start": 70.76,
+          "end": 71.52,
+          "confidence": 0.977
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 4884,
+      "start": 71.62,
+      "end": 76.48,
+      "text": " Parce qu'on a l'impression, comme le disent les utilisateurs et les services, d'être dépendants de cet objet,",
+      "tokens": [
+        20429,
+        421,
+        6,
+        266,
+        257,
+        287,
+        6,
+        36107,
+        11,
+        5173,
+        476,
+        37313,
+        1512,
+        33643,
+        25929,
+        1030,
+        1512,
+        3328,
+        11,
+        274,
+        6,
+        9498,
+        45768,
+        1719,
+        368,
+        8603,
+        14964,
+        11
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10683460109281225,
+      "compression_ratio": 1.662379421221865,
+      "no_speech_prob": 1.2805365258827806e-05,
+      "confidence": 0.815,
+      "words": [
+        {
+          "text": "Parce",
+          "start": 71.62,
+          "end": 71.86,
+          "confidence": 0.514
+        },
+        {
+          "text": "qu'on",
+          "start": 71.86,
+          "end": 72.12,
+          "confidence": 0.938
+        },
+        {
+          "text": "a",
+          "start": 72.12,
+          "end": 72.44,
+          "confidence": 0.982
+        },
+        {
+          "text": "l'impression,",
+          "start": 72.44,
+          "end": 73.56,
+          "confidence": 0.998
+        },
+        {
+          "text": "comme",
+          "start": 73.56,
+          "end": 73.84,
+          "confidence": 0.964
+        },
+        {
+          "text": "le",
+          "start": 73.84,
+          "end": 74.0,
+          "confidence": 0.984
+        },
+        {
+          "text": "disent",
+          "start": 74.0,
+          "end": 74.2,
+          "confidence": 0.998
+        },
+        {
+          "text": "les",
+          "start": 74.2,
+          "end": 74.4,
+          "confidence": 0.994
+        },
+        {
+          "text": "utilisateurs",
+          "start": 74.4,
+          "end": 74.84,
+          "confidence": 0.997
+        },
+        {
+          "text": "et",
+          "start": 74.84,
+          "end": 74.96,
+          "confidence": 0.331
+        },
+        {
+          "text": "les",
+          "start": 74.96,
+          "end": 75.0,
+          "confidence": 0.775
+        },
+        {
+          "text": "services,",
+          "start": 75.0,
+          "end": 75.22,
+          "confidence": 0.217
+        },
+        {
+          "text": "d'être",
+          "start": 75.22,
+          "end": 75.42,
+          "confidence": 0.768
+        },
+        {
+          "text": "dépendants",
+          "start": 75.42,
+          "end": 75.96,
+          "confidence": 0.79
+        },
+        {
+          "text": "de",
+          "start": 75.96,
+          "end": 76.08,
+          "confidence": 0.985
+        },
+        {
+          "text": "cet",
+          "start": 76.08,
+          "end": 76.26,
+          "confidence": 0.996
+        },
+        {
+          "text": "objet,",
+          "start": 76.26,
+          "end": 76.48,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 7684,
+      "start": 76.86,
+      "end": 83.26,
+      "text": " d'induire en fait une espèce de relation, de médiation avec le monde qui rend de l'ampleur et qui amène aussi à des formes de rejet.",
+      "tokens": [
+        274,
+        6,
+        471,
+        43612,
+        465,
+        3887,
+        2251,
+        7089,
+        30236,
+        368,
+        9721,
+        11,
+        368,
+        42436,
+        399,
+        4163,
+        476,
+        10431,
+        1956,
+        6125,
+        368,
+        287,
+        6,
+        335,
+        781,
+        374,
+        1030,
+        1956,
+        669,
+        18832,
+        6212,
+        1531,
+        730,
+        1254,
+        279,
+        368,
+        319,
+        7108,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06925634075613583,
+      "compression_ratio": 1.6787003610108304,
+      "no_speech_prob": 5.771887572336709e-06,
+      "confidence": 0.917,
+      "words": [
+        {
+          "text": "d'induire",
+          "start": 76.86,
+          "end": 77.08,
+          "confidence": 0.84
+        },
+        {
+          "text": "en",
+          "start": 77.08,
+          "end": 77.24,
+          "confidence": 0.617
+        },
+        {
+          "text": "fait",
+          "start": 77.24,
+          "end": 77.34,
+          "confidence": 0.994
+        },
+        {
+          "text": "une",
+          "start": 77.34,
+          "end": 77.52,
+          "confidence": 0.983
+        },
+        {
+          "text": "espèce",
+          "start": 77.52,
+          "end": 77.88,
+          "confidence": 0.996
+        },
+        {
+          "text": "de",
+          "start": 77.88,
+          "end": 78.48,
+          "confidence": 0.997
+        },
+        {
+          "text": "relation,",
+          "start": 78.48,
+          "end": 78.6,
+          "confidence": 0.601
+        },
+        {
+          "text": "de",
+          "start": 78.6,
+          "end": 78.94,
+          "confidence": 0.987
+        },
+        {
+          "text": "médiation",
+          "start": 78.94,
+          "end": 79.52,
+          "confidence": 0.997
+        },
+        {
+          "text": "avec",
+          "start": 79.52,
+          "end": 79.74,
+          "confidence": 0.967
+        },
+        {
+          "text": "le",
+          "start": 79.74,
+          "end": 79.92,
+          "confidence": 0.998
+        },
+        {
+          "text": "monde",
+          "start": 79.92,
+          "end": 80.64,
+          "confidence": 0.992
+        },
+        {
+          "text": "qui",
+          "start": 80.64,
+          "end": 81.1,
+          "confidence": 0.695
+        },
+        {
+          "text": "rend",
+          "start": 81.1,
+          "end": 81.64,
+          "confidence": 0.907
+        },
+        {
+          "text": "de",
+          "start": 81.64,
+          "end": 81.78,
+          "confidence": 0.714
+        },
+        {
+          "text": "l'ampleur",
+          "start": 81.78,
+          "end": 82.02,
+          "confidence": 0.987
+        },
+        {
+          "text": "et",
+          "start": 82.02,
+          "end": 82.12,
+          "confidence": 0.931
+        },
+        {
+          "text": "qui",
+          "start": 82.12,
+          "end": 82.24,
+          "confidence": 0.976
+        },
+        {
+          "text": "amène",
+          "start": 82.24,
+          "end": 82.36,
+          "confidence": 0.973
+        },
+        {
+          "text": "aussi",
+          "start": 82.36,
+          "end": 82.56,
+          "confidence": 0.939
+        },
+        {
+          "text": "à",
+          "start": 82.56,
+          "end": 82.64,
+          "confidence": 0.941
+        },
+        {
+          "text": "des",
+          "start": 82.64,
+          "end": 82.72,
+          "confidence": 0.992
+        },
+        {
+          "text": "formes",
+          "start": 82.72,
+          "end": 82.9,
+          "confidence": 0.993
+        },
+        {
+          "text": "de",
+          "start": 82.9,
+          "end": 83.02,
+          "confidence": 0.997
+        },
+        {
+          "text": "rejet.",
+          "start": 83.02,
+          "end": 83.26,
+          "confidence": 0.884
+        }
+      ]
+    },
+    {
+      "id": 17,
+      "seek": 7684,
+      "start": 83.94,
+      "end": 87.8,
+      "text": " Donc, à objet inédit, rapport inédit.",
+      "tokens": [
+        7477,
+        11,
+        1531,
+        14964,
+        294,
+        7811,
+        270,
+        11,
+        18018,
+        294,
+        7811,
+        270,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06925634075613583,
+      "compression_ratio": 1.6787003610108304,
+      "no_speech_prob": 5.771887572336709e-06,
+      "confidence": 0.962,
+      "words": [
+        {
+          "text": "Donc,",
+          "start": 83.94,
+          "end": 84.94,
+          "confidence": 0.971
+        },
+        {
+          "text": "à",
+          "start": 84.94,
+          "end": 84.98,
+          "confidence": 0.881
+        },
+        {
+          "text": "objet",
+          "start": 84.98,
+          "end": 85.36,
+          "confidence": 0.827
+        },
+        {
+          "text": "inédit,",
+          "start": 85.36,
+          "end": 86.56,
+          "confidence": 0.993
+        },
+        {
+          "text": "rapport",
+          "start": 86.56,
+          "end": 87.0,
+          "confidence": 0.981
+        },
+        {
+          "text": "inédit.",
+          "start": 87.0,
+          "end": 87.8,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 18,
+      "seek": 7684,
+      "start": 88.02,
+      "end": 95.14,
+      "text": " Et ce rapport, si j'en crois Nicolas, serait caractérisé par un mélange de dépendance et de rejet.",
+      "tokens": [
+        3790,
+        1769,
+        18018,
+        11,
+        1511,
+        361,
+        6,
+        268,
+        21724,
+        38268,
+        11,
+        23139,
+        1032,
+        578,
+        4198,
+        22118,
+        971,
+        517,
+        41953,
+        933,
+        368,
+        45768,
+        719,
+        1030,
+        368,
+        319,
+        7108,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06925634075613583,
+      "compression_ratio": 1.6787003610108304,
+      "no_speech_prob": 5.771887572336709e-06,
+      "confidence": 0.972,
+      "words": [
+        {
+          "text": "Et",
+          "start": 88.02,
+          "end": 88.48,
+          "confidence": 0.992
+        },
+        {
+          "text": "ce",
+          "start": 88.48,
+          "end": 88.86,
+          "confidence": 0.975
+        },
+        {
+          "text": "rapport,",
+          "start": 88.86,
+          "end": 89.28,
+          "confidence": 0.998
+        },
+        {
+          "text": "si",
+          "start": 89.28,
+          "end": 89.56,
+          "confidence": 0.999
+        },
+        {
+          "text": "j'en",
+          "start": 89.56,
+          "end": 89.84,
+          "confidence": 0.996
+        },
+        {
+          "text": "crois",
+          "start": 89.84,
+          "end": 89.88,
+          "confidence": 0.984
+        },
+        {
+          "text": "Nicolas,",
+          "start": 89.88,
+          "end": 90.54,
+          "confidence": 0.683
+        },
+        {
+          "text": "serait",
+          "start": 90.54,
+          "end": 90.94,
+          "confidence": 0.887
+        },
+        {
+          "text": "caractérisé",
+          "start": 90.94,
+          "end": 91.8,
+          "confidence": 0.993
+        },
+        {
+          "text": "par",
+          "start": 91.8,
+          "end": 92.12,
+          "confidence": 0.997
+        },
+        {
+          "text": "un",
+          "start": 92.12,
+          "end": 92.44,
+          "confidence": 0.997
+        },
+        {
+          "text": "mélange",
+          "start": 92.44,
+          "end": 92.98,
+          "confidence": 0.999
+        },
+        {
+          "text": "de",
+          "start": 92.98,
+          "end": 93.4,
+          "confidence": 0.998
+        },
+        {
+          "text": "dépendance",
+          "start": 93.4,
+          "end": 94.24,
+          "confidence": 0.952
+        },
+        {
+          "text": "et",
+          "start": 94.24,
+          "end": 94.54,
+          "confidence": 0.998
+        },
+        {
+          "text": "de",
+          "start": 94.54,
+          "end": 94.68,
+          "confidence": 0.999
+        },
+        {
+          "text": "rejet.",
+          "start": 94.68,
+          "end": 95.14,
+          "confidence": 0.993
+        }
+      ]
+    },
+    {
+      "id": 19,
+      "seek": 7684,
+      "start": 95.78,
+      "end": 102.86,
+      "text": " Bon, en vrai, il faudrait remonter très très finement toute l'histoire des objets techniques et de leur insertion dans nos vies",
+      "tokens": [
+        7368,
+        11,
+        465,
+        17815,
+        11,
+        1930,
+        38694,
+        8645,
+        890,
+        41806,
+        5732,
+        5732,
+        962,
+        1712,
+        14953,
+        287,
+        6,
+        29093,
+        730,
+        1111,
+        25349,
+        7512,
+        1030,
+        368,
+        9580,
+        8969,
+        313,
+        2680,
+        3269,
+        371,
+        530
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06925634075613583,
+      "compression_ratio": 1.6787003610108304,
+      "no_speech_prob": 5.771887572336709e-06,
+      "confidence": 0.941,
+      "words": [
+        {
+          "text": "Bon,",
+          "start": 95.78,
+          "end": 96.38,
+          "confidence": 0.793
+        },
+        {
+          "text": "en",
+          "start": 96.38,
+          "end": 96.52,
+          "confidence": 0.998
+        },
+        {
+          "text": "vrai,",
+          "start": 96.52,
+          "end": 97.14,
+          "confidence": 0.994
+        },
+        {
+          "text": "il",
+          "start": 97.14,
+          "end": 97.18,
+          "confidence": 0.998
+        },
+        {
+          "text": "faudrait",
+          "start": 97.18,
+          "end": 97.58,
+          "confidence": 0.997
+        },
+        {
+          "text": "remonter",
+          "start": 97.58,
+          "end": 98.08,
+          "confidence": 0.997
+        },
+        {
+          "text": "très",
+          "start": 98.08,
+          "end": 98.58,
+          "confidence": 0.997
+        },
+        {
+          "text": "très",
+          "start": 98.58,
+          "end": 98.7,
+          "confidence": 0.767
+        },
+        {
+          "text": "finement",
+          "start": 98.7,
+          "end": 99.32,
+          "confidence": 0.849
+        },
+        {
+          "text": "toute",
+          "start": 99.32,
+          "end": 99.7,
+          "confidence": 0.984
+        },
+        {
+          "text": "l'histoire",
+          "start": 99.7,
+          "end": 100.06,
+          "confidence": 0.997
+        },
+        {
+          "text": "des",
+          "start": 100.06,
+          "end": 100.24,
+          "confidence": 0.998
+        },
+        {
+          "text": "objets",
+          "start": 100.24,
+          "end": 100.48,
+          "confidence": 0.999
+        },
+        {
+          "text": "techniques",
+          "start": 100.48,
+          "end": 101.02,
+          "confidence": 0.984
+        },
+        {
+          "text": "et",
+          "start": 101.02,
+          "end": 101.48,
+          "confidence": 0.531
+        },
+        {
+          "text": "de",
+          "start": 101.48,
+          "end": 101.68,
+          "confidence": 0.994
+        },
+        {
+          "text": "leur",
+          "start": 101.68,
+          "end": 101.84,
+          "confidence": 0.829
+        },
+        {
+          "text": "insertion",
+          "start": 101.84,
+          "end": 102.32,
+          "confidence": 0.994
+        },
+        {
+          "text": "dans",
+          "start": 102.32,
+          "end": 102.48,
+          "confidence": 0.991
+        },
+        {
+          "text": "nos",
+          "start": 102.48,
+          "end": 102.66,
+          "confidence": 0.998
+        },
+        {
+          "text": "vies",
+          "start": 102.66,
+          "end": 102.86,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 20,
+      "seek": 7684,
+      "start": 102.9,
+      "end": 105.74,
+      "text": " pour déterminer si ce rapport est totalement inédit.",
+      "tokens": [
+        2016,
+        2795,
+        29725,
+        260,
+        1511,
+        1769,
+        18018,
+        871,
+        45203,
+        294,
+        7811,
+        270,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06925634075613583,
+      "compression_ratio": 1.6787003610108304,
+      "no_speech_prob": 5.771887572336709e-06,
+      "confidence": 0.981,
+      "words": [
+        {
+          "text": "pour",
+          "start": 102.9,
+          "end": 103.06,
+          "confidence": 0.819
+        },
+        {
+          "text": "déterminer",
+          "start": 103.06,
+          "end": 103.66,
+          "confidence": 0.997
+        },
+        {
+          "text": "si",
+          "start": 103.66,
+          "end": 103.76,
+          "confidence": 0.992
+        },
+        {
+          "text": "ce",
+          "start": 103.76,
+          "end": 103.94,
+          "confidence": 0.997
+        },
+        {
+          "text": "rapport",
+          "start": 103.94,
+          "end": 104.26,
+          "confidence": 0.997
+        },
+        {
+          "text": "est",
+          "start": 104.26,
+          "end": 104.74,
+          "confidence": 0.998
+        },
+        {
+          "text": "totalement",
+          "start": 104.74,
+          "end": 105.3,
+          "confidence": 0.999
+        },
+        {
+          "text": "inédit.",
+          "start": 105.3,
+          "end": 105.74,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 21,
+      "seek": 10584,
+      "start": 106.1,
+      "end": 109.34,
+      "text": " Mais j'ai l'impression comme ça que Nicolas ne se trompe pas vraiment.",
+      "tokens": [
+        6313,
+        361,
+        6,
+        1301,
+        287,
+        6,
+        36107,
+        5173,
+        2788,
+        631,
+        38268,
+        408,
+        369,
+        504,
+        298,
+        494,
+        1736,
+        8322,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07393737035254909,
+      "compression_ratio": 1.685512367491166,
+      "no_speech_prob": 5.3074043535161763e-05,
+      "confidence": 0.94,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 106.1,
+          "end": 106.36,
+          "confidence": 0.947
+        },
+        {
+          "text": "j'ai",
+          "start": 106.36,
+          "end": 106.92,
+          "confidence": 0.94
+        },
+        {
+          "text": "l'impression",
+          "start": 106.92,
+          "end": 107.36,
+          "confidence": 0.996
+        },
+        {
+          "text": "comme",
+          "start": 107.36,
+          "end": 107.56,
+          "confidence": 0.642
+        },
+        {
+          "text": "ça",
+          "start": 107.56,
+          "end": 107.82,
+          "confidence": 0.978
+        },
+        {
+          "text": "que",
+          "start": 107.82,
+          "end": 107.96,
+          "confidence": 0.976
+        },
+        {
+          "text": "Nicolas",
+          "start": 107.96,
+          "end": 108.46,
+          "confidence": 0.985
+        },
+        {
+          "text": "ne",
+          "start": 108.46,
+          "end": 108.66,
+          "confidence": 0.726
+        },
+        {
+          "text": "se",
+          "start": 108.66,
+          "end": 108.7,
+          "confidence": 0.991
+        },
+        {
+          "text": "trompe",
+          "start": 108.7,
+          "end": 108.88,
+          "confidence": 0.995
+        },
+        {
+          "text": "pas",
+          "start": 108.88,
+          "end": 109.08,
+          "confidence": 0.999
+        },
+        {
+          "text": "vraiment.",
+          "start": 109.08,
+          "end": 109.34,
+          "confidence": 0.991
+        }
+      ]
+    },
+    {
+      "id": 22,
+      "seek": 10584,
+      "start": 109.88,
+      "end": 114.98,
+      "text": " Pour autant que je sache, il y a eu plein de discussions autour de la voiture ou même du téléphone.",
+      "tokens": [
+        8732,
+        34081,
+        631,
+        1506,
+        262,
+        6000,
+        11,
+        1930,
+        288,
+        257,
+        2228,
+        21088,
+        368,
+        11088,
+        30249,
+        368,
+        635,
+        38859,
+        2820,
+        5698,
+        1581,
+        47159,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07393737035254909,
+      "compression_ratio": 1.685512367491166,
+      "no_speech_prob": 5.3074043535161763e-05,
+      "confidence": 0.969,
+      "words": [
+        {
+          "text": "Pour",
+          "start": 109.88,
+          "end": 110.08,
+          "confidence": 0.997
+        },
+        {
+          "text": "autant",
+          "start": 110.08,
+          "end": 110.24,
+          "confidence": 1.0
+        },
+        {
+          "text": "que",
+          "start": 110.24,
+          "end": 110.42,
+          "confidence": 0.988
+        },
+        {
+          "text": "je",
+          "start": 110.42,
+          "end": 110.52,
+          "confidence": 0.998
+        },
+        {
+          "text": "sache,",
+          "start": 110.52,
+          "end": 111.14,
+          "confidence": 0.962
+        },
+        {
+          "text": "il",
+          "start": 111.14,
+          "end": 111.18,
+          "confidence": 0.997
+        },
+        {
+          "text": "y",
+          "start": 111.18,
+          "end": 111.32,
+          "confidence": 0.992
+        },
+        {
+          "text": "a",
+          "start": 111.32,
+          "end": 111.36,
+          "confidence": 0.993
+        },
+        {
+          "text": "eu",
+          "start": 111.36,
+          "end": 111.68,
+          "confidence": 0.998
+        },
+        {
+          "text": "plein",
+          "start": 111.68,
+          "end": 111.88,
+          "confidence": 0.974
+        },
+        {
+          "text": "de",
+          "start": 111.88,
+          "end": 112.06,
+          "confidence": 0.997
+        },
+        {
+          "text": "discussions",
+          "start": 112.06,
+          "end": 112.6,
+          "confidence": 0.799
+        },
+        {
+          "text": "autour",
+          "start": 112.6,
+          "end": 112.94,
+          "confidence": 0.995
+        },
+        {
+          "text": "de",
+          "start": 112.94,
+          "end": 113.46,
+          "confidence": 0.997
+        },
+        {
+          "text": "la",
+          "start": 113.46,
+          "end": 113.52,
+          "confidence": 0.998
+        },
+        {
+          "text": "voiture",
+          "start": 113.52,
+          "end": 113.86,
+          "confidence": 1.0
+        },
+        {
+          "text": "ou",
+          "start": 113.86,
+          "end": 114.06,
+          "confidence": 0.765
+        },
+        {
+          "text": "même",
+          "start": 114.06,
+          "end": 114.44,
+          "confidence": 0.996
+        },
+        {
+          "text": "du",
+          "start": 114.44,
+          "end": 114.6,
+          "confidence": 0.995
+        },
+        {
+          "text": "téléphone.",
+          "start": 114.6,
+          "end": 114.98,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 23,
+      "seek": 10584,
+      "start": 115.34,
+      "end": 119.84,
+      "text": " Mais la dépendance n'était pas du même ordre. Donc le rejet non plus n'était pas du même ordre.",
+      "tokens": [
+        6313,
+        635,
+        45768,
+        719,
+        297,
+        6,
+        9743,
+        1736,
+        1581,
+        5698,
+        4792,
+        265,
+        13,
+        7477,
+        476,
+        319,
+        7108,
+        2107,
+        1804,
+        297,
+        6,
+        9743,
+        1736,
+        1581,
+        5698,
+        4792,
+        265,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07393737035254909,
+      "compression_ratio": 1.685512367491166,
+      "no_speech_prob": 5.3074043535161763e-05,
+      "confidence": 0.972,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 115.34,
+          "end": 115.72,
+          "confidence": 0.994
+        },
+        {
+          "text": "la",
+          "start": 115.72,
+          "end": 116.02,
+          "confidence": 0.936
+        },
+        {
+          "text": "dépendance",
+          "start": 116.02,
+          "end": 116.4,
+          "confidence": 0.997
+        },
+        {
+          "text": "n'était",
+          "start": 116.4,
+          "end": 116.62,
+          "confidence": 0.994
+        },
+        {
+          "text": "pas",
+          "start": 116.62,
+          "end": 117.0,
+          "confidence": 0.998
+        },
+        {
+          "text": "du",
+          "start": 117.0,
+          "end": 117.16,
+          "confidence": 0.995
+        },
+        {
+          "text": "même",
+          "start": 117.16,
+          "end": 117.46,
+          "confidence": 0.999
+        },
+        {
+          "text": "ordre.",
+          "start": 117.46,
+          "end": 117.78,
+          "confidence": 0.999
+        },
+        {
+          "text": "Donc",
+          "start": 117.78,
+          "end": 117.98,
+          "confidence": 0.806
+        },
+        {
+          "text": "le",
+          "start": 117.98,
+          "end": 118.34,
+          "confidence": 0.709
+        },
+        {
+          "text": "rejet",
+          "start": 118.34,
+          "end": 118.62,
+          "confidence": 0.999
+        },
+        {
+          "text": "non",
+          "start": 118.62,
+          "end": 118.78,
+          "confidence": 0.974
+        },
+        {
+          "text": "plus",
+          "start": 118.78,
+          "end": 118.94,
+          "confidence": 0.995
+        },
+        {
+          "text": "n'était",
+          "start": 118.94,
+          "end": 119.12,
+          "confidence": 0.987
+        },
+        {
+          "text": "pas",
+          "start": 119.12,
+          "end": 119.3,
+          "confidence": 0.998
+        },
+        {
+          "text": "du",
+          "start": 119.3,
+          "end": 119.38,
+          "confidence": 0.995
+        },
+        {
+          "text": "même",
+          "start": 119.38,
+          "end": 119.56,
+          "confidence": 0.999
+        },
+        {
+          "text": "ordre.",
+          "start": 119.56,
+          "end": 119.84,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 24,
+      "seek": 10584,
+      "start": 119.98,
+      "end": 123.02,
+      "text": " On peut adorer sa bagnole, en avoir besoin pour plein de choses.",
+      "tokens": [
+        1282,
+        5977,
+        614,
+        17618,
+        601,
+        3411,
+        1771,
+        306,
+        11,
+        465,
+        10853,
+        19207,
+        2016,
+        21088,
+        368,
+        14488,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07393737035254909,
+      "compression_ratio": 1.685512367491166,
+      "no_speech_prob": 5.3074043535161763e-05,
+      "confidence": 0.991,
+      "words": [
+        {
+          "text": "On",
+          "start": 119.98,
+          "end": 120.18,
+          "confidence": 0.996
+        },
+        {
+          "text": "peut",
+          "start": 120.18,
+          "end": 120.38,
+          "confidence": 0.997
+        },
+        {
+          "text": "adorer",
+          "start": 120.38,
+          "end": 120.66,
+          "confidence": 0.99
+        },
+        {
+          "text": "sa",
+          "start": 120.66,
+          "end": 120.88,
+          "confidence": 0.985
+        },
+        {
+          "text": "bagnole,",
+          "start": 120.88,
+          "end": 121.46,
+          "confidence": 0.984
+        },
+        {
+          "text": "en",
+          "start": 121.46,
+          "end": 121.56,
+          "confidence": 0.989
+        },
+        {
+          "text": "avoir",
+          "start": 121.56,
+          "end": 121.74,
+          "confidence": 0.998
+        },
+        {
+          "text": "besoin",
+          "start": 121.74,
+          "end": 122.1,
+          "confidence": 0.999
+        },
+        {
+          "text": "pour",
+          "start": 122.1,
+          "end": 122.34,
+          "confidence": 0.987
+        },
+        {
+          "text": "plein",
+          "start": 122.34,
+          "end": 122.68,
+          "confidence": 0.989
+        },
+        {
+          "text": "de",
+          "start": 122.68,
+          "end": 122.8,
+          "confidence": 0.998
+        },
+        {
+          "text": "choses.",
+          "start": 122.8,
+          "end": 123.02,
+          "confidence": 0.989
+        }
+      ]
+    },
+    {
+      "id": 25,
+      "seek": 10584,
+      "start": 123.28,
+      "end": 126.36,
+      "text": " Et bien, le soir, quand on va se coucher, on la laisse.",
+      "tokens": [
+        3790,
+        3610,
+        11,
+        476,
+        27105,
+        11,
+        6932,
+        322,
+        2773,
+        369,
+        1384,
+        6759,
+        11,
+        322,
+        635,
+        30969,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07393737035254909,
+      "compression_ratio": 1.685512367491166,
+      "no_speech_prob": 5.3074043535161763e-05,
+      "confidence": 0.895,
+      "words": [
+        {
+          "text": "Et",
+          "start": 123.28,
+          "end": 123.46,
+          "confidence": 0.666
+        },
+        {
+          "text": "bien,",
+          "start": 123.46,
+          "end": 123.86,
+          "confidence": 0.47
+        },
+        {
+          "text": "le",
+          "start": 123.86,
+          "end": 123.98,
+          "confidence": 0.996
+        },
+        {
+          "text": "soir,",
+          "start": 123.98,
+          "end": 124.68,
+          "confidence": 0.999
+        },
+        {
+          "text": "quand",
+          "start": 124.68,
+          "end": 124.9,
+          "confidence": 0.997
+        },
+        {
+          "text": "on",
+          "start": 124.9,
+          "end": 125.02,
+          "confidence": 0.998
+        },
+        {
+          "text": "va",
+          "start": 125.02,
+          "end": 125.14,
+          "confidence": 0.996
+        },
+        {
+          "text": "se",
+          "start": 125.14,
+          "end": 125.38,
+          "confidence": 0.988
+        },
+        {
+          "text": "coucher,",
+          "start": 125.38,
+          "end": 125.8,
+          "confidence": 0.987
+        },
+        {
+          "text": "on",
+          "start": 125.8,
+          "end": 126.02,
+          "confidence": 0.995
+        },
+        {
+          "text": "la",
+          "start": 126.02,
+          "end": 126.22,
+          "confidence": 0.801
+        },
+        {
+          "text": "laisse.",
+          "start": 126.22,
+          "end": 126.36,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 26,
+      "seek": 10584,
+      "start": 126.98,
+      "end": 130.48,
+      "text": " On ne l'a pas dans la main quand on est au lit, on ne l'emmène pas au chiottes.",
+      "tokens": [
+        1282,
+        408,
+        287,
+        6,
+        64,
+        1736,
+        2680,
+        635,
+        2135,
+        6932,
+        322,
+        871,
+        1609,
+        7997,
+        11,
+        322,
+        408,
+        287,
+        6,
+        443,
+        76,
+        18832,
+        1736,
+        1609,
+        13228,
+        1521,
+        279,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07393737035254909,
+      "compression_ratio": 1.685512367491166,
+      "no_speech_prob": 5.3074043535161763e-05,
+      "confidence": 0.914,
+      "words": [
+        {
+          "text": "On",
+          "start": 126.98,
+          "end": 127.32,
+          "confidence": 0.954
+        },
+        {
+          "text": "ne",
+          "start": 127.32,
+          "end": 127.36,
+          "confidence": 0.802
+        },
+        {
+          "text": "l'a",
+          "start": 127.36,
+          "end": 127.48,
+          "confidence": 0.974
+        },
+        {
+          "text": "pas",
+          "start": 127.48,
+          "end": 127.68,
+          "confidence": 0.999
+        },
+        {
+          "text": "dans",
+          "start": 127.68,
+          "end": 127.8,
+          "confidence": 0.996
+        },
+        {
+          "text": "la",
+          "start": 127.8,
+          "end": 128.06,
+          "confidence": 0.994
+        },
+        {
+          "text": "main",
+          "start": 128.06,
+          "end": 128.26,
+          "confidence": 0.999
+        },
+        {
+          "text": "quand",
+          "start": 128.26,
+          "end": 128.44,
+          "confidence": 0.934
+        },
+        {
+          "text": "on",
+          "start": 128.44,
+          "end": 128.62,
+          "confidence": 0.997
+        },
+        {
+          "text": "est",
+          "start": 128.62,
+          "end": 128.68,
+          "confidence": 0.993
+        },
+        {
+          "text": "au",
+          "start": 128.68,
+          "end": 129.04,
+          "confidence": 0.984
+        },
+        {
+          "text": "lit,",
+          "start": 129.04,
+          "end": 129.14,
+          "confidence": 0.999
+        },
+        {
+          "text": "on",
+          "start": 129.14,
+          "end": 129.26,
+          "confidence": 0.427
+        },
+        {
+          "text": "ne",
+          "start": 129.26,
+          "end": 129.3,
+          "confidence": 0.963
+        },
+        {
+          "text": "l'emmène",
+          "start": 129.3,
+          "end": 129.5,
+          "confidence": 0.992
+        },
+        {
+          "text": "pas",
+          "start": 129.5,
+          "end": 129.68,
+          "confidence": 0.997
+        },
+        {
+          "text": "au",
+          "start": 129.68,
+          "end": 129.86,
+          "confidence": 0.668
+        },
+        {
+          "text": "chiottes.",
+          "start": 129.86,
+          "end": 130.48,
+          "confidence": 0.829
+        }
+      ]
+    },
+    {
+      "id": 27,
+      "seek": 13084,
+      "start": 130.86,
+      "end": 136.9,
+      "text": " On pouvait être énervé par son môme qui occupait la ligne de téléphone pendant une heure chaque soir pour discuter avec un copain.",
+      "tokens": [
+        1282,
+        45913,
+        7418,
+        45045,
+        15797,
+        971,
+        1872,
+        275,
+        2851,
+        1398,
+        1956,
+        8073,
+        1001,
+        635,
+        34207,
+        368,
+        47159,
+        17338,
+        2251,
+        30027,
+        18920,
+        27105,
+        2016,
+        2983,
+        20314,
+        4163,
+        517,
+        2971,
+        491,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06175626696962299,
+      "compression_ratio": 1.6127167630057804,
+      "no_speech_prob": 1.5689402061980218e-05,
+      "confidence": 0.955,
+      "words": [
+        {
+          "text": "On",
+          "start": 130.86,
+          "end": 131.04,
+          "confidence": 0.983
+        },
+        {
+          "text": "pouvait",
+          "start": 131.04,
+          "end": 131.28,
+          "confidence": 0.989
+        },
+        {
+          "text": "être",
+          "start": 131.28,
+          "end": 131.48,
+          "confidence": 0.996
+        },
+        {
+          "text": "énervé",
+          "start": 131.48,
+          "end": 132.22,
+          "confidence": 0.906
+        },
+        {
+          "text": "par",
+          "start": 132.22,
+          "end": 132.44,
+          "confidence": 0.991
+        },
+        {
+          "text": "son",
+          "start": 132.44,
+          "end": 132.7,
+          "confidence": 0.998
+        },
+        {
+          "text": "môme",
+          "start": 132.7,
+          "end": 133.1,
+          "confidence": 0.832
+        },
+        {
+          "text": "qui",
+          "start": 133.1,
+          "end": 133.34,
+          "confidence": 0.919
+        },
+        {
+          "text": "occupait",
+          "start": 133.34,
+          "end": 133.76,
+          "confidence": 0.991
+        },
+        {
+          "text": "la",
+          "start": 133.76,
+          "end": 133.8,
+          "confidence": 0.992
+        },
+        {
+          "text": "ligne",
+          "start": 133.8,
+          "end": 134.08,
+          "confidence": 0.999
+        },
+        {
+          "text": "de",
+          "start": 134.08,
+          "end": 134.14,
+          "confidence": 0.997
+        },
+        {
+          "text": "téléphone",
+          "start": 134.14,
+          "end": 134.6,
+          "confidence": 0.985
+        },
+        {
+          "text": "pendant",
+          "start": 134.6,
+          "end": 134.82,
+          "confidence": 0.98
+        },
+        {
+          "text": "une",
+          "start": 134.82,
+          "end": 135.2,
+          "confidence": 0.87
+        },
+        {
+          "text": "heure",
+          "start": 135.2,
+          "end": 135.36,
+          "confidence": 0.998
+        },
+        {
+          "text": "chaque",
+          "start": 135.36,
+          "end": 135.54,
+          "confidence": 0.991
+        },
+        {
+          "text": "soir",
+          "start": 135.54,
+          "end": 135.8,
+          "confidence": 0.996
+        },
+        {
+          "text": "pour",
+          "start": 135.8,
+          "end": 135.96,
+          "confidence": 0.791
+        },
+        {
+          "text": "discuter",
+          "start": 135.96,
+          "end": 136.28,
+          "confidence": 0.997
+        },
+        {
+          "text": "avec",
+          "start": 136.28,
+          "end": 136.48,
+          "confidence": 0.996
+        },
+        {
+          "text": "un",
+          "start": 136.48,
+          "end": 136.6,
+          "confidence": 0.999
+        },
+        {
+          "text": "copain.",
+          "start": 136.6,
+          "end": 136.9,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 28,
+      "seek": 13084,
+      "start": 137.28,
+      "end": 141.88,
+      "text": " Mais ça ne ressemblait pas à ce qu'on peut ressentir à voir ce même môme aujourd'hui,",
+      "tokens": [
+        6313,
+        2788,
+        408,
+        725,
+        15750,
+        35235,
+        1736,
+        1531,
+        1769,
+        421,
+        6,
+        266,
+        5977,
+        24689,
+        317,
+        347,
+        1531,
+        10695,
+        1769,
+        5698,
+        275,
+        2851,
+        1398,
+        14023,
+        6,
+        10556,
+        11
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06175626696962299,
+      "compression_ratio": 1.6127167630057804,
+      "no_speech_prob": 1.5689402061980218e-05,
+      "confidence": 0.958,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 137.28,
+          "end": 137.46,
+          "confidence": 0.993
+        },
+        {
+          "text": "ça",
+          "start": 137.46,
+          "end": 137.68,
+          "confidence": 0.938
+        },
+        {
+          "text": "ne",
+          "start": 137.68,
+          "end": 137.94,
+          "confidence": 0.998
+        },
+        {
+          "text": "ressemblait",
+          "start": 137.94,
+          "end": 138.4,
+          "confidence": 0.991
+        },
+        {
+          "text": "pas",
+          "start": 138.4,
+          "end": 138.76,
+          "confidence": 0.995
+        },
+        {
+          "text": "à",
+          "start": 138.76,
+          "end": 138.94,
+          "confidence": 0.988
+        },
+        {
+          "text": "ce",
+          "start": 138.94,
+          "end": 138.98,
+          "confidence": 0.998
+        },
+        {
+          "text": "qu'on",
+          "start": 138.98,
+          "end": 139.1,
+          "confidence": 0.986
+        },
+        {
+          "text": "peut",
+          "start": 139.1,
+          "end": 139.48,
+          "confidence": 0.988
+        },
+        {
+          "text": "ressentir",
+          "start": 139.48,
+          "end": 140.12,
+          "confidence": 0.997
+        },
+        {
+          "text": "à",
+          "start": 140.12,
+          "end": 140.32,
+          "confidence": 0.498
+        },
+        {
+          "text": "voir",
+          "start": 140.32,
+          "end": 140.46,
+          "confidence": 0.852
+        },
+        {
+          "text": "ce",
+          "start": 140.46,
+          "end": 140.68,
+          "confidence": 0.989
+        },
+        {
+          "text": "même",
+          "start": 140.68,
+          "end": 140.92,
+          "confidence": 0.984
+        },
+        {
+          "text": "môme",
+          "start": 140.92,
+          "end": 141.34,
+          "confidence": 0.998
+        },
+        {
+          "text": "aujourd'hui,",
+          "start": 141.34,
+          "end": 141.88,
+          "confidence": 0.988
+        }
+      ]
+    },
+    {
+      "id": 29,
+      "seek": 13084,
+      "start": 142.14,
+      "end": 146.3,
+      "text": " continuellement avec son smartphone dans la main, comme si c'était une sorte de pacemaker externe,",
+      "tokens": [
+        2354,
+        285,
+        1712,
+        4163,
+        1872,
+        13307,
+        2680,
+        635,
+        2135,
+        11,
+        5173,
+        1511,
+        269,
+        6,
+        9743,
+        2251,
+        25559,
+        368,
+        15165,
+        49523,
+        454,
+        391,
+        716,
+        11
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06175626696962299,
+      "compression_ratio": 1.6127167630057804,
+      "no_speech_prob": 1.5689402061980218e-05,
+      "confidence": 0.963,
+      "words": [
+        {
+          "text": "continuellement",
+          "start": 142.14,
+          "end": 142.94,
+          "confidence": 0.971
+        },
+        {
+          "text": "avec",
+          "start": 142.94,
+          "end": 143.18,
+          "confidence": 0.806
+        },
+        {
+          "text": "son",
+          "start": 143.18,
+          "end": 143.38,
+          "confidence": 0.995
+        },
+        {
+          "text": "smartphone",
+          "start": 143.38,
+          "end": 143.76,
+          "confidence": 0.978
+        },
+        {
+          "text": "dans",
+          "start": 143.76,
+          "end": 143.94,
+          "confidence": 0.979
+        },
+        {
+          "text": "la",
+          "start": 143.94,
+          "end": 144.0,
+          "confidence": 0.996
+        },
+        {
+          "text": "main,",
+          "start": 144.0,
+          "end": 144.36,
+          "confidence": 0.998
+        },
+        {
+          "text": "comme",
+          "start": 144.36,
+          "end": 144.52,
+          "confidence": 0.836
+        },
+        {
+          "text": "si",
+          "start": 144.52,
+          "end": 144.64,
+          "confidence": 0.975
+        },
+        {
+          "text": "c'était",
+          "start": 144.64,
+          "end": 144.82,
+          "confidence": 0.991
+        },
+        {
+          "text": "une",
+          "start": 144.82,
+          "end": 145.06,
+          "confidence": 0.989
+        },
+        {
+          "text": "sorte",
+          "start": 145.06,
+          "end": 145.22,
+          "confidence": 0.997
+        },
+        {
+          "text": "de",
+          "start": 145.22,
+          "end": 145.3,
+          "confidence": 0.982
+        },
+        {
+          "text": "pacemaker",
+          "start": 145.3,
+          "end": 145.82,
+          "confidence": 0.917
+        },
+        {
+          "text": "externe,",
+          "start": 145.82,
+          "end": 146.3,
+          "confidence": 0.992
+        }
+      ]
+    },
+    {
+      "id": 30,
+      "seek": 13084,
+      "start": 146.34,
+      "end": 148.84,
+      "text": " comme si le lâcher allait entraîner sa mort immédiate.",
+      "tokens": [
+        5173,
+        1511,
+        476,
+        48835,
+        6759,
+        439,
+        1001,
+        22284,
+        7517,
+        1193,
+        601,
+        6599,
+        3397,
+        526,
+        4504,
+        473,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06175626696962299,
+      "compression_ratio": 1.6127167630057804,
+      "no_speech_prob": 1.5689402061980218e-05,
+      "confidence": 0.989,
+      "words": [
+        {
+          "text": "comme",
+          "start": 146.34,
+          "end": 146.58,
+          "confidence": 0.996
+        },
+        {
+          "text": "si",
+          "start": 146.58,
+          "end": 146.76,
+          "confidence": 0.994
+        },
+        {
+          "text": "le",
+          "start": 146.76,
+          "end": 146.86,
+          "confidence": 0.997
+        },
+        {
+          "text": "lâcher",
+          "start": 146.86,
+          "end": 147.36,
+          "confidence": 0.969
+        },
+        {
+          "text": "allait",
+          "start": 147.36,
+          "end": 147.56,
+          "confidence": 0.993
+        },
+        {
+          "text": "entraîner",
+          "start": 147.56,
+          "end": 147.86,
+          "confidence": 0.978
+        },
+        {
+          "text": "sa",
+          "start": 147.86,
+          "end": 148.0,
+          "confidence": 0.999
+        },
+        {
+          "text": "mort",
+          "start": 148.0,
+          "end": 148.22,
+          "confidence": 0.998
+        },
+        {
+          "text": "immédiate.",
+          "start": 148.22,
+          "end": 148.84,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 31,
+      "seek": 13084,
+      "start": 149.04,
+      "end": 151.96,
+      "text": " Bon, je dis ça pour le môme, mais c'est évidemment valable pour nous aussi.",
+      "tokens": [
+        7368,
+        11,
+        1506,
+        717,
+        2788,
+        2016,
+        476,
+        275,
+        2851,
+        1398,
+        11,
+        2420,
+        269,
+        6,
+        377,
+        24724,
+        1323,
+        712,
+        2016,
+        4666,
+        6212,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06175626696962299,
+      "compression_ratio": 1.6127167630057804,
+      "no_speech_prob": 1.5689402061980218e-05,
+      "confidence": 0.974,
+      "words": [
+        {
+          "text": "Bon,",
+          "start": 149.04,
+          "end": 149.28,
+          "confidence": 0.917
+        },
+        {
+          "text": "je",
+          "start": 149.28,
+          "end": 149.32,
+          "confidence": 0.935
+        },
+        {
+          "text": "dis",
+          "start": 149.32,
+          "end": 149.46,
+          "confidence": 0.988
+        },
+        {
+          "text": "ça",
+          "start": 149.46,
+          "end": 149.64,
+          "confidence": 0.994
+        },
+        {
+          "text": "pour",
+          "start": 149.64,
+          "end": 149.74,
+          "confidence": 0.997
+        },
+        {
+          "text": "le",
+          "start": 149.74,
+          "end": 149.88,
+          "confidence": 0.995
+        },
+        {
+          "text": "môme,",
+          "start": 149.88,
+          "end": 150.32,
+          "confidence": 0.998
+        },
+        {
+          "text": "mais",
+          "start": 150.32,
+          "end": 150.52,
+          "confidence": 0.793
+        },
+        {
+          "text": "c'est",
+          "start": 150.52,
+          "end": 150.82,
+          "confidence": 0.982
+        },
+        {
+          "text": "évidemment",
+          "start": 150.82,
+          "end": 151.14,
+          "confidence": 0.98
+        },
+        {
+          "text": "valable",
+          "start": 151.14,
+          "end": 151.48,
+          "confidence": 0.998
+        },
+        {
+          "text": "pour",
+          "start": 151.48,
+          "end": 151.62,
+          "confidence": 0.997
+        },
+        {
+          "text": "nous",
+          "start": 151.62,
+          "end": 151.76,
+          "confidence": 0.999
+        },
+        {
+          "text": "aussi.",
+          "start": 151.76,
+          "end": 151.96,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 32,
+      "seek": 13084,
+      "start": 152.34,
+      "end": 158.22,
+      "text": " Donc, rapport inédit. D'accord. Mais pourquoi a-t-on l'impression qu'on n'en sortira jamais?",
+      "tokens": [
+        7477,
+        11,
+        18018,
+        294,
+        7811,
+        270,
+        13,
+        413,
+        6,
+        19947,
+        13,
+        6313,
+        19934,
+        257,
+        12,
+        83,
+        12,
+        266,
+        287,
+        6,
+        36107,
+        421,
+        6,
+        266,
+        297,
+        6,
+        268,
+        1333,
+        4271,
+        14540,
+        2506
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06175626696962299,
+      "compression_ratio": 1.6127167630057804,
+      "no_speech_prob": 1.5689402061980218e-05,
+      "confidence": 0.948,
+      "words": [
+        {
+          "text": "Donc,",
+          "start": 152.34,
+          "end": 153.46,
+          "confidence": 0.991
+        },
+        {
+          "text": "rapport",
+          "start": 153.46,
+          "end": 153.66,
+          "confidence": 0.977
+        },
+        {
+          "text": "inédit.",
+          "start": 153.66,
+          "end": 154.24,
+          "confidence": 0.997
+        },
+        {
+          "text": "D'accord.",
+          "start": 154.24,
+          "end": 155.48,
+          "confidence": 0.979
+        },
+        {
+          "text": "Mais",
+          "start": 155.48,
+          "end": 155.82,
+          "confidence": 0.56
+        },
+        {
+          "text": "pourquoi",
+          "start": 155.82,
+          "end": 156.32,
+          "confidence": 0.994
+        },
+        {
+          "text": "a-t-on",
+          "start": 156.32,
+          "end": 156.68,
+          "confidence": 0.94
+        },
+        {
+          "text": "l'impression",
+          "start": 156.68,
+          "end": 157.06,
+          "confidence": 0.999
+        },
+        {
+          "text": "qu'on",
+          "start": 157.06,
+          "end": 157.26,
+          "confidence": 0.995
+        },
+        {
+          "text": "n'en",
+          "start": 157.26,
+          "end": 157.44,
+          "confidence": 0.878
+        },
+        {
+          "text": "sortira",
+          "start": 157.44,
+          "end": 157.9,
+          "confidence": 0.989
+        },
+        {
+          "text": "jamais?",
+          "start": 157.9,
+          "end": 158.22,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 33,
+      "seek": 15884,
+      "start": 158.86,
+      "end": 165.32,
+      "text": " Est-ce qu'il faut en remettre la faute sur les gens qui ont créé cet outil merveilleux et diabolique, et diabolique parce que merveilleux?",
+      "tokens": [
+        4410,
+        12,
+        384,
+        421,
+        6,
+        388,
+        8487,
+        465,
+        890,
+        40681,
+        635,
+        2050,
+        1169,
+        1022,
+        1512,
+        10668,
+        1956,
+        6592,
+        15609,
+        526,
+        8603,
+        484,
+        388,
+        3551,
+        303,
+        3409,
+        2449,
+        1030,
+        1026,
+        14923,
+        1925,
+        11,
+        1030,
+        1026,
+        14923,
+        1925,
+        6992,
+        631,
+        3551,
+        303,
+        3409,
+        2449,
+        2506
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07952147990733653,
+      "compression_ratio": 1.6517857142857142,
+      "no_speech_prob": 5.475811485666782e-05,
+      "confidence": 0.962,
+      "words": [
+        {
+          "text": "Est-ce",
+          "start": 158.86,
+          "end": 159.34,
+          "confidence": 0.981
+        },
+        {
+          "text": "qu'il",
+          "start": 159.34,
+          "end": 159.46,
+          "confidence": 0.997
+        },
+        {
+          "text": "faut",
+          "start": 159.46,
+          "end": 159.62,
+          "confidence": 0.999
+        },
+        {
+          "text": "en",
+          "start": 159.62,
+          "end": 159.78,
+          "confidence": 0.97
+        },
+        {
+          "text": "remettre",
+          "start": 159.78,
+          "end": 160.12,
+          "confidence": 0.999
+        },
+        {
+          "text": "la",
+          "start": 160.12,
+          "end": 160.34,
+          "confidence": 0.998
+        },
+        {
+          "text": "faute",
+          "start": 160.34,
+          "end": 160.66,
+          "confidence": 0.986
+        },
+        {
+          "text": "sur",
+          "start": 160.66,
+          "end": 160.94,
+          "confidence": 0.995
+        },
+        {
+          "text": "les",
+          "start": 160.94,
+          "end": 161.28,
+          "confidence": 0.995
+        },
+        {
+          "text": "gens",
+          "start": 161.28,
+          "end": 161.44,
+          "confidence": 1.0
+        },
+        {
+          "text": "qui",
+          "start": 161.44,
+          "end": 161.58,
+          "confidence": 0.984
+        },
+        {
+          "text": "ont",
+          "start": 161.58,
+          "end": 161.72,
+          "confidence": 0.998
+        },
+        {
+          "text": "créé",
+          "start": 161.72,
+          "end": 162.3,
+          "confidence": 0.99
+        },
+        {
+          "text": "cet",
+          "start": 162.3,
+          "end": 162.46,
+          "confidence": 0.852
+        },
+        {
+          "text": "outil",
+          "start": 162.46,
+          "end": 162.78,
+          "confidence": 0.99
+        },
+        {
+          "text": "merveilleux",
+          "start": 162.78,
+          "end": 163.34,
+          "confidence": 0.994
+        },
+        {
+          "text": "et",
+          "start": 163.34,
+          "end": 163.5,
+          "confidence": 0.954
+        },
+        {
+          "text": "diabolique,",
+          "start": 163.5,
+          "end": 163.86,
+          "confidence": 0.992
+        },
+        {
+          "text": "et",
+          "start": 163.86,
+          "end": 163.92,
+          "confidence": 0.539
+        },
+        {
+          "text": "diabolique",
+          "start": 163.92,
+          "end": 164.4,
+          "confidence": 0.951
+        },
+        {
+          "text": "parce",
+          "start": 164.4,
+          "end": 164.66,
+          "confidence": 0.704
+        },
+        {
+          "text": "que",
+          "start": 164.66,
+          "end": 164.84,
+          "confidence": 0.99
+        },
+        {
+          "text": "merveilleux?",
+          "start": 164.84,
+          "end": 165.32,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 34,
+      "seek": 15884,
+      "start": 166.34,
+      "end": 168.82,
+      "text": " Les économistes parlent de dépendance du sentier.",
+      "tokens": [
+        6965,
+        31171,
+        22368,
+        13734,
+        317,
+        368,
+        45768,
+        719,
+        1581,
+        2279,
+        811,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07952147990733653,
+      "compression_ratio": 1.6517857142857142,
+      "no_speech_prob": 5.475811485666782e-05,
+      "confidence": 0.984,
+      "words": [
+        {
+          "text": "Les",
+          "start": 166.34,
+          "end": 167.04,
+          "confidence": 0.925
+        },
+        {
+          "text": "économistes",
+          "start": 167.04,
+          "end": 167.48,
+          "confidence": 0.998
+        },
+        {
+          "text": "parlent",
+          "start": 167.48,
+          "end": 167.68,
+          "confidence": 0.995
+        },
+        {
+          "text": "de",
+          "start": 167.68,
+          "end": 167.82,
+          "confidence": 0.995
+        },
+        {
+          "text": "dépendance",
+          "start": 167.82,
+          "end": 168.36,
+          "confidence": 0.985
+        },
+        {
+          "text": "du",
+          "start": 168.36,
+          "end": 168.5,
+          "confidence": 0.997
+        },
+        {
+          "text": "sentier.",
+          "start": 168.5,
+          "end": 168.82,
+          "confidence": 0.978
+        }
+      ]
+    },
+    {
+      "id": 35,
+      "seek": 16884,
+      "start": 168.86,
+      "end": 177.42,
+      "text": " C'est l'idée qu'on est sur un sentier qui a été établi, soit volontairement en marchant dessus, soit en définissant des bornes, en définissant une signalétique.",
+      "tokens": [
+        50364,
+        383,
+        6,
+        377,
+        287,
+        6,
+        34281,
+        421,
+        6,
+        266,
+        871,
+        1022,
+        517,
+        2279,
+        811,
+        1956,
+        257,
+        8862,
+        4823,
+        455,
+        2081,
+        11,
+        12703,
+        40005,
+        9020,
+        518,
+        465,
+        8368,
+        394,
+        30677,
+        11,
+        12703,
+        465,
+        40763,
+        29492,
+        730,
+        4232,
+        279,
+        11,
+        465,
+        40763,
+        29492,
+        2251,
+        6358,
+        42379,
+        13,
+        51414
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10392295320828755,
+      "compression_ratio": 1.3916666666666666,
+      "no_speech_prob": 3.9441460103262216e-05,
+      "confidence": 0.93,
+      "words": [
+        {
+          "text": "C'est",
+          "start": 168.86,
+          "end": 169.1,
+          "confidence": 0.952
+        },
+        {
+          "text": "l'idée",
+          "start": 169.1,
+          "end": 169.34,
+          "confidence": 0.992
+        },
+        {
+          "text": "qu'on",
+          "start": 169.34,
+          "end": 169.7,
+          "confidence": 0.824
+        },
+        {
+          "text": "est",
+          "start": 169.7,
+          "end": 169.88,
+          "confidence": 0.631
+        },
+        {
+          "text": "sur",
+          "start": 169.88,
+          "end": 170.0,
+          "confidence": 0.993
+        },
+        {
+          "text": "un",
+          "start": 170.0,
+          "end": 170.54,
+          "confidence": 0.998
+        },
+        {
+          "text": "sentier",
+          "start": 170.54,
+          "end": 170.78,
+          "confidence": 0.99
+        },
+        {
+          "text": "qui",
+          "start": 170.78,
+          "end": 170.84,
+          "confidence": 0.962
+        },
+        {
+          "text": "a",
+          "start": 170.84,
+          "end": 170.94,
+          "confidence": 0.98
+        },
+        {
+          "text": "été",
+          "start": 170.94,
+          "end": 171.12,
+          "confidence": 0.996
+        },
+        {
+          "text": "établi,",
+          "start": 171.12,
+          "end": 171.9,
+          "confidence": 0.995
+        },
+        {
+          "text": "soit",
+          "start": 171.9,
+          "end": 172.12,
+          "confidence": 0.988
+        },
+        {
+          "text": "volontairement",
+          "start": 172.12,
+          "end": 172.72,
+          "confidence": 0.965
+        },
+        {
+          "text": "en",
+          "start": 172.72,
+          "end": 172.8,
+          "confidence": 0.941
+        },
+        {
+          "text": "marchant",
+          "start": 172.8,
+          "end": 173.06,
+          "confidence": 0.997
+        },
+        {
+          "text": "dessus,",
+          "start": 173.06,
+          "end": 174.24,
+          "confidence": 0.972
+        },
+        {
+          "text": "soit",
+          "start": 174.24,
+          "end": 174.92,
+          "confidence": 0.996
+        },
+        {
+          "text": "en",
+          "start": 174.92,
+          "end": 175.36,
+          "confidence": 0.991
+        },
+        {
+          "text": "définissant",
+          "start": 175.36,
+          "end": 175.5,
+          "confidence": 0.983
+        },
+        {
+          "text": "des",
+          "start": 175.5,
+          "end": 175.76,
+          "confidence": 0.984
+        },
+        {
+          "text": "bornes,",
+          "start": 175.76,
+          "end": 176.04,
+          "confidence": 0.975
+        },
+        {
+          "text": "en",
+          "start": 176.04,
+          "end": 176.08,
+          "confidence": 0.683
+        },
+        {
+          "text": "définissant",
+          "start": 176.08,
+          "end": 176.58,
+          "confidence": 0.997
+        },
+        {
+          "text": "une",
+          "start": 176.58,
+          "end": 176.82,
+          "confidence": 0.944
+        },
+        {
+          "text": "signalétique.",
+          "start": 176.82,
+          "end": 177.42,
+          "confidence": 0.643
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/data/words.wav b/tests/data/words.wav
new file mode 100644
index 0000000000000000000000000000000000000000..62f594013e3f01d28b73172dfa013e1180ff2ba9
Binary files /dev/null and b/tests/data/words.wav differ
diff --git a/tests/data/yes_punctuations.mp3.words.json b/tests/data/yes_punctuations.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..64ed44959c984ee2b8ee34cc27b8924b62bf0ee4
--- /dev/null
+++ b/tests/data/yes_punctuations.mp3.words.json
@@ -0,0 +1,68 @@
+{
+  "text": " Dis-moi, est-ce que l'avion vole?",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.4,
+      "end": 2.34,
+      "text": " Dis-moi, est-ce que l'avion vole?",
+      "tokens": [
+        50364,
+        4208,
+        12,
+        29292,
+        11,
+        871,
+        12,
+        384,
+        631,
+        287,
+        6,
+        706,
+        313,
+        49877,
+        2506,
+        50494
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3014036907869227,
+      "compression_ratio": 0.8048780487804879,
+      "no_speech_prob": 0.05134102329611778,
+      "confidence": 0.925,
+      "words": [
+        {
+          "text": "Dis-moi,",
+          "start": 0.4,
+          "end": 1.36,
+          "confidence": 0.801
+        },
+        {
+          "text": "est-ce",
+          "start": 1.36,
+          "end": 1.52,
+          "confidence": 0.966
+        },
+        {
+          "text": "que",
+          "start": 1.52,
+          "end": 1.64,
+          "confidence": 0.977
+        },
+        {
+          "text": "l'avion",
+          "start": 1.64,
+          "end": 2.02,
+          "confidence": 0.994
+        },
+        {
+          "text": "vole?",
+          "start": 2.02,
+          "end": 2.34,
+          "confidence": 0.891
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/corner_cases.cpu/accurate.tiny_apollo11.mp3.words.json b/tests/expected/corner_cases.cpu/accurate.tiny_apollo11.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..b8cef4748a2e67b9548f033c7facf02873fcab99
--- /dev/null
+++ b/tests/expected/corner_cases.cpu/accurate.tiny_apollo11.mp3.words.json
@@ -0,0 +1,1481 @@
+{
+  "text": " I'm all around my business and we gotta eat recommendations for you on your door to the VA We have 18A's I'm all around my business and I'm all around my business and I'm all around my business I got a little bit of a problem with that, and you want to have the advice down My goal is to reach these things, not to reach out to them and they're out of the bag And I can't see anything else, I don't want to hear anything else I'm at the least, I'm not making the tag I can't see anything else Yeah, I'm taking a heavy out of the bag We're on the highway, we're on the highway, we're on the highway We're on the highway, we're on the highway We want to hear that, this is the case, we know we can't get that much of our business So I guess we'll be somewhere in our place, but it's not over Okay, it's not over, it's not over, it's not over",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.6,
+      "end": 5.28,
+      "text": " I'm all around my business and we gotta eat recommendations for you on your door to the VA",
+      "tokens": [
+        286,
+        478,
+        439,
+        926,
+        452,
+        1606,
+        293,
+        321,
+        3428,
+        1862,
+        10434,
+        337,
+        291,
+        322,
+        428,
+        2853,
+        281,
+        264,
+        18527
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4247800021701389,
+      "compression_ratio": 6.281818181818182,
+      "no_speech_prob": 0.3518604338169098,
+      "confidence": 0.27,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 0.6,
+          "end": 0.74,
+          "confidence": 0.168
+        },
+        {
+          "text": "all",
+          "start": 0.74,
+          "end": 1.02,
+          "confidence": 0.083
+        },
+        {
+          "text": "around",
+          "start": 1.02,
+          "end": 1.24,
+          "confidence": 0.103
+        },
+        {
+          "text": "my",
+          "start": 1.24,
+          "end": 1.42,
+          "confidence": 0.129
+        },
+        {
+          "text": "business",
+          "start": 1.42,
+          "end": 1.62,
+          "confidence": 0.339
+        },
+        {
+          "text": "and",
+          "start": 1.62,
+          "end": 1.9,
+          "confidence": 0.613
+        },
+        {
+          "text": "we",
+          "start": 1.9,
+          "end": 1.98,
+          "confidence": 0.938
+        },
+        {
+          "text": "gotta",
+          "start": 1.98,
+          "end": 2.16,
+          "confidence": 0.402
+        },
+        {
+          "text": "eat",
+          "start": 2.16,
+          "end": 2.38,
+          "confidence": 0.246
+        },
+        {
+          "text": "recommendations",
+          "start": 2.38,
+          "end": 2.84,
+          "confidence": 0.111
+        },
+        {
+          "text": "for",
+          "start": 2.84,
+          "end": 3.48,
+          "confidence": 0.236
+        },
+        {
+          "text": "you",
+          "start": 3.48,
+          "end": 3.62,
+          "confidence": 0.95
+        },
+        {
+          "text": "on",
+          "start": 3.62,
+          "end": 3.82,
+          "confidence": 0.774
+        },
+        {
+          "text": "your",
+          "start": 3.82,
+          "end": 4.36,
+          "confidence": 0.598
+        },
+        {
+          "text": "door",
+          "start": 4.36,
+          "end": 4.62,
+          "confidence": 0.113
+        },
+        {
+          "text": "to",
+          "start": 4.62,
+          "end": 4.84,
+          "confidence": 0.194
+        },
+        {
+          "text": "the",
+          "start": 4.84,
+          "end": 4.9,
+          "confidence": 0.457
+        },
+        {
+          "text": "VA",
+          "start": 4.9,
+          "end": 5.28,
+          "confidence": 0.23
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 5.28,
+      "end": 6.82,
+      "text": " We have 18A's",
+      "tokens": [
+        492,
+        362,
+        2443,
+        32,
+        311
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4247800021701389,
+      "compression_ratio": 6.281818181818182,
+      "no_speech_prob": 0.3518604338169098,
+      "confidence": 0.189,
+      "words": [
+        {
+          "text": "We",
+          "start": 5.28,
+          "end": 5.6,
+          "confidence": 0.056
+        },
+        {
+          "text": "have",
+          "start": 5.6,
+          "end": 5.72,
+          "confidence": 0.61
+        },
+        {
+          "text": "18A's",
+          "start": 5.72,
+          "end": 6.82,
+          "confidence": 0.191
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 700,
+      "start": 7.02,
+      "end": 24.14,
+      "text": " I'm all around my business and I'm all around my business and I'm all around my business",
+      "tokens": [
+        286,
+        478,
+        439,
+        926,
+        452,
+        1606,
+        293,
+        286,
+        478,
+        439,
+        926,
+        452,
+        1606,
+        293,
+        286,
+        478,
+        439,
+        926,
+        452,
+        1606
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.8006511529286703,
+      "compression_ratio": 2.1463414634146343,
+      "no_speech_prob": 0.1812065988779068,
+      "confidence": 0.476,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 7.02,
+          "end": 11.1,
+          "confidence": 0.124
+        },
+        {
+          "text": "all",
+          "start": 11.1,
+          "end": 13.62,
+          "confidence": 0.143
+        },
+        {
+          "text": "around",
+          "start": 13.62,
+          "end": 13.66,
+          "confidence": 0.517
+        },
+        {
+          "text": "my",
+          "start": 13.66,
+          "end": 13.7,
+          "confidence": 0.294
+        },
+        {
+          "text": "business",
+          "start": 13.7,
+          "end": 13.74,
+          "confidence": 0.931
+        },
+        {
+          "text": "and",
+          "start": 13.74,
+          "end": 14.08,
+          "confidence": 0.249
+        },
+        {
+          "text": "I'm",
+          "start": 14.08,
+          "end": 14.48,
+          "confidence": 0.379
+        },
+        {
+          "text": "all",
+          "start": 14.48,
+          "end": 14.68,
+          "confidence": 0.368
+        },
+        {
+          "text": "around",
+          "start": 14.68,
+          "end": 14.72,
+          "confidence": 0.892
+        },
+        {
+          "text": "my",
+          "start": 14.72,
+          "end": 14.76,
+          "confidence": 0.743
+        },
+        {
+          "text": "business",
+          "start": 14.76,
+          "end": 14.8,
+          "confidence": 0.981
+        },
+        {
+          "text": "and",
+          "start": 14.8,
+          "end": 15.04,
+          "confidence": 0.391
+        },
+        {
+          "text": "I'm",
+          "start": 15.04,
+          "end": 16.06,
+          "confidence": 0.861
+        },
+        {
+          "text": "all",
+          "start": 16.06,
+          "end": 16.12,
+          "confidence": 0.674
+        },
+        {
+          "text": "around",
+          "start": 16.12,
+          "end": 16.8,
+          "confidence": 0.932
+        },
+        {
+          "text": "my",
+          "start": 16.8,
+          "end": 21.82,
+          "confidence": 0.765
+        },
+        {
+          "text": "business",
+          "start": 21.82,
+          "end": 24.14,
+          "confidence": 0.977
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 3100,
+      "start": 31.24,
+      "end": 36.52,
+      "text": " I got a little bit of a problem with that, and you want to have the advice down",
+      "tokens": [
+        286,
+        658,
+        257,
+        707,
+        857,
+        295,
+        257,
+        1154,
+        365,
+        300,
+        11,
+        293,
+        291,
+        528,
+        281,
+        362,
+        264,
+        5192,
+        760
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -1.0431414517489346,
+      "compression_ratio": 1.8074866310160427,
+      "no_speech_prob": 0.09527108818292618,
+      "confidence": 0.336,
+      "words": [
+        {
+          "text": "I",
+          "start": 31.24,
+          "end": 31.66,
+          "confidence": 0.447
+        },
+        {
+          "text": "got",
+          "start": 31.66,
+          "end": 31.96,
+          "confidence": 0.219
+        },
+        {
+          "text": "a",
+          "start": 31.96,
+          "end": 33.32,
+          "confidence": 0.159
+        },
+        {
+          "text": "little",
+          "start": 33.32,
+          "end": 33.52,
+          "confidence": 0.104
+        },
+        {
+          "text": "bit",
+          "start": 33.52,
+          "end": 33.74,
+          "confidence": 0.919
+        },
+        {
+          "text": "of",
+          "start": 33.74,
+          "end": 33.86,
+          "confidence": 0.903
+        },
+        {
+          "text": "a",
+          "start": 33.86,
+          "end": 33.94,
+          "confidence": 0.347
+        },
+        {
+          "text": "problem",
+          "start": 33.94,
+          "end": 34.12,
+          "confidence": 0.226
+        },
+        {
+          "text": "with",
+          "start": 34.12,
+          "end": 34.38,
+          "confidence": 0.395
+        },
+        {
+          "text": "that,",
+          "start": 34.38,
+          "end": 34.52,
+          "confidence": 0.175
+        },
+        {
+          "text": "and",
+          "start": 34.52,
+          "end": 34.58,
+          "confidence": 0.331
+        },
+        {
+          "text": "you",
+          "start": 34.58,
+          "end": 34.7,
+          "confidence": 0.511
+        },
+        {
+          "text": "want",
+          "start": 34.7,
+          "end": 35.0,
+          "confidence": 0.533
+        },
+        {
+          "text": "to",
+          "start": 35.0,
+          "end": 35.06,
+          "confidence": 0.568
+        },
+        {
+          "text": "have",
+          "start": 35.06,
+          "end": 35.36,
+          "confidence": 0.857
+        },
+        {
+          "text": "the",
+          "start": 35.36,
+          "end": 35.52,
+          "confidence": 0.519
+        },
+        {
+          "text": "advice",
+          "start": 35.52,
+          "end": 35.88,
+          "confidence": 0.077
+        },
+        {
+          "text": "down",
+          "start": 35.88,
+          "end": 36.52,
+          "confidence": 0.231
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 3100,
+      "start": 37.68,
+      "end": 41.92,
+      "text": " My goal is to reach these things, not to reach out to them and they're out of the bag",
+      "tokens": [
+        1222,
+        3387,
+        307,
+        281,
+        2524,
+        613,
+        721,
+        11,
+        406,
+        281,
+        2524,
+        484,
+        281,
+        552,
+        293,
+        436,
+        434,
+        484,
+        295,
+        264,
+        3411
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -1.0431414517489346,
+      "compression_ratio": 1.8074866310160427,
+      "no_speech_prob": 0.09527108818292618,
+      "confidence": 0.312,
+      "words": [
+        {
+          "text": "My",
+          "start": 37.68,
+          "end": 38.04,
+          "confidence": 0.443
+        },
+        {
+          "text": "goal",
+          "start": 38.04,
+          "end": 38.14,
+          "confidence": 0.106
+        },
+        {
+          "text": "is",
+          "start": 38.14,
+          "end": 38.34,
+          "confidence": 0.697
+        },
+        {
+          "text": "to",
+          "start": 38.34,
+          "end": 38.68,
+          "confidence": 0.952
+        },
+        {
+          "text": "reach",
+          "start": 38.68,
+          "end": 38.84,
+          "confidence": 0.185
+        },
+        {
+          "text": "these",
+          "start": 38.84,
+          "end": 39.12,
+          "confidence": 0.19
+        },
+        {
+          "text": "things,",
+          "start": 39.12,
+          "end": 39.62,
+          "confidence": 0.06
+        },
+        {
+          "text": "not",
+          "start": 39.62,
+          "end": 40.1,
+          "confidence": 0.865
+        },
+        {
+          "text": "to",
+          "start": 40.1,
+          "end": 40.22,
+          "confidence": 0.13
+        },
+        {
+          "text": "reach",
+          "start": 40.22,
+          "end": 40.36,
+          "confidence": 0.433
+        },
+        {
+          "text": "out",
+          "start": 40.36,
+          "end": 40.58,
+          "confidence": 0.376
+        },
+        {
+          "text": "to",
+          "start": 40.58,
+          "end": 40.72,
+          "confidence": 0.771
+        },
+        {
+          "text": "them",
+          "start": 40.72,
+          "end": 40.84,
+          "confidence": 0.296
+        },
+        {
+          "text": "and",
+          "start": 40.84,
+          "end": 40.88,
+          "confidence": 0.254
+        },
+        {
+          "text": "they're",
+          "start": 40.88,
+          "end": 41.1,
+          "confidence": 0.244
+        },
+        {
+          "text": "out",
+          "start": 41.1,
+          "end": 41.34,
+          "confidence": 0.162
+        },
+        {
+          "text": "of",
+          "start": 41.34,
+          "end": 41.58,
+          "confidence": 0.722
+        },
+        {
+          "text": "the",
+          "start": 41.58,
+          "end": 41.68,
+          "confidence": 0.562
+        },
+        {
+          "text": "bag",
+          "start": 41.68,
+          "end": 41.92,
+          "confidence": 0.277
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 3100,
+      "start": 43.52,
+      "end": 47.08,
+      "text": " And I can't see anything else, I don't want to hear anything else",
+      "tokens": [
+        400,
+        286,
+        393,
+        380,
+        536,
+        1340,
+        1646,
+        11,
+        286,
+        500,
+        380,
+        528,
+        281,
+        1568,
+        1340,
+        1646
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -1.0431414517489346,
+      "compression_ratio": 1.8074866310160427,
+      "no_speech_prob": 0.09527108818292618,
+      "confidence": 0.326,
+      "words": [
+        {
+          "text": "And",
+          "start": 43.52,
+          "end": 43.56,
+          "confidence": 0.363
+        },
+        {
+          "text": "I",
+          "start": 43.56,
+          "end": 44.12,
+          "confidence": 0.396
+        },
+        {
+          "text": "can't",
+          "start": 44.12,
+          "end": 44.9,
+          "confidence": 0.248
+        },
+        {
+          "text": "see",
+          "start": 44.9,
+          "end": 45.08,
+          "confidence": 0.22
+        },
+        {
+          "text": "anything",
+          "start": 45.08,
+          "end": 45.64,
+          "confidence": 0.254
+        },
+        {
+          "text": "else,",
+          "start": 45.64,
+          "end": 45.68,
+          "confidence": 0.295
+        },
+        {
+          "text": "I",
+          "start": 45.68,
+          "end": 46.4,
+          "confidence": 0.191
+        },
+        {
+          "text": "don't",
+          "start": 46.4,
+          "end": 46.56,
+          "confidence": 0.615
+        },
+        {
+          "text": "want",
+          "start": 46.56,
+          "end": 46.6,
+          "confidence": 0.269
+        },
+        {
+          "text": "to",
+          "start": 46.6,
+          "end": 46.64,
+          "confidence": 0.744
+        },
+        {
+          "text": "hear",
+          "start": 46.64,
+          "end": 46.76,
+          "confidence": 0.262
+        },
+        {
+          "text": "anything",
+          "start": 46.76,
+          "end": 46.88,
+          "confidence": 0.287
+        },
+        {
+          "text": "else",
+          "start": 46.88,
+          "end": 47.08,
+          "confidence": 0.311
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 3100,
+      "start": 48.24,
+      "end": 49.68,
+      "text": " I'm at the least, I'm not making the tag",
+      "tokens": [
+        286,
+        478,
+        412,
+        264,
+        1935,
+        11,
+        286,
+        478,
+        406,
+        1455,
+        264,
+        6162
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -1.0431414517489346,
+      "compression_ratio": 1.8074866310160427,
+      "no_speech_prob": 0.09527108818292618,
+      "confidence": 0.379,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 48.24,
+          "end": 48.48,
+          "confidence": 0.231
+        },
+        {
+          "text": "at",
+          "start": 48.48,
+          "end": 48.52,
+          "confidence": 0.206
+        },
+        {
+          "text": "the",
+          "start": 48.52,
+          "end": 48.68,
+          "confidence": 0.811
+        },
+        {
+          "text": "least,",
+          "start": 48.68,
+          "end": 48.94,
+          "confidence": 0.235
+        },
+        {
+          "text": "I'm",
+          "start": 48.94,
+          "end": 49.0,
+          "confidence": 0.424
+        },
+        {
+          "text": "not",
+          "start": 49.0,
+          "end": 49.12,
+          "confidence": 0.938
+        },
+        {
+          "text": "making",
+          "start": 49.12,
+          "end": 49.26,
+          "confidence": 0.293
+        },
+        {
+          "text": "the",
+          "start": 49.26,
+          "end": 49.44,
+          "confidence": 0.747
+        },
+        {
+          "text": "tag",
+          "start": 49.44,
+          "end": 49.68,
+          "confidence": 0.298
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 3100,
+      "start": 51.46,
+      "end": 52.88,
+      "text": " I can't see anything else",
+      "tokens": [
+        286,
+        393,
+        380,
+        536,
+        1340,
+        1646
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -1.0431414517489346,
+      "compression_ratio": 1.8074866310160427,
+      "no_speech_prob": 0.09527108818292618,
+      "confidence": 0.412,
+      "words": [
+        {
+          "text": "I",
+          "start": 51.46,
+          "end": 51.5,
+          "confidence": 0.173
+        },
+        {
+          "text": "can't",
+          "start": 51.5,
+          "end": 51.86,
+          "confidence": 0.374
+        },
+        {
+          "text": "see",
+          "start": 51.86,
+          "end": 52.2,
+          "confidence": 0.34
+        },
+        {
+          "text": "anything",
+          "start": 52.2,
+          "end": 52.5,
+          "confidence": 0.915
+        },
+        {
+          "text": "else",
+          "start": 52.5,
+          "end": 52.88,
+          "confidence": 0.653
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 3100,
+      "start": 53.16,
+      "end": 54.7,
+      "text": " Yeah, I'm taking a heavy out of the bag",
+      "tokens": [
+        865,
+        11,
+        286,
+        478,
+        1940,
+        257,
+        4676,
+        484,
+        295,
+        264,
+        3411
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -1.0431414517489346,
+      "compression_ratio": 1.8074866310160427,
+      "no_speech_prob": 0.09527108818292618,
+      "confidence": 0.28,
+      "words": [
+        {
+          "text": "Yeah,",
+          "start": 53.16,
+          "end": 53.38,
+          "confidence": 0.569
+        },
+        {
+          "text": "I'm",
+          "start": 53.38,
+          "end": 53.46,
+          "confidence": 0.59
+        },
+        {
+          "text": "taking",
+          "start": 53.46,
+          "end": 53.64,
+          "confidence": 0.881
+        },
+        {
+          "text": "a",
+          "start": 53.64,
+          "end": 53.76,
+          "confidence": 0.177
+        },
+        {
+          "text": "heavy",
+          "start": 53.76,
+          "end": 54.04,
+          "confidence": 0.1
+        },
+        {
+          "text": "out",
+          "start": 54.04,
+          "end": 54.28,
+          "confidence": 0.073
+        },
+        {
+          "text": "of",
+          "start": 54.28,
+          "end": 54.42,
+          "confidence": 0.948
+        },
+        {
+          "text": "the",
+          "start": 54.42,
+          "end": 54.6,
+          "confidence": 0.168
+        },
+        {
+          "text": "bag",
+          "start": 54.6,
+          "end": 54.7,
+          "confidence": 0.084
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 5600,
+      "start": 56.46,
+      "end": 59.78,
+      "text": " We're on the highway, we're on the highway, we're on the highway",
+      "tokens": [
+        492,
+        434,
+        322,
+        264,
+        17205,
+        11,
+        321,
+        434,
+        322,
+        264,
+        17205,
+        11,
+        321,
+        434,
+        322,
+        264,
+        17205
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.750541016295716,
+      "compression_ratio": 1.901840490797546,
+      "no_speech_prob": 0.01289769820868969,
+      "confidence": 0.498,
+      "words": [
+        {
+          "text": "We're",
+          "start": 56.46,
+          "end": 56.94,
+          "confidence": 0.281
+        },
+        {
+          "text": "on",
+          "start": 56.94,
+          "end": 57.18,
+          "confidence": 0.116
+        },
+        {
+          "text": "the",
+          "start": 57.18,
+          "end": 57.26,
+          "confidence": 0.261
+        },
+        {
+          "text": "highway,",
+          "start": 57.26,
+          "end": 57.78,
+          "confidence": 0.129
+        },
+        {
+          "text": "we're",
+          "start": 57.78,
+          "end": 58.32,
+          "confidence": 0.604
+        },
+        {
+          "text": "on",
+          "start": 58.32,
+          "end": 58.44,
+          "confidence": 0.813
+        },
+        {
+          "text": "the",
+          "start": 58.44,
+          "end": 58.74,
+          "confidence": 0.861
+        },
+        {
+          "text": "highway,",
+          "start": 58.74,
+          "end": 58.94,
+          "confidence": 0.925
+        },
+        {
+          "text": "we're",
+          "start": 58.94,
+          "end": 58.98,
+          "confidence": 0.742
+        },
+        {
+          "text": "on",
+          "start": 58.98,
+          "end": 59.02,
+          "confidence": 0.82
+        },
+        {
+          "text": "the",
+          "start": 59.02,
+          "end": 59.18,
+          "confidence": 0.937
+        },
+        {
+          "text": "highway",
+          "start": 59.18,
+          "end": 59.78,
+          "confidence": 0.948
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 5600,
+      "start": 60.52,
+      "end": 66.02,
+      "text": " We're on the highway, we're on the highway",
+      "tokens": [
+        492,
+        434,
+        322,
+        264,
+        17205,
+        11,
+        321,
+        434,
+        322,
+        264,
+        17205
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.750541016295716,
+      "compression_ratio": 1.901840490797546,
+      "no_speech_prob": 0.01289769820868969,
+      "confidence": 0.785,
+      "words": [
+        {
+          "text": "We're",
+          "start": 60.52,
+          "end": 60.66,
+          "confidence": 0.62
+        },
+        {
+          "text": "on",
+          "start": 60.66,
+          "end": 60.84,
+          "confidence": 0.437
+        },
+        {
+          "text": "the",
+          "start": 60.84,
+          "end": 60.88,
+          "confidence": 0.94
+        },
+        {
+          "text": "highway,",
+          "start": 60.88,
+          "end": 61.16,
+          "confidence": 0.977
+        },
+        {
+          "text": "we're",
+          "start": 61.16,
+          "end": 63.48,
+          "confidence": 0.865
+        },
+        {
+          "text": "on",
+          "start": 63.48,
+          "end": 63.62,
+          "confidence": 0.911
+        },
+        {
+          "text": "the",
+          "start": 63.62,
+          "end": 63.7,
+          "confidence": 0.892
+        },
+        {
+          "text": "highway",
+          "start": 63.7,
+          "end": 66.02,
+          "confidence": 0.945
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 5600,
+      "start": 66.02,
+      "end": 69.04,
+      "text": " We want to hear that, this is the case, we know we can't get that much of our business",
+      "tokens": [
+        492,
+        528,
+        281,
+        1568,
+        300,
+        11,
+        341,
+        307,
+        264,
+        1389,
+        11,
+        321,
+        458,
+        321,
+        393,
+        380,
+        483,
+        300,
+        709,
+        295,
+        527,
+        1606
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.750541016295716,
+      "compression_ratio": 1.901840490797546,
+      "no_speech_prob": 0.01289769820868969,
+      "confidence": 0.371,
+      "words": [
+        {
+          "text": "We",
+          "start": 66.02,
+          "end": 66.06,
+          "confidence": 0.369
+        },
+        {
+          "text": "want",
+          "start": 66.06,
+          "end": 66.1,
+          "confidence": 0.335
+        },
+        {
+          "text": "to",
+          "start": 66.1,
+          "end": 66.14,
+          "confidence": 0.662
+        },
+        {
+          "text": "hear",
+          "start": 66.14,
+          "end": 66.18,
+          "confidence": 0.323
+        },
+        {
+          "text": "that,",
+          "start": 66.18,
+          "end": 66.22,
+          "confidence": 0.878
+        },
+        {
+          "text": "this",
+          "start": 66.22,
+          "end": 66.26,
+          "confidence": 0.265
+        },
+        {
+          "text": "is",
+          "start": 66.26,
+          "end": 66.3,
+          "confidence": 0.806
+        },
+        {
+          "text": "the",
+          "start": 66.3,
+          "end": 66.34,
+          "confidence": 0.286
+        },
+        {
+          "text": "case,",
+          "start": 66.34,
+          "end": 66.38,
+          "confidence": 0.195
+        },
+        {
+          "text": "we",
+          "start": 66.38,
+          "end": 66.92,
+          "confidence": 0.423
+        },
+        {
+          "text": "know",
+          "start": 66.92,
+          "end": 66.96,
+          "confidence": 0.736
+        },
+        {
+          "text": "we",
+          "start": 66.96,
+          "end": 67.06,
+          "confidence": 0.814
+        },
+        {
+          "text": "can't",
+          "start": 67.06,
+          "end": 67.3,
+          "confidence": 0.339
+        },
+        {
+          "text": "get",
+          "start": 67.3,
+          "end": 67.4,
+          "confidence": 0.219
+        },
+        {
+          "text": "that",
+          "start": 67.4,
+          "end": 67.64,
+          "confidence": 0.209
+        },
+        {
+          "text": "much",
+          "start": 67.64,
+          "end": 68.46,
+          "confidence": 0.213
+        },
+        {
+          "text": "of",
+          "start": 68.46,
+          "end": 68.7,
+          "confidence": 0.59
+        },
+        {
+          "text": "our",
+          "start": 68.7,
+          "end": 68.74,
+          "confidence": 0.679
+        },
+        {
+          "text": "business",
+          "start": 68.74,
+          "end": 69.04,
+          "confidence": 0.077
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 5600,
+      "start": 69.04,
+      "end": 72.64,
+      "text": " So I guess we'll be somewhere in our place, but it's not over",
+      "tokens": [
+        407,
+        286,
+        2041,
+        321,
+        603,
+        312,
+        4079,
+        294,
+        527,
+        1081,
+        11,
+        457,
+        309,
+        311,
+        406,
+        670
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.750541016295716,
+      "compression_ratio": 1.901840490797546,
+      "no_speech_prob": 0.01289769820868969,
+      "confidence": 0.435,
+      "words": [
+        {
+          "text": "So",
+          "start": 69.04,
+          "end": 70.38,
+          "confidence": 0.736
+        },
+        {
+          "text": "I",
+          "start": 70.38,
+          "end": 70.52,
+          "confidence": 0.675
+        },
+        {
+          "text": "guess",
+          "start": 70.52,
+          "end": 70.68,
+          "confidence": 0.721
+        },
+        {
+          "text": "we'll",
+          "start": 70.68,
+          "end": 71.04,
+          "confidence": 0.462
+        },
+        {
+          "text": "be",
+          "start": 71.04,
+          "end": 71.22,
+          "confidence": 0.27
+        },
+        {
+          "text": "somewhere",
+          "start": 71.22,
+          "end": 71.36,
+          "confidence": 0.369
+        },
+        {
+          "text": "in",
+          "start": 71.36,
+          "end": 71.4,
+          "confidence": 0.107
+        },
+        {
+          "text": "our",
+          "start": 71.4,
+          "end": 71.5,
+          "confidence": 0.192
+        },
+        {
+          "text": "place,",
+          "start": 71.5,
+          "end": 71.92,
+          "confidence": 0.38
+        },
+        {
+          "text": "but",
+          "start": 71.92,
+          "end": 72.14,
+          "confidence": 0.431
+        },
+        {
+          "text": "it's",
+          "start": 72.14,
+          "end": 72.36,
+          "confidence": 0.939
+        },
+        {
+          "text": "not",
+          "start": 72.36,
+          "end": 72.4,
+          "confidence": 0.552
+        },
+        {
+          "text": "over",
+          "start": 72.4,
+          "end": 72.64,
+          "confidence": 0.308
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 7400,
+      "start": 74.02,
+      "end": 78.4,
+      "text": " Okay, it's not over, it's not over, it's not over",
+      "tokens": [
+        50364,
+        1033,
+        11,
+        309,
+        311,
+        406,
+        670,
+        11,
+        309,
+        311,
+        406,
+        670,
+        11,
+        309,
+        311,
+        406,
+        670,
+        51164
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.405017099882427,
+      "compression_ratio": 1.6896551724137931,
+      "no_speech_prob": 0.01679050177335739,
+      "confidence": 0.705,
+      "words": [
+        {
+          "text": "Okay,",
+          "start": 74.02,
+          "end": 75.9,
+          "confidence": 0.147
+        },
+        {
+          "text": "it's",
+          "start": 75.9,
+          "end": 76.16,
+          "confidence": 0.589
+        },
+        {
+          "text": "not",
+          "start": 76.16,
+          "end": 76.22,
+          "confidence": 0.956
+        },
+        {
+          "text": "over,",
+          "start": 76.22,
+          "end": 76.76,
+          "confidence": 0.89
+        },
+        {
+          "text": "it's",
+          "start": 76.76,
+          "end": 77.08,
+          "confidence": 0.647
+        },
+        {
+          "text": "not",
+          "start": 77.08,
+          "end": 77.18,
+          "confidence": 0.897
+        },
+        {
+          "text": "over,",
+          "start": 77.18,
+          "end": 77.36,
+          "confidence": 0.962
+        },
+        {
+          "text": "it's",
+          "start": 77.36,
+          "end": 77.86,
+          "confidence": 0.869
+        },
+        {
+          "text": "not",
+          "start": 77.86,
+          "end": 78.26,
+          "confidence": 0.955
+        },
+        {
+          "text": "over",
+          "start": 78.26,
+          "end": 78.4,
+          "confidence": 0.934
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/corner_cases.cpu/large_apollo11.mp3.words.json b/tests/expected/corner_cases.cpu/large_apollo11.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..2132c86c44928d8182b1d362dfc9798acda75397
--- /dev/null
+++ b/tests/expected/corner_cases.cpu/large_apollo11.mp3.words.json
@@ -0,0 +1,2212 @@
+{
+  "text": " Apollo 11, Houston, we got a recommendation for you on your Doige's EAs, LM EG EAs, over. Go ahead. We'd like to see it as a selected one or two on the helmet. We're gonna have it in B1, and you can put the other one on Mike's helmet, we're still seeing it. Okay. All right. We got some. We got some. We got some. We got some. We got some. We got some. We got some. We got some. We got some. We got some. We got some. We got some. We got some. We got some. We got some. We got some. We got some. We got some. We got some. We got some. We got some. We got some. We got some. We got some. We got some. We got some. We got some. Yeah, we're taking next day autumn to heal up. You won't hack me on this. You won't hack me on this. With a cover, I tried it already. Okay, fine. We weren't sure that this was a suggestion. We thought you could check it out. I'm not sure we've already done that. I guess, whatever you come up with, just let us know. Okay, no problem. Okay, no problem.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.52,
+      "end": 7.22,
+      "text": " Apollo 11, Houston, we got a recommendation for you on your Doige's EAs, LM EG EAs, over.",
+      "tokens": [
+        25187,
+        2975,
+        11,
+        18717,
+        11,
+        321,
+        658,
+        257,
+        11879,
+        337,
+        291,
+        322,
+        428,
+        1144,
+        328,
+        68,
+        311,
+        462,
+        10884,
+        11,
+        46529,
+        462,
+        38,
+        462,
+        10884,
+        11,
+        670,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6255288836599766,
+      "compression_ratio": 1.4371584699453552,
+      "no_speech_prob": 0.33187487721443176,
+      "confidence": 0.539,
+      "words": [
+        {
+          "text": "Apollo",
+          "start": 0.52,
+          "end": 0.98,
+          "confidence": 0.791
+        },
+        {
+          "text": "11,",
+          "start": 0.98,
+          "end": 1.54,
+          "confidence": 0.878
+        },
+        {
+          "text": "Houston,",
+          "start": 1.54,
+          "end": 1.98,
+          "confidence": 0.828
+        },
+        {
+          "text": "we",
+          "start": 1.98,
+          "end": 2.02,
+          "confidence": 0.892
+        },
+        {
+          "text": "got",
+          "start": 2.02,
+          "end": 2.16,
+          "confidence": 0.688
+        },
+        {
+          "text": "a",
+          "start": 2.16,
+          "end": 2.46,
+          "confidence": 0.995
+        },
+        {
+          "text": "recommendation",
+          "start": 2.46,
+          "end": 3.16,
+          "confidence": 0.71
+        },
+        {
+          "text": "for",
+          "start": 3.16,
+          "end": 3.6,
+          "confidence": 0.845
+        },
+        {
+          "text": "you",
+          "start": 3.6,
+          "end": 3.94,
+          "confidence": 0.86
+        },
+        {
+          "text": "on",
+          "start": 3.94,
+          "end": 3.98,
+          "confidence": 0.862
+        },
+        {
+          "text": "your",
+          "start": 3.98,
+          "end": 4.28,
+          "confidence": 0.767
+        },
+        {
+          "text": "Doige's",
+          "start": 4.28,
+          "end": 5.14,
+          "confidence": 0.261
+        },
+        {
+          "text": "EAs,",
+          "start": 5.14,
+          "end": 5.62,
+          "confidence": 0.347
+        },
+        {
+          "text": "LM",
+          "start": 5.62,
+          "end": 5.7,
+          "confidence": 0.275
+        },
+        {
+          "text": "EG",
+          "start": 5.7,
+          "end": 6.34,
+          "confidence": 0.3
+        },
+        {
+          "text": "EAs,",
+          "start": 6.34,
+          "end": 6.98,
+          "confidence": 0.695
+        },
+        {
+          "text": "over.",
+          "start": 6.98,
+          "end": 7.22,
+          "confidence": 0.838
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 10.84,
+      "end": 11.96,
+      "text": " Go ahead.",
+      "tokens": [
+        1037,
+        2286,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6255288836599766,
+      "compression_ratio": 1.4371584699453552,
+      "no_speech_prob": 0.33187487721443176,
+      "confidence": 0.788,
+      "words": [
+        {
+          "text": "Go",
+          "start": 10.84,
+          "end": 11.06,
+          "confidence": 0.719
+        },
+        {
+          "text": "ahead.",
+          "start": 11.06,
+          "end": 11.96,
+          "confidence": 0.863
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 12.76,
+      "end": 17.48,
+      "text": " We'd like to see it as a selected one or two on the helmet.",
+      "tokens": [
+        492,
+        1116,
+        411,
+        281,
+        536,
+        309,
+        382,
+        257,
+        8209,
+        472,
+        420,
+        732,
+        322,
+        264,
+        15922,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6255288836599766,
+      "compression_ratio": 1.4371584699453552,
+      "no_speech_prob": 0.33187487721443176,
+      "confidence": 0.359,
+      "words": [
+        {
+          "text": "We'd",
+          "start": 12.76,
+          "end": 13.28,
+          "confidence": 0.31
+        },
+        {
+          "text": "like",
+          "start": 13.28,
+          "end": 13.62,
+          "confidence": 0.874
+        },
+        {
+          "text": "to",
+          "start": 13.62,
+          "end": 13.84,
+          "confidence": 0.728
+        },
+        {
+          "text": "see",
+          "start": 13.84,
+          "end": 14.14,
+          "confidence": 0.214
+        },
+        {
+          "text": "it",
+          "start": 14.14,
+          "end": 14.56,
+          "confidence": 0.067
+        },
+        {
+          "text": "as",
+          "start": 14.56,
+          "end": 14.6,
+          "confidence": 0.108
+        },
+        {
+          "text": "a",
+          "start": 14.6,
+          "end": 14.64,
+          "confidence": 0.223
+        },
+        {
+          "text": "selected",
+          "start": 14.64,
+          "end": 15.78,
+          "confidence": 0.136
+        },
+        {
+          "text": "one",
+          "start": 15.78,
+          "end": 16.14,
+          "confidence": 0.786
+        },
+        {
+          "text": "or",
+          "start": 16.14,
+          "end": 16.32,
+          "confidence": 0.644
+        },
+        {
+          "text": "two",
+          "start": 16.32,
+          "end": 16.6,
+          "confidence": 0.333
+        },
+        {
+          "text": "on",
+          "start": 16.6,
+          "end": 16.64,
+          "confidence": 0.858
+        },
+        {
+          "text": "the",
+          "start": 16.64,
+          "end": 16.98,
+          "confidence": 0.801
+        },
+        {
+          "text": "helmet.",
+          "start": 16.98,
+          "end": 17.48,
+          "confidence": 0.626
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 17.52,
+      "end": 24.34,
+      "text": " We're gonna have it in B1, and you can put the other one on Mike's helmet, we're still seeing it.",
+      "tokens": [
+        492,
+        434,
+        799,
+        362,
+        309,
+        294,
+        363,
+        16,
+        11,
+        293,
+        291,
+        393,
+        829,
+        264,
+        661,
+        472,
+        322,
+        6602,
+        311,
+        15922,
+        11,
+        321,
+        434,
+        920,
+        2577,
+        309,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6255288836599766,
+      "compression_ratio": 1.4371584699453552,
+      "no_speech_prob": 0.33187487721443176,
+      "confidence": 0.646,
+      "words": [
+        {
+          "text": "We're",
+          "start": 17.52,
+          "end": 17.94,
+          "confidence": 0.673
+        },
+        {
+          "text": "gonna",
+          "start": 17.94,
+          "end": 18.12,
+          "confidence": 0.19
+        },
+        {
+          "text": "have",
+          "start": 18.12,
+          "end": 18.3,
+          "confidence": 0.848
+        },
+        {
+          "text": "it",
+          "start": 18.3,
+          "end": 18.4,
+          "confidence": 0.317
+        },
+        {
+          "text": "in",
+          "start": 18.4,
+          "end": 18.48,
+          "confidence": 0.667
+        },
+        {
+          "text": "B1,",
+          "start": 18.48,
+          "end": 20.24,
+          "confidence": 0.883
+        },
+        {
+          "text": "and",
+          "start": 20.24,
+          "end": 20.28,
+          "confidence": 0.824
+        },
+        {
+          "text": "you",
+          "start": 20.28,
+          "end": 20.38,
+          "confidence": 0.892
+        },
+        {
+          "text": "can",
+          "start": 20.38,
+          "end": 20.56,
+          "confidence": 0.513
+        },
+        {
+          "text": "put",
+          "start": 20.56,
+          "end": 20.74,
+          "confidence": 0.895
+        },
+        {
+          "text": "the",
+          "start": 20.74,
+          "end": 20.9,
+          "confidence": 0.812
+        },
+        {
+          "text": "other",
+          "start": 20.9,
+          "end": 21.12,
+          "confidence": 0.773
+        },
+        {
+          "text": "one",
+          "start": 21.12,
+          "end": 21.42,
+          "confidence": 0.778
+        },
+        {
+          "text": "on",
+          "start": 21.42,
+          "end": 21.82,
+          "confidence": 0.905
+        },
+        {
+          "text": "Mike's",
+          "start": 21.82,
+          "end": 22.96,
+          "confidence": 0.876
+        },
+        {
+          "text": "helmet,",
+          "start": 22.96,
+          "end": 23.12,
+          "confidence": 0.772
+        },
+        {
+          "text": "we're",
+          "start": 23.12,
+          "end": 23.26,
+          "confidence": 0.455
+        },
+        {
+          "text": "still",
+          "start": 23.26,
+          "end": 23.42,
+          "confidence": 0.773
+        },
+        {
+          "text": "seeing",
+          "start": 23.42,
+          "end": 23.72,
+          "confidence": 0.667
+        },
+        {
+          "text": "it.",
+          "start": 23.72,
+          "end": 24.34,
+          "confidence": 0.243
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 2400,
+      "start": 25.44,
+      "end": 25.48,
+      "text": " Okay.",
+      "tokens": [
+        1033,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.004,
+      "words": [
+        {
+          "text": "Okay.",
+          "start": 25.44,
+          "end": 25.48,
+          "confidence": 0.004
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 2400,
+      "start": 25.48,
+      "end": 26.0,
+      "text": " All right.",
+      "tokens": [
+        1057,
+        558,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.281,
+      "words": [
+        {
+          "text": "All",
+          "start": 25.48,
+          "end": 25.52,
+          "confidence": 0.093
+        },
+        {
+          "text": "right.",
+          "start": 25.52,
+          "end": 26.0,
+          "confidence": 0.849
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 2400,
+      "start": 26.0,
+      "end": 27.5,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.06,
+      "words": [
+        {
+          "text": "We",
+          "start": 26.0,
+          "end": 27.42,
+          "confidence": 0.08
+        },
+        {
+          "text": "got",
+          "start": 27.42,
+          "end": 27.46,
+          "confidence": 0.111
+        },
+        {
+          "text": "some.",
+          "start": 27.46,
+          "end": 27.5,
+          "confidence": 0.024
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 2400,
+      "start": 28.4,
+      "end": 28.52,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.399,
+      "words": [
+        {
+          "text": "We",
+          "start": 28.4,
+          "end": 28.44,
+          "confidence": 0.19
+        },
+        {
+          "text": "got",
+          "start": 28.44,
+          "end": 28.48,
+          "confidence": 0.527
+        },
+        {
+          "text": "some.",
+          "start": 28.48,
+          "end": 28.52,
+          "confidence": 0.633
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 2400,
+      "start": 28.52,
+      "end": 28.96,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.468,
+      "words": [
+        {
+          "text": "We",
+          "start": 28.52,
+          "end": 28.56,
+          "confidence": 0.231
+        },
+        {
+          "text": "got",
+          "start": 28.56,
+          "end": 28.6,
+          "confidence": 0.608
+        },
+        {
+          "text": "some.",
+          "start": 28.6,
+          "end": 28.96,
+          "confidence": 0.731
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 2400,
+      "start": 28.96,
+      "end": 30.01,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.529,
+      "words": [
+        {
+          "text": "We",
+          "start": 28.96,
+          "end": 29.0,
+          "confidence": 0.288
+        },
+        {
+          "text": "got",
+          "start": 29.0,
+          "end": 29.04,
+          "confidence": 0.675
+        },
+        {
+          "text": "some.",
+          "start": 29.04,
+          "end": 30.01,
+          "confidence": 0.761
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 2400,
+      "start": 30.01,
+      "end": 31.5,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.596,
+      "words": [
+        {
+          "text": "We",
+          "start": 30.01,
+          "end": 31.42,
+          "confidence": 0.378
+        },
+        {
+          "text": "got",
+          "start": 31.42,
+          "end": 31.46,
+          "confidence": 0.721
+        },
+        {
+          "text": "some.",
+          "start": 31.46,
+          "end": 31.5,
+          "confidence": 0.776
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 2400,
+      "start": 31.5,
+      "end": 32.48,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.654,
+      "words": [
+        {
+          "text": "We",
+          "start": 31.5,
+          "end": 32.14,
+          "confidence": 0.47
+        },
+        {
+          "text": "got",
+          "start": 32.14,
+          "end": 32.18,
+          "confidence": 0.757
+        },
+        {
+          "text": "some.",
+          "start": 32.18,
+          "end": 32.48,
+          "confidence": 0.787
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 2400,
+      "start": 32.76,
+      "end": 33.26,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.707,
+      "words": [
+        {
+          "text": "We",
+          "start": 32.76,
+          "end": 33.0,
+          "confidence": 0.573
+        },
+        {
+          "text": "got",
+          "start": 33.0,
+          "end": 33.22,
+          "confidence": 0.786
+        },
+        {
+          "text": "some.",
+          "start": 33.22,
+          "end": 33.26,
+          "confidence": 0.786
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 2400,
+      "start": 33.26,
+      "end": 34.26,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.743,
+      "words": [
+        {
+          "text": "We",
+          "start": 33.26,
+          "end": 33.3,
+          "confidence": 0.637
+        },
+        {
+          "text": "got",
+          "start": 33.3,
+          "end": 33.58,
+          "confidence": 0.811
+        },
+        {
+          "text": "some.",
+          "start": 33.58,
+          "end": 34.26,
+          "confidence": 0.794
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 2400,
+      "start": 34.52,
+      "end": 35.06,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.761,
+      "words": [
+        {
+          "text": "We",
+          "start": 34.52,
+          "end": 34.68,
+          "confidence": 0.672
+        },
+        {
+          "text": "got",
+          "start": 34.68,
+          "end": 35.02,
+          "confidence": 0.828
+        },
+        {
+          "text": "some.",
+          "start": 35.02,
+          "end": 35.06,
+          "confidence": 0.793
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 2400,
+      "start": 35.18,
+      "end": 36.03,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.774,
+      "words": [
+        {
+          "text": "We",
+          "start": 35.18,
+          "end": 35.48,
+          "confidence": 0.694
+        },
+        {
+          "text": "got",
+          "start": 35.48,
+          "end": 35.78,
+          "confidence": 0.843
+        },
+        {
+          "text": "some.",
+          "start": 35.78,
+          "end": 36.03,
+          "confidence": 0.792
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 2400,
+      "start": 36.03,
+      "end": 36.16,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.787,
+      "words": [
+        {
+          "text": "We",
+          "start": 36.03,
+          "end": 36.07,
+          "confidence": 0.714
+        },
+        {
+          "text": "got",
+          "start": 36.07,
+          "end": 36.11,
+          "confidence": 0.853
+        },
+        {
+          "text": "some.",
+          "start": 36.11,
+          "end": 36.16,
+          "confidence": 0.8
+        }
+      ]
+    },
+    {
+      "id": 17,
+      "seek": 2400,
+      "start": 37.66,
+      "end": 38.48,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.798,
+      "words": [
+        {
+          "text": "We",
+          "start": 37.66,
+          "end": 38.0,
+          "confidence": 0.741
+        },
+        {
+          "text": "got",
+          "start": 38.0,
+          "end": 38.16,
+          "confidence": 0.86
+        },
+        {
+          "text": "some.",
+          "start": 38.16,
+          "end": 38.48,
+          "confidence": 0.797
+        }
+      ]
+    },
+    {
+      "id": 18,
+      "seek": 2400,
+      "start": 38.48,
+      "end": 39.2,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.798,
+      "words": [
+        {
+          "text": "We",
+          "start": 38.48,
+          "end": 38.52,
+          "confidence": 0.739
+        },
+        {
+          "text": "got",
+          "start": 38.52,
+          "end": 38.56,
+          "confidence": 0.861
+        },
+        {
+          "text": "some.",
+          "start": 38.56,
+          "end": 39.2,
+          "confidence": 0.799
+        }
+      ]
+    },
+    {
+      "id": 19,
+      "seek": 2400,
+      "start": 40.16,
+      "end": 40.48,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.802,
+      "words": [
+        {
+          "text": "We",
+          "start": 40.16,
+          "end": 40.2,
+          "confidence": 0.752
+        },
+        {
+          "text": "got",
+          "start": 40.2,
+          "end": 40.44,
+          "confidence": 0.862
+        },
+        {
+          "text": "some.",
+          "start": 40.44,
+          "end": 40.48,
+          "confidence": 0.797
+        }
+      ]
+    },
+    {
+      "id": 20,
+      "seek": 2400,
+      "start": 40.48,
+      "end": 40.68,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.802,
+      "words": [
+        {
+          "text": "We",
+          "start": 40.48,
+          "end": 40.52,
+          "confidence": 0.751
+        },
+        {
+          "text": "got",
+          "start": 40.52,
+          "end": 40.56,
+          "confidence": 0.865
+        },
+        {
+          "text": "some.",
+          "start": 40.56,
+          "end": 40.68,
+          "confidence": 0.795
+        }
+      ]
+    },
+    {
+      "id": 21,
+      "seek": 2400,
+      "start": 41.36,
+      "end": 41.96,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.812,
+      "words": [
+        {
+          "text": "We",
+          "start": 41.36,
+          "end": 41.4,
+          "confidence": 0.771
+        },
+        {
+          "text": "got",
+          "start": 41.4,
+          "end": 41.44,
+          "confidence": 0.871
+        },
+        {
+          "text": "some.",
+          "start": 41.44,
+          "end": 41.96,
+          "confidence": 0.798
+        }
+      ]
+    },
+    {
+      "id": 22,
+      "seek": 2400,
+      "start": 41.96,
+      "end": 42.08,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.811,
+      "words": [
+        {
+          "text": "We",
+          "start": 41.96,
+          "end": 42.0,
+          "confidence": 0.766
+        },
+        {
+          "text": "got",
+          "start": 42.0,
+          "end": 42.04,
+          "confidence": 0.873
+        },
+        {
+          "text": "some.",
+          "start": 42.04,
+          "end": 42.08,
+          "confidence": 0.797
+        }
+      ]
+    },
+    {
+      "id": 23,
+      "seek": 2400,
+      "start": 43.84,
+      "end": 44.48,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.821,
+      "words": [
+        {
+          "text": "We",
+          "start": 43.84,
+          "end": 44.02,
+          "confidence": 0.782
+        },
+        {
+          "text": "got",
+          "start": 44.02,
+          "end": 44.28,
+          "confidence": 0.876
+        },
+        {
+          "text": "some.",
+          "start": 44.28,
+          "end": 44.48,
+          "confidence": 0.806
+        }
+      ]
+    },
+    {
+      "id": 24,
+      "seek": 2400,
+      "start": 44.56,
+      "end": 45.03,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.827,
+      "words": [
+        {
+          "text": "We",
+          "start": 44.56,
+          "end": 44.6,
+          "confidence": 0.799
+        },
+        {
+          "text": "got",
+          "start": 44.6,
+          "end": 44.64,
+          "confidence": 0.88
+        },
+        {
+          "text": "some.",
+          "start": 44.64,
+          "end": 45.03,
+          "confidence": 0.804
+        }
+      ]
+    },
+    {
+      "id": 25,
+      "seek": 2400,
+      "start": 45.03,
+      "end": 45.15,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.828,
+      "words": [
+        {
+          "text": "We",
+          "start": 45.03,
+          "end": 45.07,
+          "confidence": 0.802
+        },
+        {
+          "text": "got",
+          "start": 45.07,
+          "end": 45.11,
+          "confidence": 0.881
+        },
+        {
+          "text": "some.",
+          "start": 45.11,
+          "end": 45.15,
+          "confidence": 0.802
+        }
+      ]
+    },
+    {
+      "id": 26,
+      "seek": 2400,
+      "start": 46.24,
+      "end": 47.08,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.826,
+      "words": [
+        {
+          "text": "We",
+          "start": 46.24,
+          "end": 46.44,
+          "confidence": 0.796
+        },
+        {
+          "text": "got",
+          "start": 46.44,
+          "end": 46.8,
+          "confidence": 0.883
+        },
+        {
+          "text": "some.",
+          "start": 46.8,
+          "end": 47.08,
+          "confidence": 0.801
+        }
+      ]
+    },
+    {
+      "id": 27,
+      "seek": 2400,
+      "start": 47.96,
+      "end": 48.08,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.827,
+      "words": [
+        {
+          "text": "We",
+          "start": 47.96,
+          "end": 48.0,
+          "confidence": 0.805
+        },
+        {
+          "text": "got",
+          "start": 48.0,
+          "end": 48.04,
+          "confidence": 0.886
+        },
+        {
+          "text": "some.",
+          "start": 48.04,
+          "end": 48.08,
+          "confidence": 0.795
+        }
+      ]
+    },
+    {
+      "id": 28,
+      "seek": 2400,
+      "start": 48.3,
+      "end": 48.74,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.829,
+      "words": [
+        {
+          "text": "We",
+          "start": 48.3,
+          "end": 48.6,
+          "confidence": 0.801
+        },
+        {
+          "text": "got",
+          "start": 48.6,
+          "end": 48.66,
+          "confidence": 0.887
+        },
+        {
+          "text": "some.",
+          "start": 48.66,
+          "end": 48.74,
+          "confidence": 0.802
+        }
+      ]
+    },
+    {
+      "id": 29,
+      "seek": 2400,
+      "start": 50.16,
+      "end": 50.5,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.832,
+      "words": [
+        {
+          "text": "We",
+          "start": 50.16,
+          "end": 50.42,
+          "confidence": 0.809
+        },
+        {
+          "text": "got",
+          "start": 50.42,
+          "end": 50.46,
+          "confidence": 0.888
+        },
+        {
+          "text": "some.",
+          "start": 50.46,
+          "end": 50.5,
+          "confidence": 0.804
+        }
+      ]
+    },
+    {
+      "id": 30,
+      "seek": 2400,
+      "start": 50.5,
+      "end": 51.36,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.832,
+      "words": [
+        {
+          "text": "We",
+          "start": 50.5,
+          "end": 51.28,
+          "confidence": 0.808
+        },
+        {
+          "text": "got",
+          "start": 51.28,
+          "end": 51.32,
+          "confidence": 0.885
+        },
+        {
+          "text": "some.",
+          "start": 51.32,
+          "end": 51.36,
+          "confidence": 0.804
+        }
+      ]
+    },
+    {
+      "id": 31,
+      "seek": 2400,
+      "start": 51.36,
+      "end": 51.94,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.832,
+      "words": [
+        {
+          "text": "We",
+          "start": 51.36,
+          "end": 51.86,
+          "confidence": 0.811
+        },
+        {
+          "text": "got",
+          "start": 51.86,
+          "end": 51.9,
+          "confidence": 0.885
+        },
+        {
+          "text": "some.",
+          "start": 51.9,
+          "end": 51.94,
+          "confidence": 0.803
+        }
+      ]
+    },
+    {
+      "id": 32,
+      "seek": 2400,
+      "start": 51.94,
+      "end": 52.86,
+      "text": " We got some.",
+      "tokens": [
+        492,
+        658,
+        512,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3070566034041388,
+      "compression_ratio": 9.175,
+      "no_speech_prob": 0.6738554835319519,
+      "confidence": 0.822,
+      "words": [
+        {
+          "text": "We",
+          "start": 51.94,
+          "end": 51.98,
+          "confidence": 0.781
+        },
+        {
+          "text": "got",
+          "start": 51.98,
+          "end": 52.32,
+          "confidence": 0.887
+        },
+        {
+          "text": "some.",
+          "start": 52.32,
+          "end": 52.86,
+          "confidence": 0.8
+        }
+      ]
+    },
+    {
+      "id": 33,
+      "seek": 5300,
+      "start": 53.16,
+      "end": 56.06,
+      "text": " Yeah, we're taking next day autumn to heal up.",
+      "tokens": [
+        865,
+        11,
+        321,
+        434,
+        1940,
+        958,
+        786,
+        24604,
+        281,
+        10526,
+        493,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.7040317565437377,
+      "compression_ratio": 1.7253218884120172,
+      "no_speech_prob": 0.4773952066898346,
+      "confidence": 0.348,
+      "words": [
+        {
+          "text": "Yeah,",
+          "start": 53.16,
+          "end": 53.5,
+          "confidence": 0.243
+        },
+        {
+          "text": "we're",
+          "start": 53.5,
+          "end": 53.62,
+          "confidence": 0.597
+        },
+        {
+          "text": "taking",
+          "start": 53.62,
+          "end": 53.7,
+          "confidence": 0.694
+        },
+        {
+          "text": "next",
+          "start": 53.7,
+          "end": 53.98,
+          "confidence": 0.247
+        },
+        {
+          "text": "day",
+          "start": 53.98,
+          "end": 54.2,
+          "confidence": 0.555
+        },
+        {
+          "text": "autumn",
+          "start": 54.2,
+          "end": 54.4,
+          "confidence": 0.159
+        },
+        {
+          "text": "to",
+          "start": 54.4,
+          "end": 54.64,
+          "confidence": 0.186
+        },
+        {
+          "text": "heal",
+          "start": 54.64,
+          "end": 55.18,
+          "confidence": 0.129
+        },
+        {
+          "text": "up.",
+          "start": 55.18,
+          "end": 56.06,
+          "confidence": 0.817
+        }
+      ]
+    },
+    {
+      "id": 34,
+      "seek": 5300,
+      "start": 56.46,
+      "end": 57.86,
+      "text": " You won't hack me on this.",
+      "tokens": [
+        509,
+        1582,
+        380,
+        10339,
+        385,
+        322,
+        341,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.7040317565437377,
+      "compression_ratio": 1.7253218884120172,
+      "no_speech_prob": 0.4773952066898346,
+      "confidence": 0.432,
+      "words": [
+        {
+          "text": "You",
+          "start": 56.46,
+          "end": 56.8,
+          "confidence": 0.117
+        },
+        {
+          "text": "won't",
+          "start": 56.8,
+          "end": 57.2,
+          "confidence": 0.465
+        },
+        {
+          "text": "hack",
+          "start": 57.2,
+          "end": 57.46,
+          "confidence": 0.373
+        },
+        {
+          "text": "me",
+          "start": 57.46,
+          "end": 57.66,
+          "confidence": 0.898
+        },
+        {
+          "text": "on",
+          "start": 57.66,
+          "end": 57.82,
+          "confidence": 0.807
+        },
+        {
+          "text": "this.",
+          "start": 57.82,
+          "end": 57.86,
+          "confidence": 0.413
+        }
+      ]
+    },
+    {
+      "id": 35,
+      "seek": 5300,
+      "start": 57.86,
+      "end": 59.79,
+      "text": " You won't hack me on this.",
+      "tokens": [
+        509,
+        1582,
+        380,
+        10339,
+        385,
+        322,
+        341,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.7040317565437377,
+      "compression_ratio": 1.7253218884120172,
+      "no_speech_prob": 0.4773952066898346,
+      "confidence": 0.832,
+      "words": [
+        {
+          "text": "You",
+          "start": 57.86,
+          "end": 58.08,
+          "confidence": 0.612
+        },
+        {
+          "text": "won't",
+          "start": 58.08,
+          "end": 58.76,
+          "confidence": 0.928
+        },
+        {
+          "text": "hack",
+          "start": 58.76,
+          "end": 58.8,
+          "confidence": 0.809
+        },
+        {
+          "text": "me",
+          "start": 58.8,
+          "end": 59.2,
+          "confidence": 0.905
+        },
+        {
+          "text": "on",
+          "start": 59.2,
+          "end": 59.3,
+          "confidence": 0.884
+        },
+        {
+          "text": "this.",
+          "start": 59.3,
+          "end": 59.79,
+          "confidence": 0.808
+        }
+      ]
+    },
+    {
+      "id": 36,
+      "seek": 5300,
+      "start": 59.79,
+      "end": 62.08,
+      "text": " With a cover, I tried it already.",
+      "tokens": [
+        2022,
+        257,
+        2060,
+        11,
+        286,
+        3031,
+        309,
+        1217,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.7040317565437377,
+      "compression_ratio": 1.7253218884120172,
+      "no_speech_prob": 0.4773952066898346,
+      "confidence": 0.638,
+      "words": [
+        {
+          "text": "With",
+          "start": 59.79,
+          "end": 60.1,
+          "confidence": 0.363
+        },
+        {
+          "text": "a",
+          "start": 60.1,
+          "end": 60.14,
+          "confidence": 0.405
+        },
+        {
+          "text": "cover,",
+          "start": 60.14,
+          "end": 61.24,
+          "confidence": 0.814
+        },
+        {
+          "text": "I",
+          "start": 61.24,
+          "end": 61.28,
+          "confidence": 0.961
+        },
+        {
+          "text": "tried",
+          "start": 61.28,
+          "end": 61.56,
+          "confidence": 0.653
+        },
+        {
+          "text": "it",
+          "start": 61.56,
+          "end": 61.74,
+          "confidence": 0.73
+        },
+        {
+          "text": "already.",
+          "start": 61.74,
+          "end": 62.08,
+          "confidence": 0.785
+        }
+      ]
+    },
+    {
+      "id": 37,
+      "seek": 5300,
+      "start": 62.6,
+      "end": 65.32,
+      "text": " Okay, fine. We weren't sure that this was a suggestion.",
+      "tokens": [
+        1033,
+        11,
+        2489,
+        13,
+        492,
+        4999,
+        380,
+        988,
+        300,
+        341,
+        390,
+        257,
+        16541,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.7040317565437377,
+      "compression_ratio": 1.7253218884120172,
+      "no_speech_prob": 0.4773952066898346,
+      "confidence": 0.722,
+      "words": [
+        {
+          "text": "Okay,",
+          "start": 62.6,
+          "end": 62.92,
+          "confidence": 0.513
+        },
+        {
+          "text": "fine.",
+          "start": 62.92,
+          "end": 63.2,
+          "confidence": 0.861
+        },
+        {
+          "text": "We",
+          "start": 63.2,
+          "end": 63.36,
+          "confidence": 0.702
+        },
+        {
+          "text": "weren't",
+          "start": 63.36,
+          "end": 63.68,
+          "confidence": 0.909
+        },
+        {
+          "text": "sure",
+          "start": 63.68,
+          "end": 63.84,
+          "confidence": 0.829
+        },
+        {
+          "text": "that",
+          "start": 63.84,
+          "end": 64.24,
+          "confidence": 0.552
+        },
+        {
+          "text": "this",
+          "start": 64.24,
+          "end": 64.64,
+          "confidence": 0.741
+        },
+        {
+          "text": "was",
+          "start": 64.64,
+          "end": 64.8,
+          "confidence": 0.783
+        },
+        {
+          "text": "a",
+          "start": 64.8,
+          "end": 64.88,
+          "confidence": 0.819
+        },
+        {
+          "text": "suggestion.",
+          "start": 64.88,
+          "end": 65.32,
+          "confidence": 0.498
+        }
+      ]
+    },
+    {
+      "id": 38,
+      "seek": 5300,
+      "start": 66.76,
+      "end": 68.21,
+      "text": " We thought you could check it out.",
+      "tokens": [
+        492,
+        1194,
+        291,
+        727,
+        1520,
+        309,
+        484,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.7040317565437377,
+      "compression_ratio": 1.7253218884120172,
+      "no_speech_prob": 0.4773952066898346,
+      "confidence": 0.721,
+      "words": [
+        {
+          "text": "We",
+          "start": 66.76,
+          "end": 66.8,
+          "confidence": 0.891
+        },
+        {
+          "text": "thought",
+          "start": 66.8,
+          "end": 66.84,
+          "confidence": 0.813
+        },
+        {
+          "text": "you",
+          "start": 66.84,
+          "end": 67.06,
+          "confidence": 0.325
+        },
+        {
+          "text": "could",
+          "start": 67.06,
+          "end": 67.24,
+          "confidence": 0.784
+        },
+        {
+          "text": "check",
+          "start": 67.24,
+          "end": 67.5,
+          "confidence": 0.751
+        },
+        {
+          "text": "it",
+          "start": 67.5,
+          "end": 67.7,
+          "confidence": 0.899
+        },
+        {
+          "text": "out.",
+          "start": 67.7,
+          "end": 68.21,
+          "confidence": 0.812
+        }
+      ]
+    },
+    {
+      "id": 39,
+      "seek": 5300,
+      "start": 68.21,
+      "end": 69.48,
+      "text": " I'm not sure we've already done that.",
+      "tokens": [
+        286,
+        478,
+        406,
+        988,
+        321,
+        600,
+        1217,
+        1096,
+        300,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.7040317565437377,
+      "compression_ratio": 1.7253218884120172,
+      "no_speech_prob": 0.4773952066898346,
+      "confidence": 0.455,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 68.21,
+          "end": 68.5,
+          "confidence": 0.179
+        },
+        {
+          "text": "not",
+          "start": 68.5,
+          "end": 68.6,
+          "confidence": 0.258
+        },
+        {
+          "text": "sure",
+          "start": 68.6,
+          "end": 68.76,
+          "confidence": 0.761
+        },
+        {
+          "text": "we've",
+          "start": 68.76,
+          "end": 68.9,
+          "confidence": 0.495
+        },
+        {
+          "text": "already",
+          "start": 68.9,
+          "end": 68.94,
+          "confidence": 0.765
+        },
+        {
+          "text": "done",
+          "start": 68.94,
+          "end": 69.18,
+          "confidence": 0.799
+        },
+        {
+          "text": "that.",
+          "start": 69.18,
+          "end": 69.48,
+          "confidence": 0.878
+        }
+      ]
+    },
+    {
+      "id": 40,
+      "seek": 5300,
+      "start": 70.38,
+      "end": 72.62,
+      "text": " I guess, whatever you come up with, just let us know.",
+      "tokens": [
+        286,
+        2041,
+        11,
+        2035,
+        291,
+        808,
+        493,
+        365,
+        11,
+        445,
+        718,
+        505,
+        458,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.7040317565437377,
+      "compression_ratio": 1.7253218884120172,
+      "no_speech_prob": 0.4773952066898346,
+      "confidence": 0.738,
+      "words": [
+        {
+          "text": "I",
+          "start": 70.38,
+          "end": 70.52,
+          "confidence": 0.55
+        },
+        {
+          "text": "guess,",
+          "start": 70.52,
+          "end": 70.96,
+          "confidence": 0.903
+        },
+        {
+          "text": "whatever",
+          "start": 70.96,
+          "end": 71.18,
+          "confidence": 0.404
+        },
+        {
+          "text": "you",
+          "start": 71.18,
+          "end": 71.22,
+          "confidence": 0.89
+        },
+        {
+          "text": "come",
+          "start": 71.22,
+          "end": 71.54,
+          "confidence": 0.544
+        },
+        {
+          "text": "up",
+          "start": 71.54,
+          "end": 71.72,
+          "confidence": 0.892
+        },
+        {
+          "text": "with,",
+          "start": 71.72,
+          "end": 71.98,
+          "confidence": 0.816
+        },
+        {
+          "text": "just",
+          "start": 71.98,
+          "end": 72.16,
+          "confidence": 0.77
+        },
+        {
+          "text": "let",
+          "start": 72.16,
+          "end": 72.2,
+          "confidence": 0.898
+        },
+        {
+          "text": "us",
+          "start": 72.2,
+          "end": 72.34,
+          "confidence": 0.905
+        },
+        {
+          "text": "know.",
+          "start": 72.34,
+          "end": 72.62,
+          "confidence": 0.798
+        }
+      ]
+    },
+    {
+      "id": 41,
+      "seek": 5300,
+      "start": 74.18,
+      "end": 75.48,
+      "text": " Okay, no problem.",
+      "tokens": [
+        1033,
+        11,
+        572,
+        1154,
+        13
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.7040317565437377,
+      "compression_ratio": 1.7253218884120172,
+      "no_speech_prob": 0.4773952066898346,
+      "confidence": 0.699,
+      "words": [
+        {
+          "text": "Okay,",
+          "start": 74.18,
+          "end": 74.66,
+          "confidence": 0.789
+        },
+        {
+          "text": "no",
+          "start": 74.66,
+          "end": 74.88,
+          "confidence": 0.548
+        },
+        {
+          "text": "problem.",
+          "start": 74.88,
+          "end": 75.48,
+          "confidence": 0.79
+        }
+      ]
+    },
+    {
+      "id": 42,
+      "seek": 7544,
+      "start": 75.48,
+      "end": 76.86,
+      "text": " Okay, no problem.",
+      "tokens": [
+        50364,
+        1033,
+        11,
+        572,
+        1154,
+        13,
+        50464
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.7493470907211304,
+      "compression_ratio": 0.68,
+      "no_speech_prob": 0.06937140226364136,
+      "confidence": 0.521,
+      "words": [
+        {
+          "text": "Okay,",
+          "start": 75.48,
+          "end": 76.28,
+          "confidence": 0.386
+        },
+        {
+          "text": "no",
+          "start": 76.28,
+          "end": 76.32,
+          "confidence": 0.472
+        },
+        {
+          "text": "problem.",
+          "start": 76.32,
+          "end": 76.86,
+          "confidence": 0.775
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/corner_cases.cpu/nocond.random_music.mp4.words.json b/tests/expected/corner_cases.cpu/nocond.random_music.mp4.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..cffe4045f2a305e00267c28fb344c5011039e8b1
--- /dev/null
+++ b/tests/expected/corner_cases.cpu/nocond.random_music.mp4.words.json
@@ -0,0 +1,3209 @@
+{
+  "text": " I Oh, the misery Everybody wants to be my enemy Spare the sympathy Everybody wants to be my enemy Look out for yourself My enemy Look out for yourself But I'm ready Your words up on the wall You don't need to say I'm ready your words up on the wall as you're praying for my phone and the laughter in the holes and the names that I've I stack it in my mind and I'm waiting for the time When I show you what it's like to be worse than a mind Tell you you're the greatest But once you turn they hate us Oh, the misery Everybody wants to be my enemy I smell the sympathy Everybody wants to be my enemy Look out for yourself My enemy Look out for yourself Look, okay I'm hoping that somebody pray for me I'm praying that somebody vote for me I'm staying where nobody's supposed to be I propose to be in a rink of emotions Ready to go whenever you let me know The road is long so put the pedal into the flow The enemy on my trail, my energy unavailable I'm a tell a monster the way go Way when the plot on my track to the top I been out of shape thinking that I'm a box I'm an astronaut Blast it off the planet rock the cause catastrophe And it matters more because ahead and not ahead I thought about wreaking havoc on an opposition Kinda shockin' they want it static with precision I'm automatic quarterback I ain't talkin' second Pack it pack it up I don't panic Better batter up who the baddest It don't matter cause we it's your Everybody wants to be my enemy Spare the sympathy Everybody wants to be my enemy Oh the misery Everybody wants to be my enemy Spare the sympathy Everybody wants to be my enemy I swear, I swear I'll never be a saint I swear, my enemy I swear, I swear I'll never be a saint You got to be yourself!",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.02,
+      "end": 0.4,
+      "text": " I",
+      "tokens": [
+        50364,
+        286,
+        50464
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.9367842674255371,
+      "compression_ratio": 0.1111111111111111,
+      "no_speech_prob": 0.7794302701950073,
+      "confidence": 0.032,
+      "words": [
+        {
+          "text": "I",
+          "start": 0.02,
+          "end": 0.4,
+          "confidence": 0.032
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 6000,
+      "start": 60.02,
+      "end": 68.54,
+      "text": " Oh, the misery Everybody wants to be my enemy",
+      "tokens": [
+        876,
+        11,
+        264,
+        32309,
+        7646,
+        2738,
+        281,
+        312,
+        452,
+        5945
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.7892291628081223,
+      "compression_ratio": 1.627906976744186,
+      "no_speech_prob": 0.8689420819282532,
+      "confidence": 0.669,
+      "words": [
+        {
+          "text": "Oh,",
+          "start": 60.02,
+          "end": 65.44,
+          "confidence": 0.084
+        },
+        {
+          "text": "the",
+          "start": 65.44,
+          "end": 65.48,
+          "confidence": 0.796
+        },
+        {
+          "text": "misery",
+          "start": 65.48,
+          "end": 66.08,
+          "confidence": 0.993
+        },
+        {
+          "text": "Everybody",
+          "start": 66.08,
+          "end": 67.62,
+          "confidence": 0.431
+        },
+        {
+          "text": "wants",
+          "start": 67.62,
+          "end": 68.0,
+          "confidence": 0.983
+        },
+        {
+          "text": "to",
+          "start": 68.0,
+          "end": 68.18,
+          "confidence": 0.993
+        },
+        {
+          "text": "be",
+          "start": 68.18,
+          "end": 68.38,
+          "confidence": 0.996
+        },
+        {
+          "text": "my",
+          "start": 68.38,
+          "end": 68.5,
+          "confidence": 0.984
+        },
+        {
+          "text": "enemy",
+          "start": 68.5,
+          "end": 68.54,
+          "confidence": 0.984
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 6000,
+      "start": 70.9,
+      "end": 75.92,
+      "text": " Spare the sympathy Everybody wants to be my enemy",
+      "tokens": [
+        1738,
+        543,
+        264,
+        33240,
+        7646,
+        2738,
+        281,
+        312,
+        452,
+        5945
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.7892291628081223,
+      "compression_ratio": 1.627906976744186,
+      "no_speech_prob": 0.8689420819282532,
+      "confidence": 0.932,
+      "words": [
+        {
+          "text": "Spare",
+          "start": 70.9,
+          "end": 71.48,
+          "confidence": 0.789
+        },
+        {
+          "text": "the",
+          "start": 71.48,
+          "end": 71.7,
+          "confidence": 0.97
+        },
+        {
+          "text": "sympathy",
+          "start": 71.7,
+          "end": 72.56,
+          "confidence": 0.993
+        },
+        {
+          "text": "Everybody",
+          "start": 72.56,
+          "end": 73.86,
+          "confidence": 0.959
+        },
+        {
+          "text": "wants",
+          "start": 73.86,
+          "end": 74.26,
+          "confidence": 0.994
+        },
+        {
+          "text": "to",
+          "start": 74.26,
+          "end": 74.42,
+          "confidence": 0.998
+        },
+        {
+          "text": "be",
+          "start": 74.42,
+          "end": 75.16,
+          "confidence": 0.999
+        },
+        {
+          "text": "my",
+          "start": 75.16,
+          "end": 75.64,
+          "confidence": 0.869
+        },
+        {
+          "text": "enemy",
+          "start": 75.64,
+          "end": 75.92,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 6000,
+      "start": 79.98,
+      "end": 80.5,
+      "text": " Look out for yourself My enemy",
+      "tokens": [
+        2053,
+        484,
+        337,
+        1803,
+        1222,
+        5945
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.7892291628081223,
+      "compression_ratio": 1.627906976744186,
+      "no_speech_prob": 0.8689420819282532,
+      "confidence": 0.778,
+      "words": [
+        {
+          "text": "Look",
+          "start": 79.98,
+          "end": 80.12,
+          "confidence": 0.446
+        },
+        {
+          "text": "out",
+          "start": 80.12,
+          "end": 80.34,
+          "confidence": 0.99
+        },
+        {
+          "text": "for",
+          "start": 80.34,
+          "end": 80.38,
+          "confidence": 0.991
+        },
+        {
+          "text": "yourself",
+          "start": 80.38,
+          "end": 80.42,
+          "confidence": 0.971
+        },
+        {
+          "text": "My",
+          "start": 80.42,
+          "end": 80.46,
+          "confidence": 0.533
+        },
+        {
+          "text": "enemy",
+          "start": 80.46,
+          "end": 80.5,
+          "confidence": 0.979
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 6000,
+      "start": 80.5,
+      "end": 81.28,
+      "text": " Look out for yourself But I'm ready",
+      "tokens": [
+        2053,
+        484,
+        337,
+        1803,
+        583,
+        286,
+        478,
+        1919
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.7892291628081223,
+      "compression_ratio": 1.627906976744186,
+      "no_speech_prob": 0.8689420819282532,
+      "confidence": 0.943,
+      "words": [
+        {
+          "text": "Look",
+          "start": 80.5,
+          "end": 80.54,
+          "confidence": 0.844
+        },
+        {
+          "text": "out",
+          "start": 80.54,
+          "end": 80.58,
+          "confidence": 0.994
+        },
+        {
+          "text": "for",
+          "start": 80.58,
+          "end": 80.62,
+          "confidence": 0.999
+        },
+        {
+          "text": "yourself",
+          "start": 80.62,
+          "end": 80.66,
+          "confidence": 0.999
+        },
+        {
+          "text": "But",
+          "start": 80.66,
+          "end": 80.7,
+          "confidence": 0.767
+        },
+        {
+          "text": "I'm",
+          "start": 80.7,
+          "end": 81.04,
+          "confidence": 0.99
+        },
+        {
+          "text": "ready",
+          "start": 81.04,
+          "end": 81.28,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 6000,
+      "start": 86.14,
+      "end": 88.28,
+      "text": " Your words up on the wall You don't need to say",
+      "tokens": [
+        2260,
+        2283,
+        493,
+        322,
+        264,
+        2929,
+        509,
+        500,
+        380,
+        643,
+        281,
+        584
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.7892291628081223,
+      "compression_ratio": 1.627906976744186,
+      "no_speech_prob": 0.8689420819282532,
+      "confidence": 0.361,
+      "words": [
+        {
+          "text": "Your",
+          "start": 86.14,
+          "end": 86.4,
+          "confidence": 0.618
+        },
+        {
+          "text": "words",
+          "start": 86.4,
+          "end": 86.44,
+          "confidence": 0.786
+        },
+        {
+          "text": "up",
+          "start": 86.44,
+          "end": 86.7,
+          "confidence": 0.891
+        },
+        {
+          "text": "on",
+          "start": 86.7,
+          "end": 86.98,
+          "confidence": 0.996
+        },
+        {
+          "text": "the",
+          "start": 86.98,
+          "end": 87.1,
+          "confidence": 0.985
+        },
+        {
+          "text": "wall",
+          "start": 87.1,
+          "end": 87.62,
+          "confidence": 0.711
+        },
+        {
+          "text": "You",
+          "start": 87.62,
+          "end": 87.92,
+          "confidence": 0.084
+        },
+        {
+          "text": "don't",
+          "start": 87.92,
+          "end": 88.16,
+          "confidence": 0.172
+        },
+        {
+          "text": "need",
+          "start": 88.16,
+          "end": 88.2,
+          "confidence": 0.149
+        },
+        {
+          "text": "to",
+          "start": 88.2,
+          "end": 88.24,
+          "confidence": 0.466
+        },
+        {
+          "text": "say",
+          "start": 88.24,
+          "end": 88.28,
+          "confidence": 0.094
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 8774,
+      "start": 88.28,
+      "end": 94.25,
+      "text": " I'm ready your words up on the wall as you're praying for my phone and the laughter in the holes and the names that I've",
+      "tokens": [
+        286,
+        478,
+        1919,
+        428,
+        2283,
+        493,
+        322,
+        264,
+        2929,
+        382,
+        291,
+        434,
+        15611,
+        337,
+        452,
+        2593,
+        293,
+        264,
+        13092,
+        294,
+        264,
+        8118,
+        293,
+        264,
+        5288,
+        300,
+        286,
+        600
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.26142611746060646,
+      "compression_ratio": 1.486842105263158,
+      "no_speech_prob": 0.8554685115814209,
+      "confidence": 0.773,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 88.28,
+          "end": 88.32,
+          "confidence": 0.459
+        },
+        {
+          "text": "ready",
+          "start": 88.32,
+          "end": 88.52,
+          "confidence": 0.976
+        },
+        {
+          "text": "your",
+          "start": 88.52,
+          "end": 88.9,
+          "confidence": 0.592
+        },
+        {
+          "text": "words",
+          "start": 88.9,
+          "end": 89.14,
+          "confidence": 0.987
+        },
+        {
+          "text": "up",
+          "start": 89.14,
+          "end": 89.46,
+          "confidence": 0.974
+        },
+        {
+          "text": "on",
+          "start": 89.46,
+          "end": 89.6,
+          "confidence": 0.979
+        },
+        {
+          "text": "the",
+          "start": 89.6,
+          "end": 89.66,
+          "confidence": 0.985
+        },
+        {
+          "text": "wall",
+          "start": 89.66,
+          "end": 90.12,
+          "confidence": 0.45
+        },
+        {
+          "text": "as",
+          "start": 90.12,
+          "end": 90.32,
+          "confidence": 0.489
+        },
+        {
+          "text": "you're",
+          "start": 90.32,
+          "end": 90.64,
+          "confidence": 0.817
+        },
+        {
+          "text": "praying",
+          "start": 90.64,
+          "end": 90.8,
+          "confidence": 0.962
+        },
+        {
+          "text": "for",
+          "start": 90.8,
+          "end": 91.06,
+          "confidence": 0.956
+        },
+        {
+          "text": "my",
+          "start": 91.06,
+          "end": 91.26,
+          "confidence": 0.965
+        },
+        {
+          "text": "phone",
+          "start": 91.26,
+          "end": 91.72,
+          "confidence": 0.63
+        },
+        {
+          "text": "and",
+          "start": 91.72,
+          "end": 91.9,
+          "confidence": 0.687
+        },
+        {
+          "text": "the",
+          "start": 91.9,
+          "end": 92.0,
+          "confidence": 0.948
+        },
+        {
+          "text": "laughter",
+          "start": 92.0,
+          "end": 92.36,
+          "confidence": 0.87
+        },
+        {
+          "text": "in",
+          "start": 92.36,
+          "end": 92.72,
+          "confidence": 0.905
+        },
+        {
+          "text": "the",
+          "start": 92.72,
+          "end": 92.88,
+          "confidence": 0.982
+        },
+        {
+          "text": "holes",
+          "start": 92.88,
+          "end": 93.24,
+          "confidence": 0.593
+        },
+        {
+          "text": "and",
+          "start": 93.24,
+          "end": 93.44,
+          "confidence": 0.6
+        },
+        {
+          "text": "the",
+          "start": 93.44,
+          "end": 93.52,
+          "confidence": 0.983
+        },
+        {
+          "text": "names",
+          "start": 93.52,
+          "end": 93.82,
+          "confidence": 0.98
+        },
+        {
+          "text": "that",
+          "start": 93.82,
+          "end": 94.08,
+          "confidence": 0.827
+        },
+        {
+          "text": "I've",
+          "start": 94.08,
+          "end": 94.25,
+          "confidence": 0.75
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 9418,
+      "start": 94.25,
+      "end": 97.84,
+      "text": " I stack it in my mind and I'm waiting for the time",
+      "tokens": [
+        286,
+        8630,
+        309,
+        294,
+        452,
+        1575,
+        293,
+        286,
+        478,
+        3806,
+        337,
+        264,
+        565
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.4302098981795772,
+      "compression_ratio": 1.388157894736842,
+      "no_speech_prob": 0.8590295314788818,
+      "confidence": 0.764,
+      "words": [
+        {
+          "text": "I",
+          "start": 94.25,
+          "end": 95.04,
+          "confidence": 0.29
+        },
+        {
+          "text": "stack",
+          "start": 95.04,
+          "end": 95.38,
+          "confidence": 0.341
+        },
+        {
+          "text": "it",
+          "start": 95.38,
+          "end": 95.7,
+          "confidence": 0.988
+        },
+        {
+          "text": "in",
+          "start": 95.7,
+          "end": 95.82,
+          "confidence": 0.987
+        },
+        {
+          "text": "my",
+          "start": 95.82,
+          "end": 96.02,
+          "confidence": 0.99
+        },
+        {
+          "text": "mind",
+          "start": 96.02,
+          "end": 96.42,
+          "confidence": 0.99
+        },
+        {
+          "text": "and",
+          "start": 96.42,
+          "end": 96.62,
+          "confidence": 0.382
+        },
+        {
+          "text": "I'm",
+          "start": 96.62,
+          "end": 96.72,
+          "confidence": 0.964
+        },
+        {
+          "text": "waiting",
+          "start": 96.72,
+          "end": 97.02,
+          "confidence": 0.952
+        },
+        {
+          "text": "for",
+          "start": 97.02,
+          "end": 97.34,
+          "confidence": 0.972
+        },
+        {
+          "text": "the",
+          "start": 97.34,
+          "end": 97.5,
+          "confidence": 0.986
+        },
+        {
+          "text": "time",
+          "start": 97.5,
+          "end": 97.84,
+          "confidence": 0.985
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 9418,
+      "start": 98.0,
+      "end": 101.24,
+      "text": " When I show you what it's like to be worse than a mind",
+      "tokens": [
+        1133,
+        286,
+        855,
+        291,
+        437,
+        309,
+        311,
+        411,
+        281,
+        312,
+        5324,
+        813,
+        257,
+        1575
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.4302098981795772,
+      "compression_ratio": 1.388157894736842,
+      "no_speech_prob": 0.8590295314788818,
+      "confidence": 0.655,
+      "words": [
+        {
+          "text": "When",
+          "start": 98.0,
+          "end": 98.18,
+          "confidence": 0.768
+        },
+        {
+          "text": "I",
+          "start": 98.18,
+          "end": 98.22,
+          "confidence": 0.989
+        },
+        {
+          "text": "show",
+          "start": 98.22,
+          "end": 98.48,
+          "confidence": 0.931
+        },
+        {
+          "text": "you",
+          "start": 98.48,
+          "end": 98.76,
+          "confidence": 0.988
+        },
+        {
+          "text": "what",
+          "start": 98.76,
+          "end": 98.94,
+          "confidence": 0.991
+        },
+        {
+          "text": "it's",
+          "start": 98.94,
+          "end": 99.42,
+          "confidence": 0.981
+        },
+        {
+          "text": "like",
+          "start": 99.42,
+          "end": 99.46,
+          "confidence": 0.997
+        },
+        {
+          "text": "to",
+          "start": 99.46,
+          "end": 99.72,
+          "confidence": 0.681
+        },
+        {
+          "text": "be",
+          "start": 99.72,
+          "end": 99.78,
+          "confidence": 0.995
+        },
+        {
+          "text": "worse",
+          "start": 99.78,
+          "end": 100.04,
+          "confidence": 0.659
+        },
+        {
+          "text": "than",
+          "start": 100.04,
+          "end": 100.36,
+          "confidence": 0.173
+        },
+        {
+          "text": "a",
+          "start": 100.36,
+          "end": 100.6,
+          "confidence": 0.112
+        },
+        {
+          "text": "mind",
+          "start": 100.6,
+          "end": 101.24,
+          "confidence": 0.463
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 9418,
+      "start": 102.06,
+      "end": 106.28,
+      "text": " Tell you you're the greatest",
+      "tokens": [
+        5115,
+        291,
+        291,
+        434,
+        264,
+        6636
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.4302098981795772,
+      "compression_ratio": 1.388157894736842,
+      "no_speech_prob": 0.8590295314788818,
+      "confidence": 0.919,
+      "words": [
+        {
+          "text": "Tell",
+          "start": 102.06,
+          "end": 102.1,
+          "confidence": 0.861
+        },
+        {
+          "text": "you",
+          "start": 102.1,
+          "end": 102.72,
+          "confidence": 0.991
+        },
+        {
+          "text": "you're",
+          "start": 102.72,
+          "end": 103.66,
+          "confidence": 0.855
+        },
+        {
+          "text": "the",
+          "start": 103.66,
+          "end": 104.1,
+          "confidence": 0.985
+        },
+        {
+          "text": "greatest",
+          "start": 104.1,
+          "end": 106.28,
+          "confidence": 0.978
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 9418,
+      "start": 107.14,
+      "end": 112.98,
+      "text": " But once you turn they hate us",
+      "tokens": [
+        583,
+        1564,
+        291,
+        1261,
+        436,
+        4700,
+        505
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.4302098981795772,
+      "compression_ratio": 1.388157894736842,
+      "no_speech_prob": 0.8590295314788818,
+      "confidence": 0.893,
+      "words": [
+        {
+          "text": "But",
+          "start": 107.14,
+          "end": 107.54,
+          "confidence": 0.976
+        },
+        {
+          "text": "once",
+          "start": 107.54,
+          "end": 108.38,
+          "confidence": 0.799
+        },
+        {
+          "text": "you",
+          "start": 108.38,
+          "end": 108.92,
+          "confidence": 0.998
+        },
+        {
+          "text": "turn",
+          "start": 108.92,
+          "end": 109.84,
+          "confidence": 0.889
+        },
+        {
+          "text": "they",
+          "start": 109.84,
+          "end": 110.4,
+          "confidence": 0.662
+        },
+        {
+          "text": "hate",
+          "start": 110.4,
+          "end": 111.88,
+          "confidence": 0.99
+        },
+        {
+          "text": "us",
+          "start": 111.88,
+          "end": 112.98,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 9418,
+      "start": 114.54,
+      "end": 119.18,
+      "text": " Oh, the misery Everybody wants to be my enemy",
+      "tokens": [
+        876,
+        11,
+        264,
+        32309,
+        7646,
+        2738,
+        281,
+        312,
+        452,
+        5945
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.4302098981795772,
+      "compression_ratio": 1.388157894736842,
+      "no_speech_prob": 0.8590295314788818,
+      "confidence": 0.874,
+      "words": [
+        {
+          "text": "Oh,",
+          "start": 114.54,
+          "end": 115.32,
+          "confidence": 0.74
+        },
+        {
+          "text": "the",
+          "start": 115.32,
+          "end": 115.36,
+          "confidence": 0.97
+        },
+        {
+          "text": "misery",
+          "start": 115.36,
+          "end": 116.36,
+          "confidence": 0.999
+        },
+        {
+          "text": "Everybody",
+          "start": 116.36,
+          "end": 117.52,
+          "confidence": 0.432
+        },
+        {
+          "text": "wants",
+          "start": 117.52,
+          "end": 117.9,
+          "confidence": 0.989
+        },
+        {
+          "text": "to",
+          "start": 117.9,
+          "end": 118.24,
+          "confidence": 0.998
+        },
+        {
+          "text": "be",
+          "start": 118.24,
+          "end": 118.28,
+          "confidence": 0.998
+        },
+        {
+          "text": "my",
+          "start": 118.28,
+          "end": 118.54,
+          "confidence": 0.997
+        },
+        {
+          "text": "enemy",
+          "start": 118.54,
+          "end": 119.18,
+          "confidence": 0.984
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 12018,
+      "start": 120.2,
+      "end": 122.16,
+      "text": " I smell the sympathy",
+      "tokens": [
+        286,
+        4316,
+        264,
+        33240
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3580510299817651,
+      "compression_ratio": 1.7621145374449338,
+      "no_speech_prob": 0.8322692513465881,
+      "confidence": 0.755,
+      "words": [
+        {
+          "text": "I",
+          "start": 120.2,
+          "end": 120.54,
+          "confidence": 0.42
+        },
+        {
+          "text": "smell",
+          "start": 120.54,
+          "end": 121.36,
+          "confidence": 0.889
+        },
+        {
+          "text": "the",
+          "start": 121.36,
+          "end": 121.76,
+          "confidence": 0.892
+        },
+        {
+          "text": "sympathy",
+          "start": 121.76,
+          "end": 122.16,
+          "confidence": 0.979
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 12018,
+      "start": 122.16,
+      "end": 126.08,
+      "text": " Everybody wants to be my enemy",
+      "tokens": [
+        7646,
+        2738,
+        281,
+        312,
+        452,
+        5945
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3580510299817651,
+      "compression_ratio": 1.7621145374449338,
+      "no_speech_prob": 0.8322692513465881,
+      "confidence": 0.912,
+      "words": [
+        {
+          "text": "Everybody",
+          "start": 122.16,
+          "end": 123.72,
+          "confidence": 0.923
+        },
+        {
+          "text": "wants",
+          "start": 123.72,
+          "end": 124.1,
+          "confidence": 0.984
+        },
+        {
+          "text": "to",
+          "start": 124.1,
+          "end": 124.68,
+          "confidence": 0.995
+        },
+        {
+          "text": "be",
+          "start": 124.68,
+          "end": 125.24,
+          "confidence": 0.996
+        },
+        {
+          "text": "my",
+          "start": 125.24,
+          "end": 125.5,
+          "confidence": 0.659
+        },
+        {
+          "text": "enemy",
+          "start": 125.5,
+          "end": 126.08,
+          "confidence": 0.97
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 12018,
+      "start": 129.9,
+      "end": 130.86,
+      "text": " Look out for yourself",
+      "tokens": [
+        2053,
+        484,
+        337,
+        1803
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3580510299817651,
+      "compression_ratio": 1.7621145374449338,
+      "no_speech_prob": 0.8322692513465881,
+      "confidence": 0.731,
+      "words": [
+        {
+          "text": "Look",
+          "start": 129.9,
+          "end": 130.04,
+          "confidence": 0.313
+        },
+        {
+          "text": "out",
+          "start": 130.04,
+          "end": 130.3,
+          "confidence": 0.932
+        },
+        {
+          "text": "for",
+          "start": 130.3,
+          "end": 130.44,
+          "confidence": 0.991
+        },
+        {
+          "text": "yourself",
+          "start": 130.44,
+          "end": 130.86,
+          "confidence": 0.986
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 12018,
+      "start": 131.52,
+      "end": 132.54,
+      "text": " My enemy",
+      "tokens": [
+        1222,
+        5945
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3580510299817651,
+      "compression_ratio": 1.7621145374449338,
+      "no_speech_prob": 0.8322692513465881,
+      "confidence": 0.937,
+      "words": [
+        {
+          "text": "My",
+          "start": 131.52,
+          "end": 131.74,
+          "confidence": 0.891
+        },
+        {
+          "text": "enemy",
+          "start": 131.74,
+          "end": 132.54,
+          "confidence": 0.985
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 12018,
+      "start": 136.06,
+      "end": 137.14,
+      "text": " Look out for yourself",
+      "tokens": [
+        2053,
+        484,
+        337,
+        1803
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3580510299817651,
+      "compression_ratio": 1.7621145374449338,
+      "no_speech_prob": 0.8322692513465881,
+      "confidence": 0.991,
+      "words": [
+        {
+          "text": "Look",
+          "start": 136.06,
+          "end": 136.18,
+          "confidence": 0.974
+        },
+        {
+          "text": "out",
+          "start": 136.18,
+          "end": 136.54,
+          "confidence": 0.994
+        },
+        {
+          "text": "for",
+          "start": 136.54,
+          "end": 136.74,
+          "confidence": 0.999
+        },
+        {
+          "text": "yourself",
+          "start": 136.74,
+          "end": 137.14,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 17,
+      "seek": 12018,
+      "start": 137.66,
+      "end": 140.18,
+      "text": " Look, okay I'm hoping that somebody pray for me",
+      "tokens": [
+        2053,
+        11,
+        1392,
+        286,
+        478,
+        7159,
+        300,
+        2618,
+        3690,
+        337,
+        385
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3580510299817651,
+      "compression_ratio": 1.7621145374449338,
+      "no_speech_prob": 0.8322692513465881,
+      "confidence": 0.792,
+      "words": [
+        {
+          "text": "Look,",
+          "start": 137.66,
+          "end": 138.46,
+          "confidence": 0.849
+        },
+        {
+          "text": "okay",
+          "start": 138.46,
+          "end": 138.6,
+          "confidence": 0.646
+        },
+        {
+          "text": "I'm",
+          "start": 138.6,
+          "end": 138.86,
+          "confidence": 0.658
+        },
+        {
+          "text": "hoping",
+          "start": 138.86,
+          "end": 139.12,
+          "confidence": 0.576
+        },
+        {
+          "text": "that",
+          "start": 139.12,
+          "end": 139.32,
+          "confidence": 0.958
+        },
+        {
+          "text": "somebody",
+          "start": 139.32,
+          "end": 139.52,
+          "confidence": 0.975
+        },
+        {
+          "text": "pray",
+          "start": 139.52,
+          "end": 139.8,
+          "confidence": 0.85
+        },
+        {
+          "text": "for",
+          "start": 139.8,
+          "end": 140.02,
+          "confidence": 0.899
+        },
+        {
+          "text": "me",
+          "start": 140.02,
+          "end": 140.18,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 18,
+      "seek": 12018,
+      "start": 140.38,
+      "end": 141.64,
+      "text": " I'm praying that somebody vote for me",
+      "tokens": [
+        286,
+        478,
+        15611,
+        300,
+        2618,
+        4740,
+        337,
+        385
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3580510299817651,
+      "compression_ratio": 1.7621145374449338,
+      "no_speech_prob": 0.8322692513465881,
+      "confidence": 0.821,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 140.38,
+          "end": 140.58,
+          "confidence": 0.756
+        },
+        {
+          "text": "praying",
+          "start": 140.58,
+          "end": 140.62,
+          "confidence": 0.956
+        },
+        {
+          "text": "that",
+          "start": 140.62,
+          "end": 140.82,
+          "confidence": 0.959
+        },
+        {
+          "text": "somebody",
+          "start": 140.82,
+          "end": 141.06,
+          "confidence": 0.995
+        },
+        {
+          "text": "vote",
+          "start": 141.06,
+          "end": 141.32,
+          "confidence": 0.396
+        },
+        {
+          "text": "for",
+          "start": 141.32,
+          "end": 141.52,
+          "confidence": 0.999
+        },
+        {
+          "text": "me",
+          "start": 141.52,
+          "end": 141.64,
+          "confidence": 1.0
+        }
+      ]
+    },
+    {
+      "id": 19,
+      "seek": 12018,
+      "start": 141.72,
+      "end": 143.2,
+      "text": " I'm staying where nobody's supposed to be",
+      "tokens": [
+        286,
+        478,
+        7939,
+        689,
+        5079,
+        311,
+        3442,
+        281,
+        312
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3580510299817651,
+      "compression_ratio": 1.7621145374449338,
+      "no_speech_prob": 0.8322692513465881,
+      "confidence": 0.893,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 141.72,
+          "end": 141.9,
+          "confidence": 0.937
+        },
+        {
+          "text": "staying",
+          "start": 141.9,
+          "end": 142.12,
+          "confidence": 0.82
+        },
+        {
+          "text": "where",
+          "start": 142.12,
+          "end": 142.3,
+          "confidence": 0.976
+        },
+        {
+          "text": "nobody's",
+          "start": 142.3,
+          "end": 142.88,
+          "confidence": 0.735
+        },
+        {
+          "text": "supposed",
+          "start": 142.88,
+          "end": 142.92,
+          "confidence": 0.957
+        },
+        {
+          "text": "to",
+          "start": 142.92,
+          "end": 143.12,
+          "confidence": 0.998
+        },
+        {
+          "text": "be",
+          "start": 143.12,
+          "end": 143.2,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 20,
+      "seek": 12018,
+      "start": 143.2,
+      "end": 144.86,
+      "text": " I propose to be in a rink of emotions",
+      "tokens": [
+        286,
+        17421,
+        281,
+        312,
+        294,
+        257,
+        367,
+        475,
+        295,
+        8462
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3580510299817651,
+      "compression_ratio": 1.7621145374449338,
+      "no_speech_prob": 0.8322692513465881,
+      "confidence": 0.554,
+      "words": [
+        {
+          "text": "I",
+          "start": 143.2,
+          "end": 143.36,
+          "confidence": 0.354
+        },
+        {
+          "text": "propose",
+          "start": 143.36,
+          "end": 143.64,
+          "confidence": 0.323
+        },
+        {
+          "text": "to",
+          "start": 143.64,
+          "end": 143.86,
+          "confidence": 0.856
+        },
+        {
+          "text": "be",
+          "start": 143.86,
+          "end": 144.04,
+          "confidence": 0.579
+        },
+        {
+          "text": "in",
+          "start": 144.04,
+          "end": 144.18,
+          "confidence": 0.837
+        },
+        {
+          "text": "a",
+          "start": 144.18,
+          "end": 144.24,
+          "confidence": 0.631
+        },
+        {
+          "text": "rink",
+          "start": 144.24,
+          "end": 144.42,
+          "confidence": 0.309
+        },
+        {
+          "text": "of",
+          "start": 144.42,
+          "end": 144.54,
+          "confidence": 0.996
+        },
+        {
+          "text": "emotions",
+          "start": 144.54,
+          "end": 144.86,
+          "confidence": 0.952
+        }
+      ]
+    },
+    {
+      "id": 21,
+      "seek": 12018,
+      "start": 145.06,
+      "end": 146.28,
+      "text": " Ready to go whenever you let me know",
+      "tokens": [
+        9944,
+        281,
+        352,
+        5699,
+        291,
+        718,
+        385,
+        458
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3580510299817651,
+      "compression_ratio": 1.7621145374449338,
+      "no_speech_prob": 0.8322692513465881,
+      "confidence": 0.902,
+      "words": [
+        {
+          "text": "Ready",
+          "start": 145.06,
+          "end": 145.26,
+          "confidence": 0.938
+        },
+        {
+          "text": "to",
+          "start": 145.26,
+          "end": 145.5,
+          "confidence": 0.997
+        },
+        {
+          "text": "go",
+          "start": 145.5,
+          "end": 145.58,
+          "confidence": 0.996
+        },
+        {
+          "text": "whenever",
+          "start": 145.58,
+          "end": 145.74,
+          "confidence": 0.85
+        },
+        {
+          "text": "you",
+          "start": 145.74,
+          "end": 145.92,
+          "confidence": 0.575
+        },
+        {
+          "text": "let",
+          "start": 145.92,
+          "end": 146.04,
+          "confidence": 0.97
+        },
+        {
+          "text": "me",
+          "start": 146.04,
+          "end": 146.16,
+          "confidence": 0.998
+        },
+        {
+          "text": "know",
+          "start": 146.16,
+          "end": 146.28,
+          "confidence": 0.992
+        }
+      ]
+    },
+    {
+      "id": 22,
+      "seek": 12018,
+      "start": 146.28,
+      "end": 147.84,
+      "text": " The road is long so put the pedal into the flow",
+      "tokens": [
+        440,
+        3060,
+        307,
+        938,
+        370,
+        829,
+        264,
+        19122,
+        666,
+        264,
+        3095
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3580510299817651,
+      "compression_ratio": 1.7621145374449338,
+      "no_speech_prob": 0.8322692513465881,
+      "confidence": 0.944,
+      "words": [
+        {
+          "text": "The",
+          "start": 146.28,
+          "end": 146.5,
+          "confidence": 0.977
+        },
+        {
+          "text": "road",
+          "start": 146.5,
+          "end": 146.64,
+          "confidence": 0.989
+        },
+        {
+          "text": "is",
+          "start": 146.64,
+          "end": 146.74,
+          "confidence": 0.977
+        },
+        {
+          "text": "long",
+          "start": 146.74,
+          "end": 146.9,
+          "confidence": 0.936
+        },
+        {
+          "text": "so",
+          "start": 146.9,
+          "end": 147.04,
+          "confidence": 0.811
+        },
+        {
+          "text": "put",
+          "start": 147.04,
+          "end": 147.16,
+          "confidence": 0.94
+        },
+        {
+          "text": "the",
+          "start": 147.16,
+          "end": 147.3,
+          "confidence": 0.969
+        },
+        {
+          "text": "pedal",
+          "start": 147.3,
+          "end": 147.4,
+          "confidence": 0.947
+        },
+        {
+          "text": "into",
+          "start": 147.4,
+          "end": 147.58,
+          "confidence": 0.955
+        },
+        {
+          "text": "the",
+          "start": 147.58,
+          "end": 147.76,
+          "confidence": 0.993
+        },
+        {
+          "text": "flow",
+          "start": 147.76,
+          "end": 147.84,
+          "confidence": 0.902
+        }
+      ]
+    },
+    {
+      "id": 23,
+      "seek": 12018,
+      "start": 147.96,
+      "end": 149.78,
+      "text": " The enemy on my trail, my energy unavailable",
+      "tokens": [
+        440,
+        5945,
+        322,
+        452,
+        9924,
+        11,
+        452,
+        2281,
+        36541,
+        32699
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.3580510299817651,
+      "compression_ratio": 1.7621145374449338,
+      "no_speech_prob": 0.8322692513465881,
+      "confidence": 0.866,
+      "words": [
+        {
+          "text": "The",
+          "start": 147.96,
+          "end": 148.08,
+          "confidence": 0.714
+        },
+        {
+          "text": "enemy",
+          "start": 148.08,
+          "end": 148.24,
+          "confidence": 0.473
+        },
+        {
+          "text": "on",
+          "start": 148.24,
+          "end": 148.44,
+          "confidence": 0.969
+        },
+        {
+          "text": "my",
+          "start": 148.44,
+          "end": 148.54,
+          "confidence": 0.977
+        },
+        {
+          "text": "trail,",
+          "start": 148.54,
+          "end": 148.76,
+          "confidence": 0.993
+        },
+        {
+          "text": "my",
+          "start": 148.76,
+          "end": 148.8,
+          "confidence": 0.988
+        },
+        {
+          "text": "energy",
+          "start": 148.8,
+          "end": 149.06,
+          "confidence": 0.993
+        },
+        {
+          "text": "unavailable",
+          "start": 149.06,
+          "end": 149.78,
+          "confidence": 0.935
+        }
+      ]
+    },
+    {
+      "id": 24,
+      "seek": 14968,
+      "start": 150.0,
+      "end": 151.16,
+      "text": " I'm a tell a monster the way go",
+      "tokens": [
+        286,
+        478,
+        257,
+        980,
+        257,
+        10090,
+        264,
+        636,
+        352
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.5499832056745698,
+      "compression_ratio": 1.8025078369905956,
+      "no_speech_prob": 0.8352975249290466,
+      "confidence": 0.443,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 150.0,
+          "end": 150.18,
+          "confidence": 0.73
+        },
+        {
+          "text": "a",
+          "start": 150.18,
+          "end": 150.28,
+          "confidence": 0.203
+        },
+        {
+          "text": "tell",
+          "start": 150.28,
+          "end": 150.34,
+          "confidence": 0.507
+        },
+        {
+          "text": "a",
+          "start": 150.34,
+          "end": 150.46,
+          "confidence": 0.137
+        },
+        {
+          "text": "monster",
+          "start": 150.46,
+          "end": 150.66,
+          "confidence": 0.238
+        },
+        {
+          "text": "the",
+          "start": 150.66,
+          "end": 150.9,
+          "confidence": 0.585
+        },
+        {
+          "text": "way",
+          "start": 150.9,
+          "end": 150.98,
+          "confidence": 0.953
+        },
+        {
+          "text": "go",
+          "start": 150.98,
+          "end": 151.16,
+          "confidence": 0.664
+        }
+      ]
+    },
+    {
+      "id": 25,
+      "seek": 14968,
+      "start": 151.2,
+      "end": 152.54,
+      "text": " Way when the plot on my track to the top",
+      "tokens": [
+        9558,
+        562,
+        264,
+        7542,
+        322,
+        452,
+        2837,
+        281,
+        264,
+        1192
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.5499832056745698,
+      "compression_ratio": 1.8025078369905956,
+      "no_speech_prob": 0.8352975249290466,
+      "confidence": 0.517,
+      "words": [
+        {
+          "text": "Way",
+          "start": 151.2,
+          "end": 151.38,
+          "confidence": 0.102
+        },
+        {
+          "text": "when",
+          "start": 151.38,
+          "end": 151.54,
+          "confidence": 0.434
+        },
+        {
+          "text": "the",
+          "start": 151.54,
+          "end": 151.66,
+          "confidence": 0.263
+        },
+        {
+          "text": "plot",
+          "start": 151.66,
+          "end": 151.78,
+          "confidence": 0.627
+        },
+        {
+          "text": "on",
+          "start": 151.78,
+          "end": 151.92,
+          "confidence": 0.605
+        },
+        {
+          "text": "my",
+          "start": 151.92,
+          "end": 152.0,
+          "confidence": 0.975
+        },
+        {
+          "text": "track",
+          "start": 152.0,
+          "end": 152.14,
+          "confidence": 0.338
+        },
+        {
+          "text": "to",
+          "start": 152.14,
+          "end": 152.32,
+          "confidence": 0.946
+        },
+        {
+          "text": "the",
+          "start": 152.32,
+          "end": 152.4,
+          "confidence": 0.991
+        },
+        {
+          "text": "top",
+          "start": 152.4,
+          "end": 152.54,
+          "confidence": 0.993
+        }
+      ]
+    },
+    {
+      "id": 26,
+      "seek": 14968,
+      "start": 152.54,
+      "end": 154.32,
+      "text": " I been out of shape thinking that I'm a box I'm an astronaut",
+      "tokens": [
+        286,
+        668,
+        484,
+        295,
+        3909,
+        1953,
+        300,
+        286,
+        478,
+        257,
+        2424,
+        286,
+        478,
+        364,
+        18516
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.5499832056745698,
+      "compression_ratio": 1.8025078369905956,
+      "no_speech_prob": 0.8352975249290466,
+      "confidence": 0.667,
+      "words": [
+        {
+          "text": "I",
+          "start": 152.54,
+          "end": 152.7,
+          "confidence": 0.972
+        },
+        {
+          "text": "been",
+          "start": 152.7,
+          "end": 152.76,
+          "confidence": 0.691
+        },
+        {
+          "text": "out",
+          "start": 152.76,
+          "end": 152.9,
+          "confidence": 0.72
+        },
+        {
+          "text": "of",
+          "start": 152.9,
+          "end": 153.0,
+          "confidence": 0.959
+        },
+        {
+          "text": "shape",
+          "start": 153.0,
+          "end": 153.1,
+          "confidence": 0.998
+        },
+        {
+          "text": "thinking",
+          "start": 153.1,
+          "end": 153.3,
+          "confidence": 0.385
+        },
+        {
+          "text": "that",
+          "start": 153.3,
+          "end": 153.5,
+          "confidence": 0.353
+        },
+        {
+          "text": "I'm",
+          "start": 153.5,
+          "end": 153.66,
+          "confidence": 0.572
+        },
+        {
+          "text": "a",
+          "start": 153.66,
+          "end": 153.7,
+          "confidence": 0.703
+        },
+        {
+          "text": "box",
+          "start": 153.7,
+          "end": 153.74,
+          "confidence": 0.874
+        },
+        {
+          "text": "I'm",
+          "start": 153.74,
+          "end": 153.92,
+          "confidence": 0.451
+        },
+        {
+          "text": "an",
+          "start": 153.92,
+          "end": 153.96,
+          "confidence": 0.976
+        },
+        {
+          "text": "astronaut",
+          "start": 153.96,
+          "end": 154.32,
+          "confidence": 0.926
+        }
+      ]
+    },
+    {
+      "id": 27,
+      "seek": 14968,
+      "start": 154.52,
+      "end": 156.34,
+      "text": " Blast it off the planet rock the cause catastrophe",
+      "tokens": [
+        2177,
+        525,
+        309,
+        766,
+        264,
+        5054,
+        3727,
+        264,
+        3082,
+        36043
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.5499832056745698,
+      "compression_ratio": 1.8025078369905956,
+      "no_speech_prob": 0.8352975249290466,
+      "confidence": 0.583,
+      "words": [
+        {
+          "text": "Blast",
+          "start": 154.52,
+          "end": 154.76,
+          "confidence": 0.476
+        },
+        {
+          "text": "it",
+          "start": 154.76,
+          "end": 154.9,
+          "confidence": 0.954
+        },
+        {
+          "text": "off",
+          "start": 154.9,
+          "end": 155.02,
+          "confidence": 0.984
+        },
+        {
+          "text": "the",
+          "start": 155.02,
+          "end": 155.2,
+          "confidence": 0.956
+        },
+        {
+          "text": "planet",
+          "start": 155.2,
+          "end": 155.34,
+          "confidence": 0.99
+        },
+        {
+          "text": "rock",
+          "start": 155.34,
+          "end": 155.52,
+          "confidence": 0.24
+        },
+        {
+          "text": "the",
+          "start": 155.52,
+          "end": 155.68,
+          "confidence": 0.301
+        },
+        {
+          "text": "cause",
+          "start": 155.68,
+          "end": 155.88,
+          "confidence": 0.701
+        },
+        {
+          "text": "catastrophe",
+          "start": 155.88,
+          "end": 156.34,
+          "confidence": 0.444
+        }
+      ]
+    },
+    {
+      "id": 28,
+      "seek": 14968,
+      "start": 156.44,
+      "end": 158.08,
+      "text": " And it matters more because ahead and not ahead",
+      "tokens": [
+        400,
+        309,
+        7001,
+        544,
+        570,
+        2286,
+        293,
+        406,
+        2286
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.5499832056745698,
+      "compression_ratio": 1.8025078369905956,
+      "no_speech_prob": 0.8352975249290466,
+      "confidence": 0.721,
+      "words": [
+        {
+          "text": "And",
+          "start": 156.44,
+          "end": 156.64,
+          "confidence": 0.828
+        },
+        {
+          "text": "it",
+          "start": 156.64,
+          "end": 156.78,
+          "confidence": 0.715
+        },
+        {
+          "text": "matters",
+          "start": 156.78,
+          "end": 156.94,
+          "confidence": 0.994
+        },
+        {
+          "text": "more",
+          "start": 156.94,
+          "end": 157.16,
+          "confidence": 0.981
+        },
+        {
+          "text": "because",
+          "start": 157.16,
+          "end": 157.38,
+          "confidence": 0.909
+        },
+        {
+          "text": "ahead",
+          "start": 157.38,
+          "end": 157.64,
+          "confidence": 0.432
+        },
+        {
+          "text": "and",
+          "start": 157.64,
+          "end": 157.82,
+          "confidence": 0.616
+        },
+        {
+          "text": "not",
+          "start": 157.82,
+          "end": 157.94,
+          "confidence": 0.716
+        },
+        {
+          "text": "ahead",
+          "start": 157.94,
+          "end": 158.08,
+          "confidence": 0.524
+        }
+      ]
+    },
+    {
+      "id": 29,
+      "seek": 14968,
+      "start": 158.1,
+      "end": 159.74,
+      "text": " I thought about wreaking havoc on an opposition",
+      "tokens": [
+        286,
+        1194,
+        466,
+        46674,
+        2456,
+        47367,
+        322,
+        364,
+        13504
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.5499832056745698,
+      "compression_ratio": 1.8025078369905956,
+      "no_speech_prob": 0.8352975249290466,
+      "confidence": 0.963,
+      "words": [
+        {
+          "text": "I",
+          "start": 158.1,
+          "end": 158.24,
+          "confidence": 0.986
+        },
+        {
+          "text": "thought",
+          "start": 158.24,
+          "end": 158.36,
+          "confidence": 0.977
+        },
+        {
+          "text": "about",
+          "start": 158.36,
+          "end": 158.58,
+          "confidence": 0.975
+        },
+        {
+          "text": "wreaking",
+          "start": 158.58,
+          "end": 158.84,
+          "confidence": 0.944
+        },
+        {
+          "text": "havoc",
+          "start": 158.84,
+          "end": 159.08,
+          "confidence": 1.0
+        },
+        {
+          "text": "on",
+          "start": 159.08,
+          "end": 159.3,
+          "confidence": 0.944
+        },
+        {
+          "text": "an",
+          "start": 159.3,
+          "end": 159.44,
+          "confidence": 0.913
+        },
+        {
+          "text": "opposition",
+          "start": 159.44,
+          "end": 159.74,
+          "confidence": 0.987
+        }
+      ]
+    },
+    {
+      "id": 30,
+      "seek": 14968,
+      "start": 159.88,
+      "end": 161.52,
+      "text": " Kinda shockin' they want it static with precision",
+      "tokens": [
+        35553,
+        5588,
+        259,
+        6,
+        436,
+        528,
+        309,
+        13437,
+        365,
+        18356
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.5499832056745698,
+      "compression_ratio": 1.8025078369905956,
+      "no_speech_prob": 0.8352975249290466,
+      "confidence": 0.537,
+      "words": [
+        {
+          "text": "Kinda",
+          "start": 159.88,
+          "end": 160.1,
+          "confidence": 0.574
+        },
+        {
+          "text": "shockin'",
+          "start": 160.1,
+          "end": 160.5,
+          "confidence": 0.408
+        },
+        {
+          "text": "they",
+          "start": 160.5,
+          "end": 160.58,
+          "confidence": 0.371
+        },
+        {
+          "text": "want",
+          "start": 160.58,
+          "end": 160.74,
+          "confidence": 0.454
+        },
+        {
+          "text": "it",
+          "start": 160.74,
+          "end": 160.84,
+          "confidence": 0.577
+        },
+        {
+          "text": "static",
+          "start": 160.84,
+          "end": 161.02,
+          "confidence": 0.993
+        },
+        {
+          "text": "with",
+          "start": 161.02,
+          "end": 161.22,
+          "confidence": 0.609
+        },
+        {
+          "text": "precision",
+          "start": 161.22,
+          "end": 161.52,
+          "confidence": 0.877
+        }
+      ]
+    },
+    {
+      "id": 31,
+      "seek": 14968,
+      "start": 161.62,
+      "end": 163.36,
+      "text": " I'm automatic quarterback I ain't talkin' second",
+      "tokens": [
+        286,
+        478,
+        12509,
+        31952,
+        286,
+        7862,
+        380,
+        39243,
+        6,
+        1150
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.5499832056745698,
+      "compression_ratio": 1.8025078369905956,
+      "no_speech_prob": 0.8352975249290466,
+      "confidence": 0.735,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 161.62,
+          "end": 161.78,
+          "confidence": 0.935
+        },
+        {
+          "text": "automatic",
+          "start": 161.78,
+          "end": 162.18,
+          "confidence": 0.975
+        },
+        {
+          "text": "quarterback",
+          "start": 162.18,
+          "end": 162.58,
+          "confidence": 0.419
+        },
+        {
+          "text": "I",
+          "start": 162.58,
+          "end": 162.8,
+          "confidence": 0.405
+        },
+        {
+          "text": "ain't",
+          "start": 162.8,
+          "end": 162.88,
+          "confidence": 0.968
+        },
+        {
+          "text": "talkin'",
+          "start": 162.88,
+          "end": 163.18,
+          "confidence": 0.783
+        },
+        {
+          "text": "second",
+          "start": 163.18,
+          "end": 163.36,
+          "confidence": 0.556
+        }
+      ]
+    },
+    {
+      "id": 32,
+      "seek": 14968,
+      "start": 163.4,
+      "end": 164.58,
+      "text": " Pack it pack it up I don't panic",
+      "tokens": [
+        18466,
+        309,
+        2844,
+        309,
+        493,
+        286,
+        500,
+        380,
+        14783
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.5499832056745698,
+      "compression_ratio": 1.8025078369905956,
+      "no_speech_prob": 0.8352975249290466,
+      "confidence": 0.786,
+      "words": [
+        {
+          "text": "Pack",
+          "start": 163.4,
+          "end": 163.6,
+          "confidence": 0.931
+        },
+        {
+          "text": "it",
+          "start": 163.6,
+          "end": 163.66,
+          "confidence": 0.88
+        },
+        {
+          "text": "pack",
+          "start": 163.66,
+          "end": 163.82,
+          "confidence": 0.298
+        },
+        {
+          "text": "it",
+          "start": 163.82,
+          "end": 164.04,
+          "confidence": 0.994
+        },
+        {
+          "text": "up",
+          "start": 164.04,
+          "end": 164.1,
+          "confidence": 0.977
+        },
+        {
+          "text": "I",
+          "start": 164.1,
+          "end": 164.2,
+          "confidence": 0.637
+        },
+        {
+          "text": "don't",
+          "start": 164.2,
+          "end": 164.54,
+          "confidence": 0.87
+        },
+        {
+          "text": "panic",
+          "start": 164.54,
+          "end": 164.58,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 33,
+      "seek": 14968,
+      "start": 164.58,
+      "end": 165.7,
+      "text": " Better batter up who the baddest",
+      "tokens": [
+        15753,
+        4220,
+        493,
+        567,
+        264,
+        1578,
+        23748
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.5499832056745698,
+      "compression_ratio": 1.8025078369905956,
+      "no_speech_prob": 0.8352975249290466,
+      "confidence": 0.703,
+      "words": [
+        {
+          "text": "Better",
+          "start": 164.58,
+          "end": 164.82,
+          "confidence": 0.627
+        },
+        {
+          "text": "batter",
+          "start": 164.82,
+          "end": 165.1,
+          "confidence": 0.265
+        },
+        {
+          "text": "up",
+          "start": 165.1,
+          "end": 165.24,
+          "confidence": 0.963
+        },
+        {
+          "text": "who",
+          "start": 165.24,
+          "end": 165.4,
+          "confidence": 0.861
+        },
+        {
+          "text": "the",
+          "start": 165.4,
+          "end": 165.52,
+          "confidence": 0.973
+        },
+        {
+          "text": "baddest",
+          "start": 165.52,
+          "end": 165.7,
+          "confidence": 0.797
+        }
+      ]
+    },
+    {
+      "id": 34,
+      "seek": 14968,
+      "start": 165.7,
+      "end": 166.74,
+      "text": " It don't matter cause we it's your",
+      "tokens": [
+        467,
+        500,
+        380,
+        1871,
+        3082,
+        321,
+        309,
+        311,
+        428
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.5499832056745698,
+      "compression_ratio": 1.8025078369905956,
+      "no_speech_prob": 0.8352975249290466,
+      "confidence": 0.727,
+      "words": [
+        {
+          "text": "It",
+          "start": 165.7,
+          "end": 165.9,
+          "confidence": 0.979
+        },
+        {
+          "text": "don't",
+          "start": 165.9,
+          "end": 166.14,
+          "confidence": 0.995
+        },
+        {
+          "text": "matter",
+          "start": 166.14,
+          "end": 166.18,
+          "confidence": 0.998
+        },
+        {
+          "text": "cause",
+          "start": 166.18,
+          "end": 166.4,
+          "confidence": 0.588
+        },
+        {
+          "text": "we",
+          "start": 166.4,
+          "end": 166.52,
+          "confidence": 0.973
+        },
+        {
+          "text": "it's",
+          "start": 166.52,
+          "end": 166.7,
+          "confidence": 0.404
+        },
+        {
+          "text": "your",
+          "start": 166.7,
+          "end": 166.74,
+          "confidence": 0.632
+        }
+      ]
+    },
+    {
+      "id": 35,
+      "seek": 14968,
+      "start": 166.8,
+      "end": 169.52,
+      "text": " Everybody wants to be my enemy",
+      "tokens": [
+        7646,
+        2738,
+        281,
+        312,
+        452,
+        5945
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.5499832056745698,
+      "compression_ratio": 1.8025078369905956,
+      "no_speech_prob": 0.8352975249290466,
+      "confidence": 0.966,
+      "words": [
+        {
+          "text": "Everybody",
+          "start": 166.8,
+          "end": 167.34,
+          "confidence": 0.896
+        },
+        {
+          "text": "wants",
+          "start": 167.34,
+          "end": 167.74,
+          "confidence": 0.97
+        },
+        {
+          "text": "to",
+          "start": 167.74,
+          "end": 167.94,
+          "confidence": 0.996
+        },
+        {
+          "text": "be",
+          "start": 167.94,
+          "end": 168.14,
+          "confidence": 0.996
+        },
+        {
+          "text": "my",
+          "start": 168.14,
+          "end": 168.46,
+          "confidence": 0.991
+        },
+        {
+          "text": "enemy",
+          "start": 168.46,
+          "end": 169.52,
+          "confidence": 0.95
+        }
+      ]
+    },
+    {
+      "id": 36,
+      "seek": 14968,
+      "start": 170.66,
+      "end": 172.2,
+      "text": " Spare the sympathy",
+      "tokens": [
+        1738,
+        543,
+        264,
+        33240
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.5499832056745698,
+      "compression_ratio": 1.8025078369905956,
+      "no_speech_prob": 0.8352975249290466,
+      "confidence": 0.687,
+      "words": [
+        {
+          "text": "Spare",
+          "start": 170.66,
+          "end": 171.22,
+          "confidence": 0.494
+        },
+        {
+          "text": "the",
+          "start": 171.22,
+          "end": 171.46,
+          "confidence": 0.976
+        },
+        {
+          "text": "sympathy",
+          "start": 171.46,
+          "end": 172.2,
+          "confidence": 0.937
+        }
+      ]
+    },
+    {
+      "id": 37,
+      "seek": 14968,
+      "start": 172.96,
+      "end": 176.18,
+      "text": " Everybody wants to be my enemy",
+      "tokens": [
+        7646,
+        2738,
+        281,
+        312,
+        452,
+        5945
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.5499832056745698,
+      "compression_ratio": 1.8025078369905956,
+      "no_speech_prob": 0.8352975249290466,
+      "confidence": 0.983,
+      "words": [
+        {
+          "text": "Everybody",
+          "start": 172.96,
+          "end": 173.62,
+          "confidence": 0.994
+        },
+        {
+          "text": "wants",
+          "start": 173.62,
+          "end": 174.02,
+          "confidence": 0.99
+        },
+        {
+          "text": "to",
+          "start": 174.02,
+          "end": 174.36,
+          "confidence": 0.999
+        },
+        {
+          "text": "be",
+          "start": 174.36,
+          "end": 175.0,
+          "confidence": 0.999
+        },
+        {
+          "text": "my",
+          "start": 175.0,
+          "end": 175.4,
+          "confidence": 0.924
+        },
+        {
+          "text": "enemy",
+          "start": 175.4,
+          "end": 176.18,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 38,
+      "seek": 14968,
+      "start": 176.84,
+      "end": 178.44,
+      "text": " Oh the misery",
+      "tokens": [
+        876,
+        264,
+        32309
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.5499832056745698,
+      "compression_ratio": 1.8025078369905956,
+      "no_speech_prob": 0.8352975249290466,
+      "confidence": 0.813,
+      "words": [
+        {
+          "text": "Oh",
+          "start": 176.84,
+          "end": 177.48,
+          "confidence": 0.677
+        },
+        {
+          "text": "the",
+          "start": 177.48,
+          "end": 177.66,
+          "confidence": 0.794
+        },
+        {
+          "text": "misery",
+          "start": 177.66,
+          "end": 178.44,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 39,
+      "seek": 17906,
+      "start": 179.28,
+      "end": 181.44,
+      "text": " Everybody wants to be my enemy",
+      "tokens": [
+        7646,
+        2738,
+        281,
+        312,
+        452,
+        5945
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6545042613195995,
+      "compression_ratio": 1.97,
+      "no_speech_prob": 0.5597606301307678,
+      "confidence": 0.955,
+      "words": [
+        {
+          "text": "Everybody",
+          "start": 179.28,
+          "end": 179.84,
+          "confidence": 0.802
+        },
+        {
+          "text": "wants",
+          "start": 179.84,
+          "end": 180.22,
+          "confidence": 0.984
+        },
+        {
+          "text": "to",
+          "start": 180.22,
+          "end": 180.44,
+          "confidence": 0.997
+        },
+        {
+          "text": "be",
+          "start": 180.44,
+          "end": 180.58,
+          "confidence": 0.998
+        },
+        {
+          "text": "my",
+          "start": 180.58,
+          "end": 180.86,
+          "confidence": 0.992
+        },
+        {
+          "text": "enemy",
+          "start": 180.86,
+          "end": 181.44,
+          "confidence": 0.976
+        }
+      ]
+    },
+    {
+      "id": 40,
+      "seek": 17906,
+      "start": 183.12,
+      "end": 184.52,
+      "text": " Spare the sympathy",
+      "tokens": [
+        1738,
+        543,
+        264,
+        33240
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6545042613195995,
+      "compression_ratio": 1.97,
+      "no_speech_prob": 0.5597606301307678,
+      "confidence": 0.678,
+      "words": [
+        {
+          "text": "Spare",
+          "start": 183.12,
+          "end": 183.7,
+          "confidence": 0.479
+        },
+        {
+          "text": "the",
+          "start": 183.7,
+          "end": 183.92,
+          "confidence": 0.934
+        },
+        {
+          "text": "sympathy",
+          "start": 183.92,
+          "end": 184.52,
+          "confidence": 0.986
+        }
+      ]
+    },
+    {
+      "id": 41,
+      "seek": 17906,
+      "start": 185.56,
+      "end": 188.46,
+      "text": " Everybody wants to be my enemy",
+      "tokens": [
+        7646,
+        2738,
+        281,
+        312,
+        452,
+        5945
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6545042613195995,
+      "compression_ratio": 1.97,
+      "no_speech_prob": 0.5597606301307678,
+      "confidence": 0.959,
+      "words": [
+        {
+          "text": "Everybody",
+          "start": 185.56,
+          "end": 186.08,
+          "confidence": 0.993
+        },
+        {
+          "text": "wants",
+          "start": 186.08,
+          "end": 186.46,
+          "confidence": 0.99
+        },
+        {
+          "text": "to",
+          "start": 186.46,
+          "end": 186.72,
+          "confidence": 0.999
+        },
+        {
+          "text": "be",
+          "start": 186.72,
+          "end": 187.22,
+          "confidence": 0.999
+        },
+        {
+          "text": "my",
+          "start": 187.22,
+          "end": 187.86,
+          "confidence": 0.798
+        },
+        {
+          "text": "enemy",
+          "start": 187.86,
+          "end": 188.46,
+          "confidence": 0.991
+        }
+      ]
+    },
+    {
+      "id": 42,
+      "seek": 17906,
+      "start": 190.1,
+      "end": 191.96,
+      "text": " I swear, I swear I'll never be a saint",
+      "tokens": [
+        286,
+        11902,
+        11,
+        286,
+        11902,
+        286,
+        603,
+        1128,
+        312,
+        257,
+        28374
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6545042613195995,
+      "compression_ratio": 1.97,
+      "no_speech_prob": 0.5597606301307678,
+      "confidence": 0.662,
+      "words": [
+        {
+          "text": "I",
+          "start": 190.1,
+          "end": 190.14,
+          "confidence": 0.107
+        },
+        {
+          "text": "swear,",
+          "start": 190.14,
+          "end": 190.44,
+          "confidence": 0.908
+        },
+        {
+          "text": "I",
+          "start": 190.44,
+          "end": 190.48,
+          "confidence": 0.962
+        },
+        {
+          "text": "swear",
+          "start": 190.48,
+          "end": 190.52,
+          "confidence": 0.867
+        },
+        {
+          "text": "I'll",
+          "start": 190.52,
+          "end": 191.24,
+          "confidence": 0.628
+        },
+        {
+          "text": "never",
+          "start": 191.24,
+          "end": 191.28,
+          "confidence": 0.987
+        },
+        {
+          "text": "be",
+          "start": 191.28,
+          "end": 191.56,
+          "confidence": 0.993
+        },
+        {
+          "text": "a",
+          "start": 191.56,
+          "end": 191.76,
+          "confidence": 0.602
+        },
+        {
+          "text": "saint",
+          "start": 191.76,
+          "end": 191.96,
+          "confidence": 0.858
+        }
+      ]
+    },
+    {
+      "id": 43,
+      "seek": 17906,
+      "start": 192.12,
+      "end": 194.66,
+      "text": " I swear, my enemy",
+      "tokens": [
+        286,
+        11902,
+        11,
+        452,
+        5945
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6545042613195995,
+      "compression_ratio": 1.97,
+      "no_speech_prob": 0.5597606301307678,
+      "confidence": 0.529,
+      "words": [
+        {
+          "text": "I",
+          "start": 192.12,
+          "end": 192.62,
+          "confidence": 0.35
+        },
+        {
+          "text": "swear,",
+          "start": 192.62,
+          "end": 193.88,
+          "confidence": 0.83
+        },
+        {
+          "text": "my",
+          "start": 193.88,
+          "end": 194.02,
+          "confidence": 0.279
+        },
+        {
+          "text": "enemy",
+          "start": 194.02,
+          "end": 194.66,
+          "confidence": 0.964
+        }
+      ]
+    },
+    {
+      "id": 44,
+      "seek": 17906,
+      "start": 196.34,
+      "end": 198.36,
+      "text": " I swear, I swear I'll never be a saint",
+      "tokens": [
+        286,
+        11902,
+        11,
+        286,
+        11902,
+        286,
+        603,
+        1128,
+        312,
+        257,
+        28374
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6545042613195995,
+      "compression_ratio": 1.97,
+      "no_speech_prob": 0.5597606301307678,
+      "confidence": 0.976,
+      "words": [
+        {
+          "text": "I",
+          "start": 196.34,
+          "end": 196.38,
+          "confidence": 0.945
+        },
+        {
+          "text": "swear,",
+          "start": 196.38,
+          "end": 196.56,
+          "confidence": 0.999
+        },
+        {
+          "text": "I",
+          "start": 196.56,
+          "end": 196.6,
+          "confidence": 0.875
+        },
+        {
+          "text": "swear",
+          "start": 196.6,
+          "end": 196.84,
+          "confidence": 0.995
+        },
+        {
+          "text": "I'll",
+          "start": 196.84,
+          "end": 197.36,
+          "confidence": 0.982
+        },
+        {
+          "text": "never",
+          "start": 197.36,
+          "end": 197.5,
+          "confidence": 0.999
+        },
+        {
+          "text": "be",
+          "start": 197.5,
+          "end": 197.8,
+          "confidence": 0.999
+        },
+        {
+          "text": "a",
+          "start": 197.8,
+          "end": 198.04,
+          "confidence": 0.997
+        },
+        {
+          "text": "saint",
+          "start": 198.04,
+          "end": 198.36,
+          "confidence": 0.994
+        }
+      ]
+    },
+    {
+      "id": 45,
+      "seek": 19822,
+      "start": 198.44,
+      "end": 200.22,
+      "text": " You got to be yourself!",
+      "tokens": [
+        50364,
+        509,
+        658,
+        281,
+        312,
+        1803,
+        0,
+        50464
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.8683164384629991,
+      "compression_ratio": 0.7419354838709677,
+      "no_speech_prob": 0.6954998970031738,
+      "confidence": 0.365,
+      "words": [
+        {
+          "text": "You",
+          "start": 198.44,
+          "end": 198.62,
+          "confidence": 0.054
+        },
+        {
+          "text": "got",
+          "start": 198.62,
+          "end": 198.8,
+          "confidence": 0.163
+        },
+        {
+          "text": "to",
+          "start": 198.8,
+          "end": 198.98,
+          "confidence": 0.918
+        },
+        {
+          "text": "be",
+          "start": 198.98,
+          "end": 199.06,
+          "confidence": 0.87
+        },
+        {
+          "text": "yourself!",
+          "start": 199.06,
+          "end": 200.22,
+          "confidence": 0.913
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/corner_cases.cpu/nocond_music.mp4.words.json b/tests/expected/corner_cases.cpu/nocond_music.mp4.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..ddd3ddeb2eb18ea98bb99dffe65159d92a046d85
--- /dev/null
+++ b/tests/expected/corner_cases.cpu/nocond_music.mp4.words.json
@@ -0,0 +1,2687 @@
+{
+  "text": " I Oh, the misery Everybody wants to be my enemy Spare the sympathy Everybody wants to be my enemy Look out for yourself My enemy Look out for yourself But I'm ready Your words up on the wall as you're praying for my phone And the laughter in the holes and the names that I've been called I stack it in my mind and I'm waiting for the time When I show you what it's like to be worse but in the mind Tell you you're the greatest But once you turn they hate us Oh, the misery Everybody wants to be my enemy Spare the sympathy Everybody wants to be my enemy Look out for yourself My enemy Look out for yourself Look, okay I'm hoping that somebody pray for me I'm praying that somebody hold for me. I'm staying where nobody's supposed to be. I propose to be in a wreck of emotions. Ready to go whenever you let me know. The road is long, so put the pedal into the flow. The enemy on my trail, my energy unavailable. I'ma tell them I said away, go away. When I'm plotting, I'ma drive to the top. I've been out of shape, thinking out of the box. I'm an astronaut, blasted off the planet. Rock the cars, catastrophic, and it matters more because I had it now. Had I thought about wreaking havoc on an opposition. Kind of shocking, they want it static. With precision, I'm automatic. Quarterback, I ain't talking second. Pack it, pack it up. I don't panic, better, better. Up who the baddest. it don't matter cause we is your enemy. I swear I'll never be insane You got to be yourself",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.02,
+      "end": 0.4,
+      "text": " I",
+      "tokens": [
+        50364,
+        286,
+        50464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9367842674255371,
+      "compression_ratio": 0.1111111111111111,
+      "no_speech_prob": 0.7794302701950073,
+      "confidence": 0.032,
+      "words": [
+        {
+          "text": "I",
+          "start": 0.02,
+          "end": 0.4,
+          "confidence": 0.032
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 6000,
+      "start": 60.02,
+      "end": 69.26,
+      "text": " Oh, the misery Everybody wants to be my enemy",
+      "tokens": [
+        876,
+        11,
+        264,
+        32309,
+        7646,
+        2738,
+        281,
+        312,
+        452,
+        5945
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.45698386972600763,
+      "compression_ratio": 1.62,
+      "no_speech_prob": 0.8689420819282532,
+      "confidence": 0.669,
+      "words": [
+        {
+          "text": "Oh,",
+          "start": 60.02,
+          "end": 65.44,
+          "confidence": 0.084
+        },
+        {
+          "text": "the",
+          "start": 65.44,
+          "end": 65.48,
+          "confidence": 0.796
+        },
+        {
+          "text": "misery",
+          "start": 65.48,
+          "end": 66.08,
+          "confidence": 0.993
+        },
+        {
+          "text": "Everybody",
+          "start": 66.08,
+          "end": 67.62,
+          "confidence": 0.431
+        },
+        {
+          "text": "wants",
+          "start": 67.62,
+          "end": 68.0,
+          "confidence": 0.983
+        },
+        {
+          "text": "to",
+          "start": 68.0,
+          "end": 68.2,
+          "confidence": 0.993
+        },
+        {
+          "text": "be",
+          "start": 68.2,
+          "end": 68.4,
+          "confidence": 0.996
+        },
+        {
+          "text": "my",
+          "start": 68.4,
+          "end": 68.74,
+          "confidence": 0.984
+        },
+        {
+          "text": "enemy",
+          "start": 68.74,
+          "end": 69.26,
+          "confidence": 0.984
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 6000,
+      "start": 70.9,
+      "end": 76.38,
+      "text": " Spare the sympathy Everybody wants to be my enemy",
+      "tokens": [
+        1738,
+        543,
+        264,
+        33240,
+        7646,
+        2738,
+        281,
+        312,
+        452,
+        5945
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.45698386972600763,
+      "compression_ratio": 1.62,
+      "no_speech_prob": 0.8689420819282532,
+      "confidence": 0.934,
+      "words": [
+        {
+          "text": "Spare",
+          "start": 70.9,
+          "end": 71.4,
+          "confidence": 0.812
+        },
+        {
+          "text": "the",
+          "start": 71.4,
+          "end": 71.74,
+          "confidence": 0.968
+        },
+        {
+          "text": "sympathy",
+          "start": 71.74,
+          "end": 72.58,
+          "confidence": 0.993
+        },
+        {
+          "text": "Everybody",
+          "start": 72.58,
+          "end": 73.88,
+          "confidence": 0.962
+        },
+        {
+          "text": "wants",
+          "start": 73.88,
+          "end": 74.24,
+          "confidence": 0.994
+        },
+        {
+          "text": "to",
+          "start": 74.24,
+          "end": 74.42,
+          "confidence": 0.999
+        },
+        {
+          "text": "be",
+          "start": 74.42,
+          "end": 75.36,
+          "confidence": 0.999
+        },
+        {
+          "text": "my",
+          "start": 75.36,
+          "end": 75.68,
+          "confidence": 0.837
+        },
+        {
+          "text": "enemy",
+          "start": 75.68,
+          "end": 76.38,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 6000,
+      "start": 79.94,
+      "end": 82.58,
+      "text": " Look out for yourself My enemy",
+      "tokens": [
+        2053,
+        484,
+        337,
+        1803,
+        1222,
+        5945
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.45698386972600763,
+      "compression_ratio": 1.62,
+      "no_speech_prob": 0.8689420819282532,
+      "confidence": 0.774,
+      "words": [
+        {
+          "text": "Look",
+          "start": 79.94,
+          "end": 80.14,
+          "confidence": 0.43
+        },
+        {
+          "text": "out",
+          "start": 80.14,
+          "end": 80.46,
+          "confidence": 0.991
+        },
+        {
+          "text": "for",
+          "start": 80.46,
+          "end": 80.6,
+          "confidence": 0.989
+        },
+        {
+          "text": "yourself",
+          "start": 80.6,
+          "end": 81.24,
+          "confidence": 0.97
+        },
+        {
+          "text": "My",
+          "start": 81.24,
+          "end": 81.88,
+          "confidence": 0.536
+        },
+        {
+          "text": "enemy",
+          "start": 81.88,
+          "end": 82.58,
+          "confidence": 0.98
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 6000,
+      "start": 86.18,
+      "end": 88.46,
+      "text": " Look out for yourself But I'm ready",
+      "tokens": [
+        2053,
+        484,
+        337,
+        1803,
+        583,
+        286,
+        478,
+        1919
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.45698386972600763,
+      "compression_ratio": 1.62,
+      "no_speech_prob": 0.8689420819282532,
+      "confidence": 0.927,
+      "words": [
+        {
+          "text": "Look",
+          "start": 86.18,
+          "end": 86.4,
+          "confidence": 0.747
+        },
+        {
+          "text": "out",
+          "start": 86.4,
+          "end": 86.64,
+          "confidence": 0.988
+        },
+        {
+          "text": "for",
+          "start": 86.64,
+          "end": 86.82,
+          "confidence": 0.998
+        },
+        {
+          "text": "yourself",
+          "start": 86.82,
+          "end": 87.62,
+          "confidence": 0.999
+        },
+        {
+          "text": "But",
+          "start": 87.62,
+          "end": 87.88,
+          "confidence": 0.764
+        },
+        {
+          "text": "I'm",
+          "start": 87.88,
+          "end": 88.12,
+          "confidence": 0.989
+        },
+        {
+          "text": "ready",
+          "start": 88.12,
+          "end": 88.46,
+          "confidence": 0.995
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 8856,
+      "start": 88.58,
+      "end": 91.58,
+      "text": " Your words up on the wall as you're praying for my phone",
+      "tokens": [
+        2260,
+        2283,
+        493,
+        322,
+        264,
+        2929,
+        382,
+        291,
+        434,
+        15611,
+        337,
+        452,
+        2593
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2876515737394007,
+      "compression_ratio": 1.5869565217391304,
+      "no_speech_prob": 0.7907973527908325,
+      "confidence": 0.82,
+      "words": [
+        {
+          "text": "Your",
+          "start": 88.58,
+          "end": 88.86,
+          "confidence": 0.549
+        },
+        {
+          "text": "words",
+          "start": 88.86,
+          "end": 89.12,
+          "confidence": 0.921
+        },
+        {
+          "text": "up",
+          "start": 89.12,
+          "end": 89.46,
+          "confidence": 0.965
+        },
+        {
+          "text": "on",
+          "start": 89.46,
+          "end": 89.6,
+          "confidence": 0.995
+        },
+        {
+          "text": "the",
+          "start": 89.6,
+          "end": 89.66,
+          "confidence": 0.991
+        },
+        {
+          "text": "wall",
+          "start": 89.66,
+          "end": 90.12,
+          "confidence": 0.88
+        },
+        {
+          "text": "as",
+          "start": 90.12,
+          "end": 90.34,
+          "confidence": 0.403
+        },
+        {
+          "text": "you're",
+          "start": 90.34,
+          "end": 90.8,
+          "confidence": 0.828
+        },
+        {
+          "text": "praying",
+          "start": 90.8,
+          "end": 90.84,
+          "confidence": 0.967
+        },
+        {
+          "text": "for",
+          "start": 90.84,
+          "end": 91.06,
+          "confidence": 0.97
+        },
+        {
+          "text": "my",
+          "start": 91.06,
+          "end": 91.24,
+          "confidence": 0.989
+        },
+        {
+          "text": "phone",
+          "start": 91.24,
+          "end": 91.58,
+          "confidence": 0.702
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 8856,
+      "start": 91.78,
+      "end": 94.68,
+      "text": " And the laughter in the holes and the names that I've been called",
+      "tokens": [
+        400,
+        264,
+        13092,
+        294,
+        264,
+        8118,
+        293,
+        264,
+        5288,
+        300,
+        286,
+        600,
+        668,
+        1219
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2876515737394007,
+      "compression_ratio": 1.5869565217391304,
+      "no_speech_prob": 0.7907973527908325,
+      "confidence": 0.885,
+      "words": [
+        {
+          "text": "And",
+          "start": 91.78,
+          "end": 91.92,
+          "confidence": 0.844
+        },
+        {
+          "text": "the",
+          "start": 91.92,
+          "end": 92.0,
+          "confidence": 0.987
+        },
+        {
+          "text": "laughter",
+          "start": 92.0,
+          "end": 92.4,
+          "confidence": 0.994
+        },
+        {
+          "text": "in",
+          "start": 92.4,
+          "end": 92.72,
+          "confidence": 0.849
+        },
+        {
+          "text": "the",
+          "start": 92.72,
+          "end": 92.92,
+          "confidence": 0.997
+        },
+        {
+          "text": "holes",
+          "start": 92.92,
+          "end": 93.2,
+          "confidence": 0.609
+        },
+        {
+          "text": "and",
+          "start": 93.2,
+          "end": 93.44,
+          "confidence": 0.596
+        },
+        {
+          "text": "the",
+          "start": 93.44,
+          "end": 93.54,
+          "confidence": 0.991
+        },
+        {
+          "text": "names",
+          "start": 93.54,
+          "end": 93.82,
+          "confidence": 0.991
+        },
+        {
+          "text": "that",
+          "start": 93.82,
+          "end": 94.12,
+          "confidence": 0.957
+        },
+        {
+          "text": "I've",
+          "start": 94.12,
+          "end": 94.28,
+          "confidence": 0.915
+        },
+        {
+          "text": "been",
+          "start": 94.28,
+          "end": 94.42,
+          "confidence": 0.986
+        },
+        {
+          "text": "called",
+          "start": 94.42,
+          "end": 94.68,
+          "confidence": 0.912
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 8856,
+      "start": 95.0,
+      "end": 97.82,
+      "text": " I stack it in my mind and I'm waiting for the time",
+      "tokens": [
+        286,
+        8630,
+        309,
+        294,
+        452,
+        1575,
+        293,
+        286,
+        478,
+        3806,
+        337,
+        264,
+        565
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2876515737394007,
+      "compression_ratio": 1.5869565217391304,
+      "no_speech_prob": 0.7907973527908325,
+      "confidence": 0.96,
+      "words": [
+        {
+          "text": "I",
+          "start": 95.0,
+          "end": 95.12,
+          "confidence": 0.987
+        },
+        {
+          "text": "stack",
+          "start": 95.12,
+          "end": 95.42,
+          "confidence": 0.825
+        },
+        {
+          "text": "it",
+          "start": 95.42,
+          "end": 95.7,
+          "confidence": 0.995
+        },
+        {
+          "text": "in",
+          "start": 95.7,
+          "end": 95.82,
+          "confidence": 0.996
+        },
+        {
+          "text": "my",
+          "start": 95.82,
+          "end": 96.02,
+          "confidence": 0.994
+        },
+        {
+          "text": "mind",
+          "start": 96.02,
+          "end": 96.4,
+          "confidence": 0.999
+        },
+        {
+          "text": "and",
+          "start": 96.4,
+          "end": 96.62,
+          "confidence": 0.762
+        },
+        {
+          "text": "I'm",
+          "start": 96.62,
+          "end": 97.02,
+          "confidence": 0.991
+        },
+        {
+          "text": "waiting",
+          "start": 97.02,
+          "end": 97.06,
+          "confidence": 0.988
+        },
+        {
+          "text": "for",
+          "start": 97.06,
+          "end": 97.32,
+          "confidence": 0.996
+        },
+        {
+          "text": "the",
+          "start": 97.32,
+          "end": 97.5,
+          "confidence": 0.996
+        },
+        {
+          "text": "time",
+          "start": 97.5,
+          "end": 97.82,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 8856,
+      "start": 97.98,
+      "end": 101.24,
+      "text": " When I show you what it's like to be worse but in the mind",
+      "tokens": [
+        1133,
+        286,
+        855,
+        291,
+        437,
+        309,
+        311,
+        411,
+        281,
+        312,
+        5324,
+        457,
+        294,
+        264,
+        1575
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2876515737394007,
+      "compression_ratio": 1.5869565217391304,
+      "no_speech_prob": 0.7907973527908325,
+      "confidence": 0.755,
+      "words": [
+        {
+          "text": "When",
+          "start": 97.98,
+          "end": 98.16,
+          "confidence": 0.923
+        },
+        {
+          "text": "I",
+          "start": 98.16,
+          "end": 98.22,
+          "confidence": 0.993
+        },
+        {
+          "text": "show",
+          "start": 98.22,
+          "end": 98.48,
+          "confidence": 0.959
+        },
+        {
+          "text": "you",
+          "start": 98.48,
+          "end": 98.74,
+          "confidence": 0.994
+        },
+        {
+          "text": "what",
+          "start": 98.74,
+          "end": 98.96,
+          "confidence": 0.996
+        },
+        {
+          "text": "it's",
+          "start": 98.96,
+          "end": 99.38,
+          "confidence": 0.988
+        },
+        {
+          "text": "like",
+          "start": 99.38,
+          "end": 99.42,
+          "confidence": 0.998
+        },
+        {
+          "text": "to",
+          "start": 99.42,
+          "end": 99.68,
+          "confidence": 0.877
+        },
+        {
+          "text": "be",
+          "start": 99.68,
+          "end": 99.78,
+          "confidence": 0.997
+        },
+        {
+          "text": "worse",
+          "start": 99.78,
+          "end": 100.04,
+          "confidence": 0.444
+        },
+        {
+          "text": "but",
+          "start": 100.04,
+          "end": 100.36,
+          "confidence": 0.196
+        },
+        {
+          "text": "in",
+          "start": 100.36,
+          "end": 100.52,
+          "confidence": 0.862
+        },
+        {
+          "text": "the",
+          "start": 100.52,
+          "end": 100.8,
+          "confidence": 0.426
+        },
+        {
+          "text": "mind",
+          "start": 100.8,
+          "end": 101.24,
+          "confidence": 0.621
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 8856,
+      "start": 101.32,
+      "end": 106.28,
+      "text": " Tell you you're the greatest",
+      "tokens": [
+        5115,
+        291,
+        291,
+        434,
+        264,
+        6636
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2876515737394007,
+      "compression_ratio": 1.5869565217391304,
+      "no_speech_prob": 0.7907973527908325,
+      "confidence": 0.94,
+      "words": [
+        {
+          "text": "Tell",
+          "start": 101.32,
+          "end": 102.08,
+          "confidence": 0.937
+        },
+        {
+          "text": "you",
+          "start": 102.08,
+          "end": 102.68,
+          "confidence": 0.993
+        },
+        {
+          "text": "you're",
+          "start": 102.68,
+          "end": 103.66,
+          "confidence": 0.873
+        },
+        {
+          "text": "the",
+          "start": 103.66,
+          "end": 104.14,
+          "confidence": 0.985
+        },
+        {
+          "text": "greatest",
+          "start": 104.14,
+          "end": 106.28,
+          "confidence": 0.986
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 8856,
+      "start": 107.18,
+      "end": 113.0,
+      "text": " But once you turn they hate us",
+      "tokens": [
+        583,
+        1564,
+        291,
+        1261,
+        436,
+        4700,
+        505
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2876515737394007,
+      "compression_ratio": 1.5869565217391304,
+      "no_speech_prob": 0.7907973527908325,
+      "confidence": 0.909,
+      "words": [
+        {
+          "text": "But",
+          "start": 107.18,
+          "end": 107.52,
+          "confidence": 0.963
+        },
+        {
+          "text": "once",
+          "start": 107.52,
+          "end": 108.34,
+          "confidence": 0.79
+        },
+        {
+          "text": "you",
+          "start": 108.34,
+          "end": 108.9,
+          "confidence": 0.998
+        },
+        {
+          "text": "turn",
+          "start": 108.9,
+          "end": 109.84,
+          "confidence": 0.913
+        },
+        {
+          "text": "they",
+          "start": 109.84,
+          "end": 110.34,
+          "confidence": 0.754
+        },
+        {
+          "text": "hate",
+          "start": 110.34,
+          "end": 111.9,
+          "confidence": 0.985
+        },
+        {
+          "text": "us",
+          "start": 111.9,
+          "end": 113.0,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 11312,
+      "start": 113.14,
+      "end": 119.18,
+      "text": " Oh, the misery Everybody wants to be my enemy",
+      "tokens": [
+        876,
+        11,
+        264,
+        32309,
+        7646,
+        2738,
+        281,
+        312,
+        452,
+        5945
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2736021077857827,
+      "compression_ratio": 1.6610169491525424,
+      "no_speech_prob": 0.8637643456459045,
+      "confidence": 0.804,
+      "words": [
+        {
+          "text": "Oh,",
+          "start": 113.14,
+          "end": 115.14,
+          "confidence": 0.317
+        },
+        {
+          "text": "the",
+          "start": 115.14,
+          "end": 115.34,
+          "confidence": 0.964
+        },
+        {
+          "text": "misery",
+          "start": 115.34,
+          "end": 116.08,
+          "confidence": 0.995
+        },
+        {
+          "text": "Everybody",
+          "start": 116.08,
+          "end": 117.48,
+          "confidence": 0.482
+        },
+        {
+          "text": "wants",
+          "start": 117.48,
+          "end": 117.86,
+          "confidence": 0.986
+        },
+        {
+          "text": "to",
+          "start": 117.86,
+          "end": 118.08,
+          "confidence": 0.995
+        },
+        {
+          "text": "be",
+          "start": 118.08,
+          "end": 118.26,
+          "confidence": 0.998
+        },
+        {
+          "text": "my",
+          "start": 118.26,
+          "end": 118.58,
+          "confidence": 0.993
+        },
+        {
+          "text": "enemy",
+          "start": 118.58,
+          "end": 119.18,
+          "confidence": 0.983
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 11312,
+      "start": 119.94,
+      "end": 126.08,
+      "text": " Spare the sympathy Everybody wants to be my enemy",
+      "tokens": [
+        1738,
+        543,
+        264,
+        33240,
+        7646,
+        2738,
+        281,
+        312,
+        452,
+        5945
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2736021077857827,
+      "compression_ratio": 1.6610169491525424,
+      "no_speech_prob": 0.8637643456459045,
+      "confidence": 0.874,
+      "words": [
+        {
+          "text": "Spare",
+          "start": 119.94,
+          "end": 121.26,
+          "confidence": 0.576
+        },
+        {
+          "text": "the",
+          "start": 121.26,
+          "end": 121.62,
+          "confidence": 0.985
+        },
+        {
+          "text": "sympathy",
+          "start": 121.62,
+          "end": 122.32,
+          "confidence": 0.994
+        },
+        {
+          "text": "Everybody",
+          "start": 122.32,
+          "end": 123.76,
+          "confidence": 0.969
+        },
+        {
+          "text": "wants",
+          "start": 123.76,
+          "end": 124.12,
+          "confidence": 0.994
+        },
+        {
+          "text": "to",
+          "start": 124.12,
+          "end": 124.6,
+          "confidence": 0.999
+        },
+        {
+          "text": "be",
+          "start": 124.6,
+          "end": 125.34,
+          "confidence": 0.999
+        },
+        {
+          "text": "my",
+          "start": 125.34,
+          "end": 125.58,
+          "confidence": 0.835
+        },
+        {
+          "text": "enemy",
+          "start": 125.58,
+          "end": 126.08,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 11312,
+      "start": 129.86,
+      "end": 132.32,
+      "text": " Look out for yourself My enemy",
+      "tokens": [
+        2053,
+        484,
+        337,
+        1803,
+        1222,
+        5945
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2736021077857827,
+      "compression_ratio": 1.6610169491525424,
+      "no_speech_prob": 0.8637643456459045,
+      "confidence": 0.794,
+      "words": [
+        {
+          "text": "Look",
+          "start": 129.86,
+          "end": 130.08,
+          "confidence": 0.592
+        },
+        {
+          "text": "out",
+          "start": 130.08,
+          "end": 130.3,
+          "confidence": 0.892
+        },
+        {
+          "text": "for",
+          "start": 130.3,
+          "end": 130.44,
+          "confidence": 0.978
+        },
+        {
+          "text": "yourself",
+          "start": 130.44,
+          "end": 130.92,
+          "confidence": 0.988
+        },
+        {
+          "text": "My",
+          "start": 130.92,
+          "end": 131.74,
+          "confidence": 0.496
+        },
+        {
+          "text": "enemy",
+          "start": 131.74,
+          "end": 132.32,
+          "confidence": 0.989
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 11312,
+      "start": 133.7,
+      "end": 137.14,
+      "text": " Look out for yourself",
+      "tokens": [
+        2053,
+        484,
+        337,
+        1803
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2736021077857827,
+      "compression_ratio": 1.6610169491525424,
+      "no_speech_prob": 0.8637643456459045,
+      "confidence": 0.97,
+      "words": [
+        {
+          "text": "Look",
+          "start": 133.7,
+          "end": 134.62,
+          "confidence": 0.907
+        },
+        {
+          "text": "out",
+          "start": 134.62,
+          "end": 136.52,
+          "confidence": 0.978
+        },
+        {
+          "text": "for",
+          "start": 136.52,
+          "end": 136.66,
+          "confidence": 0.999
+        },
+        {
+          "text": "yourself",
+          "start": 136.66,
+          "end": 137.14,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 11312,
+      "start": 137.64,
+      "end": 140.16,
+      "text": " Look, okay I'm hoping that somebody pray for me",
+      "tokens": [
+        2053,
+        11,
+        1392,
+        286,
+        478,
+        7159,
+        300,
+        2618,
+        3690,
+        337,
+        385
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2736021077857827,
+      "compression_ratio": 1.6610169491525424,
+      "no_speech_prob": 0.8637643456459045,
+      "confidence": 0.786,
+      "words": [
+        {
+          "text": "Look,",
+          "start": 137.64,
+          "end": 138.46,
+          "confidence": 0.727
+        },
+        {
+          "text": "okay",
+          "start": 138.46,
+          "end": 138.62,
+          "confidence": 0.727
+        },
+        {
+          "text": "I'm",
+          "start": 138.62,
+          "end": 138.88,
+          "confidence": 0.698
+        },
+        {
+          "text": "hoping",
+          "start": 138.88,
+          "end": 139.14,
+          "confidence": 0.501
+        },
+        {
+          "text": "that",
+          "start": 139.14,
+          "end": 139.34,
+          "confidence": 0.958
+        },
+        {
+          "text": "somebody",
+          "start": 139.34,
+          "end": 139.52,
+          "confidence": 0.981
+        },
+        {
+          "text": "pray",
+          "start": 139.52,
+          "end": 139.8,
+          "confidence": 0.821
+        },
+        {
+          "text": "for",
+          "start": 139.8,
+          "end": 140.04,
+          "confidence": 0.9
+        },
+        {
+          "text": "me",
+          "start": 140.04,
+          "end": 140.16,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 14012,
+      "start": 140.18,
+      "end": 141.7,
+      "text": " I'm praying that somebody hold for me.",
+      "tokens": [
+        286,
+        478,
+        15611,
+        300,
+        2618,
+        1797,
+        337,
+        385,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3642334662543403,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7768110036849976,
+      "confidence": 0.795,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 140.18,
+          "end": 140.38,
+          "confidence": 0.819
+        },
+        {
+          "text": "praying",
+          "start": 140.38,
+          "end": 140.62,
+          "confidence": 0.694
+        },
+        {
+          "text": "that",
+          "start": 140.62,
+          "end": 140.82,
+          "confidence": 0.786
+        },
+        {
+          "text": "somebody",
+          "start": 140.82,
+          "end": 141.08,
+          "confidence": 0.985
+        },
+        {
+          "text": "hold",
+          "start": 141.08,
+          "end": 141.32,
+          "confidence": 0.447
+        },
+        {
+          "text": "for",
+          "start": 141.32,
+          "end": 141.52,
+          "confidence": 0.993
+        },
+        {
+          "text": "me.",
+          "start": 141.52,
+          "end": 141.7,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 17,
+      "seek": 14012,
+      "start": 141.72,
+      "end": 143.43,
+      "text": " I'm staying where nobody's supposed to be.",
+      "tokens": [
+        286,
+        478,
+        7939,
+        689,
+        5079,
+        311,
+        3442,
+        281,
+        312,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3642334662543403,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7768110036849976,
+      "confidence": 0.853,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 141.72,
+          "end": 141.9,
+          "confidence": 0.976
+        },
+        {
+          "text": "staying",
+          "start": 141.9,
+          "end": 142.12,
+          "confidence": 0.708
+        },
+        {
+          "text": "where",
+          "start": 142.12,
+          "end": 142.3,
+          "confidence": 0.906
+        },
+        {
+          "text": "nobody's",
+          "start": 142.3,
+          "end": 142.88,
+          "confidence": 0.654
+        },
+        {
+          "text": "supposed",
+          "start": 142.88,
+          "end": 142.92,
+          "confidence": 0.924
+        },
+        {
+          "text": "to",
+          "start": 142.92,
+          "end": 143.12,
+          "confidence": 0.992
+        },
+        {
+          "text": "be.",
+          "start": 143.12,
+          "end": 143.43,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 18,
+      "seek": 14012,
+      "start": 143.43,
+      "end": 145.29,
+      "text": " I propose to be in a wreck of emotions.",
+      "tokens": [
+        286,
+        17421,
+        281,
+        312,
+        294,
+        257,
+        21478,
+        295,
+        8462,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3642334662543403,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7768110036849976,
+      "confidence": 0.645,
+      "words": [
+        {
+          "text": "I",
+          "start": 143.43,
+          "end": 143.47,
+          "confidence": 0.492
+        },
+        {
+          "text": "propose",
+          "start": 143.47,
+          "end": 143.66,
+          "confidence": 0.332
+        },
+        {
+          "text": "to",
+          "start": 143.66,
+          "end": 143.84,
+          "confidence": 0.78
+        },
+        {
+          "text": "be",
+          "start": 143.84,
+          "end": 144.04,
+          "confidence": 0.442
+        },
+        {
+          "text": "in",
+          "start": 144.04,
+          "end": 144.16,
+          "confidence": 0.81
+        },
+        {
+          "text": "a",
+          "start": 144.16,
+          "end": 144.24,
+          "confidence": 0.555
+        },
+        {
+          "text": "wreck",
+          "start": 144.24,
+          "end": 144.36,
+          "confidence": 0.81
+        },
+        {
+          "text": "of",
+          "start": 144.36,
+          "end": 144.54,
+          "confidence": 0.99
+        },
+        {
+          "text": "emotions.",
+          "start": 144.54,
+          "end": 145.29,
+          "confidence": 0.953
+        }
+      ]
+    },
+    {
+      "id": 19,
+      "seek": 14012,
+      "start": 145.29,
+      "end": 146.56,
+      "text": " Ready to go whenever you let me know.",
+      "tokens": [
+        9944,
+        281,
+        352,
+        5699,
+        291,
+        718,
+        385,
+        458,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3642334662543403,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7768110036849976,
+      "confidence": 0.834,
+      "words": [
+        {
+          "text": "Ready",
+          "start": 145.29,
+          "end": 145.33,
+          "confidence": 0.951
+        },
+        {
+          "text": "to",
+          "start": 145.33,
+          "end": 145.5,
+          "confidence": 0.997
+        },
+        {
+          "text": "go",
+          "start": 145.5,
+          "end": 145.56,
+          "confidence": 0.997
+        },
+        {
+          "text": "whenever",
+          "start": 145.56,
+          "end": 145.76,
+          "confidence": 0.659
+        },
+        {
+          "text": "you",
+          "start": 145.76,
+          "end": 145.92,
+          "confidence": 0.403
+        },
+        {
+          "text": "let",
+          "start": 145.92,
+          "end": 146.04,
+          "confidence": 0.952
+        },
+        {
+          "text": "me",
+          "start": 146.04,
+          "end": 146.16,
+          "confidence": 0.998
+        },
+        {
+          "text": "know.",
+          "start": 146.16,
+          "end": 146.56,
+          "confidence": 0.977
+        }
+      ]
+    },
+    {
+      "id": 20,
+      "seek": 14012,
+      "start": 146.56,
+      "end": 147.86,
+      "text": " The road is long, so put the pedal into the flow.",
+      "tokens": [
+        440,
+        3060,
+        307,
+        938,
+        11,
+        370,
+        829,
+        264,
+        19122,
+        666,
+        264,
+        3095,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3642334662543403,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7768110036849976,
+      "confidence": 0.959,
+      "words": [
+        {
+          "text": "The",
+          "start": 146.56,
+          "end": 146.6,
+          "confidence": 0.99
+        },
+        {
+          "text": "road",
+          "start": 146.6,
+          "end": 146.66,
+          "confidence": 0.99
+        },
+        {
+          "text": "is",
+          "start": 146.66,
+          "end": 146.74,
+          "confidence": 0.987
+        },
+        {
+          "text": "long,",
+          "start": 146.74,
+          "end": 146.96,
+          "confidence": 0.961
+        },
+        {
+          "text": "so",
+          "start": 146.96,
+          "end": 147.02,
+          "confidence": 0.968
+        },
+        {
+          "text": "put",
+          "start": 147.02,
+          "end": 147.14,
+          "confidence": 0.954
+        },
+        {
+          "text": "the",
+          "start": 147.14,
+          "end": 147.28,
+          "confidence": 0.972
+        },
+        {
+          "text": "pedal",
+          "start": 147.28,
+          "end": 147.38,
+          "confidence": 0.993
+        },
+        {
+          "text": "into",
+          "start": 147.38,
+          "end": 147.58,
+          "confidence": 0.898
+        },
+        {
+          "text": "the",
+          "start": 147.58,
+          "end": 147.74,
+          "confidence": 0.992
+        },
+        {
+          "text": "flow.",
+          "start": 147.74,
+          "end": 147.86,
+          "confidence": 0.857
+        }
+      ]
+    },
+    {
+      "id": 21,
+      "seek": 14012,
+      "start": 147.94,
+      "end": 150.22,
+      "text": " The enemy on my trail, my energy unavailable.",
+      "tokens": [
+        440,
+        5945,
+        322,
+        452,
+        9924,
+        11,
+        452,
+        2281,
+        36541,
+        32699,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3642334662543403,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7768110036849976,
+      "confidence": 0.949,
+      "words": [
+        {
+          "text": "The",
+          "start": 147.94,
+          "end": 148.06,
+          "confidence": 0.968
+        },
+        {
+          "text": "enemy",
+          "start": 148.06,
+          "end": 148.24,
+          "confidence": 0.727
+        },
+        {
+          "text": "on",
+          "start": 148.24,
+          "end": 148.44,
+          "confidence": 0.974
+        },
+        {
+          "text": "my",
+          "start": 148.44,
+          "end": 148.5,
+          "confidence": 0.974
+        },
+        {
+          "text": "trail,",
+          "start": 148.5,
+          "end": 148.72,
+          "confidence": 0.986
+        },
+        {
+          "text": "my",
+          "start": 148.72,
+          "end": 148.82,
+          "confidence": 0.99
+        },
+        {
+          "text": "energy",
+          "start": 148.82,
+          "end": 149.06,
+          "confidence": 0.996
+        },
+        {
+          "text": "unavailable.",
+          "start": 149.06,
+          "end": 150.22,
+          "confidence": 0.978
+        }
+      ]
+    },
+    {
+      "id": 22,
+      "seek": 14012,
+      "start": 150.22,
+      "end": 151.35,
+      "text": " I'ma tell them I said away, go away.",
+      "tokens": [
+        286,
+        478,
+        64,
+        980,
+        552,
+        286,
+        848,
+        1314,
+        11,
+        352,
+        1314,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3642334662543403,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7768110036849976,
+      "confidence": 0.571,
+      "words": [
+        {
+          "text": "I'ma",
+          "start": 150.22,
+          "end": 150.26,
+          "confidence": 0.767
+        },
+        {
+          "text": "tell",
+          "start": 150.26,
+          "end": 150.36,
+          "confidence": 0.989
+        },
+        {
+          "text": "them",
+          "start": 150.36,
+          "end": 150.5,
+          "confidence": 0.336
+        },
+        {
+          "text": "I",
+          "start": 150.5,
+          "end": 150.58,
+          "confidence": 0.358
+        },
+        {
+          "text": "said",
+          "start": 150.58,
+          "end": 150.74,
+          "confidence": 0.3
+        },
+        {
+          "text": "away,",
+          "start": 150.74,
+          "end": 151.14,
+          "confidence": 0.323
+        },
+        {
+          "text": "go",
+          "start": 151.14,
+          "end": 151.18,
+          "confidence": 0.911
+        },
+        {
+          "text": "away.",
+          "start": 151.18,
+          "end": 151.35,
+          "confidence": 0.781
+        }
+      ]
+    },
+    {
+      "id": 23,
+      "seek": 14012,
+      "start": 151.35,
+      "end": 152.78,
+      "text": " When I'm plotting, I'ma drive to the top.",
+      "tokens": [
+        1133,
+        286,
+        478,
+        41178,
+        11,
+        286,
+        478,
+        64,
+        3332,
+        281,
+        264,
+        1192,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3642334662543403,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7768110036849976,
+      "confidence": 0.645,
+      "words": [
+        {
+          "text": "When",
+          "start": 151.35,
+          "end": 151.54,
+          "confidence": 0.884
+        },
+        {
+          "text": "I'm",
+          "start": 151.54,
+          "end": 151.72,
+          "confidence": 0.594
+        },
+        {
+          "text": "plotting,",
+          "start": 151.72,
+          "end": 151.92,
+          "confidence": 0.367
+        },
+        {
+          "text": "I'ma",
+          "start": 151.92,
+          "end": 152.04,
+          "confidence": 0.488
+        },
+        {
+          "text": "drive",
+          "start": 152.04,
+          "end": 152.14,
+          "confidence": 0.621
+        },
+        {
+          "text": "to",
+          "start": 152.14,
+          "end": 152.32,
+          "confidence": 0.984
+        },
+        {
+          "text": "the",
+          "start": 152.32,
+          "end": 152.38,
+          "confidence": 0.997
+        },
+        {
+          "text": "top.",
+          "start": 152.38,
+          "end": 152.78,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 24,
+      "seek": 14012,
+      "start": 152.78,
+      "end": 153.76,
+      "text": " I've been out of shape, thinking out of the box.",
+      "tokens": [
+        286,
+        600,
+        668,
+        484,
+        295,
+        3909,
+        11,
+        1953,
+        484,
+        295,
+        264,
+        2424,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3642334662543403,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7768110036849976,
+      "confidence": 0.769,
+      "words": [
+        {
+          "text": "I've",
+          "start": 152.78,
+          "end": 152.82,
+          "confidence": 0.721
+        },
+        {
+          "text": "been",
+          "start": 152.82,
+          "end": 152.86,
+          "confidence": 0.998
+        },
+        {
+          "text": "out",
+          "start": 152.86,
+          "end": 152.9,
+          "confidence": 0.905
+        },
+        {
+          "text": "of",
+          "start": 152.9,
+          "end": 152.96,
+          "confidence": 0.986
+        },
+        {
+          "text": "shape,",
+          "start": 152.96,
+          "end": 153.12,
+          "confidence": 0.998
+        },
+        {
+          "text": "thinking",
+          "start": 153.12,
+          "end": 153.3,
+          "confidence": 0.842
+        },
+        {
+          "text": "out",
+          "start": 153.3,
+          "end": 153.48,
+          "confidence": 0.347
+        },
+        {
+          "text": "of",
+          "start": 153.48,
+          "end": 153.54,
+          "confidence": 0.507
+        },
+        {
+          "text": "the",
+          "start": 153.54,
+          "end": 153.58,
+          "confidence": 0.819
+        },
+        {
+          "text": "box.",
+          "start": 153.58,
+          "end": 153.76,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 25,
+      "seek": 14012,
+      "start": 153.76,
+      "end": 155.34,
+      "text": " I'm an astronaut, blasted off the planet.",
+      "tokens": [
+        286,
+        478,
+        364,
+        18516,
+        11,
+        12035,
+        292,
+        766,
+        264,
+        5054,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3642334662543403,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7768110036849976,
+      "confidence": 0.967,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 153.76,
+          "end": 153.9,
+          "confidence": 0.996
+        },
+        {
+          "text": "an",
+          "start": 153.9,
+          "end": 153.98,
+          "confidence": 0.996
+        },
+        {
+          "text": "astronaut,",
+          "start": 153.98,
+          "end": 154.68,
+          "confidence": 0.991
+        },
+        {
+          "text": "blasted",
+          "start": 154.68,
+          "end": 154.86,
+          "confidence": 0.895
+        },
+        {
+          "text": "off",
+          "start": 154.86,
+          "end": 155.0,
+          "confidence": 0.987
+        },
+        {
+          "text": "the",
+          "start": 155.0,
+          "end": 155.16,
+          "confidence": 0.959
+        },
+        {
+          "text": "planet.",
+          "start": 155.16,
+          "end": 155.34,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 26,
+      "seek": 14012,
+      "start": 155.36,
+      "end": 157.11,
+      "text": " Rock the cars, catastrophic, and it matters more",
+      "tokens": [
+        6922,
+        264,
+        5163,
+        11,
+        34915,
+        11,
+        293,
+        309,
+        7001,
+        544
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3642334662543403,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7768110036849976,
+      "confidence": 0.703,
+      "words": [
+        {
+          "text": "Rock",
+          "start": 155.36,
+          "end": 155.56,
+          "confidence": 0.563
+        },
+        {
+          "text": "the",
+          "start": 155.56,
+          "end": 155.7,
+          "confidence": 0.504
+        },
+        {
+          "text": "cars,",
+          "start": 155.7,
+          "end": 156.36,
+          "confidence": 0.472
+        },
+        {
+          "text": "catastrophic,",
+          "start": 156.36,
+          "end": 156.4,
+          "confidence": 0.77
+        },
+        {
+          "text": "and",
+          "start": 156.4,
+          "end": 156.62,
+          "confidence": 0.925
+        },
+        {
+          "text": "it",
+          "start": 156.62,
+          "end": 156.7,
+          "confidence": 0.73
+        },
+        {
+          "text": "matters",
+          "start": 156.7,
+          "end": 156.94,
+          "confidence": 0.874
+        },
+        {
+          "text": "more",
+          "start": 156.94,
+          "end": 157.11,
+          "confidence": 0.973
+        }
+      ]
+    },
+    {
+      "id": 27,
+      "seek": 14012,
+      "start": 157.11,
+      "end": 157.93,
+      "text": " because I had it now.",
+      "tokens": [
+        570,
+        286,
+        632,
+        309,
+        586,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3642334662543403,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7768110036849976,
+      "confidence": 0.648,
+      "words": [
+        {
+          "text": "because",
+          "start": 157.11,
+          "end": 157.38,
+          "confidence": 0.99
+        },
+        {
+          "text": "I",
+          "start": 157.38,
+          "end": 157.56,
+          "confidence": 0.528
+        },
+        {
+          "text": "had",
+          "start": 157.56,
+          "end": 157.68,
+          "confidence": 0.935
+        },
+        {
+          "text": "it",
+          "start": 157.68,
+          "end": 157.76,
+          "confidence": 0.984
+        },
+        {
+          "text": "now.",
+          "start": 157.76,
+          "end": 157.93,
+          "confidence": 0.237
+        }
+      ]
+    },
+    {
+      "id": 28,
+      "seek": 14012,
+      "start": 157.93,
+      "end": 160.1,
+      "text": " Had I thought about wreaking havoc on an opposition.",
+      "tokens": [
+        12298,
+        286,
+        1194,
+        466,
+        46674,
+        2456,
+        47367,
+        322,
+        364,
+        13504,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3642334662543403,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7768110036849976,
+      "confidence": 0.955,
+      "words": [
+        {
+          "text": "Had",
+          "start": 157.93,
+          "end": 158.12,
+          "confidence": 0.852
+        },
+        {
+          "text": "I",
+          "start": 158.12,
+          "end": 158.2,
+          "confidence": 0.971
+        },
+        {
+          "text": "thought",
+          "start": 158.2,
+          "end": 158.4,
+          "confidence": 0.991
+        },
+        {
+          "text": "about",
+          "start": 158.4,
+          "end": 158.58,
+          "confidence": 0.995
+        },
+        {
+          "text": "wreaking",
+          "start": 158.58,
+          "end": 158.84,
+          "confidence": 0.996
+        },
+        {
+          "text": "havoc",
+          "start": 158.84,
+          "end": 159.08,
+          "confidence": 1.0
+        },
+        {
+          "text": "on",
+          "start": 159.08,
+          "end": 159.28,
+          "confidence": 0.861
+        },
+        {
+          "text": "an",
+          "start": 159.28,
+          "end": 159.44,
+          "confidence": 0.913
+        },
+        {
+          "text": "opposition.",
+          "start": 159.44,
+          "end": 160.1,
+          "confidence": 0.991
+        }
+      ]
+    },
+    {
+      "id": 29,
+      "seek": 14012,
+      "start": 160.1,
+      "end": 161.04,
+      "text": " Kind of shocking, they want it static.",
+      "tokens": [
+        9242,
+        295,
+        18776,
+        11,
+        436,
+        528,
+        309,
+        13437,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3642334662543403,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7768110036849976,
+      "confidence": 0.666,
+      "words": [
+        {
+          "text": "Kind",
+          "start": 160.1,
+          "end": 160.14,
+          "confidence": 0.663
+        },
+        {
+          "text": "of",
+          "start": 160.14,
+          "end": 160.22,
+          "confidence": 0.995
+        },
+        {
+          "text": "shocking,",
+          "start": 160.22,
+          "end": 160.5,
+          "confidence": 0.656
+        },
+        {
+          "text": "they",
+          "start": 160.5,
+          "end": 160.58,
+          "confidence": 0.366
+        },
+        {
+          "text": "want",
+          "start": 160.58,
+          "end": 160.74,
+          "confidence": 0.573
+        },
+        {
+          "text": "it",
+          "start": 160.74,
+          "end": 160.84,
+          "confidence": 0.648
+        },
+        {
+          "text": "static.",
+          "start": 160.84,
+          "end": 161.04,
+          "confidence": 0.993
+        }
+      ]
+    },
+    {
+      "id": 30,
+      "seek": 14012,
+      "start": 161.06,
+      "end": 162.14,
+      "text": " With precision, I'm automatic.",
+      "tokens": [
+        2022,
+        18356,
+        11,
+        286,
+        478,
+        12509,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3642334662543403,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7768110036849976,
+      "confidence": 0.875,
+      "words": [
+        {
+          "text": "With",
+          "start": 161.06,
+          "end": 161.24,
+          "confidence": 0.59
+        },
+        {
+          "text": "precision,",
+          "start": 161.24,
+          "end": 161.72,
+          "confidence": 0.904
+        },
+        {
+          "text": "I'm",
+          "start": 161.72,
+          "end": 161.78,
+          "confidence": 0.987
+        },
+        {
+          "text": "automatic.",
+          "start": 161.78,
+          "end": 162.14,
+          "confidence": 0.987
+        }
+      ]
+    },
+    {
+      "id": 31,
+      "seek": 14012,
+      "start": 162.24,
+      "end": 163.36,
+      "text": " Quarterback, I ain't talking second.",
+      "tokens": [
+        43794,
+        3207,
+        11,
+        286,
+        7862,
+        380,
+        1417,
+        1150,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3642334662543403,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7768110036849976,
+      "confidence": 0.688,
+      "words": [
+        {
+          "text": "Quarterback,",
+          "start": 162.24,
+          "end": 162.66,
+          "confidence": 0.513
+        },
+        {
+          "text": "I",
+          "start": 162.66,
+          "end": 162.78,
+          "confidence": 0.965
+        },
+        {
+          "text": "ain't",
+          "start": 162.78,
+          "end": 162.86,
+          "confidence": 0.99
+        },
+        {
+          "text": "talking",
+          "start": 162.86,
+          "end": 163.1,
+          "confidence": 0.892
+        },
+        {
+          "text": "second.",
+          "start": 163.1,
+          "end": 163.36,
+          "confidence": 0.328
+        }
+      ]
+    },
+    {
+      "id": 32,
+      "seek": 14012,
+      "start": 163.4,
+      "end": 164.17,
+      "text": " Pack it, pack it up.",
+      "tokens": [
+        18466,
+        309,
+        11,
+        2844,
+        309,
+        493,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3642334662543403,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7768110036849976,
+      "confidence": 0.973,
+      "words": [
+        {
+          "text": "Pack",
+          "start": 163.4,
+          "end": 163.6,
+          "confidence": 0.968
+        },
+        {
+          "text": "it,",
+          "start": 163.6,
+          "end": 163.68,
+          "confidence": 0.937
+        },
+        {
+          "text": "pack",
+          "start": 163.68,
+          "end": 163.84,
+          "confidence": 0.986
+        },
+        {
+          "text": "it",
+          "start": 163.84,
+          "end": 163.98,
+          "confidence": 0.999
+        },
+        {
+          "text": "up.",
+          "start": 163.98,
+          "end": 164.17,
+          "confidence": 0.979
+        }
+      ]
+    },
+    {
+      "id": 33,
+      "seek": 14012,
+      "start": 164.17,
+      "end": 165.1,
+      "text": " I don't panic, better, better.",
+      "tokens": [
+        286,
+        500,
+        380,
+        14783,
+        11,
+        1101,
+        11,
+        1101,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3642334662543403,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7768110036849976,
+      "confidence": 0.76,
+      "words": [
+        {
+          "text": "I",
+          "start": 164.17,
+          "end": 164.21,
+          "confidence": 0.984
+        },
+        {
+          "text": "don't",
+          "start": 164.21,
+          "end": 164.34,
+          "confidence": 0.913
+        },
+        {
+          "text": "panic,",
+          "start": 164.34,
+          "end": 164.8,
+          "confidence": 0.999
+        },
+        {
+          "text": "better,",
+          "start": 164.8,
+          "end": 164.84,
+          "confidence": 0.423
+        },
+        {
+          "text": "better.",
+          "start": 164.84,
+          "end": 165.1,
+          "confidence": 0.556
+        }
+      ]
+    },
+    {
+      "id": 34,
+      "seek": 14012,
+      "start": 165.16,
+      "end": 165.76,
+      "text": " Up who the baddest.",
+      "tokens": [
+        5858,
+        567,
+        264,
+        1578,
+        23748,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3642334662543403,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7768110036849976,
+      "confidence": 0.752,
+      "words": [
+        {
+          "text": "Up",
+          "start": 165.16,
+          "end": 165.24,
+          "confidence": 0.518
+        },
+        {
+          "text": "who",
+          "start": 165.24,
+          "end": 165.38,
+          "confidence": 0.751
+        },
+        {
+          "text": "the",
+          "start": 165.38,
+          "end": 165.52,
+          "confidence": 0.926
+        },
+        {
+          "text": "baddest.",
+          "start": 165.52,
+          "end": 165.76,
+          "confidence": 0.817
+        }
+      ]
+    },
+    {
+      "id": 35,
+      "seek": 16572,
+      "start": 165.76,
+      "end": 166.86,
+      "text": " it don't matter cause we is your enemy.",
+      "tokens": [
+        50364,
+        309,
+        500,
+        380,
+        1871,
+        3082,
+        321,
+        307,
+        428,
+        5945,
+        13,
+        50414
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.910880969120906,
+      "compression_ratio": 0.8297872340425532,
+      "no_speech_prob": 0.6945543885231018,
+      "confidence": 0.448,
+      "words": [
+        {
+          "text": "it",
+          "start": 165.76,
+          "end": 165.86,
+          "confidence": 0.124
+        },
+        {
+          "text": "don't",
+          "start": 165.86,
+          "end": 166.18,
+          "confidence": 0.825
+        },
+        {
+          "text": "matter",
+          "start": 166.18,
+          "end": 166.22,
+          "confidence": 0.996
+        },
+        {
+          "text": "cause",
+          "start": 166.22,
+          "end": 166.4,
+          "confidence": 0.287
+        },
+        {
+          "text": "we",
+          "start": 166.4,
+          "end": 166.5,
+          "confidence": 0.889
+        },
+        {
+          "text": "is",
+          "start": 166.5,
+          "end": 166.68,
+          "confidence": 0.231
+        },
+        {
+          "text": "your",
+          "start": 166.68,
+          "end": 166.74,
+          "confidence": 0.562
+        },
+        {
+          "text": "enemy.",
+          "start": 166.74,
+          "end": 166.86,
+          "confidence": 0.258
+        }
+      ]
+    },
+    {
+      "id": 36,
+      "seek": 19572,
+      "start": 196.18,
+      "end": 198.2,
+      "text": " I swear I'll never be insane",
+      "tokens": [
+        286,
+        11902,
+        286,
+        603,
+        1128,
+        312,
+        10838
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5786522030830383,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.756009578704834,
+      "confidence": 0.75,
+      "words": [
+        {
+          "text": "I",
+          "start": 196.18,
+          "end": 196.4,
+          "confidence": 0.623
+        },
+        {
+          "text": "swear",
+          "start": 196.4,
+          "end": 196.66,
+          "confidence": 0.959
+        },
+        {
+          "text": "I'll",
+          "start": 196.66,
+          "end": 197.2,
+          "confidence": 0.643
+        },
+        {
+          "text": "never",
+          "start": 197.2,
+          "end": 197.5,
+          "confidence": 0.997
+        },
+        {
+          "text": "be",
+          "start": 197.5,
+          "end": 197.84,
+          "confidence": 0.993
+        },
+        {
+          "text": "insane",
+          "start": 197.84,
+          "end": 198.2,
+          "confidence": 0.546
+        }
+      ]
+    },
+    {
+      "id": 37,
+      "seek": 19772,
+      "start": 198.38,
+      "end": 199.72,
+      "text": " You got to be yourself",
+      "tokens": [
+        50364,
+        509,
+        658,
+        281,
+        312,
+        1803,
+        50464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7925397753715515,
+      "compression_ratio": 0.7333333333333333,
+      "no_speech_prob": 0.7818466424942017,
+      "confidence": 0.406,
+      "words": [
+        {
+          "text": "You",
+          "start": 198.38,
+          "end": 198.54,
+          "confidence": 0.093
+        },
+        {
+          "text": "got",
+          "start": 198.54,
+          "end": 198.8,
+          "confidence": 0.199
+        },
+        {
+          "text": "to",
+          "start": 198.8,
+          "end": 198.98,
+          "confidence": 0.803
+        },
+        {
+          "text": "be",
+          "start": 198.98,
+          "end": 199.08,
+          "confidence": 0.826
+        },
+        {
+          "text": "yourself",
+          "start": 199.08,
+          "end": 199.72,
+          "confidence": 0.903
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/corner_cases.cpu/random.nocond_apollo11.mp3.words.json b/tests/expected/corner_cases.cpu/random.nocond_apollo11.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..411722411d7434ca27a340d8cf4629331e376df9
--- /dev/null
+++ b/tests/expected/corner_cases.cpu/random.nocond_apollo11.mp3.words.json
@@ -0,0 +1,1192 @@
+{
+  "text": " Apollo 11, Houston we got a recommendation for you on your Soyuz-VA GLEME GVA. All right. Okay, we like to say that they make it one or two on the helmet. We're going to have a B1 and you can put the other one on the mic helmet with those GVA blizzard frames. We were going to hack me on the ground with a cover. I tried it already. Okay, fine. We weren't sure of that. Just a suggestion. We thought we'd get you to check it out. I'm not sure if you've already turned that. So I guess we're going to come up with this. Let us know. Okay, no problem. Okay, no problem. No problem. No one at the end of the line.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.64,
+      "end": 6.68,
+      "text": " Apollo 11, Houston we got a recommendation for you on your Soyuz-VA GLEME GVA.",
+      "tokens": [
+        25187,
+        2975,
+        11,
+        18717,
+        321,
+        658,
+        257,
+        11879,
+        337,
+        291,
+        322,
+        428,
+        24758,
+        3334,
+        12,
+        20914,
+        460,
+        2634,
+        15454,
+        460,
+        20914,
+        13
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.709779328937772,
+      "compression_ratio": 1.3631578947368421,
+      "no_speech_prob": 0.45045843720436096,
+      "confidence": 0.542,
+      "words": [
+        {
+          "text": "Apollo",
+          "start": 0.64,
+          "end": 0.98,
+          "confidence": 0.155
+        },
+        {
+          "text": "11,",
+          "start": 0.98,
+          "end": 1.54,
+          "confidence": 0.977
+        },
+        {
+          "text": "Houston",
+          "start": 1.54,
+          "end": 1.8,
+          "confidence": 0.986
+        },
+        {
+          "text": "we",
+          "start": 1.8,
+          "end": 1.98,
+          "confidence": 0.52
+        },
+        {
+          "text": "got",
+          "start": 1.98,
+          "end": 2.16,
+          "confidence": 0.824
+        },
+        {
+          "text": "a",
+          "start": 2.16,
+          "end": 2.38,
+          "confidence": 0.989
+        },
+        {
+          "text": "recommendation",
+          "start": 2.38,
+          "end": 3.1,
+          "confidence": 0.968
+        },
+        {
+          "text": "for",
+          "start": 3.1,
+          "end": 3.52,
+          "confidence": 0.947
+        },
+        {
+          "text": "you",
+          "start": 3.52,
+          "end": 3.9,
+          "confidence": 0.984
+        },
+        {
+          "text": "on",
+          "start": 3.9,
+          "end": 4.28,
+          "confidence": 0.909
+        },
+        {
+          "text": "your",
+          "start": 4.28,
+          "end": 4.32,
+          "confidence": 0.971
+        },
+        {
+          "text": "Soyuz-VA",
+          "start": 4.32,
+          "end": 5.38,
+          "confidence": 0.26
+        },
+        {
+          "text": "GLEME",
+          "start": 5.38,
+          "end": 6.04,
+          "confidence": 0.478
+        },
+        {
+          "text": "GVA.",
+          "start": 6.04,
+          "end": 6.68,
+          "confidence": 0.436
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 7.5,
+      "end": 11.0,
+      "text": " All right.",
+      "tokens": [
+        1057,
+        558,
+        13
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.709779328937772,
+      "compression_ratio": 1.3631578947368421,
+      "no_speech_prob": 0.45045843720436096,
+      "confidence": 0.456,
+      "words": [
+        {
+          "text": "All",
+          "start": 7.5,
+          "end": 7.7,
+          "confidence": 0.212
+        },
+        {
+          "text": "right.",
+          "start": 7.7,
+          "end": 11.0,
+          "confidence": 0.982
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 11.5,
+      "end": 17.19,
+      "text": " Okay, we like to say that they make it one or two on the helmet.",
+      "tokens": [
+        1033,
+        11,
+        321,
+        411,
+        281,
+        584,
+        300,
+        436,
+        652,
+        309,
+        472,
+        420,
+        732,
+        322,
+        264,
+        15922,
+        13
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.709779328937772,
+      "compression_ratio": 1.3631578947368421,
+      "no_speech_prob": 0.45045843720436096,
+      "confidence": 0.428,
+      "words": [
+        {
+          "text": "Okay,",
+          "start": 11.5,
+          "end": 12.82,
+          "confidence": 0.577
+        },
+        {
+          "text": "we",
+          "start": 12.82,
+          "end": 13.12,
+          "confidence": 0.541
+        },
+        {
+          "text": "like",
+          "start": 13.12,
+          "end": 13.44,
+          "confidence": 0.493
+        },
+        {
+          "text": "to",
+          "start": 13.44,
+          "end": 13.68,
+          "confidence": 0.307
+        },
+        {
+          "text": "say",
+          "start": 13.68,
+          "end": 14.96,
+          "confidence": 0.172
+        },
+        {
+          "text": "that",
+          "start": 14.96,
+          "end": 15.56,
+          "confidence": 0.203
+        },
+        {
+          "text": "they",
+          "start": 15.56,
+          "end": 15.6,
+          "confidence": 0.472
+        },
+        {
+          "text": "make",
+          "start": 15.6,
+          "end": 15.76,
+          "confidence": 0.378
+        },
+        {
+          "text": "it",
+          "start": 15.76,
+          "end": 15.96,
+          "confidence": 0.259
+        },
+        {
+          "text": "one",
+          "start": 15.96,
+          "end": 16.1,
+          "confidence": 0.481
+        },
+        {
+          "text": "or",
+          "start": 16.1,
+          "end": 16.34,
+          "confidence": 0.221
+        },
+        {
+          "text": "two",
+          "start": 16.34,
+          "end": 16.46,
+          "confidence": 0.938
+        },
+        {
+          "text": "on",
+          "start": 16.46,
+          "end": 16.7,
+          "confidence": 0.638
+        },
+        {
+          "text": "the",
+          "start": 16.7,
+          "end": 16.96,
+          "confidence": 0.885
+        },
+        {
+          "text": "helmet.",
+          "start": 16.96,
+          "end": 17.19,
+          "confidence": 0.695
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 17.19,
+      "end": 24.74,
+      "text": " We're going to have a B1 and you can put the other one on the mic helmet with those GVA blizzard frames.",
+      "tokens": [
+        492,
+        434,
+        516,
+        281,
+        362,
+        257,
+        363,
+        16,
+        293,
+        291,
+        393,
+        829,
+        264,
+        661,
+        472,
+        322,
+        264,
+        3123,
+        15922,
+        365,
+        729,
+        460,
+        20914,
+        888,
+        31062,
+        12083,
+        13
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.709779328937772,
+      "compression_ratio": 1.3631578947368421,
+      "no_speech_prob": 0.45045843720436096,
+      "confidence": 0.515,
+      "words": [
+        {
+          "text": "We're",
+          "start": 17.19,
+          "end": 17.86,
+          "confidence": 0.63
+        },
+        {
+          "text": "going",
+          "start": 17.86,
+          "end": 18.06,
+          "confidence": 0.62
+        },
+        {
+          "text": "to",
+          "start": 18.06,
+          "end": 18.24,
+          "confidence": 0.993
+        },
+        {
+          "text": "have",
+          "start": 18.24,
+          "end": 18.3,
+          "confidence": 0.959
+        },
+        {
+          "text": "a",
+          "start": 18.3,
+          "end": 18.42,
+          "confidence": 0.32
+        },
+        {
+          "text": "B1",
+          "start": 18.42,
+          "end": 19.3,
+          "confidence": 0.799
+        },
+        {
+          "text": "and",
+          "start": 19.3,
+          "end": 20.18,
+          "confidence": 0.498
+        },
+        {
+          "text": "you",
+          "start": 20.18,
+          "end": 20.36,
+          "confidence": 0.87
+        },
+        {
+          "text": "can",
+          "start": 20.36,
+          "end": 20.54,
+          "confidence": 0.672
+        },
+        {
+          "text": "put",
+          "start": 20.54,
+          "end": 20.72,
+          "confidence": 0.967
+        },
+        {
+          "text": "the",
+          "start": 20.72,
+          "end": 20.88,
+          "confidence": 0.974
+        },
+        {
+          "text": "other",
+          "start": 20.88,
+          "end": 21.06,
+          "confidence": 0.995
+        },
+        {
+          "text": "one",
+          "start": 21.06,
+          "end": 21.26,
+          "confidence": 0.973
+        },
+        {
+          "text": "on",
+          "start": 21.26,
+          "end": 21.68,
+          "confidence": 0.973
+        },
+        {
+          "text": "the",
+          "start": 21.68,
+          "end": 21.96,
+          "confidence": 0.585
+        },
+        {
+          "text": "mic",
+          "start": 21.96,
+          "end": 22.6,
+          "confidence": 0.48
+        },
+        {
+          "text": "helmet",
+          "start": 22.6,
+          "end": 22.94,
+          "confidence": 0.949
+        },
+        {
+          "text": "with",
+          "start": 22.94,
+          "end": 23.2,
+          "confidence": 0.444
+        },
+        {
+          "text": "those",
+          "start": 23.2,
+          "end": 23.5,
+          "confidence": 0.351
+        },
+        {
+          "text": "GVA",
+          "start": 23.5,
+          "end": 23.86,
+          "confidence": 0.169
+        },
+        {
+          "text": "blizzard",
+          "start": 23.86,
+          "end": 24.32,
+          "confidence": 0.094
+        },
+        {
+          "text": "frames.",
+          "start": 24.32,
+          "end": 24.74,
+          "confidence": 0.245
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 5500,
+      "start": 56.0,
+      "end": 61.1,
+      "text": " We were going to hack me on the ground with a cover.",
+      "tokens": [
+        492,
+        645,
+        516,
+        281,
+        10339,
+        385,
+        322,
+        264,
+        2727,
+        365,
+        257,
+        2060,
+        13
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.46802620968576203,
+      "compression_ratio": 1.6418604651162791,
+      "no_speech_prob": 0.7498895525932312,
+      "confidence": 0.342,
+      "words": [
+        {
+          "text": "We",
+          "start": 56.0,
+          "end": 56.68,
+          "confidence": 0.071
+        },
+        {
+          "text": "were",
+          "start": 56.68,
+          "end": 56.98,
+          "confidence": 0.177
+        },
+        {
+          "text": "going",
+          "start": 56.98,
+          "end": 57.2,
+          "confidence": 0.148
+        },
+        {
+          "text": "to",
+          "start": 57.2,
+          "end": 57.46,
+          "confidence": 0.932
+        },
+        {
+          "text": "hack",
+          "start": 57.46,
+          "end": 57.5,
+          "confidence": 0.261
+        },
+        {
+          "text": "me",
+          "start": 57.5,
+          "end": 57.64,
+          "confidence": 0.544
+        },
+        {
+          "text": "on",
+          "start": 57.64,
+          "end": 59.2,
+          "confidence": 0.433
+        },
+        {
+          "text": "the",
+          "start": 59.2,
+          "end": 59.5,
+          "confidence": 0.309
+        },
+        {
+          "text": "ground",
+          "start": 59.5,
+          "end": 59.78,
+          "confidence": 0.356
+        },
+        {
+          "text": "with",
+          "start": 59.78,
+          "end": 60.62,
+          "confidence": 0.471
+        },
+        {
+          "text": "a",
+          "start": 60.62,
+          "end": 60.78,
+          "confidence": 0.538
+        },
+        {
+          "text": "cover.",
+          "start": 60.78,
+          "end": 61.1,
+          "confidence": 0.855
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 5500,
+      "start": 61.12,
+      "end": 61.88,
+      "text": " I tried it already.",
+      "tokens": [
+        286,
+        3031,
+        309,
+        1217,
+        13
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.46802620968576203,
+      "compression_ratio": 1.6418604651162791,
+      "no_speech_prob": 0.7498895525932312,
+      "confidence": 0.682,
+      "words": [
+        {
+          "text": "I",
+          "start": 61.12,
+          "end": 61.26,
+          "confidence": 0.407
+        },
+        {
+          "text": "tried",
+          "start": 61.26,
+          "end": 61.52,
+          "confidence": 0.889
+        },
+        {
+          "text": "it",
+          "start": 61.52,
+          "end": 61.7,
+          "confidence": 0.746
+        },
+        {
+          "text": "already.",
+          "start": 61.7,
+          "end": 61.88,
+          "confidence": 0.803
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 5500,
+      "start": 62.5,
+      "end": 63.12,
+      "text": " Okay, fine.",
+      "tokens": [
+        1033,
+        11,
+        2489,
+        13
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.46802620968576203,
+      "compression_ratio": 1.6418604651162791,
+      "no_speech_prob": 0.7498895525932312,
+      "confidence": 0.683,
+      "words": [
+        {
+          "text": "Okay,",
+          "start": 62.5,
+          "end": 63.04,
+          "confidence": 0.521
+        },
+        {
+          "text": "fine.",
+          "start": 63.04,
+          "end": 63.12,
+          "confidence": 0.895
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 5500,
+      "start": 63.12,
+      "end": 64.12,
+      "text": " We weren't sure of that.",
+      "tokens": [
+        492,
+        4999,
+        380,
+        988,
+        295,
+        300,
+        13
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.46802620968576203,
+      "compression_ratio": 1.6418604651162791,
+      "no_speech_prob": 0.7498895525932312,
+      "confidence": 0.895,
+      "words": [
+        {
+          "text": "We",
+          "start": 63.12,
+          "end": 63.34,
+          "confidence": 0.959
+        },
+        {
+          "text": "weren't",
+          "start": 63.34,
+          "end": 63.62,
+          "confidence": 0.988
+        },
+        {
+          "text": "sure",
+          "start": 63.62,
+          "end": 63.82,
+          "confidence": 0.903
+        },
+        {
+          "text": "of",
+          "start": 63.82,
+          "end": 64.08,
+          "confidence": 0.613
+        },
+        {
+          "text": "that.",
+          "start": 64.08,
+          "end": 64.12,
+          "confidence": 0.989
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 5500,
+      "start": 64.46,
+      "end": 65.2,
+      "text": " Just a suggestion.",
+      "tokens": [
+        1449,
+        257,
+        16541,
+        13
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.46802620968576203,
+      "compression_ratio": 1.6418604651162791,
+      "no_speech_prob": 0.7498895525932312,
+      "confidence": 0.755,
+      "words": [
+        {
+          "text": "Just",
+          "start": 64.46,
+          "end": 64.66,
+          "confidence": 0.545
+        },
+        {
+          "text": "a",
+          "start": 64.66,
+          "end": 64.76,
+          "confidence": 0.791
+        },
+        {
+          "text": "suggestion.",
+          "start": 64.76,
+          "end": 65.2,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 5500,
+      "start": 65.34,
+      "end": 67.92,
+      "text": " We thought we'd get you to check it out.",
+      "tokens": [
+        492,
+        1194,
+        321,
+        1116,
+        483,
+        291,
+        281,
+        1520,
+        309,
+        484,
+        13
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.46802620968576203,
+      "compression_ratio": 1.6418604651162791,
+      "no_speech_prob": 0.7498895525932312,
+      "confidence": 0.692,
+      "words": [
+        {
+          "text": "We",
+          "start": 65.34,
+          "end": 65.44,
+          "confidence": 0.873
+        },
+        {
+          "text": "thought",
+          "start": 65.44,
+          "end": 65.62,
+          "confidence": 0.968
+        },
+        {
+          "text": "we'd",
+          "start": 65.62,
+          "end": 66.76,
+          "confidence": 0.686
+        },
+        {
+          "text": "get",
+          "start": 66.76,
+          "end": 67.06,
+          "confidence": 0.093
+        },
+        {
+          "text": "you",
+          "start": 67.06,
+          "end": 67.14,
+          "confidence": 0.823
+        },
+        {
+          "text": "to",
+          "start": 67.14,
+          "end": 67.32,
+          "confidence": 0.987
+        },
+        {
+          "text": "check",
+          "start": 67.32,
+          "end": 67.46,
+          "confidence": 0.845
+        },
+        {
+          "text": "it",
+          "start": 67.46,
+          "end": 67.68,
+          "confidence": 0.991
+        },
+        {
+          "text": "out.",
+          "start": 67.68,
+          "end": 67.92,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 5500,
+      "start": 68.28,
+      "end": 69.34,
+      "text": " I'm not sure if you've already turned that.",
+      "tokens": [
+        286,
+        478,
+        406,
+        988,
+        498,
+        291,
+        600,
+        1217,
+        3574,
+        300,
+        13
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.46802620968576203,
+      "compression_ratio": 1.6418604651162791,
+      "no_speech_prob": 0.7498895525932312,
+      "confidence": 0.444,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 68.28,
+          "end": 68.5,
+          "confidence": 0.314
+        },
+        {
+          "text": "not",
+          "start": 68.5,
+          "end": 68.56,
+          "confidence": 0.319
+        },
+        {
+          "text": "sure",
+          "start": 68.56,
+          "end": 68.74,
+          "confidence": 0.82
+        },
+        {
+          "text": "if",
+          "start": 68.74,
+          "end": 68.78,
+          "confidence": 0.334
+        },
+        {
+          "text": "you've",
+          "start": 68.78,
+          "end": 68.84,
+          "confidence": 0.389
+        },
+        {
+          "text": "already",
+          "start": 68.84,
+          "end": 68.94,
+          "confidence": 0.588
+        },
+        {
+          "text": "turned",
+          "start": 68.94,
+          "end": 69.12,
+          "confidence": 0.738
+        },
+        {
+          "text": "that.",
+          "start": 69.12,
+          "end": 69.34,
+          "confidence": 0.524
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 5500,
+      "start": 70.42,
+      "end": 71.98,
+      "text": " So I guess we're going to come up with this.",
+      "tokens": [
+        407,
+        286,
+        2041,
+        321,
+        434,
+        516,
+        281,
+        808,
+        493,
+        365,
+        341,
+        13
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.46802620968576203,
+      "compression_ratio": 1.6418604651162791,
+      "no_speech_prob": 0.7498895525932312,
+      "confidence": 0.709,
+      "words": [
+        {
+          "text": "So",
+          "start": 70.42,
+          "end": 70.5,
+          "confidence": 0.533
+        },
+        {
+          "text": "I",
+          "start": 70.5,
+          "end": 70.54,
+          "confidence": 0.454
+        },
+        {
+          "text": "guess",
+          "start": 70.54,
+          "end": 70.82,
+          "confidence": 0.991
+        },
+        {
+          "text": "we're",
+          "start": 70.82,
+          "end": 71.12,
+          "confidence": 0.654
+        },
+        {
+          "text": "going",
+          "start": 71.12,
+          "end": 71.28,
+          "confidence": 0.815
+        },
+        {
+          "text": "to",
+          "start": 71.28,
+          "end": 71.36,
+          "confidence": 0.992
+        },
+        {
+          "text": "come",
+          "start": 71.36,
+          "end": 71.48,
+          "confidence": 0.97
+        },
+        {
+          "text": "up",
+          "start": 71.48,
+          "end": 71.68,
+          "confidence": 0.958
+        },
+        {
+          "text": "with",
+          "start": 71.68,
+          "end": 71.92,
+          "confidence": 0.915
+        },
+        {
+          "text": "this.",
+          "start": 71.92,
+          "end": 71.98,
+          "confidence": 0.323
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 5500,
+      "start": 73.5,
+      "end": 73.62,
+      "text": " Let us know.",
+      "tokens": [
+        961,
+        505,
+        458,
+        13
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.46802620968576203,
+      "compression_ratio": 1.6418604651162791,
+      "no_speech_prob": 0.7498895525932312,
+      "confidence": 0.847,
+      "words": [
+        {
+          "text": "Let",
+          "start": 73.5,
+          "end": 73.54,
+          "confidence": 0.615
+        },
+        {
+          "text": "us",
+          "start": 73.54,
+          "end": 73.58,
+          "confidence": 0.99
+        },
+        {
+          "text": "know.",
+          "start": 73.58,
+          "end": 73.62,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 5500,
+      "start": 74.22,
+      "end": 75.22,
+      "text": " Okay, no problem.",
+      "tokens": [
+        1033,
+        11,
+        572,
+        1154,
+        13
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.46802620968576203,
+      "compression_ratio": 1.6418604651162791,
+      "no_speech_prob": 0.7498895525932312,
+      "confidence": 0.851,
+      "words": [
+        {
+          "text": "Okay,",
+          "start": 74.22,
+          "end": 74.7,
+          "confidence": 0.687
+        },
+        {
+          "text": "no",
+          "start": 74.7,
+          "end": 74.86,
+          "confidence": 0.917
+        },
+        {
+          "text": "problem.",
+          "start": 74.86,
+          "end": 75.22,
+          "confidence": 0.976
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 5500,
+      "start": 75.28,
+      "end": 76.46,
+      "text": " Okay, no problem.",
+      "tokens": [
+        1033,
+        11,
+        572,
+        1154,
+        13
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.46802620968576203,
+      "compression_ratio": 1.6418604651162791,
+      "no_speech_prob": 0.7498895525932312,
+      "confidence": 0.623,
+      "words": [
+        {
+          "text": "Okay,",
+          "start": 75.28,
+          "end": 75.98,
+          "confidence": 0.258
+        },
+        {
+          "text": "no",
+          "start": 75.98,
+          "end": 76.2,
+          "confidence": 0.948
+        },
+        {
+          "text": "problem.",
+          "start": 76.2,
+          "end": 76.46,
+          "confidence": 0.993
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 7600,
+      "start": 76.46,
+      "end": 76.62,
+      "text": " No problem.",
+      "tokens": [
+        883,
+        1154,
+        13
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.7044810771942138,
+      "compression_ratio": 0.9344262295081968,
+      "no_speech_prob": 0.35927486419677734,
+      "confidence": 0.653,
+      "words": [
+        {
+          "text": "No",
+          "start": 76.46,
+          "end": 76.5,
+          "confidence": 0.463
+        },
+        {
+          "text": "problem.",
+          "start": 76.5,
+          "end": 76.62,
+          "confidence": 0.922
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 7700,
+      "start": 77.02,
+      "end": 78.32,
+      "text": " No one at the end of the line.",
+      "tokens": [
+        50364,
+        883,
+        472,
+        412,
+        264,
+        917,
+        295,
+        264,
+        1622,
+        13,
+        50464
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.676593542098999,
+      "compression_ratio": 0.8823529411764706,
+      "no_speech_prob": 0.2589211165904999,
+      "confidence": 0.558,
+      "words": [
+        {
+          "text": "No",
+          "start": 77.02,
+          "end": 77.22,
+          "confidence": 0.139
+        },
+        {
+          "text": "one",
+          "start": 77.22,
+          "end": 77.36,
+          "confidence": 0.335
+        },
+        {
+          "text": "at",
+          "start": 77.36,
+          "end": 77.44,
+          "confidence": 0.483
+        },
+        {
+          "text": "the",
+          "start": 77.44,
+          "end": 77.48,
+          "confidence": 0.996
+        },
+        {
+          "text": "end",
+          "start": 77.48,
+          "end": 77.92,
+          "confidence": 0.995
+        },
+        {
+          "text": "of",
+          "start": 77.92,
+          "end": 78.1,
+          "confidence": 0.968
+        },
+        {
+          "text": "the",
+          "start": 78.1,
+          "end": 78.2,
+          "confidence": 0.536
+        },
+        {
+          "text": "line.",
+          "start": 78.2,
+          "end": 78.32,
+          "confidence": 0.816
+        }
+      ]
+    }
+  ],
+  "language": "English"
+}
\ No newline at end of file
diff --git a/tests/expected/corner_cases.cpu/random_apollo11.mp3.words.json b/tests/expected/corner_cases.cpu/random_apollo11.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..23ccd701318a10a1d5462a5b3b9a55f8ce872217
--- /dev/null
+++ b/tests/expected/corner_cases.cpu/random_apollo11.mp3.words.json
@@ -0,0 +1,3815 @@
+{
+  "text": " Apollo 11, Houston we got a recommendation for you on your Soyuz-EA GLEME GVA. Alright, okay, we like to say that they make the one that's on the helmet we're going to have in B1. And you can put the other one on the mic helmet with those GVA blizzard frames. Alright, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.64,
+      "end": 6.94,
+      "text": " Apollo 11, Houston we got a recommendation for you on your Soyuz-EA GLEME GVA.",
+      "tokens": [
+        25187,
+        2975,
+        11,
+        18717,
+        321,
+        658,
+        257,
+        11879,
+        337,
+        291,
+        322,
+        428,
+        24758,
+        3334,
+        12,
+        36,
+        32,
+        460,
+        2634,
+        15454,
+        460,
+        20914,
+        13
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.6937426777629109,
+      "compression_ratio": 1.39247311827957,
+      "no_speech_prob": 0.45045843720436096,
+      "confidence": 0.549,
+      "words": [
+        {
+          "text": "Apollo",
+          "start": 0.64,
+          "end": 0.98,
+          "confidence": 0.155
+        },
+        {
+          "text": "11,",
+          "start": 0.98,
+          "end": 1.54,
+          "confidence": 0.977
+        },
+        {
+          "text": "Houston",
+          "start": 1.54,
+          "end": 1.8,
+          "confidence": 0.986
+        },
+        {
+          "text": "we",
+          "start": 1.8,
+          "end": 1.98,
+          "confidence": 0.52
+        },
+        {
+          "text": "got",
+          "start": 1.98,
+          "end": 2.16,
+          "confidence": 0.824
+        },
+        {
+          "text": "a",
+          "start": 2.16,
+          "end": 2.38,
+          "confidence": 0.989
+        },
+        {
+          "text": "recommendation",
+          "start": 2.38,
+          "end": 3.1,
+          "confidence": 0.968
+        },
+        {
+          "text": "for",
+          "start": 3.1,
+          "end": 3.52,
+          "confidence": 0.947
+        },
+        {
+          "text": "you",
+          "start": 3.52,
+          "end": 3.9,
+          "confidence": 0.984
+        },
+        {
+          "text": "on",
+          "start": 3.9,
+          "end": 4.28,
+          "confidence": 0.909
+        },
+        {
+          "text": "your",
+          "start": 4.28,
+          "end": 4.32,
+          "confidence": 0.971
+        },
+        {
+          "text": "Soyuz-EA",
+          "start": 4.32,
+          "end": 5.42,
+          "confidence": 0.321
+        },
+        {
+          "text": "GLEME",
+          "start": 5.42,
+          "end": 6.04,
+          "confidence": 0.561
+        },
+        {
+          "text": "GVA.",
+          "start": 6.04,
+          "end": 6.94,
+          "confidence": 0.336
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 10.82,
+      "end": 19.86,
+      "text": " Alright, okay, we like to say that they make the one that's on the helmet we're going to have in B1.",
+      "tokens": [
+        2798,
+        11,
+        1392,
+        11,
+        321,
+        411,
+        281,
+        584,
+        300,
+        436,
+        652,
+        264,
+        472,
+        300,
+        311,
+        322,
+        264,
+        15922,
+        321,
+        434,
+        516,
+        281,
+        362,
+        294,
+        363,
+        16,
+        13
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.6937426777629109,
+      "compression_ratio": 1.39247311827957,
+      "no_speech_prob": 0.45045843720436096,
+      "confidence": 0.469,
+      "words": [
+        {
+          "text": "Alright,",
+          "start": 10.82,
+          "end": 12.5,
+          "confidence": 0.295
+        },
+        {
+          "text": "okay,",
+          "start": 12.5,
+          "end": 12.94,
+          "confidence": 0.513
+        },
+        {
+          "text": "we",
+          "start": 12.94,
+          "end": 13.12,
+          "confidence": 0.614
+        },
+        {
+          "text": "like",
+          "start": 13.12,
+          "end": 13.44,
+          "confidence": 0.496
+        },
+        {
+          "text": "to",
+          "start": 13.44,
+          "end": 13.68,
+          "confidence": 0.26
+        },
+        {
+          "text": "say",
+          "start": 13.68,
+          "end": 14.98,
+          "confidence": 0.135
+        },
+        {
+          "text": "that",
+          "start": 14.98,
+          "end": 15.56,
+          "confidence": 0.203
+        },
+        {
+          "text": "they",
+          "start": 15.56,
+          "end": 15.6,
+          "confidence": 0.425
+        },
+        {
+          "text": "make",
+          "start": 15.6,
+          "end": 15.76,
+          "confidence": 0.408
+        },
+        {
+          "text": "the",
+          "start": 15.76,
+          "end": 15.92,
+          "confidence": 0.255
+        },
+        {
+          "text": "one",
+          "start": 15.92,
+          "end": 16.1,
+          "confidence": 0.609
+        },
+        {
+          "text": "that's",
+          "start": 16.1,
+          "end": 16.34,
+          "confidence": 0.447
+        },
+        {
+          "text": "on",
+          "start": 16.34,
+          "end": 16.62,
+          "confidence": 0.598
+        },
+        {
+          "text": "the",
+          "start": 16.62,
+          "end": 16.96,
+          "confidence": 0.837
+        },
+        {
+          "text": "helmet",
+          "start": 16.96,
+          "end": 17.36,
+          "confidence": 0.836
+        },
+        {
+          "text": "we're",
+          "start": 17.36,
+          "end": 17.86,
+          "confidence": 0.301
+        },
+        {
+          "text": "going",
+          "start": 17.86,
+          "end": 18.06,
+          "confidence": 0.606
+        },
+        {
+          "text": "to",
+          "start": 18.06,
+          "end": 18.22,
+          "confidence": 0.818
+        },
+        {
+          "text": "have",
+          "start": 18.22,
+          "end": 18.26,
+          "confidence": 0.846
+        },
+        {
+          "text": "in",
+          "start": 18.26,
+          "end": 18.42,
+          "confidence": 0.718
+        },
+        {
+          "text": "B1.",
+          "start": 18.42,
+          "end": 19.86,
+          "confidence": 0.798
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 20.1,
+      "end": 24.76,
+      "text": " And you can put the other one on the mic helmet with those GVA blizzard frames.",
+      "tokens": [
+        400,
+        291,
+        393,
+        829,
+        264,
+        661,
+        472,
+        322,
+        264,
+        3123,
+        15922,
+        365,
+        729,
+        460,
+        20914,
+        888,
+        31062,
+        12083,
+        13
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.6937426777629109,
+      "compression_ratio": 1.39247311827957,
+      "no_speech_prob": 0.45045843720436096,
+      "confidence": 0.52,
+      "words": [
+        {
+          "text": "And",
+          "start": 20.1,
+          "end": 20.26,
+          "confidence": 0.62
+        },
+        {
+          "text": "you",
+          "start": 20.26,
+          "end": 20.38,
+          "confidence": 0.948
+        },
+        {
+          "text": "can",
+          "start": 20.38,
+          "end": 20.54,
+          "confidence": 0.731
+        },
+        {
+          "text": "put",
+          "start": 20.54,
+          "end": 20.72,
+          "confidence": 0.98
+        },
+        {
+          "text": "the",
+          "start": 20.72,
+          "end": 20.88,
+          "confidence": 0.989
+        },
+        {
+          "text": "other",
+          "start": 20.88,
+          "end": 21.06,
+          "confidence": 0.991
+        },
+        {
+          "text": "one",
+          "start": 21.06,
+          "end": 21.26,
+          "confidence": 0.977
+        },
+        {
+          "text": "on",
+          "start": 21.26,
+          "end": 21.68,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 21.68,
+          "end": 21.96,
+          "confidence": 0.554
+        },
+        {
+          "text": "mic",
+          "start": 21.96,
+          "end": 22.58,
+          "confidence": 0.442
+        },
+        {
+          "text": "helmet",
+          "start": 22.58,
+          "end": 22.94,
+          "confidence": 0.842
+        },
+        {
+          "text": "with",
+          "start": 22.94,
+          "end": 23.2,
+          "confidence": 0.433
+        },
+        {
+          "text": "those",
+          "start": 23.2,
+          "end": 23.5,
+          "confidence": 0.471
+        },
+        {
+          "text": "GVA",
+          "start": 23.5,
+          "end": 23.88,
+          "confidence": 0.414
+        },
+        {
+          "text": "blizzard",
+          "start": 23.88,
+          "end": 24.32,
+          "confidence": 0.104
+        },
+        {
+          "text": "frames.",
+          "start": 24.32,
+          "end": 24.76,
+          "confidence": 0.25
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 2500,
+      "start": 25.02,
+      "end": 55.0,
+      "text": " Alright, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them",
+      "tokens": [
+        50364,
+        2798,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.10773486667209202,
+      "compression_ratio": 24.096774193548388,
+      "no_speech_prob": 0.0012825782177969813,
+      "confidence": 0.936,
+      "words": [
+        {
+          "text": "Alright,",
+          "start": 25.02,
+          "end": 31.98,
+          "confidence": 0.245
+        },
+        {
+          "text": "got",
+          "start": 31.98,
+          "end": 32.02,
+          "confidence": 0.356
+        },
+        {
+          "text": "them,",
+          "start": 32.02,
+          "end": 32.58,
+          "confidence": 0.323
+        },
+        {
+          "text": "got",
+          "start": 32.58,
+          "end": 33.08,
+          "confidence": 0.519
+        },
+        {
+          "text": "them,",
+          "start": 33.08,
+          "end": 33.78,
+          "confidence": 0.941
+        },
+        {
+          "text": "got",
+          "start": 33.78,
+          "end": 33.82,
+          "confidence": 0.507
+        },
+        {
+          "text": "them,",
+          "start": 33.82,
+          "end": 34.12,
+          "confidence": 0.926
+        },
+        {
+          "text": "got",
+          "start": 34.12,
+          "end": 34.16,
+          "confidence": 0.475
+        },
+        {
+          "text": "them,",
+          "start": 34.16,
+          "end": 34.92,
+          "confidence": 0.897
+        },
+        {
+          "text": "got",
+          "start": 34.92,
+          "end": 34.96,
+          "confidence": 0.597
+        },
+        {
+          "text": "them,",
+          "start": 34.96,
+          "end": 35.88,
+          "confidence": 0.914
+        },
+        {
+          "text": "got",
+          "start": 35.88,
+          "end": 35.92,
+          "confidence": 0.662
+        },
+        {
+          "text": "them,",
+          "start": 35.92,
+          "end": 35.96,
+          "confidence": 0.942
+        },
+        {
+          "text": "got",
+          "start": 35.96,
+          "end": 36.0,
+          "confidence": 0.738
+        },
+        {
+          "text": "them,",
+          "start": 36.0,
+          "end": 36.04,
+          "confidence": 0.963
+        },
+        {
+          "text": "got",
+          "start": 36.04,
+          "end": 36.08,
+          "confidence": 0.819
+        },
+        {
+          "text": "them,",
+          "start": 36.08,
+          "end": 36.12,
+          "confidence": 0.974
+        },
+        {
+          "text": "got",
+          "start": 36.12,
+          "end": 36.16,
+          "confidence": 0.843
+        },
+        {
+          "text": "them,",
+          "start": 36.16,
+          "end": 36.2,
+          "confidence": 0.981
+        },
+        {
+          "text": "got",
+          "start": 36.2,
+          "end": 36.24,
+          "confidence": 0.894
+        },
+        {
+          "text": "them,",
+          "start": 36.24,
+          "end": 36.28,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 36.28,
+          "end": 36.32,
+          "confidence": 0.918
+        },
+        {
+          "text": "them,",
+          "start": 36.32,
+          "end": 36.36,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 36.36,
+          "end": 36.4,
+          "confidence": 0.936
+        },
+        {
+          "text": "them,",
+          "start": 36.4,
+          "end": 36.44,
+          "confidence": 0.988
+        },
+        {
+          "text": "got",
+          "start": 36.44,
+          "end": 36.48,
+          "confidence": 0.941
+        },
+        {
+          "text": "them,",
+          "start": 36.48,
+          "end": 36.52,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 36.52,
+          "end": 36.56,
+          "confidence": 0.943
+        },
+        {
+          "text": "them,",
+          "start": 36.56,
+          "end": 36.6,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 36.6,
+          "end": 36.64,
+          "confidence": 0.946
+        },
+        {
+          "text": "them,",
+          "start": 36.64,
+          "end": 36.68,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 36.68,
+          "end": 36.72,
+          "confidence": 0.944
+        },
+        {
+          "text": "them,",
+          "start": 36.72,
+          "end": 36.76,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 36.76,
+          "end": 36.8,
+          "confidence": 0.944
+        },
+        {
+          "text": "them,",
+          "start": 36.8,
+          "end": 36.84,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 36.84,
+          "end": 36.88,
+          "confidence": 0.946
+        },
+        {
+          "text": "them,",
+          "start": 36.88,
+          "end": 36.92,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 36.92,
+          "end": 36.96,
+          "confidence": 0.948
+        },
+        {
+          "text": "them,",
+          "start": 36.96,
+          "end": 37.0,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 37.0,
+          "end": 37.04,
+          "confidence": 0.953
+        },
+        {
+          "text": "them,",
+          "start": 37.04,
+          "end": 37.08,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 37.08,
+          "end": 37.12,
+          "confidence": 0.954
+        },
+        {
+          "text": "them,",
+          "start": 37.12,
+          "end": 37.16,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 37.16,
+          "end": 37.2,
+          "confidence": 0.956
+        },
+        {
+          "text": "them,",
+          "start": 37.2,
+          "end": 37.24,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 37.24,
+          "end": 37.28,
+          "confidence": 0.957
+        },
+        {
+          "text": "them,",
+          "start": 37.28,
+          "end": 37.32,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 37.32,
+          "end": 37.36,
+          "confidence": 0.958
+        },
+        {
+          "text": "them,",
+          "start": 37.36,
+          "end": 37.4,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 37.4,
+          "end": 37.44,
+          "confidence": 0.96
+        },
+        {
+          "text": "them,",
+          "start": 37.44,
+          "end": 37.48,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 37.48,
+          "end": 37.52,
+          "confidence": 0.961
+        },
+        {
+          "text": "them,",
+          "start": 37.52,
+          "end": 37.56,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 37.56,
+          "end": 37.6,
+          "confidence": 0.961
+        },
+        {
+          "text": "them,",
+          "start": 37.6,
+          "end": 37.64,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 37.64,
+          "end": 37.68,
+          "confidence": 0.962
+        },
+        {
+          "text": "them,",
+          "start": 37.68,
+          "end": 37.72,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 37.72,
+          "end": 37.76,
+          "confidence": 0.965
+        },
+        {
+          "text": "them,",
+          "start": 37.76,
+          "end": 37.8,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 37.8,
+          "end": 37.84,
+          "confidence": 0.965
+        },
+        {
+          "text": "them,",
+          "start": 37.84,
+          "end": 37.88,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 37.88,
+          "end": 37.92,
+          "confidence": 0.965
+        },
+        {
+          "text": "them,",
+          "start": 37.92,
+          "end": 37.96,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 37.96,
+          "end": 38.0,
+          "confidence": 0.968
+        },
+        {
+          "text": "them,",
+          "start": 38.0,
+          "end": 38.04,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 38.04,
+          "end": 38.08,
+          "confidence": 0.968
+        },
+        {
+          "text": "them,",
+          "start": 38.08,
+          "end": 38.12,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 38.12,
+          "end": 38.16,
+          "confidence": 0.969
+        },
+        {
+          "text": "them,",
+          "start": 38.16,
+          "end": 38.2,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 38.2,
+          "end": 38.24,
+          "confidence": 0.971
+        },
+        {
+          "text": "them,",
+          "start": 38.24,
+          "end": 38.28,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 38.28,
+          "end": 38.32,
+          "confidence": 0.973
+        },
+        {
+          "text": "them,",
+          "start": 38.32,
+          "end": 38.36,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 38.36,
+          "end": 38.4,
+          "confidence": 0.972
+        },
+        {
+          "text": "them,",
+          "start": 38.4,
+          "end": 38.44,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 38.44,
+          "end": 38.48,
+          "confidence": 0.973
+        },
+        {
+          "text": "them,",
+          "start": 38.48,
+          "end": 38.52,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 38.52,
+          "end": 38.56,
+          "confidence": 0.976
+        },
+        {
+          "text": "them,",
+          "start": 38.56,
+          "end": 38.6,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 38.6,
+          "end": 38.64,
+          "confidence": 0.977
+        },
+        {
+          "text": "them,",
+          "start": 38.64,
+          "end": 38.68,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 38.68,
+          "end": 38.72,
+          "confidence": 0.979
+        },
+        {
+          "text": "them,",
+          "start": 38.72,
+          "end": 38.76,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 38.76,
+          "end": 38.8,
+          "confidence": 0.98
+        },
+        {
+          "text": "them,",
+          "start": 38.8,
+          "end": 38.84,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 38.84,
+          "end": 38.88,
+          "confidence": 0.983
+        },
+        {
+          "text": "them,",
+          "start": 38.88,
+          "end": 38.92,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 38.92,
+          "end": 38.96,
+          "confidence": 0.984
+        },
+        {
+          "text": "them,",
+          "start": 38.96,
+          "end": 39.0,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.0,
+          "end": 39.04,
+          "confidence": 0.985
+        },
+        {
+          "text": "them,",
+          "start": 39.04,
+          "end": 39.08,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.08,
+          "end": 39.12,
+          "confidence": 0.986
+        },
+        {
+          "text": "them,",
+          "start": 39.12,
+          "end": 39.16,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.16,
+          "end": 39.2,
+          "confidence": 0.987
+        },
+        {
+          "text": "them,",
+          "start": 39.2,
+          "end": 39.24,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.24,
+          "end": 39.28,
+          "confidence": 0.986
+        },
+        {
+          "text": "them,",
+          "start": 39.28,
+          "end": 39.32,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.32,
+          "end": 39.36,
+          "confidence": 0.986
+        },
+        {
+          "text": "them,",
+          "start": 39.36,
+          "end": 39.4,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.4,
+          "end": 39.44,
+          "confidence": 0.988
+        },
+        {
+          "text": "them,",
+          "start": 39.44,
+          "end": 39.48,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.48,
+          "end": 39.52,
+          "confidence": 0.988
+        },
+        {
+          "text": "them,",
+          "start": 39.52,
+          "end": 39.56,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.56,
+          "end": 39.6,
+          "confidence": 0.988
+        },
+        {
+          "text": "them,",
+          "start": 39.6,
+          "end": 39.64,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.64,
+          "end": 39.68,
+          "confidence": 0.989
+        },
+        {
+          "text": "them,",
+          "start": 39.68,
+          "end": 39.72,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.72,
+          "end": 39.76,
+          "confidence": 0.989
+        },
+        {
+          "text": "them,",
+          "start": 39.76,
+          "end": 39.8,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.8,
+          "end": 39.84,
+          "confidence": 0.99
+        },
+        {
+          "text": "them,",
+          "start": 39.84,
+          "end": 39.88,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.88,
+          "end": 39.92,
+          "confidence": 0.99
+        },
+        {
+          "text": "them,",
+          "start": 39.92,
+          "end": 39.96,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.96,
+          "end": 40.0,
+          "confidence": 0.991
+        },
+        {
+          "text": "them,",
+          "start": 40.0,
+          "end": 40.04,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 40.04,
+          "end": 40.08,
+          "confidence": 0.991
+        },
+        {
+          "text": "them,",
+          "start": 40.08,
+          "end": 40.12,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 40.12,
+          "end": 40.16,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 40.16,
+          "end": 40.2,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 40.2,
+          "end": 40.24,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 40.24,
+          "end": 40.28,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 40.28,
+          "end": 40.32,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 40.32,
+          "end": 40.36,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 40.36,
+          "end": 40.4,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 40.4,
+          "end": 40.44,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 40.44,
+          "end": 40.48,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 40.48,
+          "end": 40.52,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 40.52,
+          "end": 40.56,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 40.56,
+          "end": 40.6,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 40.6,
+          "end": 40.64,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 40.64,
+          "end": 40.68,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 40.68,
+          "end": 40.72,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 40.72,
+          "end": 40.76,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 40.76,
+          "end": 40.8,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 40.8,
+          "end": 40.84,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 40.84,
+          "end": 40.88,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 40.88,
+          "end": 40.92,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 40.92,
+          "end": 40.96,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 40.96,
+          "end": 41.0,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 41.0,
+          "end": 41.04,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 41.04,
+          "end": 41.08,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 41.08,
+          "end": 41.12,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 41.12,
+          "end": 41.16,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 41.16,
+          "end": 41.2,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 41.2,
+          "end": 42.94,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 42.94,
+          "end": 46.82,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 46.82,
+          "end": 47.8,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 47.8,
+          "end": 48.58,
+          "confidence": 0.995
+        },
+        {
+          "text": "them",
+          "start": 48.58,
+          "end": 55.0,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 5500,
+      "start": 72.06,
+      "end": 85.0,
+      "text": " got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them",
+      "tokens": [
+        50364,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.053046889369263245,
+      "compression_ratio": 29.52,
+      "no_speech_prob": 0.24410122632980347,
+      "confidence": 0.948,
+      "words": [
+        {
+          "text": "got",
+          "start": 72.06,
+          "end": 72.1,
+          "confidence": 0.214
+        },
+        {
+          "text": "them,",
+          "start": 72.1,
+          "end": 72.14,
+          "confidence": 0.95
+        },
+        {
+          "text": "got",
+          "start": 72.14,
+          "end": 72.18,
+          "confidence": 0.954
+        },
+        {
+          "text": "them,",
+          "start": 72.18,
+          "end": 72.22,
+          "confidence": 0.997
+        },
+        {
+          "text": "got",
+          "start": 72.22,
+          "end": 72.26,
+          "confidence": 0.963
+        },
+        {
+          "text": "them,",
+          "start": 72.26,
+          "end": 72.3,
+          "confidence": 0.997
+        },
+        {
+          "text": "got",
+          "start": 72.3,
+          "end": 72.34,
+          "confidence": 0.957
+        },
+        {
+          "text": "them,",
+          "start": 72.34,
+          "end": 72.38,
+          "confidence": 0.997
+        },
+        {
+          "text": "got",
+          "start": 72.38,
+          "end": 72.42,
+          "confidence": 0.938
+        },
+        {
+          "text": "them,",
+          "start": 72.42,
+          "end": 72.46,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 72.46,
+          "end": 72.5,
+          "confidence": 0.912
+        },
+        {
+          "text": "them,",
+          "start": 72.5,
+          "end": 72.54,
+          "confidence": 0.988
+        },
+        {
+          "text": "got",
+          "start": 72.54,
+          "end": 72.58,
+          "confidence": 0.873
+        },
+        {
+          "text": "them,",
+          "start": 72.58,
+          "end": 72.62,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 72.62,
+          "end": 72.66,
+          "confidence": 0.863
+        },
+        {
+          "text": "them,",
+          "start": 72.66,
+          "end": 72.7,
+          "confidence": 0.984
+        },
+        {
+          "text": "got",
+          "start": 72.7,
+          "end": 72.74,
+          "confidence": 0.889
+        },
+        {
+          "text": "them,",
+          "start": 72.74,
+          "end": 72.78,
+          "confidence": 0.984
+        },
+        {
+          "text": "got",
+          "start": 72.78,
+          "end": 72.82,
+          "confidence": 0.852
+        },
+        {
+          "text": "them,",
+          "start": 72.82,
+          "end": 72.86,
+          "confidence": 0.925
+        },
+        {
+          "text": "got",
+          "start": 72.86,
+          "end": 72.9,
+          "confidence": 0.56
+        },
+        {
+          "text": "them,",
+          "start": 72.9,
+          "end": 72.94,
+          "confidence": 0.958
+        },
+        {
+          "text": "got",
+          "start": 72.94,
+          "end": 72.98,
+          "confidence": 0.81
+        },
+        {
+          "text": "them,",
+          "start": 72.98,
+          "end": 73.02,
+          "confidence": 0.976
+        },
+        {
+          "text": "got",
+          "start": 73.02,
+          "end": 73.06,
+          "confidence": 0.843
+        },
+        {
+          "text": "them,",
+          "start": 73.06,
+          "end": 73.1,
+          "confidence": 0.977
+        },
+        {
+          "text": "got",
+          "start": 73.1,
+          "end": 73.14,
+          "confidence": 0.835
+        },
+        {
+          "text": "them,",
+          "start": 73.14,
+          "end": 73.18,
+          "confidence": 0.977
+        },
+        {
+          "text": "got",
+          "start": 73.18,
+          "end": 73.22,
+          "confidence": 0.836
+        },
+        {
+          "text": "them,",
+          "start": 73.22,
+          "end": 73.26,
+          "confidence": 0.979
+        },
+        {
+          "text": "got",
+          "start": 73.26,
+          "end": 73.3,
+          "confidence": 0.853
+        },
+        {
+          "text": "them,",
+          "start": 73.3,
+          "end": 73.34,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 73.34,
+          "end": 73.38,
+          "confidence": 0.874
+        },
+        {
+          "text": "them,",
+          "start": 73.38,
+          "end": 73.42,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 73.42,
+          "end": 73.46,
+          "confidence": 0.892
+        },
+        {
+          "text": "them,",
+          "start": 73.46,
+          "end": 73.5,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 73.5,
+          "end": 73.54,
+          "confidence": 0.885
+        },
+        {
+          "text": "them,",
+          "start": 73.54,
+          "end": 73.58,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 73.58,
+          "end": 73.62,
+          "confidence": 0.877
+        },
+        {
+          "text": "them,",
+          "start": 73.62,
+          "end": 73.66,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 73.66,
+          "end": 73.7,
+          "confidence": 0.873
+        },
+        {
+          "text": "them,",
+          "start": 73.7,
+          "end": 73.74,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 73.74,
+          "end": 73.78,
+          "confidence": 0.871
+        },
+        {
+          "text": "them,",
+          "start": 73.78,
+          "end": 73.82,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 73.82,
+          "end": 73.86,
+          "confidence": 0.88
+        },
+        {
+          "text": "them,",
+          "start": 73.86,
+          "end": 73.9,
+          "confidence": 0.988
+        },
+        {
+          "text": "got",
+          "start": 73.9,
+          "end": 73.94,
+          "confidence": 0.883
+        },
+        {
+          "text": "them,",
+          "start": 73.94,
+          "end": 73.98,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 73.98,
+          "end": 74.02,
+          "confidence": 0.889
+        },
+        {
+          "text": "them,",
+          "start": 74.02,
+          "end": 74.06,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 74.06,
+          "end": 74.1,
+          "confidence": 0.895
+        },
+        {
+          "text": "them,",
+          "start": 74.1,
+          "end": 74.14,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 74.14,
+          "end": 74.18,
+          "confidence": 0.902
+        },
+        {
+          "text": "them,",
+          "start": 74.18,
+          "end": 74.22,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 74.22,
+          "end": 74.26,
+          "confidence": 0.905
+        },
+        {
+          "text": "them,",
+          "start": 74.26,
+          "end": 74.3,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 74.3,
+          "end": 74.34,
+          "confidence": 0.911
+        },
+        {
+          "text": "them,",
+          "start": 74.34,
+          "end": 74.38,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 74.38,
+          "end": 74.42,
+          "confidence": 0.916
+        },
+        {
+          "text": "them,",
+          "start": 74.42,
+          "end": 74.46,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 74.46,
+          "end": 74.5,
+          "confidence": 0.919
+        },
+        {
+          "text": "them,",
+          "start": 74.5,
+          "end": 74.54,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 74.54,
+          "end": 74.58,
+          "confidence": 0.922
+        },
+        {
+          "text": "them,",
+          "start": 74.58,
+          "end": 74.62,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 74.62,
+          "end": 74.66,
+          "confidence": 0.93
+        },
+        {
+          "text": "them,",
+          "start": 74.66,
+          "end": 74.7,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 74.7,
+          "end": 74.74,
+          "confidence": 0.932
+        },
+        {
+          "text": "them,",
+          "start": 74.74,
+          "end": 74.78,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 74.78,
+          "end": 74.82,
+          "confidence": 0.937
+        },
+        {
+          "text": "them,",
+          "start": 74.82,
+          "end": 74.86,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 74.86,
+          "end": 74.9,
+          "confidence": 0.943
+        },
+        {
+          "text": "them,",
+          "start": 74.9,
+          "end": 74.94,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 74.94,
+          "end": 74.98,
+          "confidence": 0.944
+        },
+        {
+          "text": "them,",
+          "start": 74.98,
+          "end": 75.02,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 75.02,
+          "end": 75.06,
+          "confidence": 0.95
+        },
+        {
+          "text": "them,",
+          "start": 75.06,
+          "end": 75.1,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 75.1,
+          "end": 75.14,
+          "confidence": 0.953
+        },
+        {
+          "text": "them,",
+          "start": 75.14,
+          "end": 75.18,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 75.18,
+          "end": 75.22,
+          "confidence": 0.955
+        },
+        {
+          "text": "them,",
+          "start": 75.22,
+          "end": 75.26,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 75.26,
+          "end": 75.3,
+          "confidence": 0.956
+        },
+        {
+          "text": "them,",
+          "start": 75.3,
+          "end": 75.34,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 75.34,
+          "end": 75.38,
+          "confidence": 0.96
+        },
+        {
+          "text": "them,",
+          "start": 75.38,
+          "end": 75.42,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 75.42,
+          "end": 75.46,
+          "confidence": 0.961
+        },
+        {
+          "text": "them,",
+          "start": 75.46,
+          "end": 75.5,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 75.5,
+          "end": 75.54,
+          "confidence": 0.961
+        },
+        {
+          "text": "them,",
+          "start": 75.54,
+          "end": 75.58,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 75.58,
+          "end": 75.62,
+          "confidence": 0.963
+        },
+        {
+          "text": "them,",
+          "start": 75.62,
+          "end": 75.66,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 75.66,
+          "end": 75.7,
+          "confidence": 0.965
+        },
+        {
+          "text": "them,",
+          "start": 75.7,
+          "end": 75.74,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 75.74,
+          "end": 75.78,
+          "confidence": 0.967
+        },
+        {
+          "text": "them,",
+          "start": 75.78,
+          "end": 75.82,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 75.82,
+          "end": 75.86,
+          "confidence": 0.967
+        },
+        {
+          "text": "them,",
+          "start": 75.86,
+          "end": 75.9,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 75.9,
+          "end": 75.94,
+          "confidence": 0.969
+        },
+        {
+          "text": "them,",
+          "start": 75.94,
+          "end": 75.98,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 75.98,
+          "end": 76.02,
+          "confidence": 0.97
+        },
+        {
+          "text": "them,",
+          "start": 76.02,
+          "end": 76.06,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 76.06,
+          "end": 76.1,
+          "confidence": 0.97
+        },
+        {
+          "text": "them,",
+          "start": 76.1,
+          "end": 76.14,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 76.14,
+          "end": 76.18,
+          "confidence": 0.972
+        },
+        {
+          "text": "them,",
+          "start": 76.18,
+          "end": 76.22,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 76.22,
+          "end": 76.26,
+          "confidence": 0.973
+        },
+        {
+          "text": "them,",
+          "start": 76.26,
+          "end": 76.3,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 76.3,
+          "end": 76.34,
+          "confidence": 0.973
+        },
+        {
+          "text": "them,",
+          "start": 76.34,
+          "end": 76.38,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 76.38,
+          "end": 76.42,
+          "confidence": 0.973
+        },
+        {
+          "text": "them,",
+          "start": 76.42,
+          "end": 76.46,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 76.46,
+          "end": 76.5,
+          "confidence": 0.974
+        },
+        {
+          "text": "them,",
+          "start": 76.5,
+          "end": 76.54,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 76.54,
+          "end": 76.58,
+          "confidence": 0.974
+        },
+        {
+          "text": "them,",
+          "start": 76.58,
+          "end": 76.62,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 76.62,
+          "end": 76.66,
+          "confidence": 0.974
+        },
+        {
+          "text": "them,",
+          "start": 76.66,
+          "end": 76.7,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 76.7,
+          "end": 76.74,
+          "confidence": 0.976
+        },
+        {
+          "text": "them,",
+          "start": 76.74,
+          "end": 76.78,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 76.78,
+          "end": 76.82,
+          "confidence": 0.975
+        },
+        {
+          "text": "them,",
+          "start": 76.82,
+          "end": 76.86,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 76.86,
+          "end": 76.9,
+          "confidence": 0.975
+        },
+        {
+          "text": "them,",
+          "start": 76.9,
+          "end": 76.94,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 76.94,
+          "end": 76.98,
+          "confidence": 0.976
+        },
+        {
+          "text": "them,",
+          "start": 76.98,
+          "end": 77.02,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 77.02,
+          "end": 77.06,
+          "confidence": 0.977
+        },
+        {
+          "text": "them,",
+          "start": 77.06,
+          "end": 77.1,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 77.1,
+          "end": 77.14,
+          "confidence": 0.977
+        },
+        {
+          "text": "them,",
+          "start": 77.14,
+          "end": 77.18,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 77.18,
+          "end": 77.22,
+          "confidence": 0.977
+        },
+        {
+          "text": "them,",
+          "start": 77.22,
+          "end": 77.26,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 77.26,
+          "end": 77.3,
+          "confidence": 0.978
+        },
+        {
+          "text": "them,",
+          "start": 77.3,
+          "end": 77.34,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 77.34,
+          "end": 77.38,
+          "confidence": 0.978
+        },
+        {
+          "text": "them,",
+          "start": 77.38,
+          "end": 77.42,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 77.42,
+          "end": 77.46,
+          "confidence": 0.978
+        },
+        {
+          "text": "them,",
+          "start": 77.46,
+          "end": 77.5,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 77.5,
+          "end": 77.54,
+          "confidence": 0.98
+        },
+        {
+          "text": "them,",
+          "start": 77.54,
+          "end": 77.58,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 77.58,
+          "end": 77.62,
+          "confidence": 0.98
+        },
+        {
+          "text": "them,",
+          "start": 77.62,
+          "end": 77.66,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 77.66,
+          "end": 77.7,
+          "confidence": 0.98
+        },
+        {
+          "text": "them,",
+          "start": 77.7,
+          "end": 77.74,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 77.74,
+          "end": 77.78,
+          "confidence": 0.981
+        },
+        {
+          "text": "them,",
+          "start": 77.78,
+          "end": 77.82,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 77.82,
+          "end": 77.86,
+          "confidence": 0.981
+        },
+        {
+          "text": "them,",
+          "start": 77.86,
+          "end": 79.56,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 79.56,
+          "end": 79.6,
+          "confidence": 0.981
+        },
+        {
+          "text": "them",
+          "start": 79.6,
+          "end": 85.0,
+          "confidence": 0.994
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 8500,
+      "start": 85.02,
+      "end": 115.0,
+      "text": " got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them",
+      "tokens": [
+        50364,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.04965524716227578,
+      "compression_ratio": 29.52,
+      "no_speech_prob": 0.6971923112869263,
+      "confidence": 0.948,
+      "words": [
+        {
+          "text": "got",
+          "start": 85.02,
+          "end": 85.46,
+          "confidence": 0.438
+        },
+        {
+          "text": "them,",
+          "start": 85.46,
+          "end": 86.26,
+          "confidence": 0.943
+        },
+        {
+          "text": "got",
+          "start": 86.26,
+          "end": 86.78,
+          "confidence": 0.963
+        },
+        {
+          "text": "them,",
+          "start": 86.78,
+          "end": 87.18,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 87.18,
+          "end": 87.8,
+          "confidence": 0.963
+        },
+        {
+          "text": "them,",
+          "start": 87.8,
+          "end": 87.84,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 87.84,
+          "end": 88.6,
+          "confidence": 0.951
+        },
+        {
+          "text": "them,",
+          "start": 88.6,
+          "end": 88.64,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 88.64,
+          "end": 88.9,
+          "confidence": 0.934
+        },
+        {
+          "text": "them,",
+          "start": 88.9,
+          "end": 88.94,
+          "confidence": 0.988
+        },
+        {
+          "text": "got",
+          "start": 88.94,
+          "end": 88.98,
+          "confidence": 0.915
+        },
+        {
+          "text": "them,",
+          "start": 88.98,
+          "end": 89.02,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 89.02,
+          "end": 89.06,
+          "confidence": 0.9
+        },
+        {
+          "text": "them,",
+          "start": 89.06,
+          "end": 89.1,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 89.1,
+          "end": 89.14,
+          "confidence": 0.899
+        },
+        {
+          "text": "them,",
+          "start": 89.14,
+          "end": 89.18,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 89.18,
+          "end": 89.22,
+          "confidence": 0.907
+        },
+        {
+          "text": "them,",
+          "start": 89.22,
+          "end": 89.26,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 89.26,
+          "end": 89.3,
+          "confidence": 0.905
+        },
+        {
+          "text": "them,",
+          "start": 89.3,
+          "end": 89.34,
+          "confidence": 0.971
+        },
+        {
+          "text": "got",
+          "start": 89.34,
+          "end": 89.38,
+          "confidence": 0.866
+        },
+        {
+          "text": "them,",
+          "start": 89.38,
+          "end": 89.42,
+          "confidence": 0.959
+        },
+        {
+          "text": "got",
+          "start": 89.42,
+          "end": 89.46,
+          "confidence": 0.845
+        },
+        {
+          "text": "them,",
+          "start": 89.46,
+          "end": 89.5,
+          "confidence": 0.96
+        },
+        {
+          "text": "got",
+          "start": 89.5,
+          "end": 89.54,
+          "confidence": 0.861
+        },
+        {
+          "text": "them,",
+          "start": 89.54,
+          "end": 89.58,
+          "confidence": 0.963
+        },
+        {
+          "text": "got",
+          "start": 89.58,
+          "end": 89.62,
+          "confidence": 0.88
+        },
+        {
+          "text": "them,",
+          "start": 89.62,
+          "end": 89.66,
+          "confidence": 0.965
+        },
+        {
+          "text": "got",
+          "start": 89.66,
+          "end": 89.7,
+          "confidence": 0.888
+        },
+        {
+          "text": "them,",
+          "start": 89.7,
+          "end": 89.74,
+          "confidence": 0.966
+        },
+        {
+          "text": "got",
+          "start": 89.74,
+          "end": 89.78,
+          "confidence": 0.887
+        },
+        {
+          "text": "them,",
+          "start": 89.78,
+          "end": 89.82,
+          "confidence": 0.966
+        },
+        {
+          "text": "got",
+          "start": 89.82,
+          "end": 89.86,
+          "confidence": 0.875
+        },
+        {
+          "text": "them,",
+          "start": 89.86,
+          "end": 89.9,
+          "confidence": 0.968
+        },
+        {
+          "text": "got",
+          "start": 89.9,
+          "end": 89.94,
+          "confidence": 0.871
+        },
+        {
+          "text": "them,",
+          "start": 89.94,
+          "end": 89.98,
+          "confidence": 0.968
+        },
+        {
+          "text": "got",
+          "start": 89.98,
+          "end": 90.02,
+          "confidence": 0.868
+        },
+        {
+          "text": "them,",
+          "start": 90.02,
+          "end": 90.06,
+          "confidence": 0.966
+        },
+        {
+          "text": "got",
+          "start": 90.06,
+          "end": 90.1,
+          "confidence": 0.865
+        },
+        {
+          "text": "them,",
+          "start": 90.1,
+          "end": 90.14,
+          "confidence": 0.964
+        },
+        {
+          "text": "got",
+          "start": 90.14,
+          "end": 90.18,
+          "confidence": 0.865
+        },
+        {
+          "text": "them,",
+          "start": 90.18,
+          "end": 90.22,
+          "confidence": 0.965
+        },
+        {
+          "text": "got",
+          "start": 90.22,
+          "end": 90.26,
+          "confidence": 0.86
+        },
+        {
+          "text": "them,",
+          "start": 90.26,
+          "end": 90.3,
+          "confidence": 0.965
+        },
+        {
+          "text": "got",
+          "start": 90.3,
+          "end": 90.34,
+          "confidence": 0.867
+        },
+        {
+          "text": "them,",
+          "start": 90.34,
+          "end": 90.38,
+          "confidence": 0.966
+        },
+        {
+          "text": "got",
+          "start": 90.38,
+          "end": 90.42,
+          "confidence": 0.866
+        },
+        {
+          "text": "them,",
+          "start": 90.42,
+          "end": 90.46,
+          "confidence": 0.967
+        },
+        {
+          "text": "got",
+          "start": 90.46,
+          "end": 90.5,
+          "confidence": 0.866
+        },
+        {
+          "text": "them,",
+          "start": 90.5,
+          "end": 90.54,
+          "confidence": 0.968
+        },
+        {
+          "text": "got",
+          "start": 90.54,
+          "end": 90.58,
+          "confidence": 0.87
+        },
+        {
+          "text": "them,",
+          "start": 90.58,
+          "end": 90.62,
+          "confidence": 0.969
+        },
+        {
+          "text": "got",
+          "start": 90.62,
+          "end": 90.66,
+          "confidence": 0.874
+        },
+        {
+          "text": "them,",
+          "start": 90.66,
+          "end": 90.7,
+          "confidence": 0.971
+        },
+        {
+          "text": "got",
+          "start": 90.7,
+          "end": 90.74,
+          "confidence": 0.874
+        },
+        {
+          "text": "them,",
+          "start": 90.74,
+          "end": 90.78,
+          "confidence": 0.971
+        },
+        {
+          "text": "got",
+          "start": 90.78,
+          "end": 90.82,
+          "confidence": 0.88
+        },
+        {
+          "text": "them,",
+          "start": 90.82,
+          "end": 90.86,
+          "confidence": 0.971
+        },
+        {
+          "text": "got",
+          "start": 90.86,
+          "end": 90.9,
+          "confidence": 0.884
+        },
+        {
+          "text": "them,",
+          "start": 90.9,
+          "end": 90.94,
+          "confidence": 0.973
+        },
+        {
+          "text": "got",
+          "start": 90.94,
+          "end": 90.98,
+          "confidence": 0.883
+        },
+        {
+          "text": "them,",
+          "start": 90.98,
+          "end": 91.02,
+          "confidence": 0.973
+        },
+        {
+          "text": "got",
+          "start": 91.02,
+          "end": 91.06,
+          "confidence": 0.884
+        },
+        {
+          "text": "them,",
+          "start": 91.06,
+          "end": 91.1,
+          "confidence": 0.973
+        },
+        {
+          "text": "got",
+          "start": 91.1,
+          "end": 91.14,
+          "confidence": 0.893
+        },
+        {
+          "text": "them,",
+          "start": 91.14,
+          "end": 91.18,
+          "confidence": 0.975
+        },
+        {
+          "text": "got",
+          "start": 91.18,
+          "end": 91.22,
+          "confidence": 0.894
+        },
+        {
+          "text": "them,",
+          "start": 91.22,
+          "end": 91.26,
+          "confidence": 0.975
+        },
+        {
+          "text": "got",
+          "start": 91.26,
+          "end": 91.3,
+          "confidence": 0.9
+        },
+        {
+          "text": "them,",
+          "start": 91.3,
+          "end": 91.34,
+          "confidence": 0.976
+        },
+        {
+          "text": "got",
+          "start": 91.34,
+          "end": 91.38,
+          "confidence": 0.906
+        },
+        {
+          "text": "them,",
+          "start": 91.38,
+          "end": 91.42,
+          "confidence": 0.977
+        },
+        {
+          "text": "got",
+          "start": 91.42,
+          "end": 91.46,
+          "confidence": 0.905
+        },
+        {
+          "text": "them,",
+          "start": 91.46,
+          "end": 91.5,
+          "confidence": 0.978
+        },
+        {
+          "text": "got",
+          "start": 91.5,
+          "end": 91.54,
+          "confidence": 0.915
+        },
+        {
+          "text": "them,",
+          "start": 91.54,
+          "end": 91.58,
+          "confidence": 0.979
+        },
+        {
+          "text": "got",
+          "start": 91.58,
+          "end": 91.62,
+          "confidence": 0.92
+        },
+        {
+          "text": "them,",
+          "start": 91.62,
+          "end": 91.66,
+          "confidence": 0.98
+        },
+        {
+          "text": "got",
+          "start": 91.66,
+          "end": 91.7,
+          "confidence": 0.922
+        },
+        {
+          "text": "them,",
+          "start": 91.7,
+          "end": 91.74,
+          "confidence": 0.981
+        },
+        {
+          "text": "got",
+          "start": 91.74,
+          "end": 91.78,
+          "confidence": 0.925
+        },
+        {
+          "text": "them,",
+          "start": 91.78,
+          "end": 91.82,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 91.82,
+          "end": 91.86,
+          "confidence": 0.932
+        },
+        {
+          "text": "them,",
+          "start": 91.86,
+          "end": 91.9,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 91.9,
+          "end": 91.94,
+          "confidence": 0.936
+        },
+        {
+          "text": "them,",
+          "start": 91.94,
+          "end": 91.98,
+          "confidence": 0.984
+        },
+        {
+          "text": "got",
+          "start": 91.98,
+          "end": 92.02,
+          "confidence": 0.935
+        },
+        {
+          "text": "them,",
+          "start": 92.02,
+          "end": 92.06,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 92.06,
+          "end": 92.1,
+          "confidence": 0.941
+        },
+        {
+          "text": "them,",
+          "start": 92.1,
+          "end": 92.14,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 92.14,
+          "end": 92.18,
+          "confidence": 0.946
+        },
+        {
+          "text": "them,",
+          "start": 92.18,
+          "end": 92.22,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 92.22,
+          "end": 92.26,
+          "confidence": 0.95
+        },
+        {
+          "text": "them,",
+          "start": 92.26,
+          "end": 92.3,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 92.3,
+          "end": 92.34,
+          "confidence": 0.951
+        },
+        {
+          "text": "them,",
+          "start": 92.34,
+          "end": 92.38,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 92.38,
+          "end": 92.42,
+          "confidence": 0.954
+        },
+        {
+          "text": "them,",
+          "start": 92.42,
+          "end": 92.46,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 92.46,
+          "end": 92.5,
+          "confidence": 0.959
+        },
+        {
+          "text": "them,",
+          "start": 92.5,
+          "end": 92.54,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 92.54,
+          "end": 92.58,
+          "confidence": 0.959
+        },
+        {
+          "text": "them,",
+          "start": 92.58,
+          "end": 92.62,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 92.62,
+          "end": 92.66,
+          "confidence": 0.963
+        },
+        {
+          "text": "them,",
+          "start": 92.66,
+          "end": 92.7,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 92.7,
+          "end": 92.74,
+          "confidence": 0.966
+        },
+        {
+          "text": "them,",
+          "start": 92.74,
+          "end": 92.78,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 92.78,
+          "end": 92.82,
+          "confidence": 0.967
+        },
+        {
+          "text": "them,",
+          "start": 92.82,
+          "end": 92.86,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 92.86,
+          "end": 92.9,
+          "confidence": 0.97
+        },
+        {
+          "text": "them,",
+          "start": 92.9,
+          "end": 92.94,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 92.94,
+          "end": 92.98,
+          "confidence": 0.971
+        },
+        {
+          "text": "them,",
+          "start": 92.98,
+          "end": 93.02,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 93.02,
+          "end": 93.06,
+          "confidence": 0.97
+        },
+        {
+          "text": "them,",
+          "start": 93.06,
+          "end": 93.1,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 93.1,
+          "end": 93.14,
+          "confidence": 0.973
+        },
+        {
+          "text": "them,",
+          "start": 93.14,
+          "end": 93.18,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 93.18,
+          "end": 93.22,
+          "confidence": 0.974
+        },
+        {
+          "text": "them,",
+          "start": 93.22,
+          "end": 93.26,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 93.26,
+          "end": 93.3,
+          "confidence": 0.974
+        },
+        {
+          "text": "them,",
+          "start": 93.3,
+          "end": 93.34,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 93.34,
+          "end": 93.38,
+          "confidence": 0.976
+        },
+        {
+          "text": "them,",
+          "start": 93.38,
+          "end": 93.42,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 93.42,
+          "end": 93.46,
+          "confidence": 0.978
+        },
+        {
+          "text": "them,",
+          "start": 93.46,
+          "end": 93.5,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 93.5,
+          "end": 93.54,
+          "confidence": 0.979
+        },
+        {
+          "text": "them,",
+          "start": 93.54,
+          "end": 93.58,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 93.58,
+          "end": 93.62,
+          "confidence": 0.98
+        },
+        {
+          "text": "them,",
+          "start": 93.62,
+          "end": 93.66,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 93.66,
+          "end": 93.7,
+          "confidence": 0.981
+        },
+        {
+          "text": "them,",
+          "start": 93.7,
+          "end": 93.74,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 93.74,
+          "end": 93.78,
+          "confidence": 0.98
+        },
+        {
+          "text": "them,",
+          "start": 93.78,
+          "end": 93.82,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 93.82,
+          "end": 93.86,
+          "confidence": 0.982
+        },
+        {
+          "text": "them,",
+          "start": 93.86,
+          "end": 93.9,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 93.9,
+          "end": 93.94,
+          "confidence": 0.982
+        },
+        {
+          "text": "them,",
+          "start": 93.94,
+          "end": 93.98,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 93.98,
+          "end": 94.02,
+          "confidence": 0.984
+        },
+        {
+          "text": "them,",
+          "start": 94.02,
+          "end": 94.06,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 94.06,
+          "end": 94.1,
+          "confidence": 0.984
+        },
+        {
+          "text": "them,",
+          "start": 94.1,
+          "end": 94.14,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 94.14,
+          "end": 94.18,
+          "confidence": 0.985
+        },
+        {
+          "text": "them,",
+          "start": 94.18,
+          "end": 94.22,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 94.22,
+          "end": 94.26,
+          "confidence": 0.986
+        },
+        {
+          "text": "them,",
+          "start": 94.26,
+          "end": 94.3,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 94.3,
+          "end": 94.34,
+          "confidence": 0.986
+        },
+        {
+          "text": "them,",
+          "start": 94.34,
+          "end": 94.38,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 94.38,
+          "end": 94.42,
+          "confidence": 0.987
+        },
+        {
+          "text": "them",
+          "start": 94.42,
+          "end": 115.0,
+          "confidence": 0.996
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/corner_cases.cpu/stucked_lm_apollo11.mp3.words.json b/tests/expected/corner_cases.cpu/stucked_lm_apollo11.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..527def1f7142f05644333ecb9e358b7e067d0468
--- /dev/null
+++ b/tests/expected/corner_cases.cpu/stucked_lm_apollo11.mp3.words.json
@@ -0,0 +1,3814 @@
+{
+  "text": " Apollo 11, Houston we got a recommendation for you on your Soyuz-VA GLEME GVA. Alright, okay, we like to say that they make the one that's on the helmet we're going to have in B1. And you can put the other one on the mic helmet with those GVA blizzard frames. Alright, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.64,
+      "end": 6.94,
+      "text": " Apollo 11, Houston we got a recommendation for you on your Soyuz-VA GLEME GVA.",
+      "tokens": [
+        25187,
+        2975,
+        11,
+        18717,
+        321,
+        658,
+        257,
+        11879,
+        337,
+        291,
+        322,
+        428,
+        24758,
+        3334,
+        12,
+        20914,
+        460,
+        2634,
+        15454,
+        460,
+        20914,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7224321867290296,
+      "compression_ratio": 1.39247311827957,
+      "no_speech_prob": 0.45045843720436096,
+      "confidence": 0.542,
+      "words": [
+        {
+          "text": "Apollo",
+          "start": 0.64,
+          "end": 0.98,
+          "confidence": 0.155
+        },
+        {
+          "text": "11,",
+          "start": 0.98,
+          "end": 1.54,
+          "confidence": 0.977
+        },
+        {
+          "text": "Houston",
+          "start": 1.54,
+          "end": 1.8,
+          "confidence": 0.986
+        },
+        {
+          "text": "we",
+          "start": 1.8,
+          "end": 1.98,
+          "confidence": 0.52
+        },
+        {
+          "text": "got",
+          "start": 1.98,
+          "end": 2.16,
+          "confidence": 0.824
+        },
+        {
+          "text": "a",
+          "start": 2.16,
+          "end": 2.38,
+          "confidence": 0.989
+        },
+        {
+          "text": "recommendation",
+          "start": 2.38,
+          "end": 3.1,
+          "confidence": 0.968
+        },
+        {
+          "text": "for",
+          "start": 3.1,
+          "end": 3.52,
+          "confidence": 0.947
+        },
+        {
+          "text": "you",
+          "start": 3.52,
+          "end": 3.9,
+          "confidence": 0.984
+        },
+        {
+          "text": "on",
+          "start": 3.9,
+          "end": 4.28,
+          "confidence": 0.909
+        },
+        {
+          "text": "your",
+          "start": 4.28,
+          "end": 4.32,
+          "confidence": 0.971
+        },
+        {
+          "text": "Soyuz-VA",
+          "start": 4.32,
+          "end": 5.38,
+          "confidence": 0.26
+        },
+        {
+          "text": "GLEME",
+          "start": 5.38,
+          "end": 6.04,
+          "confidence": 0.478
+        },
+        {
+          "text": "GVA.",
+          "start": 6.04,
+          "end": 6.94,
+          "confidence": 0.436
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 10.82,
+      "end": 19.24,
+      "text": " Alright, okay, we like to say that they make the one that's on the helmet we're going to have in B1.",
+      "tokens": [
+        2798,
+        11,
+        1392,
+        11,
+        321,
+        411,
+        281,
+        584,
+        300,
+        436,
+        652,
+        264,
+        472,
+        300,
+        311,
+        322,
+        264,
+        15922,
+        321,
+        434,
+        516,
+        281,
+        362,
+        294,
+        363,
+        16,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7224321867290296,
+      "compression_ratio": 1.39247311827957,
+      "no_speech_prob": 0.45045843720436096,
+      "confidence": 0.468,
+      "words": [
+        {
+          "text": "Alright,",
+          "start": 10.82,
+          "end": 12.5,
+          "confidence": 0.309
+        },
+        {
+          "text": "okay,",
+          "start": 12.5,
+          "end": 12.94,
+          "confidence": 0.507
+        },
+        {
+          "text": "we",
+          "start": 12.94,
+          "end": 13.12,
+          "confidence": 0.61
+        },
+        {
+          "text": "like",
+          "start": 13.12,
+          "end": 13.48,
+          "confidence": 0.503
+        },
+        {
+          "text": "to",
+          "start": 13.48,
+          "end": 13.68,
+          "confidence": 0.264
+        },
+        {
+          "text": "say",
+          "start": 13.68,
+          "end": 14.98,
+          "confidence": 0.138
+        },
+        {
+          "text": "that",
+          "start": 14.98,
+          "end": 15.56,
+          "confidence": 0.2
+        },
+        {
+          "text": "they",
+          "start": 15.56,
+          "end": 15.6,
+          "confidence": 0.418
+        },
+        {
+          "text": "make",
+          "start": 15.6,
+          "end": 15.76,
+          "confidence": 0.398
+        },
+        {
+          "text": "the",
+          "start": 15.76,
+          "end": 15.92,
+          "confidence": 0.253
+        },
+        {
+          "text": "one",
+          "start": 15.92,
+          "end": 16.1,
+          "confidence": 0.608
+        },
+        {
+          "text": "that's",
+          "start": 16.1,
+          "end": 16.34,
+          "confidence": 0.443
+        },
+        {
+          "text": "on",
+          "start": 16.34,
+          "end": 16.62,
+          "confidence": 0.595
+        },
+        {
+          "text": "the",
+          "start": 16.62,
+          "end": 16.96,
+          "confidence": 0.871
+        },
+        {
+          "text": "helmet",
+          "start": 16.96,
+          "end": 17.36,
+          "confidence": 0.853
+        },
+        {
+          "text": "we're",
+          "start": 17.36,
+          "end": 17.86,
+          "confidence": 0.299
+        },
+        {
+          "text": "going",
+          "start": 17.86,
+          "end": 18.06,
+          "confidence": 0.6
+        },
+        {
+          "text": "to",
+          "start": 18.06,
+          "end": 18.22,
+          "confidence": 0.818
+        },
+        {
+          "text": "have",
+          "start": 18.22,
+          "end": 18.26,
+          "confidence": 0.84
+        },
+        {
+          "text": "in",
+          "start": 18.26,
+          "end": 18.42,
+          "confidence": 0.717
+        },
+        {
+          "text": "B1.",
+          "start": 18.42,
+          "end": 19.24,
+          "confidence": 0.764
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 20.1,
+      "end": 24.76,
+      "text": " And you can put the other one on the mic helmet with those GVA blizzard frames.",
+      "tokens": [
+        400,
+        291,
+        393,
+        829,
+        264,
+        661,
+        472,
+        322,
+        264,
+        3123,
+        15922,
+        365,
+        729,
+        460,
+        20914,
+        888,
+        31062,
+        12083,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7224321867290296,
+      "compression_ratio": 1.39247311827957,
+      "no_speech_prob": 0.45045843720436096,
+      "confidence": 0.485,
+      "words": [
+        {
+          "text": "And",
+          "start": 20.1,
+          "end": 20.24,
+          "confidence": 0.67
+        },
+        {
+          "text": "you",
+          "start": 20.24,
+          "end": 20.38,
+          "confidence": 0.947
+        },
+        {
+          "text": "can",
+          "start": 20.38,
+          "end": 20.54,
+          "confidence": 0.729
+        },
+        {
+          "text": "put",
+          "start": 20.54,
+          "end": 20.72,
+          "confidence": 0.98
+        },
+        {
+          "text": "the",
+          "start": 20.72,
+          "end": 20.88,
+          "confidence": 0.989
+        },
+        {
+          "text": "other",
+          "start": 20.88,
+          "end": 21.08,
+          "confidence": 0.991
+        },
+        {
+          "text": "one",
+          "start": 21.08,
+          "end": 21.26,
+          "confidence": 0.978
+        },
+        {
+          "text": "on",
+          "start": 21.26,
+          "end": 21.68,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 21.68,
+          "end": 21.96,
+          "confidence": 0.52
+        },
+        {
+          "text": "mic",
+          "start": 21.96,
+          "end": 22.58,
+          "confidence": 0.413
+        },
+        {
+          "text": "helmet",
+          "start": 22.58,
+          "end": 22.94,
+          "confidence": 0.882
+        },
+        {
+          "text": "with",
+          "start": 22.94,
+          "end": 23.2,
+          "confidence": 0.425
+        },
+        {
+          "text": "those",
+          "start": 23.2,
+          "end": 23.5,
+          "confidence": 0.465
+        },
+        {
+          "text": "GVA",
+          "start": 23.5,
+          "end": 23.88,
+          "confidence": 0.216
+        },
+        {
+          "text": "blizzard",
+          "start": 23.88,
+          "end": 24.32,
+          "confidence": 0.107
+        },
+        {
+          "text": "frames.",
+          "start": 24.32,
+          "end": 24.76,
+          "confidence": 0.254
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 2500,
+      "start": 25.02,
+      "end": 55.0,
+      "text": " Alright, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them",
+      "tokens": [
+        50364,
+        2798,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1079042222764757,
+      "compression_ratio": 24.096774193548388,
+      "no_speech_prob": 0.00111382023897022,
+      "confidence": 0.936,
+      "words": [
+        {
+          "text": "Alright,",
+          "start": 25.02,
+          "end": 31.98,
+          "confidence": 0.213
+        },
+        {
+          "text": "got",
+          "start": 31.98,
+          "end": 32.02,
+          "confidence": 0.333
+        },
+        {
+          "text": "them,",
+          "start": 32.02,
+          "end": 32.58,
+          "confidence": 0.334
+        },
+        {
+          "text": "got",
+          "start": 32.58,
+          "end": 33.08,
+          "confidence": 0.526
+        },
+        {
+          "text": "them,",
+          "start": 33.08,
+          "end": 33.78,
+          "confidence": 0.942
+        },
+        {
+          "text": "got",
+          "start": 33.78,
+          "end": 33.82,
+          "confidence": 0.539
+        },
+        {
+          "text": "them,",
+          "start": 33.82,
+          "end": 34.18,
+          "confidence": 0.924
+        },
+        {
+          "text": "got",
+          "start": 34.18,
+          "end": 34.22,
+          "confidence": 0.48
+        },
+        {
+          "text": "them,",
+          "start": 34.22,
+          "end": 35.14,
+          "confidence": 0.907
+        },
+        {
+          "text": "got",
+          "start": 35.14,
+          "end": 35.18,
+          "confidence": 0.604
+        },
+        {
+          "text": "them,",
+          "start": 35.18,
+          "end": 35.22,
+          "confidence": 0.922
+        },
+        {
+          "text": "got",
+          "start": 35.22,
+          "end": 35.5,
+          "confidence": 0.661
+        },
+        {
+          "text": "them,",
+          "start": 35.5,
+          "end": 35.9,
+          "confidence": 0.948
+        },
+        {
+          "text": "got",
+          "start": 35.9,
+          "end": 35.94,
+          "confidence": 0.743
+        },
+        {
+          "text": "them,",
+          "start": 35.94,
+          "end": 35.98,
+          "confidence": 0.968
+        },
+        {
+          "text": "got",
+          "start": 35.98,
+          "end": 36.02,
+          "confidence": 0.825
+        },
+        {
+          "text": "them,",
+          "start": 36.02,
+          "end": 36.06,
+          "confidence": 0.975
+        },
+        {
+          "text": "got",
+          "start": 36.06,
+          "end": 36.1,
+          "confidence": 0.839
+        },
+        {
+          "text": "them,",
+          "start": 36.1,
+          "end": 36.14,
+          "confidence": 0.981
+        },
+        {
+          "text": "got",
+          "start": 36.14,
+          "end": 36.18,
+          "confidence": 0.891
+        },
+        {
+          "text": "them,",
+          "start": 36.18,
+          "end": 36.22,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 36.22,
+          "end": 36.26,
+          "confidence": 0.919
+        },
+        {
+          "text": "them,",
+          "start": 36.26,
+          "end": 36.3,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 36.3,
+          "end": 36.34,
+          "confidence": 0.937
+        },
+        {
+          "text": "them,",
+          "start": 36.34,
+          "end": 36.38,
+          "confidence": 0.988
+        },
+        {
+          "text": "got",
+          "start": 36.38,
+          "end": 36.42,
+          "confidence": 0.941
+        },
+        {
+          "text": "them,",
+          "start": 36.42,
+          "end": 36.46,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 36.46,
+          "end": 36.5,
+          "confidence": 0.944
+        },
+        {
+          "text": "them,",
+          "start": 36.5,
+          "end": 36.54,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 36.54,
+          "end": 36.58,
+          "confidence": 0.945
+        },
+        {
+          "text": "them,",
+          "start": 36.58,
+          "end": 36.62,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 36.62,
+          "end": 36.66,
+          "confidence": 0.943
+        },
+        {
+          "text": "them,",
+          "start": 36.66,
+          "end": 36.7,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 36.7,
+          "end": 36.74,
+          "confidence": 0.944
+        },
+        {
+          "text": "them,",
+          "start": 36.74,
+          "end": 36.78,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 36.78,
+          "end": 36.82,
+          "confidence": 0.945
+        },
+        {
+          "text": "them,",
+          "start": 36.82,
+          "end": 36.86,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 36.86,
+          "end": 36.9,
+          "confidence": 0.951
+        },
+        {
+          "text": "them,",
+          "start": 36.9,
+          "end": 36.94,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 36.94,
+          "end": 36.98,
+          "confidence": 0.952
+        },
+        {
+          "text": "them,",
+          "start": 36.98,
+          "end": 37.02,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 37.02,
+          "end": 37.06,
+          "confidence": 0.956
+        },
+        {
+          "text": "them,",
+          "start": 37.06,
+          "end": 37.1,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 37.1,
+          "end": 37.14,
+          "confidence": 0.958
+        },
+        {
+          "text": "them,",
+          "start": 37.14,
+          "end": 37.18,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 37.18,
+          "end": 37.22,
+          "confidence": 0.958
+        },
+        {
+          "text": "them,",
+          "start": 37.22,
+          "end": 37.26,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 37.26,
+          "end": 37.3,
+          "confidence": 0.959
+        },
+        {
+          "text": "them,",
+          "start": 37.3,
+          "end": 37.34,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 37.34,
+          "end": 37.38,
+          "confidence": 0.961
+        },
+        {
+          "text": "them,",
+          "start": 37.38,
+          "end": 37.42,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 37.42,
+          "end": 37.46,
+          "confidence": 0.961
+        },
+        {
+          "text": "them,",
+          "start": 37.46,
+          "end": 37.5,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 37.5,
+          "end": 37.54,
+          "confidence": 0.962
+        },
+        {
+          "text": "them,",
+          "start": 37.54,
+          "end": 37.58,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 37.58,
+          "end": 37.62,
+          "confidence": 0.963
+        },
+        {
+          "text": "them,",
+          "start": 37.62,
+          "end": 37.66,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 37.66,
+          "end": 37.7,
+          "confidence": 0.965
+        },
+        {
+          "text": "them,",
+          "start": 37.7,
+          "end": 37.74,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 37.74,
+          "end": 37.78,
+          "confidence": 0.965
+        },
+        {
+          "text": "them,",
+          "start": 37.78,
+          "end": 37.82,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 37.82,
+          "end": 37.86,
+          "confidence": 0.966
+        },
+        {
+          "text": "them,",
+          "start": 37.86,
+          "end": 37.9,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 37.9,
+          "end": 37.94,
+          "confidence": 0.967
+        },
+        {
+          "text": "them,",
+          "start": 37.94,
+          "end": 37.98,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 37.98,
+          "end": 38.02,
+          "confidence": 0.968
+        },
+        {
+          "text": "them,",
+          "start": 38.02,
+          "end": 38.06,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 38.06,
+          "end": 38.1,
+          "confidence": 0.969
+        },
+        {
+          "text": "them,",
+          "start": 38.1,
+          "end": 38.14,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 38.14,
+          "end": 38.18,
+          "confidence": 0.97
+        },
+        {
+          "text": "them,",
+          "start": 38.18,
+          "end": 38.22,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 38.22,
+          "end": 38.26,
+          "confidence": 0.971
+        },
+        {
+          "text": "them,",
+          "start": 38.26,
+          "end": 38.3,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 38.3,
+          "end": 38.34,
+          "confidence": 0.972
+        },
+        {
+          "text": "them,",
+          "start": 38.34,
+          "end": 38.38,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 38.38,
+          "end": 38.42,
+          "confidence": 0.974
+        },
+        {
+          "text": "them,",
+          "start": 38.42,
+          "end": 38.46,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 38.46,
+          "end": 38.5,
+          "confidence": 0.975
+        },
+        {
+          "text": "them,",
+          "start": 38.5,
+          "end": 38.54,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 38.54,
+          "end": 38.58,
+          "confidence": 0.978
+        },
+        {
+          "text": "them,",
+          "start": 38.58,
+          "end": 38.62,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 38.62,
+          "end": 38.66,
+          "confidence": 0.978
+        },
+        {
+          "text": "them,",
+          "start": 38.66,
+          "end": 38.7,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 38.7,
+          "end": 38.74,
+          "confidence": 0.98
+        },
+        {
+          "text": "them,",
+          "start": 38.74,
+          "end": 38.78,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 38.78,
+          "end": 38.82,
+          "confidence": 0.981
+        },
+        {
+          "text": "them,",
+          "start": 38.82,
+          "end": 38.86,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 38.86,
+          "end": 38.9,
+          "confidence": 0.984
+        },
+        {
+          "text": "them,",
+          "start": 38.9,
+          "end": 38.94,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 38.94,
+          "end": 38.98,
+          "confidence": 0.984
+        },
+        {
+          "text": "them,",
+          "start": 38.98,
+          "end": 39.02,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.02,
+          "end": 39.06,
+          "confidence": 0.986
+        },
+        {
+          "text": "them,",
+          "start": 39.06,
+          "end": 39.1,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.1,
+          "end": 39.14,
+          "confidence": 0.987
+        },
+        {
+          "text": "them,",
+          "start": 39.14,
+          "end": 39.18,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.18,
+          "end": 39.22,
+          "confidence": 0.987
+        },
+        {
+          "text": "them,",
+          "start": 39.22,
+          "end": 39.26,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.26,
+          "end": 39.3,
+          "confidence": 0.985
+        },
+        {
+          "text": "them,",
+          "start": 39.3,
+          "end": 39.34,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.34,
+          "end": 39.38,
+          "confidence": 0.989
+        },
+        {
+          "text": "them,",
+          "start": 39.38,
+          "end": 39.42,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.42,
+          "end": 39.46,
+          "confidence": 0.99
+        },
+        {
+          "text": "them,",
+          "start": 39.46,
+          "end": 39.5,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.5,
+          "end": 39.54,
+          "confidence": 0.99
+        },
+        {
+          "text": "them,",
+          "start": 39.54,
+          "end": 39.58,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.58,
+          "end": 39.62,
+          "confidence": 0.99
+        },
+        {
+          "text": "them,",
+          "start": 39.62,
+          "end": 39.66,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.66,
+          "end": 39.7,
+          "confidence": 0.991
+        },
+        {
+          "text": "them,",
+          "start": 39.7,
+          "end": 39.74,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.74,
+          "end": 39.78,
+          "confidence": 0.991
+        },
+        {
+          "text": "them,",
+          "start": 39.78,
+          "end": 39.82,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.82,
+          "end": 39.86,
+          "confidence": 0.991
+        },
+        {
+          "text": "them,",
+          "start": 39.86,
+          "end": 39.9,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.9,
+          "end": 39.94,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 39.94,
+          "end": 39.98,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.98,
+          "end": 40.02,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 40.02,
+          "end": 40.06,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 40.06,
+          "end": 40.1,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 40.1,
+          "end": 40.14,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 40.14,
+          "end": 40.18,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 40.18,
+          "end": 40.22,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 40.22,
+          "end": 40.26,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 40.26,
+          "end": 40.3,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 40.3,
+          "end": 40.34,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 40.34,
+          "end": 40.38,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 40.38,
+          "end": 40.42,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 40.42,
+          "end": 40.46,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 40.46,
+          "end": 40.5,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 40.5,
+          "end": 40.54,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 40.54,
+          "end": 40.58,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 40.58,
+          "end": 40.62,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 40.62,
+          "end": 40.66,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 40.66,
+          "end": 40.7,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 40.7,
+          "end": 40.74,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 40.74,
+          "end": 40.78,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 40.78,
+          "end": 40.82,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 40.82,
+          "end": 40.86,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 40.86,
+          "end": 40.9,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 40.9,
+          "end": 40.94,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 40.94,
+          "end": 40.98,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 40.98,
+          "end": 41.02,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 41.02,
+          "end": 41.06,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 41.06,
+          "end": 42.94,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 42.94,
+          "end": 46.82,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 46.82,
+          "end": 47.8,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 47.8,
+          "end": 48.58,
+          "confidence": 0.996
+        },
+        {
+          "text": "them,",
+          "start": 48.58,
+          "end": 50.82,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 50.82,
+          "end": 51.64,
+          "confidence": 0.996
+        },
+        {
+          "text": "them",
+          "start": 51.64,
+          "end": 55.0,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 5500,
+      "start": 72.06,
+      "end": 85.0,
+      "text": " got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them",
+      "tokens": [
+        50364,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.053046889369263245,
+      "compression_ratio": 29.52,
+      "no_speech_prob": 0.24410122632980347,
+      "confidence": 0.948,
+      "words": [
+        {
+          "text": "got",
+          "start": 72.06,
+          "end": 72.1,
+          "confidence": 0.214
+        },
+        {
+          "text": "them,",
+          "start": 72.1,
+          "end": 72.14,
+          "confidence": 0.95
+        },
+        {
+          "text": "got",
+          "start": 72.14,
+          "end": 72.18,
+          "confidence": 0.954
+        },
+        {
+          "text": "them,",
+          "start": 72.18,
+          "end": 72.22,
+          "confidence": 0.997
+        },
+        {
+          "text": "got",
+          "start": 72.22,
+          "end": 72.26,
+          "confidence": 0.963
+        },
+        {
+          "text": "them,",
+          "start": 72.26,
+          "end": 72.3,
+          "confidence": 0.997
+        },
+        {
+          "text": "got",
+          "start": 72.3,
+          "end": 72.34,
+          "confidence": 0.957
+        },
+        {
+          "text": "them,",
+          "start": 72.34,
+          "end": 72.38,
+          "confidence": 0.997
+        },
+        {
+          "text": "got",
+          "start": 72.38,
+          "end": 72.42,
+          "confidence": 0.938
+        },
+        {
+          "text": "them,",
+          "start": 72.42,
+          "end": 72.46,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 72.46,
+          "end": 72.5,
+          "confidence": 0.912
+        },
+        {
+          "text": "them,",
+          "start": 72.5,
+          "end": 72.54,
+          "confidence": 0.988
+        },
+        {
+          "text": "got",
+          "start": 72.54,
+          "end": 72.58,
+          "confidence": 0.873
+        },
+        {
+          "text": "them,",
+          "start": 72.58,
+          "end": 72.62,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 72.62,
+          "end": 72.66,
+          "confidence": 0.863
+        },
+        {
+          "text": "them,",
+          "start": 72.66,
+          "end": 72.7,
+          "confidence": 0.984
+        },
+        {
+          "text": "got",
+          "start": 72.7,
+          "end": 72.74,
+          "confidence": 0.889
+        },
+        {
+          "text": "them,",
+          "start": 72.74,
+          "end": 72.78,
+          "confidence": 0.984
+        },
+        {
+          "text": "got",
+          "start": 72.78,
+          "end": 72.82,
+          "confidence": 0.852
+        },
+        {
+          "text": "them,",
+          "start": 72.82,
+          "end": 72.86,
+          "confidence": 0.925
+        },
+        {
+          "text": "got",
+          "start": 72.86,
+          "end": 72.9,
+          "confidence": 0.56
+        },
+        {
+          "text": "them,",
+          "start": 72.9,
+          "end": 72.94,
+          "confidence": 0.958
+        },
+        {
+          "text": "got",
+          "start": 72.94,
+          "end": 72.98,
+          "confidence": 0.81
+        },
+        {
+          "text": "them,",
+          "start": 72.98,
+          "end": 73.02,
+          "confidence": 0.976
+        },
+        {
+          "text": "got",
+          "start": 73.02,
+          "end": 73.06,
+          "confidence": 0.843
+        },
+        {
+          "text": "them,",
+          "start": 73.06,
+          "end": 73.1,
+          "confidence": 0.977
+        },
+        {
+          "text": "got",
+          "start": 73.1,
+          "end": 73.14,
+          "confidence": 0.835
+        },
+        {
+          "text": "them,",
+          "start": 73.14,
+          "end": 73.18,
+          "confidence": 0.977
+        },
+        {
+          "text": "got",
+          "start": 73.18,
+          "end": 73.22,
+          "confidence": 0.836
+        },
+        {
+          "text": "them,",
+          "start": 73.22,
+          "end": 73.26,
+          "confidence": 0.979
+        },
+        {
+          "text": "got",
+          "start": 73.26,
+          "end": 73.3,
+          "confidence": 0.853
+        },
+        {
+          "text": "them,",
+          "start": 73.3,
+          "end": 73.34,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 73.34,
+          "end": 73.38,
+          "confidence": 0.874
+        },
+        {
+          "text": "them,",
+          "start": 73.38,
+          "end": 73.42,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 73.42,
+          "end": 73.46,
+          "confidence": 0.892
+        },
+        {
+          "text": "them,",
+          "start": 73.46,
+          "end": 73.5,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 73.5,
+          "end": 73.54,
+          "confidence": 0.885
+        },
+        {
+          "text": "them,",
+          "start": 73.54,
+          "end": 73.58,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 73.58,
+          "end": 73.62,
+          "confidence": 0.877
+        },
+        {
+          "text": "them,",
+          "start": 73.62,
+          "end": 73.66,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 73.66,
+          "end": 73.7,
+          "confidence": 0.873
+        },
+        {
+          "text": "them,",
+          "start": 73.7,
+          "end": 73.74,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 73.74,
+          "end": 73.78,
+          "confidence": 0.871
+        },
+        {
+          "text": "them,",
+          "start": 73.78,
+          "end": 73.82,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 73.82,
+          "end": 73.86,
+          "confidence": 0.88
+        },
+        {
+          "text": "them,",
+          "start": 73.86,
+          "end": 73.9,
+          "confidence": 0.988
+        },
+        {
+          "text": "got",
+          "start": 73.9,
+          "end": 73.94,
+          "confidence": 0.883
+        },
+        {
+          "text": "them,",
+          "start": 73.94,
+          "end": 73.98,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 73.98,
+          "end": 74.02,
+          "confidence": 0.889
+        },
+        {
+          "text": "them,",
+          "start": 74.02,
+          "end": 74.06,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 74.06,
+          "end": 74.1,
+          "confidence": 0.895
+        },
+        {
+          "text": "them,",
+          "start": 74.1,
+          "end": 74.14,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 74.14,
+          "end": 74.18,
+          "confidence": 0.902
+        },
+        {
+          "text": "them,",
+          "start": 74.18,
+          "end": 74.22,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 74.22,
+          "end": 74.26,
+          "confidence": 0.905
+        },
+        {
+          "text": "them,",
+          "start": 74.26,
+          "end": 74.3,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 74.3,
+          "end": 74.34,
+          "confidence": 0.911
+        },
+        {
+          "text": "them,",
+          "start": 74.34,
+          "end": 74.38,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 74.38,
+          "end": 74.42,
+          "confidence": 0.916
+        },
+        {
+          "text": "them,",
+          "start": 74.42,
+          "end": 74.46,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 74.46,
+          "end": 74.5,
+          "confidence": 0.919
+        },
+        {
+          "text": "them,",
+          "start": 74.5,
+          "end": 74.54,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 74.54,
+          "end": 74.58,
+          "confidence": 0.922
+        },
+        {
+          "text": "them,",
+          "start": 74.58,
+          "end": 74.62,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 74.62,
+          "end": 74.66,
+          "confidence": 0.93
+        },
+        {
+          "text": "them,",
+          "start": 74.66,
+          "end": 74.7,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 74.7,
+          "end": 74.74,
+          "confidence": 0.932
+        },
+        {
+          "text": "them,",
+          "start": 74.74,
+          "end": 74.78,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 74.78,
+          "end": 74.82,
+          "confidence": 0.937
+        },
+        {
+          "text": "them,",
+          "start": 74.82,
+          "end": 74.86,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 74.86,
+          "end": 74.9,
+          "confidence": 0.943
+        },
+        {
+          "text": "them,",
+          "start": 74.9,
+          "end": 74.94,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 74.94,
+          "end": 74.98,
+          "confidence": 0.944
+        },
+        {
+          "text": "them,",
+          "start": 74.98,
+          "end": 75.02,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 75.02,
+          "end": 75.06,
+          "confidence": 0.95
+        },
+        {
+          "text": "them,",
+          "start": 75.06,
+          "end": 75.1,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 75.1,
+          "end": 75.14,
+          "confidence": 0.953
+        },
+        {
+          "text": "them,",
+          "start": 75.14,
+          "end": 75.18,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 75.18,
+          "end": 75.22,
+          "confidence": 0.955
+        },
+        {
+          "text": "them,",
+          "start": 75.22,
+          "end": 75.26,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 75.26,
+          "end": 75.3,
+          "confidence": 0.956
+        },
+        {
+          "text": "them,",
+          "start": 75.3,
+          "end": 75.34,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 75.34,
+          "end": 75.38,
+          "confidence": 0.96
+        },
+        {
+          "text": "them,",
+          "start": 75.38,
+          "end": 75.42,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 75.42,
+          "end": 75.46,
+          "confidence": 0.961
+        },
+        {
+          "text": "them,",
+          "start": 75.46,
+          "end": 75.5,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 75.5,
+          "end": 75.54,
+          "confidence": 0.961
+        },
+        {
+          "text": "them,",
+          "start": 75.54,
+          "end": 75.58,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 75.58,
+          "end": 75.62,
+          "confidence": 0.963
+        },
+        {
+          "text": "them,",
+          "start": 75.62,
+          "end": 75.66,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 75.66,
+          "end": 75.7,
+          "confidence": 0.965
+        },
+        {
+          "text": "them,",
+          "start": 75.7,
+          "end": 75.74,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 75.74,
+          "end": 75.78,
+          "confidence": 0.967
+        },
+        {
+          "text": "them,",
+          "start": 75.78,
+          "end": 75.82,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 75.82,
+          "end": 75.86,
+          "confidence": 0.967
+        },
+        {
+          "text": "them,",
+          "start": 75.86,
+          "end": 75.9,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 75.9,
+          "end": 75.94,
+          "confidence": 0.969
+        },
+        {
+          "text": "them,",
+          "start": 75.94,
+          "end": 75.98,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 75.98,
+          "end": 76.02,
+          "confidence": 0.97
+        },
+        {
+          "text": "them,",
+          "start": 76.02,
+          "end": 76.06,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 76.06,
+          "end": 76.1,
+          "confidence": 0.97
+        },
+        {
+          "text": "them,",
+          "start": 76.1,
+          "end": 76.14,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 76.14,
+          "end": 76.18,
+          "confidence": 0.972
+        },
+        {
+          "text": "them,",
+          "start": 76.18,
+          "end": 76.22,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 76.22,
+          "end": 76.26,
+          "confidence": 0.973
+        },
+        {
+          "text": "them,",
+          "start": 76.26,
+          "end": 76.3,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 76.3,
+          "end": 76.34,
+          "confidence": 0.973
+        },
+        {
+          "text": "them,",
+          "start": 76.34,
+          "end": 76.38,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 76.38,
+          "end": 76.42,
+          "confidence": 0.973
+        },
+        {
+          "text": "them,",
+          "start": 76.42,
+          "end": 76.46,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 76.46,
+          "end": 76.5,
+          "confidence": 0.974
+        },
+        {
+          "text": "them,",
+          "start": 76.5,
+          "end": 76.54,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 76.54,
+          "end": 76.58,
+          "confidence": 0.974
+        },
+        {
+          "text": "them,",
+          "start": 76.58,
+          "end": 76.62,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 76.62,
+          "end": 76.66,
+          "confidence": 0.974
+        },
+        {
+          "text": "them,",
+          "start": 76.66,
+          "end": 76.7,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 76.7,
+          "end": 76.74,
+          "confidence": 0.976
+        },
+        {
+          "text": "them,",
+          "start": 76.74,
+          "end": 76.78,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 76.78,
+          "end": 76.82,
+          "confidence": 0.975
+        },
+        {
+          "text": "them,",
+          "start": 76.82,
+          "end": 76.86,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 76.86,
+          "end": 76.9,
+          "confidence": 0.975
+        },
+        {
+          "text": "them,",
+          "start": 76.9,
+          "end": 76.94,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 76.94,
+          "end": 76.98,
+          "confidence": 0.976
+        },
+        {
+          "text": "them,",
+          "start": 76.98,
+          "end": 77.02,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 77.02,
+          "end": 77.06,
+          "confidence": 0.977
+        },
+        {
+          "text": "them,",
+          "start": 77.06,
+          "end": 77.1,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 77.1,
+          "end": 77.14,
+          "confidence": 0.977
+        },
+        {
+          "text": "them,",
+          "start": 77.14,
+          "end": 77.18,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 77.18,
+          "end": 77.22,
+          "confidence": 0.977
+        },
+        {
+          "text": "them,",
+          "start": 77.22,
+          "end": 77.26,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 77.26,
+          "end": 77.3,
+          "confidence": 0.978
+        },
+        {
+          "text": "them,",
+          "start": 77.3,
+          "end": 77.34,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 77.34,
+          "end": 77.38,
+          "confidence": 0.978
+        },
+        {
+          "text": "them,",
+          "start": 77.38,
+          "end": 77.42,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 77.42,
+          "end": 77.46,
+          "confidence": 0.978
+        },
+        {
+          "text": "them,",
+          "start": 77.46,
+          "end": 77.5,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 77.5,
+          "end": 77.54,
+          "confidence": 0.98
+        },
+        {
+          "text": "them,",
+          "start": 77.54,
+          "end": 77.58,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 77.58,
+          "end": 77.62,
+          "confidence": 0.98
+        },
+        {
+          "text": "them,",
+          "start": 77.62,
+          "end": 77.66,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 77.66,
+          "end": 77.7,
+          "confidence": 0.98
+        },
+        {
+          "text": "them,",
+          "start": 77.7,
+          "end": 77.74,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 77.74,
+          "end": 77.78,
+          "confidence": 0.981
+        },
+        {
+          "text": "them,",
+          "start": 77.78,
+          "end": 77.82,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 77.82,
+          "end": 77.86,
+          "confidence": 0.981
+        },
+        {
+          "text": "them,",
+          "start": 77.86,
+          "end": 79.56,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 79.56,
+          "end": 79.6,
+          "confidence": 0.981
+        },
+        {
+          "text": "them",
+          "start": 79.6,
+          "end": 85.0,
+          "confidence": 0.994
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 8500,
+      "start": 85.02,
+      "end": 115.0,
+      "text": " got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them",
+      "tokens": [
+        50364,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.04965524716227578,
+      "compression_ratio": 29.52,
+      "no_speech_prob": 0.6971923112869263,
+      "confidence": 0.948,
+      "words": [
+        {
+          "text": "got",
+          "start": 85.02,
+          "end": 85.46,
+          "confidence": 0.438
+        },
+        {
+          "text": "them,",
+          "start": 85.46,
+          "end": 86.26,
+          "confidence": 0.943
+        },
+        {
+          "text": "got",
+          "start": 86.26,
+          "end": 86.78,
+          "confidence": 0.963
+        },
+        {
+          "text": "them,",
+          "start": 86.78,
+          "end": 87.18,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 87.18,
+          "end": 87.8,
+          "confidence": 0.963
+        },
+        {
+          "text": "them,",
+          "start": 87.8,
+          "end": 87.84,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 87.84,
+          "end": 88.6,
+          "confidence": 0.951
+        },
+        {
+          "text": "them,",
+          "start": 88.6,
+          "end": 88.64,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 88.64,
+          "end": 88.9,
+          "confidence": 0.934
+        },
+        {
+          "text": "them,",
+          "start": 88.9,
+          "end": 88.94,
+          "confidence": 0.988
+        },
+        {
+          "text": "got",
+          "start": 88.94,
+          "end": 88.98,
+          "confidence": 0.915
+        },
+        {
+          "text": "them,",
+          "start": 88.98,
+          "end": 89.02,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 89.02,
+          "end": 89.06,
+          "confidence": 0.9
+        },
+        {
+          "text": "them,",
+          "start": 89.06,
+          "end": 89.1,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 89.1,
+          "end": 89.14,
+          "confidence": 0.899
+        },
+        {
+          "text": "them,",
+          "start": 89.14,
+          "end": 89.18,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 89.18,
+          "end": 89.22,
+          "confidence": 0.907
+        },
+        {
+          "text": "them,",
+          "start": 89.22,
+          "end": 89.26,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 89.26,
+          "end": 89.3,
+          "confidence": 0.905
+        },
+        {
+          "text": "them,",
+          "start": 89.3,
+          "end": 89.34,
+          "confidence": 0.971
+        },
+        {
+          "text": "got",
+          "start": 89.34,
+          "end": 89.38,
+          "confidence": 0.866
+        },
+        {
+          "text": "them,",
+          "start": 89.38,
+          "end": 89.42,
+          "confidence": 0.959
+        },
+        {
+          "text": "got",
+          "start": 89.42,
+          "end": 89.46,
+          "confidence": 0.845
+        },
+        {
+          "text": "them,",
+          "start": 89.46,
+          "end": 89.5,
+          "confidence": 0.96
+        },
+        {
+          "text": "got",
+          "start": 89.5,
+          "end": 89.54,
+          "confidence": 0.861
+        },
+        {
+          "text": "them,",
+          "start": 89.54,
+          "end": 89.58,
+          "confidence": 0.963
+        },
+        {
+          "text": "got",
+          "start": 89.58,
+          "end": 89.62,
+          "confidence": 0.88
+        },
+        {
+          "text": "them,",
+          "start": 89.62,
+          "end": 89.66,
+          "confidence": 0.965
+        },
+        {
+          "text": "got",
+          "start": 89.66,
+          "end": 89.7,
+          "confidence": 0.888
+        },
+        {
+          "text": "them,",
+          "start": 89.7,
+          "end": 89.74,
+          "confidence": 0.966
+        },
+        {
+          "text": "got",
+          "start": 89.74,
+          "end": 89.78,
+          "confidence": 0.887
+        },
+        {
+          "text": "them,",
+          "start": 89.78,
+          "end": 89.82,
+          "confidence": 0.966
+        },
+        {
+          "text": "got",
+          "start": 89.82,
+          "end": 89.86,
+          "confidence": 0.875
+        },
+        {
+          "text": "them,",
+          "start": 89.86,
+          "end": 89.9,
+          "confidence": 0.968
+        },
+        {
+          "text": "got",
+          "start": 89.9,
+          "end": 89.94,
+          "confidence": 0.871
+        },
+        {
+          "text": "them,",
+          "start": 89.94,
+          "end": 89.98,
+          "confidence": 0.968
+        },
+        {
+          "text": "got",
+          "start": 89.98,
+          "end": 90.02,
+          "confidence": 0.868
+        },
+        {
+          "text": "them,",
+          "start": 90.02,
+          "end": 90.06,
+          "confidence": 0.966
+        },
+        {
+          "text": "got",
+          "start": 90.06,
+          "end": 90.1,
+          "confidence": 0.865
+        },
+        {
+          "text": "them,",
+          "start": 90.1,
+          "end": 90.14,
+          "confidence": 0.964
+        },
+        {
+          "text": "got",
+          "start": 90.14,
+          "end": 90.18,
+          "confidence": 0.865
+        },
+        {
+          "text": "them,",
+          "start": 90.18,
+          "end": 90.22,
+          "confidence": 0.965
+        },
+        {
+          "text": "got",
+          "start": 90.22,
+          "end": 90.26,
+          "confidence": 0.86
+        },
+        {
+          "text": "them,",
+          "start": 90.26,
+          "end": 90.3,
+          "confidence": 0.965
+        },
+        {
+          "text": "got",
+          "start": 90.3,
+          "end": 90.34,
+          "confidence": 0.867
+        },
+        {
+          "text": "them,",
+          "start": 90.34,
+          "end": 90.38,
+          "confidence": 0.966
+        },
+        {
+          "text": "got",
+          "start": 90.38,
+          "end": 90.42,
+          "confidence": 0.866
+        },
+        {
+          "text": "them,",
+          "start": 90.42,
+          "end": 90.46,
+          "confidence": 0.967
+        },
+        {
+          "text": "got",
+          "start": 90.46,
+          "end": 90.5,
+          "confidence": 0.866
+        },
+        {
+          "text": "them,",
+          "start": 90.5,
+          "end": 90.54,
+          "confidence": 0.968
+        },
+        {
+          "text": "got",
+          "start": 90.54,
+          "end": 90.58,
+          "confidence": 0.87
+        },
+        {
+          "text": "them,",
+          "start": 90.58,
+          "end": 90.62,
+          "confidence": 0.969
+        },
+        {
+          "text": "got",
+          "start": 90.62,
+          "end": 90.66,
+          "confidence": 0.874
+        },
+        {
+          "text": "them,",
+          "start": 90.66,
+          "end": 90.7,
+          "confidence": 0.971
+        },
+        {
+          "text": "got",
+          "start": 90.7,
+          "end": 90.74,
+          "confidence": 0.874
+        },
+        {
+          "text": "them,",
+          "start": 90.74,
+          "end": 90.78,
+          "confidence": 0.971
+        },
+        {
+          "text": "got",
+          "start": 90.78,
+          "end": 90.82,
+          "confidence": 0.88
+        },
+        {
+          "text": "them,",
+          "start": 90.82,
+          "end": 90.86,
+          "confidence": 0.971
+        },
+        {
+          "text": "got",
+          "start": 90.86,
+          "end": 90.9,
+          "confidence": 0.884
+        },
+        {
+          "text": "them,",
+          "start": 90.9,
+          "end": 90.94,
+          "confidence": 0.973
+        },
+        {
+          "text": "got",
+          "start": 90.94,
+          "end": 90.98,
+          "confidence": 0.883
+        },
+        {
+          "text": "them,",
+          "start": 90.98,
+          "end": 91.02,
+          "confidence": 0.973
+        },
+        {
+          "text": "got",
+          "start": 91.02,
+          "end": 91.06,
+          "confidence": 0.884
+        },
+        {
+          "text": "them,",
+          "start": 91.06,
+          "end": 91.1,
+          "confidence": 0.973
+        },
+        {
+          "text": "got",
+          "start": 91.1,
+          "end": 91.14,
+          "confidence": 0.893
+        },
+        {
+          "text": "them,",
+          "start": 91.14,
+          "end": 91.18,
+          "confidence": 0.975
+        },
+        {
+          "text": "got",
+          "start": 91.18,
+          "end": 91.22,
+          "confidence": 0.894
+        },
+        {
+          "text": "them,",
+          "start": 91.22,
+          "end": 91.26,
+          "confidence": 0.975
+        },
+        {
+          "text": "got",
+          "start": 91.26,
+          "end": 91.3,
+          "confidence": 0.9
+        },
+        {
+          "text": "them,",
+          "start": 91.3,
+          "end": 91.34,
+          "confidence": 0.976
+        },
+        {
+          "text": "got",
+          "start": 91.34,
+          "end": 91.38,
+          "confidence": 0.906
+        },
+        {
+          "text": "them,",
+          "start": 91.38,
+          "end": 91.42,
+          "confidence": 0.977
+        },
+        {
+          "text": "got",
+          "start": 91.42,
+          "end": 91.46,
+          "confidence": 0.905
+        },
+        {
+          "text": "them,",
+          "start": 91.46,
+          "end": 91.5,
+          "confidence": 0.978
+        },
+        {
+          "text": "got",
+          "start": 91.5,
+          "end": 91.54,
+          "confidence": 0.915
+        },
+        {
+          "text": "them,",
+          "start": 91.54,
+          "end": 91.58,
+          "confidence": 0.979
+        },
+        {
+          "text": "got",
+          "start": 91.58,
+          "end": 91.62,
+          "confidence": 0.92
+        },
+        {
+          "text": "them,",
+          "start": 91.62,
+          "end": 91.66,
+          "confidence": 0.98
+        },
+        {
+          "text": "got",
+          "start": 91.66,
+          "end": 91.7,
+          "confidence": 0.922
+        },
+        {
+          "text": "them,",
+          "start": 91.7,
+          "end": 91.74,
+          "confidence": 0.981
+        },
+        {
+          "text": "got",
+          "start": 91.74,
+          "end": 91.78,
+          "confidence": 0.925
+        },
+        {
+          "text": "them,",
+          "start": 91.78,
+          "end": 91.82,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 91.82,
+          "end": 91.86,
+          "confidence": 0.932
+        },
+        {
+          "text": "them,",
+          "start": 91.86,
+          "end": 91.9,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 91.9,
+          "end": 91.94,
+          "confidence": 0.936
+        },
+        {
+          "text": "them,",
+          "start": 91.94,
+          "end": 91.98,
+          "confidence": 0.984
+        },
+        {
+          "text": "got",
+          "start": 91.98,
+          "end": 92.02,
+          "confidence": 0.935
+        },
+        {
+          "text": "them,",
+          "start": 92.02,
+          "end": 92.06,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 92.06,
+          "end": 92.1,
+          "confidence": 0.941
+        },
+        {
+          "text": "them,",
+          "start": 92.1,
+          "end": 92.14,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 92.14,
+          "end": 92.18,
+          "confidence": 0.946
+        },
+        {
+          "text": "them,",
+          "start": 92.18,
+          "end": 92.22,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 92.22,
+          "end": 92.26,
+          "confidence": 0.95
+        },
+        {
+          "text": "them,",
+          "start": 92.26,
+          "end": 92.3,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 92.3,
+          "end": 92.34,
+          "confidence": 0.951
+        },
+        {
+          "text": "them,",
+          "start": 92.34,
+          "end": 92.38,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 92.38,
+          "end": 92.42,
+          "confidence": 0.954
+        },
+        {
+          "text": "them,",
+          "start": 92.42,
+          "end": 92.46,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 92.46,
+          "end": 92.5,
+          "confidence": 0.959
+        },
+        {
+          "text": "them,",
+          "start": 92.5,
+          "end": 92.54,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 92.54,
+          "end": 92.58,
+          "confidence": 0.959
+        },
+        {
+          "text": "them,",
+          "start": 92.58,
+          "end": 92.62,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 92.62,
+          "end": 92.66,
+          "confidence": 0.963
+        },
+        {
+          "text": "them,",
+          "start": 92.66,
+          "end": 92.7,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 92.7,
+          "end": 92.74,
+          "confidence": 0.966
+        },
+        {
+          "text": "them,",
+          "start": 92.74,
+          "end": 92.78,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 92.78,
+          "end": 92.82,
+          "confidence": 0.967
+        },
+        {
+          "text": "them,",
+          "start": 92.82,
+          "end": 92.86,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 92.86,
+          "end": 92.9,
+          "confidence": 0.97
+        },
+        {
+          "text": "them,",
+          "start": 92.9,
+          "end": 92.94,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 92.94,
+          "end": 92.98,
+          "confidence": 0.971
+        },
+        {
+          "text": "them,",
+          "start": 92.98,
+          "end": 93.02,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 93.02,
+          "end": 93.06,
+          "confidence": 0.97
+        },
+        {
+          "text": "them,",
+          "start": 93.06,
+          "end": 93.1,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 93.1,
+          "end": 93.14,
+          "confidence": 0.973
+        },
+        {
+          "text": "them,",
+          "start": 93.14,
+          "end": 93.18,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 93.18,
+          "end": 93.22,
+          "confidence": 0.974
+        },
+        {
+          "text": "them,",
+          "start": 93.22,
+          "end": 93.26,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 93.26,
+          "end": 93.3,
+          "confidence": 0.974
+        },
+        {
+          "text": "them,",
+          "start": 93.3,
+          "end": 93.34,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 93.34,
+          "end": 93.38,
+          "confidence": 0.976
+        },
+        {
+          "text": "them,",
+          "start": 93.38,
+          "end": 93.42,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 93.42,
+          "end": 93.46,
+          "confidence": 0.978
+        },
+        {
+          "text": "them,",
+          "start": 93.46,
+          "end": 93.5,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 93.5,
+          "end": 93.54,
+          "confidence": 0.979
+        },
+        {
+          "text": "them,",
+          "start": 93.54,
+          "end": 93.58,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 93.58,
+          "end": 93.62,
+          "confidence": 0.98
+        },
+        {
+          "text": "them,",
+          "start": 93.62,
+          "end": 93.66,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 93.66,
+          "end": 93.7,
+          "confidence": 0.981
+        },
+        {
+          "text": "them,",
+          "start": 93.7,
+          "end": 93.74,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 93.74,
+          "end": 93.78,
+          "confidence": 0.98
+        },
+        {
+          "text": "them,",
+          "start": 93.78,
+          "end": 93.82,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 93.82,
+          "end": 93.86,
+          "confidence": 0.982
+        },
+        {
+          "text": "them,",
+          "start": 93.86,
+          "end": 93.9,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 93.9,
+          "end": 93.94,
+          "confidence": 0.982
+        },
+        {
+          "text": "them,",
+          "start": 93.94,
+          "end": 93.98,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 93.98,
+          "end": 94.02,
+          "confidence": 0.984
+        },
+        {
+          "text": "them,",
+          "start": 94.02,
+          "end": 94.06,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 94.06,
+          "end": 94.1,
+          "confidence": 0.984
+        },
+        {
+          "text": "them,",
+          "start": 94.1,
+          "end": 94.14,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 94.14,
+          "end": 94.18,
+          "confidence": 0.985
+        },
+        {
+          "text": "them,",
+          "start": 94.18,
+          "end": 94.22,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 94.22,
+          "end": 94.26,
+          "confidence": 0.986
+        },
+        {
+          "text": "them,",
+          "start": 94.26,
+          "end": 94.3,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 94.3,
+          "end": 94.34,
+          "confidence": 0.986
+        },
+        {
+          "text": "them,",
+          "start": 94.34,
+          "end": 94.38,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 94.38,
+          "end": 94.42,
+          "confidence": 0.987
+        },
+        {
+          "text": "them",
+          "start": 94.42,
+          "end": 115.0,
+          "confidence": 0.996
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/corner_cases/accurate.tiny_apollo11.mp3.words.json b/tests/expected/corner_cases/accurate.tiny_apollo11.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..7ad6577bcc1c1e5d972ee3a7a905627ce5e41386
--- /dev/null
+++ b/tests/expected/corner_cases/accurate.tiny_apollo11.mp3.words.json
@@ -0,0 +1,1261 @@
+{
+  "text": " I'm all around my business and we got a recommendation for you on your door to the VA We have 18A's Okay, okay, I think I'll just get him or if they like just want to go on the Yeah, now what you want is on having a B1 And you just get the other one on my Now when we're here, we're going to go on the Yeah Okay, we want to hear that This is it, we know we just You can hit that That's how much you've ordered in that So I guess I'm working on my position but it's not Oh my god Okay, no problem No idea No idea Okay Okay",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.6,
+      "end": 5.36,
+      "text": " I'm all around my business and we got a recommendation for you on your door to the VA",
+      "tokens": [
+        50364,
+        286,
+        478,
+        439,
+        926,
+        452,
+        1606,
+        293,
+        321,
+        658,
+        257,
+        11879,
+        337,
+        291,
+        322,
+        428,
+        2853,
+        281,
+        264,
+        18527,
+        50628
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -1.1827944879946501,
+      "compression_ratio": 1.52020202020202,
+      "no_speech_prob": 0.35403239727020264,
+      "confidence": 0.324,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 0.6,
+          "end": 0.82,
+          "confidence": 0.168
+        },
+        {
+          "text": "all",
+          "start": 0.82,
+          "end": 1.06,
+          "confidence": 0.082
+        },
+        {
+          "text": "around",
+          "start": 1.06,
+          "end": 1.28,
+          "confidence": 0.104
+        },
+        {
+          "text": "my",
+          "start": 1.28,
+          "end": 1.46,
+          "confidence": 0.128
+        },
+        {
+          "text": "business",
+          "start": 1.46,
+          "end": 1.72,
+          "confidence": 0.342
+        },
+        {
+          "text": "and",
+          "start": 1.72,
+          "end": 1.92,
+          "confidence": 0.613
+        },
+        {
+          "text": "we",
+          "start": 1.92,
+          "end": 1.98,
+          "confidence": 0.937
+        },
+        {
+          "text": "got",
+          "start": 1.98,
+          "end": 2.18,
+          "confidence": 0.4
+        },
+        {
+          "text": "a",
+          "start": 2.18,
+          "end": 2.4,
+          "confidence": 0.639
+        },
+        {
+          "text": "recommendation",
+          "start": 2.4,
+          "end": 3.06,
+          "confidence": 0.599
+        },
+        {
+          "text": "for",
+          "start": 3.06,
+          "end": 3.5,
+          "confidence": 0.371
+        },
+        {
+          "text": "you",
+          "start": 3.5,
+          "end": 3.68,
+          "confidence": 0.974
+        },
+        {
+          "text": "on",
+          "start": 3.68,
+          "end": 3.88,
+          "confidence": 0.805
+        },
+        {
+          "text": "your",
+          "start": 3.88,
+          "end": 4.24,
+          "confidence": 0.562
+        },
+        {
+          "text": "door",
+          "start": 4.24,
+          "end": 4.68,
+          "confidence": 0.145
+        },
+        {
+          "text": "to",
+          "start": 4.68,
+          "end": 4.88,
+          "confidence": 0.182
+        },
+        {
+          "text": "the",
+          "start": 4.88,
+          "end": 5.08,
+          "confidence": 0.501
+        },
+        {
+          "text": "VA",
+          "start": 5.08,
+          "end": 5.36,
+          "confidence": 0.249
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 5.36,
+      "end": 6.94,
+      "text": " We have 18A's",
+      "tokens": [
+        50628,
+        492,
+        362,
+        2443,
+        32,
+        311,
+        50714
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -1.1827944879946501,
+      "compression_ratio": 1.52020202020202,
+      "no_speech_prob": 0.35403239727020264,
+      "confidence": 0.175,
+      "words": [
+        {
+          "text": "We",
+          "start": 5.36,
+          "end": 5.74,
+          "confidence": 0.042
+        },
+        {
+          "text": "have",
+          "start": 5.74,
+          "end": 5.76,
+          "confidence": 0.652
+        },
+        {
+          "text": "18A's",
+          "start": 5.76,
+          "end": 6.94,
+          "confidence": 0.182
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 12.0,
+      "end": 16.79,
+      "text": " Okay, okay, I think I'll just get him or if they like just want to go on the",
+      "tokens": [
+        50914,
+        1033,
+        11,
+        1392,
+        11,
+        286,
+        519,
+        286,
+        603,
+        445,
+        483,
+        796,
+        420,
+        498,
+        436,
+        411,
+        445,
+        528,
+        281,
+        352,
+        322,
+        264,
+        51197
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -1.1827944879946501,
+      "compression_ratio": 1.52020202020202,
+      "no_speech_prob": 0.35403239727020264,
+      "confidence": 0.327,
+      "words": [
+        {
+          "text": "Okay,",
+          "start": 12.0,
+          "end": 12.38,
+          "confidence": 0.662
+        },
+        {
+          "text": "okay,",
+          "start": 12.88,
+          "end": 13.12,
+          "confidence": 0.291
+        },
+        {
+          "text": "I",
+          "start": 13.12,
+          "end": 13.3,
+          "confidence": 0.209
+        },
+        {
+          "text": "think",
+          "start": 13.3,
+          "end": 13.58,
+          "confidence": 0.263
+        },
+        {
+          "text": "I'll",
+          "start": 13.58,
+          "end": 13.9,
+          "confidence": 0.2
+        },
+        {
+          "text": "just",
+          "start": 13.9,
+          "end": 14.1,
+          "confidence": 0.17
+        },
+        {
+          "text": "get",
+          "start": 14.1,
+          "end": 14.28,
+          "confidence": 0.248
+        },
+        {
+          "text": "him",
+          "start": 14.28,
+          "end": 14.52,
+          "confidence": 0.153
+        },
+        {
+          "text": "or",
+          "start": 14.52,
+          "end": 14.74,
+          "confidence": 0.199
+        },
+        {
+          "text": "if",
+          "start": 14.74,
+          "end": 14.94,
+          "confidence": 0.088
+        },
+        {
+          "text": "they",
+          "start": 14.94,
+          "end": 15.44,
+          "confidence": 0.607
+        },
+        {
+          "text": "like",
+          "start": 15.44,
+          "end": 15.74,
+          "confidence": 0.2
+        },
+        {
+          "text": "just",
+          "start": 15.74,
+          "end": 15.96,
+          "confidence": 0.462
+        },
+        {
+          "text": "want",
+          "start": 15.96,
+          "end": 16.18,
+          "confidence": 0.765
+        },
+        {
+          "text": "to",
+          "start": 16.18,
+          "end": 16.36,
+          "confidence": 0.91
+        },
+        {
+          "text": "go",
+          "start": 16.36,
+          "end": 16.56,
+          "confidence": 0.948
+        },
+        {
+          "text": "on",
+          "start": 16.56,
+          "end": 16.7,
+          "confidence": 0.566
+        },
+        {
+          "text": "the",
+          "start": 16.7,
+          "end": 16.79,
+          "confidence": 0.585
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 16.79,
+      "end": 19.0,
+      "text": " Yeah, now what you want is on having a B1",
+      "tokens": [
+        51197,
+        865,
+        11,
+        586,
+        437,
+        291,
+        528,
+        307,
+        322,
+        1419,
+        257,
+        363,
+        16,
+        51322
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -1.1827944879946501,
+      "compression_ratio": 1.52020202020202,
+      "no_speech_prob": 0.35403239727020264,
+      "confidence": 0.471,
+      "words": [
+        {
+          "text": "Yeah,",
+          "start": 16.79,
+          "end": 17.1,
+          "confidence": 0.28
+        },
+        {
+          "text": "now",
+          "start": 17.18,
+          "end": 17.3,
+          "confidence": 0.365
+        },
+        {
+          "text": "what",
+          "start": 17.3,
+          "end": 17.48,
+          "confidence": 0.743
+        },
+        {
+          "text": "you",
+          "start": 17.48,
+          "end": 17.62,
+          "confidence": 0.932
+        },
+        {
+          "text": "want",
+          "start": 17.62,
+          "end": 17.84,
+          "confidence": 0.743
+        },
+        {
+          "text": "is",
+          "start": 17.84,
+          "end": 17.96,
+          "confidence": 0.674
+        },
+        {
+          "text": "on",
+          "start": 17.96,
+          "end": 18.16,
+          "confidence": 0.327
+        },
+        {
+          "text": "having",
+          "start": 18.16,
+          "end": 18.44,
+          "confidence": 0.563
+        },
+        {
+          "text": "a",
+          "start": 18.44,
+          "end": 18.76,
+          "confidence": 0.287
+        },
+        {
+          "text": "B1",
+          "start": 18.76,
+          "end": 19.0,
+          "confidence": 0.37
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 19.0,
+      "end": 21.88,
+      "text": " And you just get the other one on my",
+      "tokens": [
+        51322,
+        400,
+        291,
+        445,
+        483,
+        264,
+        661,
+        472,
+        322,
+        452,
+        51462
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -1.1827944879946501,
+      "compression_ratio": 1.52020202020202,
+      "no_speech_prob": 0.35403239727020264,
+      "confidence": 0.516,
+      "words": [
+        {
+          "text": "And",
+          "start": 19.0,
+          "end": 20.26,
+          "confidence": 0.272
+        },
+        {
+          "text": "you",
+          "start": 20.26,
+          "end": 20.4,
+          "confidence": 0.846
+        },
+        {
+          "text": "just",
+          "start": 20.4,
+          "end": 20.64,
+          "confidence": 0.694
+        },
+        {
+          "text": "get",
+          "start": 20.64,
+          "end": 20.8,
+          "confidence": 0.134
+        },
+        {
+          "text": "the",
+          "start": 20.8,
+          "end": 20.9,
+          "confidence": 0.65
+        },
+        {
+          "text": "other",
+          "start": 20.9,
+          "end": 21.08,
+          "confidence": 0.937
+        },
+        {
+          "text": "one",
+          "start": 21.08,
+          "end": 21.26,
+          "confidence": 0.976
+        },
+        {
+          "text": "on",
+          "start": 21.26,
+          "end": 21.66,
+          "confidence": 0.872
+        },
+        {
+          "text": "my",
+          "start": 21.66,
+          "end": 21.88,
+          "confidence": 0.232
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 0,
+      "start": 22.12,
+      "end": 25.36,
+      "text": " Now when we're here, we're going to go on the",
+      "tokens": [
+        51462,
+        823,
+        562,
+        321,
+        434,
+        510,
+        11,
+        321,
+        434,
+        516,
+        281,
+        352,
+        322,
+        264,
+        51616
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -1.1827944879946501,
+      "compression_ratio": 1.52020202020202,
+      "no_speech_prob": 0.35403239727020264,
+      "confidence": 0.336,
+      "words": [
+        {
+          "text": "Now",
+          "start": 22.12,
+          "end": 22.8,
+          "confidence": 0.168
+        },
+        {
+          "text": "when",
+          "start": 22.8,
+          "end": 23.04,
+          "confidence": 0.35
+        },
+        {
+          "text": "we're",
+          "start": 23.04,
+          "end": 23.24,
+          "confidence": 0.745
+        },
+        {
+          "text": "here,",
+          "start": 23.24,
+          "end": 23.44,
+          "confidence": 0.492
+        },
+        {
+          "text": "we're",
+          "start": 23.66,
+          "end": 23.88,
+          "confidence": 0.293
+        },
+        {
+          "text": "going",
+          "start": 23.88,
+          "end": 23.94,
+          "confidence": 0.291
+        },
+        {
+          "text": "to",
+          "start": 23.94,
+          "end": 24.38,
+          "confidence": 0.88
+        },
+        {
+          "text": "go",
+          "start": 24.38,
+          "end": 24.72,
+          "confidence": 0.119
+        },
+        {
+          "text": "on",
+          "start": 24.72,
+          "end": 25.34,
+          "confidence": 0.133
+        },
+        {
+          "text": "the",
+          "start": 25.34,
+          "end": 25.36,
+          "confidence": 0.364
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 3000,
+      "start": 31.36,
+      "end": 31.56,
+      "text": " Yeah",
+      "tokens": [
+        50364,
+        865,
+        50464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -1.6116297245025635,
+      "compression_ratio": 0.3333333333333333,
+      "no_speech_prob": 0.29405874013900757,
+      "confidence": 0.057,
+      "words": [
+        {
+          "text": "Yeah",
+          "start": 31.36,
+          "end": 31.56,
+          "confidence": 0.057
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 6000,
+      "start": 62.7,
+      "end": 64.14,
+      "text": " Okay, we want to hear that",
+      "tokens": [
+        50364,
+        1033,
+        11,
+        321,
+        528,
+        281,
+        1568,
+        300,
+        50564
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9387273416890727,
+      "compression_ratio": 1.4172185430463575,
+      "no_speech_prob": 0.10345567017793655,
+      "confidence": 0.355,
+      "words": [
+        {
+          "text": "Okay,",
+          "start": 62.7,
+          "end": 62.72,
+          "confidence": 0.125
+        },
+        {
+          "text": "we",
+          "start": 63.1,
+          "end": 63.32,
+          "confidence": 0.238
+        },
+        {
+          "text": "want",
+          "start": 63.32,
+          "end": 63.62,
+          "confidence": 0.529
+        },
+        {
+          "text": "to",
+          "start": 63.62,
+          "end": 63.72,
+          "confidence": 0.571
+        },
+        {
+          "text": "hear",
+          "start": 63.72,
+          "end": 63.84,
+          "confidence": 0.245
+        },
+        {
+          "text": "that",
+          "start": 63.84,
+          "end": 64.14,
+          "confidence": 0.92
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 6000,
+      "start": 64.46,
+      "end": 66.82,
+      "text": " This is it, we know we just",
+      "tokens": [
+        50564,
+        639,
+        307,
+        309,
+        11,
+        321,
+        458,
+        321,
+        445,
+        50714
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9387273416890727,
+      "compression_ratio": 1.4172185430463575,
+      "no_speech_prob": 0.10345567017793655,
+      "confidence": 0.459,
+      "words": [
+        {
+          "text": "This",
+          "start": 64.46,
+          "end": 64.72,
+          "confidence": 0.243
+        },
+        {
+          "text": "is",
+          "start": 64.72,
+          "end": 64.94,
+          "confidence": 0.663
+        },
+        {
+          "text": "it,",
+          "start": 64.94,
+          "end": 65.12,
+          "confidence": 0.243
+        },
+        {
+          "text": "we",
+          "start": 65.22,
+          "end": 65.42,
+          "confidence": 0.475
+        },
+        {
+          "text": "know",
+          "start": 65.42,
+          "end": 65.62,
+          "confidence": 0.696
+        },
+        {
+          "text": "we",
+          "start": 65.62,
+          "end": 65.88,
+          "confidence": 0.823
+        },
+        {
+          "text": "just",
+          "start": 65.88,
+          "end": 66.82,
+          "confidence": 0.405
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 6000,
+      "start": 66.86,
+      "end": 68.3,
+      "text": " You can hit that",
+      "tokens": [
+        50714,
+        509,
+        393,
+        2045,
+        300,
+        50764
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9387273416890727,
+      "compression_ratio": 1.4172185430463575,
+      "no_speech_prob": 0.10345567017793655,
+      "confidence": 0.329,
+      "words": [
+        {
+          "text": "You",
+          "start": 66.86,
+          "end": 67.14,
+          "confidence": 0.246
+        },
+        {
+          "text": "can",
+          "start": 67.14,
+          "end": 67.32,
+          "confidence": 0.577
+        },
+        {
+          "text": "hit",
+          "start": 67.32,
+          "end": 67.52,
+          "confidence": 0.126
+        },
+        {
+          "text": "that",
+          "start": 67.52,
+          "end": 68.3,
+          "confidence": 0.656
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 6000,
+      "start": 68.32,
+      "end": 69.46,
+      "text": " That's how much you've ordered in that",
+      "tokens": [
+        50764,
+        663,
+        311,
+        577,
+        709,
+        291,
+        600,
+        8866,
+        294,
+        300,
+        50864
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9387273416890727,
+      "compression_ratio": 1.4172185430463575,
+      "no_speech_prob": 0.10345567017793655,
+      "confidence": 0.3,
+      "words": [
+        {
+          "text": "That's",
+          "start": 68.32,
+          "end": 68.58,
+          "confidence": 0.262
+        },
+        {
+          "text": "how",
+          "start": 68.58,
+          "end": 68.6,
+          "confidence": 0.237
+        },
+        {
+          "text": "much",
+          "start": 68.6,
+          "end": 68.68,
+          "confidence": 0.974
+        },
+        {
+          "text": "you've",
+          "start": 68.68,
+          "end": 68.84,
+          "confidence": 0.416
+        },
+        {
+          "text": "ordered",
+          "start": 68.84,
+          "end": 69.02,
+          "confidence": 0.145
+        },
+        {
+          "text": "in",
+          "start": 69.02,
+          "end": 69.22,
+          "confidence": 0.204
+        },
+        {
+          "text": "that",
+          "start": 69.22,
+          "end": 69.46,
+          "confidence": 0.246
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 6000,
+      "start": 70.4,
+      "end": 72.52,
+      "text": " So I guess I'm working on my position but it's not",
+      "tokens": [
+        50864,
+        407,
+        286,
+        2041,
+        286,
+        478,
+        1364,
+        322,
+        452,
+        2535,
+        457,
+        309,
+        311,
+        406,
+        51014
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9387273416890727,
+      "compression_ratio": 1.4172185430463575,
+      "no_speech_prob": 0.10345567017793655,
+      "confidence": 0.458,
+      "words": [
+        {
+          "text": "So",
+          "start": 70.4,
+          "end": 70.42,
+          "confidence": 0.914
+        },
+        {
+          "text": "I",
+          "start": 70.42,
+          "end": 70.54,
+          "confidence": 0.727
+        },
+        {
+          "text": "guess",
+          "start": 70.54,
+          "end": 70.8,
+          "confidence": 0.767
+        },
+        {
+          "text": "I'm",
+          "start": 70.8,
+          "end": 71.3,
+          "confidence": 0.363
+        },
+        {
+          "text": "working",
+          "start": 71.3,
+          "end": 71.32,
+          "confidence": 0.653
+        },
+        {
+          "text": "on",
+          "start": 71.32,
+          "end": 71.58,
+          "confidence": 0.396
+        },
+        {
+          "text": "my",
+          "start": 71.58,
+          "end": 71.74,
+          "confidence": 0.261
+        },
+        {
+          "text": "position",
+          "start": 71.74,
+          "end": 71.98,
+          "confidence": 0.081
+        },
+        {
+          "text": "but",
+          "start": 71.98,
+          "end": 72.18,
+          "confidence": 0.291
+        },
+        {
+          "text": "it's",
+          "start": 72.18,
+          "end": 72.38,
+          "confidence": 0.792
+        },
+        {
+          "text": "not",
+          "start": 72.38,
+          "end": 72.52,
+          "confidence": 0.585
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 6000,
+      "start": 74.72,
+      "end": 75.22,
+      "text": " Oh my god",
+      "tokens": [
+        51014,
+        876,
+        452,
+        3044,
+        51114
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9387273416890727,
+      "compression_ratio": 1.4172185430463575,
+      "no_speech_prob": 0.10345567017793655,
+      "confidence": 0.199,
+      "words": [
+        {
+          "text": "Oh",
+          "start": 74.72,
+          "end": 74.74,
+          "confidence": 0.145
+        },
+        {
+          "text": "my",
+          "start": 74.74,
+          "end": 75.08,
+          "confidence": 0.273
+        },
+        {
+          "text": "god",
+          "start": 75.08,
+          "end": 75.22,
+          "confidence": 0.2
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 6000,
+      "start": 75.22,
+      "end": 76.64,
+      "text": " Okay, no problem",
+      "tokens": [
+        51114,
+        1033,
+        11,
+        572,
+        1154,
+        51214
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9387273416890727,
+      "compression_ratio": 1.4172185430463575,
+      "no_speech_prob": 0.10345567017793655,
+      "confidence": 0.623,
+      "words": [
+        {
+          "text": "Okay,",
+          "start": 75.22,
+          "end": 75.9,
+          "confidence": 0.682
+        },
+        {
+          "text": "no",
+          "start": 76.26,
+          "end": 76.32,
+          "confidence": 0.365
+        },
+        {
+          "text": "problem",
+          "start": 76.32,
+          "end": 76.64,
+          "confidence": 0.97
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 6000,
+      "start": 76.64,
+      "end": 77.5,
+      "text": " No idea",
+      "tokens": [
+        51214,
+        883,
+        1558,
+        51264
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9387273416890727,
+      "compression_ratio": 1.4172185430463575,
+      "no_speech_prob": 0.10345567017793655,
+      "confidence": 0.223,
+      "words": [
+        {
+          "text": "No",
+          "start": 76.64,
+          "end": 77.28,
+          "confidence": 0.223
+        },
+        {
+          "text": "idea",
+          "start": 77.28,
+          "end": 77.5,
+          "confidence": 0.224
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 6000,
+      "start": 78.06,
+      "end": 78.6,
+      "text": " No idea",
+      "tokens": [
+        51264,
+        883,
+        1558,
+        51314
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9387273416890727,
+      "compression_ratio": 1.4172185430463575,
+      "no_speech_prob": 0.10345567017793655,
+      "confidence": 0.282,
+      "words": [
+        {
+          "text": "No",
+          "start": 78.06,
+          "end": 78.38,
+          "confidence": 0.105
+        },
+        {
+          "text": "idea",
+          "start": 78.38,
+          "end": 78.6,
+          "confidence": 0.76
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 6000,
+      "start": 85.28,
+      "end": 85.58,
+      "text": " Okay",
+      "tokens": [
+        51614,
+        1033,
+        51664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9387273416890727,
+      "compression_ratio": 1.4172185430463575,
+      "no_speech_prob": 0.10345567017793655,
+      "confidence": 0.101,
+      "words": [
+        {
+          "text": "Okay",
+          "start": 85.28,
+          "end": 85.58,
+          "confidence": 0.101
+        }
+      ]
+    },
+    {
+      "id": 17,
+      "seek": 6000,
+      "start": 86.6,
+      "end": 86.86,
+      "text": " Okay",
+      "tokens": [
+        51664,
+        1033,
+        51714
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9387273416890727,
+      "compression_ratio": 1.4172185430463575,
+      "no_speech_prob": 0.10345567017793655,
+      "confidence": 0.159,
+      "words": [
+        {
+          "text": "Okay",
+          "start": 86.6,
+          "end": 86.86,
+          "confidence": 0.159
+        }
+      ]
+    }
+  ],
+  "language": "en",
+  "language_probs": {
+    "en": 0.90898597240448,
+    "zh": 0.0063686794601380825,
+    "de": 0.0015729529550299048,
+    "es": 0.0061727361753582954,
+    "ru": 0.0024746020790189505,
+    "ko": 0.004695970099419355,
+    "fr": 0.0016613693442195654,
+    "ja": 0.003055725945159793,
+    "pt": 0.002100167563185096,
+    "tr": 0.0005608535720966756,
+    "pl": 0.00023197913833428174,
+    "ca": 5.729480835725553e-05,
+    "nl": 0.0019272222416475415,
+    "ar": 0.0010980981169268489,
+    "sv": 0.0010980981169268489,
+    "it": 0.0002393429313087836,
+    "id": 0.0011873272014781833,
+    "hi": 0.00014977698447182775,
+    "fi": 0.0010076714679598808,
+    "vi": 0.005533204879611731,
+    "he": 0.00017239226144738495,
+    "uk": 0.0002932491188403219,
+    "el": 0.0003401749418117106,
+    "ms": 0.0010076714679598808,
+    "cs": 4.4621239794651046e-05,
+    "ro": 0.0002079447585856542,
+    "da": 0.0010980981169268489,
+    "hu": 0.0001657880056882277,
+    "ta": 0.00026492850156500936,
+    "no": 8.873992919689044e-05,
+    "th": 0.0017685183556750417,
+    "ur": 0.0001606872392585501,
+    "hr": 3.6135381378699094e-05,
+    "bg": 3.8767600926803425e-05,
+    "lt": 1.964646617125254e-05,
+    "la": 0.002067607594653964,
+    "mi": 0.001782389241270721,
+    "ml": 0.001432189834304154,
+    "cy": 0.002436236944049597,
+    "sk": 8.650221388961654e-06,
+    "te": 9.084433986572549e-05,
+    "fa": 7.186378206824884e-05,
+    "lv": 2.4260149075416848e-05,
+    "bn": 8.01698406576179e-05,
+    "sr": 1.1869727131852414e-05,
+    "az": 8.416896889684722e-06,
+    "sl": 3.18893653457053e-05,
+    "kn": 5.105106083647115e-06,
+    "et": 1.059847363649169e-05,
+    "mk": 5.2466243687376846e-06,
+    "br": 0.0005696857697330415,
+    "eu": 1.7203019524458796e-05,
+    "is": 3.7282443372532725e-05,
+    "hy": 1.7203019524458796e-05,
+    "ne": 4.567940050037578e-05,
+    "mn": 0.00018640047346707433,
+    "bs": 2.7923257221118547e-05,
+    "kk": 4.5405749915516935e-06,
+    "sq": 2.5030247343238443e-05,
+    "sw": 9.670329018263146e-05,
+    "gl": 0.00016971956938505173,
+    "mr": 1.874678855529055e-05,
+    "pa": 6.182035122037632e-06,
+    "si": 0.00013425922952592373,
+    "km": 0.0008033857448026538,
+    "sn": 0.00027548204525373876,
+    "yo": 0.00018494989490136504,
+    "so": 4.215781245875405e-06,
+    "af": 8.01698406576179e-05,
+    "oc": 3.18893653457053e-05,
+    "ka": 8.221919415518641e-06,
+    "be": 1.7203019524458796e-05,
+    "tg": 1.2656181525017018e-07,
+    "sd": 3.0908227927284315e-05,
+    "gu": 3.4950057852256577e-06,
+    "am": 1.1685703611874487e-05,
+    "yi": 0.00014977698447182775,
+    "lo": 2.8809638024540618e-05,
+    "uz": 1.9721213551093797e-09,
+    "fo": 0.00045419312664307654,
+    "ht": 0.00015574341523461044,
+    "ps": 9.316655450675171e-06,
+    "tk": 1.7671988317147225e-08,
+    "nn": 0.015158776193857193,
+    "mt": 1.2439366400940344e-05,
+    "sa": 9.446316107641906e-05,
+    "lb": 1.3684594080132229e-07,
+    "my": 0.00024311205197591335,
+    "bo": 0.00028422678587958217,
+    "tl": 0.0014776524621993303,
+    "mg": 3.611920007529079e-08,
+    "as": 1.2635258826776408e-05,
+    "tt": 1.3765013306965557e-07,
+    "haw": 0.010665531270205975,
+    "ln": 9.956344001693651e-06,
+    "ha": 1.6636236921385716e-07,
+    "ba": 1.7880301683703692e-08,
+    "jw": 0.004480925854295492,
+    "su": 1.108212259737229e-07
+  }
+}
\ No newline at end of file
diff --git a/tests/expected/corner_cases/arabic.mp3.words.json b/tests/expected/corner_cases/arabic.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..f88ce5e8e84ed6fbfd0acd935f21544d17bd4c95
--- /dev/null
+++ b/tests/expected/corner_cases/arabic.mp3.words.json
@@ -0,0 +1,393 @@
+{
+  "text": " حبّي أنصار الهدى حبّي ركب الفدا وطلّبي سأر الشاهد وطلّبي سأر الشاهد لمتى سنضل رقودا نغرق في النوم ونشخر وعن الآذان نسمّه ونغمّض كي لا نمسر",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 1.8,
+      "end": 7.48,
+      "text": " حبّي أنصار الهدى",
+      "tokens": [
+        50364,
+        11331,
+        3555,
+        11703,
+        1829,
+        14739,
+        9381,
+        9640,
+        2423,
+        3224,
+        3215,
+        7578,
+        50714
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5114130362486228,
+      "compression_ratio": 1.1842105263157894,
+      "no_speech_prob": 0.7993651032447815,
+      "confidence": 0.651,
+      "words": [
+        {
+          "text": "حبّي",
+          "start": 1.8,
+          "end": 4.26,
+          "confidence": 0.436
+        },
+        {
+          "text": "أنصار",
+          "start": 4.26,
+          "end": 5.7,
+          "confidence": 0.795
+        },
+        {
+          "text": "الهدى",
+          "start": 5.7,
+          "end": 7.48,
+          "confidence": 0.837
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 9.24,
+      "end": 15.2,
+      "text": " حبّي ركب الفدا",
+      "tokens": [
+        50714,
+        11331,
+        3555,
+        11703,
+        1829,
+        12602,
+        4117,
+        3555,
+        27188,
+        28259,
+        51114
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5114130362486228,
+      "compression_ratio": 1.1842105263157894,
+      "no_speech_prob": 0.7993651032447815,
+      "confidence": 0.829,
+      "words": [
+        {
+          "text": "حبّي",
+          "start": 9.24,
+          "end": 12.58,
+          "confidence": 0.875
+        },
+        {
+          "text": "ركب",
+          "start": 12.58,
+          "end": 13.76,
+          "confidence": 0.853
+        },
+        {
+          "text": "الفدا",
+          "start": 13.76,
+          "end": 15.2,
+          "confidence": 0.711
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 18.86,
+      "end": 23.42,
+      "text": " وطلّبي سأر الشاهد",
+      "tokens": [
+        51114,
+        4032,
+        9566,
+        1211,
+        11703,
+        21292,
+        8608,
+        10721,
+        2288,
+        25124,
+        40294,
+        3215,
+        51514
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5114130362486228,
+      "compression_ratio": 1.1842105263157894,
+      "no_speech_prob": 0.7993651032447815,
+      "confidence": 0.587,
+      "words": [
+        {
+          "text": "وطلّبي",
+          "start": 18.86,
+          "end": 20.68,
+          "confidence": 0.54
+        },
+        {
+          "text": "سأر",
+          "start": 20.68,
+          "end": 21.78,
+          "confidence": 0.94
+        },
+        {
+          "text": "الشاهد",
+          "start": 21.78,
+          "end": 23.42,
+          "confidence": 0.421
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 2300,
+      "start": 24.2,
+      "end": 28.96,
+      "text": " وطلّبي سأر الشاهد",
+      "tokens": [
+        50414,
+        4032,
+        9566,
+        1211,
+        11703,
+        21292,
+        8608,
+        10721,
+        2288,
+        25124,
+        40294,
+        3215,
+        50714
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.24054829042349288,
+      "compression_ratio": 1.3675213675213675,
+      "no_speech_prob": 0.008175775408744812,
+      "confidence": 0.875,
+      "words": [
+        {
+          "text": "وطلّبي",
+          "start": 24.2,
+          "end": 25.98,
+          "confidence": 0.799
+        },
+        {
+          "text": "سأر",
+          "start": 25.98,
+          "end": 27.12,
+          "confidence": 0.95
+        },
+        {
+          "text": "الشاهد",
+          "start": 27.12,
+          "end": 28.96,
+          "confidence": 0.936
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 2300,
+      "start": 30.88,
+      "end": 33.34,
+      "text": " لمتى سنضل رقودا",
+      "tokens": [
+        50714,
+        32767,
+        49975,
+        8608,
+        1863,
+        11242,
+        1211,
+        12602,
+        4587,
+        23328,
+        995,
+        50864
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.24054829042349288,
+      "compression_ratio": 1.3675213675213675,
+      "no_speech_prob": 0.008175775408744812,
+      "confidence": 0.714,
+      "words": [
+        {
+          "text": "لمتى",
+          "start": 30.88,
+          "end": 31.48,
+          "confidence": 0.692
+        },
+        {
+          "text": "سنضل",
+          "start": 31.48,
+          "end": 32.34,
+          "confidence": 0.754
+        },
+        {
+          "text": "رقودا",
+          "start": 32.34,
+          "end": 33.34,
+          "confidence": 0.686
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 2300,
+      "start": 33.36,
+      "end": 35.88,
+      "text": " نغرق في النوم ونشخر",
+      "tokens": [
+        50864,
+        8717,
+        17082,
+        2288,
+        4587,
+        8978,
+        28239,
+        20498,
+        4032,
+        1863,
+        8592,
+        34740,
+        51014
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.24054829042349288,
+      "compression_ratio": 1.3675213675213675,
+      "no_speech_prob": 0.008175775408744812,
+      "confidence": 0.926,
+      "words": [
+        {
+          "text": "نغرق",
+          "start": 33.36,
+          "end": 34.22,
+          "confidence": 0.901
+        },
+        {
+          "text": "في",
+          "start": 34.22,
+          "end": 34.44,
+          "confidence": 0.873
+        },
+        {
+          "text": "النوم",
+          "start": 34.44,
+          "end": 35.04,
+          "confidence": 0.974
+        },
+        {
+          "text": "ونشخر",
+          "start": 35.04,
+          "end": 35.88,
+          "confidence": 0.942
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 2300,
+      "start": 36.24,
+      "end": 38.72,
+      "text": " وعن الآذان نسمّه",
+      "tokens": [
+        51014,
+        4032,
+        3615,
+        1863,
+        6024,
+        95,
+        8848,
+        7649,
+        8717,
+        38251,
+        11703,
+        3224,
+        51164
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.24054829042349288,
+      "compression_ratio": 1.3675213675213675,
+      "no_speech_prob": 0.008175775408744812,
+      "confidence": 0.765,
+      "words": [
+        {
+          "text": "وعن",
+          "start": 36.24,
+          "end": 36.76,
+          "confidence": 0.923
+        },
+        {
+          "text": "الآذان",
+          "start": 36.76,
+          "end": 37.72,
+          "confidence": 0.82
+        },
+        {
+          "text": "نسمّه",
+          "start": 37.72,
+          "end": 38.72,
+          "confidence": 0.619
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 2300,
+      "start": 38.88,
+      "end": 41.3,
+      "text": " ونغمّض كي لا نمسر",
+      "tokens": [
+        51164,
+        4032,
+        1863,
+        17082,
+        2304,
+        11703,
+        11242,
+        9122,
+        1829,
+        20193,
+        8717,
+        2304,
+        3794,
+        2288,
+        51264
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.24054829042349288,
+      "compression_ratio": 1.3675213675213675,
+      "no_speech_prob": 0.008175775408744812,
+      "confidence": 0.79,
+      "words": [
+        {
+          "text": "ونغمّض",
+          "start": 38.88,
+          "end": 39.9,
+          "confidence": 0.91
+        },
+        {
+          "text": "كي",
+          "start": 39.9,
+          "end": 40.28,
+          "confidence": 0.833
+        },
+        {
+          "text": "لا",
+          "start": 40.28,
+          "end": 40.56,
+          "confidence": 0.804
+        },
+        {
+          "text": "نمسر",
+          "start": 40.56,
+          "end": 41.3,
+          "confidence": 0.619
+        }
+      ]
+    }
+  ],
+  "language": "Arabic"
+}
\ No newline at end of file
diff --git a/tests/expected/corner_cases/issue24_empty.wav.words.json b/tests/expected/corner_cases/issue24_empty.wav.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..2fb877fdb2d3636b652056874c7de84a30c4567f
--- /dev/null
+++ b/tests/expected/corner_cases/issue24_empty.wav.words.json
@@ -0,0 +1,992 @@
+{
+  "text": " I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.0,
+      "end": 0.96,
+      "text": " I'm sorry.",
+      "tokens": [
+        50363,
+        314,
+        1101,
+        7926,
+        13,
+        50413
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.102,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 0.0,
+          "end": 0.94,
+          "confidence": 0.105
+        },
+        {
+          "text": "sorry",
+          "start": 0.94,
+          "end": 0.96,
+          "confidence": 0.096
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 0.96,
+      "end": 2.38,
+      "text": " I'm sorry.",
+      "tokens": [
+        50413,
+        314,
+        1101,
+        7926,
+        13,
+        50463
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.405,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 0.96,
+          "end": 2.26,
+          "confidence": 0.353
+        },
+        {
+          "text": "sorry",
+          "start": 2.26,
+          "end": 2.38,
+          "confidence": 0.533
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 2.38,
+      "end": 2.42,
+      "text": " I'm sorry.",
+      "tokens": [
+        50463,
+        314,
+        1101,
+        7926,
+        13,
+        50513
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.611,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 2.38,
+          "end": 2.4,
+          "confidence": 0.551
+        },
+        {
+          "text": "sorry",
+          "start": 2.4,
+          "end": 2.42,
+          "confidence": 0.752
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 3.0,
+      "end": 3.24,
+      "text": " I'm sorry.",
+      "tokens": [
+        50513,
+        314,
+        1101,
+        7926,
+        13,
+        50563
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.765,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 3.0,
+          "end": 3.22,
+          "confidence": 0.714
+        },
+        {
+          "text": "sorry",
+          "start": 3.22,
+          "end": 3.24,
+          "confidence": 0.877
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 4.36,
+      "end": 4.48,
+      "text": " I'm sorry.",
+      "tokens": [
+        50563,
+        314,
+        1101,
+        7926,
+        13,
+        50613
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.849,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 4.36,
+          "end": 4.42,
+          "confidence": 0.804
+        },
+        {
+          "text": "sorry",
+          "start": 4.42,
+          "end": 4.48,
+          "confidence": 0.947
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 0,
+      "start": 5.5,
+      "end": 5.78,
+      "text": " I'm sorry.",
+      "tokens": [
+        50613,
+        314,
+        1101,
+        7926,
+        13,
+        50663
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.89,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 5.5,
+          "end": 5.54,
+          "confidence": 0.852
+        },
+        {
+          "text": "sorry",
+          "start": 5.54,
+          "end": 5.78,
+          "confidence": 0.972
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 0,
+      "start": 5.92,
+      "end": 6.8,
+      "text": " I'm sorry.",
+      "tokens": [
+        50663,
+        314,
+        1101,
+        7926,
+        13,
+        50713
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.918,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 5.92,
+          "end": 6.14,
+          "confidence": 0.887
+        },
+        {
+          "text": "sorry",
+          "start": 6.14,
+          "end": 6.8,
+          "confidence": 0.983
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 0,
+      "start": 7.5,
+      "end": 8.5,
+      "text": " I'm sorry.",
+      "tokens": [
+        50713,
+        314,
+        1101,
+        7926,
+        13,
+        50763
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.941,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 7.5,
+          "end": 8.48,
+          "confidence": 0.919
+        },
+        {
+          "text": "sorry",
+          "start": 8.48,
+          "end": 8.5,
+          "confidence": 0.988
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 0,
+      "start": 8.56,
+      "end": 9.48,
+      "text": " I'm sorry.",
+      "tokens": [
+        50763,
+        314,
+        1101,
+        7926,
+        13,
+        50813
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.95,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 8.56,
+          "end": 9.0,
+          "confidence": 0.93
+        },
+        {
+          "text": "sorry",
+          "start": 9.0,
+          "end": 9.48,
+          "confidence": 0.991
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 0,
+      "start": 9.54,
+      "end": 10.38,
+      "text": " I'm sorry.",
+      "tokens": [
+        50813,
+        314,
+        1101,
+        7926,
+        13,
+        50863
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.963,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 9.54,
+          "end": 9.56,
+          "confidence": 0.948
+        },
+        {
+          "text": "sorry",
+          "start": 9.56,
+          "end": 10.38,
+          "confidence": 0.993
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 0,
+      "start": 10.38,
+      "end": 11.36,
+      "text": " I'm sorry.",
+      "tokens": [
+        50863,
+        314,
+        1101,
+        7926,
+        13,
+        50913
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.968,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 10.38,
+          "end": 11.34,
+          "confidence": 0.955
+        },
+        {
+          "text": "sorry",
+          "start": 11.34,
+          "end": 11.36,
+          "confidence": 0.994
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 0,
+      "start": 11.36,
+      "end": 12.48,
+      "text": " I'm sorry.",
+      "tokens": [
+        50913,
+        314,
+        1101,
+        7926,
+        13,
+        50963
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.978,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 11.36,
+          "end": 12.06,
+          "confidence": 0.969
+        },
+        {
+          "text": "sorry",
+          "start": 12.06,
+          "end": 12.48,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 0,
+      "start": 12.54,
+      "end": 12.93,
+      "text": " I'm sorry.",
+      "tokens": [
+        50963,
+        314,
+        1101,
+        7926,
+        13,
+        51013
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.98,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 12.54,
+          "end": 12.56,
+          "confidence": 0.972
+        },
+        {
+          "text": "sorry",
+          "start": 12.56,
+          "end": 12.93,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 0,
+      "start": 12.93,
+      "end": 14.5,
+      "text": " I'm sorry.",
+      "tokens": [
+        51013,
+        314,
+        1101,
+        7926,
+        13,
+        51063
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.979,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 12.93,
+          "end": 14.48,
+          "confidence": 0.971
+        },
+        {
+          "text": "sorry",
+          "start": 14.48,
+          "end": 14.5,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 0,
+      "start": 14.5,
+      "end": 15.46,
+      "text": " I'm sorry.",
+      "tokens": [
+        51063,
+        314,
+        1101,
+        7926,
+        13,
+        51113
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.982,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 14.5,
+          "end": 15.42,
+          "confidence": 0.974
+        },
+        {
+          "text": "sorry",
+          "start": 15.42,
+          "end": 15.46,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 0,
+      "start": 15.46,
+      "end": 16.48,
+      "text": " I'm sorry.",
+      "tokens": [
+        51113,
+        314,
+        1101,
+        7926,
+        13,
+        51163
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.983,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 15.46,
+          "end": 16.4,
+          "confidence": 0.976
+        },
+        {
+          "text": "sorry",
+          "start": 16.4,
+          "end": 16.48,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 0,
+      "start": 16.48,
+      "end": 17.5,
+      "text": " I'm sorry.",
+      "tokens": [
+        51163,
+        314,
+        1101,
+        7926,
+        13,
+        51213
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.982,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 16.48,
+          "end": 17.48,
+          "confidence": 0.975
+        },
+        {
+          "text": "sorry",
+          "start": 17.48,
+          "end": 17.5,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 17,
+      "seek": 0,
+      "start": 17.54,
+      "end": 18.5,
+      "text": " I'm sorry.",
+      "tokens": [
+        51213,
+        314,
+        1101,
+        7926,
+        13,
+        51263
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.984,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 17.54,
+          "end": 18.48,
+          "confidence": 0.978
+        },
+        {
+          "text": "sorry",
+          "start": 18.48,
+          "end": 18.5,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 18,
+      "seek": 0,
+      "start": 18.5,
+      "end": 19.48,
+      "text": " I'm sorry.",
+      "tokens": [
+        51263,
+        314,
+        1101,
+        7926,
+        13,
+        51313
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.984,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 18.5,
+          "end": 19.34,
+          "confidence": 0.978
+        },
+        {
+          "text": "sorry",
+          "start": 19.34,
+          "end": 19.48,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 19,
+      "seek": 0,
+      "start": 19.64,
+      "end": 20.32,
+      "text": " I'm sorry.",
+      "tokens": [
+        51313,
+        314,
+        1101,
+        7926,
+        13,
+        51363
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.986,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 19.64,
+          "end": 19.68,
+          "confidence": 0.98
+        },
+        {
+          "text": "sorry",
+          "start": 19.68,
+          "end": 20.32,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 20,
+      "seek": 0,
+      "start": 20.32,
+      "end": 20.36,
+      "text": " I'm sorry.",
+      "tokens": [
+        51363,
+        314,
+        1101,
+        7926,
+        13,
+        51413
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.986,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 20.32,
+          "end": 20.34,
+          "confidence": 0.98
+        },
+        {
+          "text": "sorry",
+          "start": 20.34,
+          "end": 20.36,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 21,
+      "seek": 0,
+      "start": 21.58,
+      "end": 22.5,
+      "text": " I'm sorry.",
+      "tokens": [
+        51413,
+        314,
+        1101,
+        7926,
+        13,
+        51463
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.987,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 21.58,
+          "end": 22.48,
+          "confidence": 0.983
+        },
+        {
+          "text": "sorry",
+          "start": 22.48,
+          "end": 22.5,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 22,
+      "seek": 0,
+      "start": 22.58,
+      "end": 23.46,
+      "text": " I'm sorry.",
+      "tokens": [
+        51463,
+        314,
+        1101,
+        7926,
+        13,
+        51513
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.987,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 22.58,
+          "end": 22.6,
+          "confidence": 0.982
+        },
+        {
+          "text": "sorry",
+          "start": 22.6,
+          "end": 23.46,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 23,
+      "seek": 0,
+      "start": 23.46,
+      "end": 23.7,
+      "text": " I'm sorry.",
+      "tokens": [
+        51513,
+        314,
+        1101,
+        7926,
+        13,
+        51563
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.988,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 23.46,
+          "end": 23.48,
+          "confidence": 0.984
+        },
+        {
+          "text": "sorry",
+          "start": 23.48,
+          "end": 23.7,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 24,
+      "seek": 0,
+      "start": 24.5,
+      "end": 24.54,
+      "text": " I'm sorry.",
+      "tokens": [
+        51563,
+        314,
+        1101,
+        7926,
+        13,
+        51613
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.988,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 24.5,
+          "end": 24.52,
+          "confidence": 0.984
+        },
+        {
+          "text": "sorry",
+          "start": 24.52,
+          "end": 24.54,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 25,
+      "seek": 0,
+      "start": 24.54,
+      "end": 26.48,
+      "text": " I'm sorry.",
+      "tokens": [
+        51613,
+        314,
+        1101,
+        7926,
+        13,
+        51663
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.985,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 24.54,
+          "end": 26.26,
+          "confidence": 0.979
+        },
+        {
+          "text": "sorry",
+          "start": 26.26,
+          "end": 26.48,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 26,
+      "seek": 0,
+      "start": 26.48,
+      "end": 27.5,
+      "text": " I'm sorry.",
+      "tokens": [
+        51663,
+        314,
+        1101,
+        7926,
+        13,
+        51713
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.982,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 26.48,
+          "end": 27.48,
+          "confidence": 0.974
+        },
+        {
+          "text": "sorry",
+          "start": 27.48,
+          "end": 27.5,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 27,
+      "seek": 0,
+      "start": 27.5,
+      "end": 28.46,
+      "text": " I'm sorry.",
+      "tokens": [
+        51713,
+        314,
+        1101,
+        7926,
+        13,
+        51763
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.975,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 27.5,
+          "end": 28.44,
+          "confidence": 0.964
+        },
+        {
+          "text": "sorry",
+          "start": 28.44,
+          "end": 28.46,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 28,
+      "seek": 0,
+      "start": 28.46,
+      "end": 29.32,
+      "text": " I'm sorry.",
+      "tokens": [
+        51763,
+        314,
+        1101,
+        7926,
+        13,
+        51813
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12369282679124312,
+      "compression_ratio": 13.25,
+      "no_speech_prob": 0.7658452391624451,
+      "confidence": 0.954,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 28.46,
+          "end": 29.3,
+          "confidence": 0.933
+        },
+        {
+          "text": "sorry",
+          "start": 29.3,
+          "end": 29.32,
+          "confidence": 0.998
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/corner_cases/large-v2.accurate_gloria.mp3.words.json b/tests/expected/corner_cases/large-v2.accurate_gloria.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..841b9608aec18ab79018280551a269d44efac00d
--- /dev/null
+++ b/tests/expected/corner_cases/large-v2.accurate_gloria.mp3.words.json
@@ -0,0 +1,540 @@
+{
+  "text": " Ella, my glorious love, how are you? Oh, I'm okay. I will be. I said she could stay with us tomorrow just until she feels better. Of course she can. No, this won't be for long. Well, if you can stay as long as you want, my love. I've really missed you. Pops.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.0,
+      "end": 6.28,
+      "text": " Ella, my glorious love, how are you?",
+      "tokens": [
+        50364,
+        29261,
+        11,
+        452,
+        24026,
+        959,
+        11,
+        577,
+        366,
+        291,
+        30,
+        50664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3579153639546941,
+      "compression_ratio": 1.425414364640884,
+      "no_speech_prob": 0.24429768323898315,
+      "confidence": 0.452,
+      "words": [
+        {
+          "text": "Ella,",
+          "start": 0.0,
+          "end": 1.68,
+          "confidence": 0.126
+        },
+        {
+          "text": "my",
+          "start": 1.94,
+          "end": 2.7,
+          "confidence": 0.368
+        },
+        {
+          "text": "glorious",
+          "start": 2.7,
+          "end": 3.5,
+          "confidence": 0.729
+        },
+        {
+          "text": "love,",
+          "start": 3.5,
+          "end": 4.18,
+          "confidence": 0.432
+        },
+        {
+          "text": "how",
+          "start": 4.94,
+          "end": 5.66,
+          "confidence": 0.693
+        },
+        {
+          "text": "are",
+          "start": 5.66,
+          "end": 6.02,
+          "confidence": 0.902
+        },
+        {
+          "text": "you?",
+          "start": 6.02,
+          "end": 6.28,
+          "confidence": 0.845
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 6.28,
+      "end": 9.18,
+      "text": " Oh, I'm okay. I will be.",
+      "tokens": [
+        50664,
+        876,
+        11,
+        286,
+        478,
+        1392,
+        13,
+        286,
+        486,
+        312,
+        13,
+        50814
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3579153639546941,
+      "compression_ratio": 1.425414364640884,
+      "no_speech_prob": 0.24429768323898315,
+      "confidence": 0.68,
+      "words": [
+        {
+          "text": "Oh,",
+          "start": 6.28,
+          "end": 6.6,
+          "confidence": 0.427
+        },
+        {
+          "text": "I'm",
+          "start": 6.68,
+          "end": 7.02,
+          "confidence": 0.958
+        },
+        {
+          "text": "okay.",
+          "start": 7.02,
+          "end": 7.64,
+          "confidence": 0.605
+        },
+        {
+          "text": "I",
+          "start": 8.3,
+          "end": 8.58,
+          "confidence": 0.562
+        },
+        {
+          "text": "will",
+          "start": 8.58,
+          "end": 8.86,
+          "confidence": 0.813
+        },
+        {
+          "text": "be.",
+          "start": 8.86,
+          "end": 9.18,
+          "confidence": 0.871
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 9.18,
+      "end": 11.48,
+      "text": " I said she could stay with us tomorrow just until she feels better.",
+      "tokens": [
+        50814,
+        286,
+        848,
+        750,
+        727,
+        1754,
+        365,
+        505,
+        4153,
+        445,
+        1826,
+        750,
+        3417,
+        1101,
+        13,
+        50964
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3579153639546941,
+      "compression_ratio": 1.425414364640884,
+      "no_speech_prob": 0.24429768323898315,
+      "confidence": 0.571,
+      "words": [
+        {
+          "text": "I",
+          "start": 9.18,
+          "end": 9.44,
+          "confidence": 0.66
+        },
+        {
+          "text": "said",
+          "start": 9.44,
+          "end": 9.62,
+          "confidence": 0.869
+        },
+        {
+          "text": "she",
+          "start": 9.62,
+          "end": 9.76,
+          "confidence": 0.748
+        },
+        {
+          "text": "could",
+          "start": 9.76,
+          "end": 9.88,
+          "confidence": 0.813
+        },
+        {
+          "text": "stay",
+          "start": 9.88,
+          "end": 10.08,
+          "confidence": 0.925
+        },
+        {
+          "text": "with",
+          "start": 10.08,
+          "end": 10.22,
+          "confidence": 0.808
+        },
+        {
+          "text": "us",
+          "start": 10.22,
+          "end": 10.34,
+          "confidence": 0.628
+        },
+        {
+          "text": "tomorrow",
+          "start": 10.34,
+          "end": 10.56,
+          "confidence": 0.219
+        },
+        {
+          "text": "just",
+          "start": 10.56,
+          "end": 10.74,
+          "confidence": 0.067
+        },
+        {
+          "text": "until",
+          "start": 10.74,
+          "end": 10.86,
+          "confidence": 0.4
+        },
+        {
+          "text": "she",
+          "start": 10.86,
+          "end": 10.98,
+          "confidence": 0.803
+        },
+        {
+          "text": "feels",
+          "start": 10.98,
+          "end": 11.18,
+          "confidence": 0.788
+        },
+        {
+          "text": "better.",
+          "start": 11.18,
+          "end": 11.48,
+          "confidence": 0.807
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 11.5,
+      "end": 13.34,
+      "text": " Of course she can.",
+      "tokens": [
+        50964,
+        2720,
+        1164,
+        750,
+        393,
+        13,
+        51014
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3579153639546941,
+      "compression_ratio": 1.425414364640884,
+      "no_speech_prob": 0.24429768323898315,
+      "confidence": 0.333,
+      "words": [
+        {
+          "text": "Of",
+          "start": 11.5,
+          "end": 12.1,
+          "confidence": 0.123
+        },
+        {
+          "text": "course",
+          "start": 12.1,
+          "end": 12.6,
+          "confidence": 0.86
+        },
+        {
+          "text": "she",
+          "start": 12.6,
+          "end": 12.88,
+          "confidence": 0.085
+        },
+        {
+          "text": "can.",
+          "start": 12.88,
+          "end": 13.34,
+          "confidence": 0.674
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 13.34,
+      "end": 15.2,
+      "text": " No, this won't be for long.",
+      "tokens": [
+        51014,
+        883,
+        11,
+        341,
+        1582,
+        380,
+        312,
+        337,
+        938,
+        13,
+        51114
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3579153639546941,
+      "compression_ratio": 1.425414364640884,
+      "no_speech_prob": 0.24429768323898315,
+      "confidence": 0.649,
+      "words": [
+        {
+          "text": "No,",
+          "start": 13.34,
+          "end": 13.78,
+          "confidence": 0.328
+        },
+        {
+          "text": "this",
+          "start": 13.9,
+          "end": 14.24,
+          "confidence": 0.419
+        },
+        {
+          "text": "won't",
+          "start": 14.24,
+          "end": 14.54,
+          "confidence": 0.917
+        },
+        {
+          "text": "be",
+          "start": 14.54,
+          "end": 14.68,
+          "confidence": 0.906
+        },
+        {
+          "text": "for",
+          "start": 14.68,
+          "end": 14.88,
+          "confidence": 0.884
+        },
+        {
+          "text": "long.",
+          "start": 14.88,
+          "end": 15.2,
+          "confidence": 0.823
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 0,
+      "start": 15.2,
+      "end": 17.44,
+      "text": " Well, if you can stay as long as you want, my love.",
+      "tokens": [
+        51114,
+        1042,
+        11,
+        498,
+        291,
+        393,
+        1754,
+        382,
+        938,
+        382,
+        291,
+        528,
+        11,
+        452,
+        959,
+        13,
+        51214
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3579153639546941,
+      "compression_ratio": 1.425414364640884,
+      "no_speech_prob": 0.24429768323898315,
+      "confidence": 0.69,
+      "words": [
+        {
+          "text": "Well,",
+          "start": 15.2,
+          "end": 15.46,
+          "confidence": 0.553
+        },
+        {
+          "text": "if",
+          "start": 15.52,
+          "end": 15.6,
+          "confidence": 0.084
+        },
+        {
+          "text": "you",
+          "start": 15.6,
+          "end": 15.68,
+          "confidence": 0.898
+        },
+        {
+          "text": "can",
+          "start": 15.68,
+          "end": 15.8,
+          "confidence": 0.827
+        },
+        {
+          "text": "stay",
+          "start": 15.8,
+          "end": 16.04,
+          "confidence": 0.922
+        },
+        {
+          "text": "as",
+          "start": 16.04,
+          "end": 16.18,
+          "confidence": 0.896
+        },
+        {
+          "text": "long",
+          "start": 16.18,
+          "end": 16.32,
+          "confidence": 0.893
+        },
+        {
+          "text": "as",
+          "start": 16.32,
+          "end": 16.46,
+          "confidence": 0.902
+        },
+        {
+          "text": "you",
+          "start": 16.46,
+          "end": 16.58,
+          "confidence": 0.905
+        },
+        {
+          "text": "want,",
+          "start": 16.58,
+          "end": 16.76,
+          "confidence": 0.731
+        },
+        {
+          "text": "my",
+          "start": 16.88,
+          "end": 17.02,
+          "confidence": 0.901
+        },
+        {
+          "text": "love.",
+          "start": 17.02,
+          "end": 17.44,
+          "confidence": 0.831
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 0,
+      "start": 17.44,
+      "end": 18.96,
+      "text": " I've really missed you.",
+      "tokens": [
+        51214,
+        286,
+        600,
+        534,
+        6721,
+        291,
+        13,
+        51314
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3579153639546941,
+      "compression_ratio": 1.425414364640884,
+      "no_speech_prob": 0.24429768323898315,
+      "confidence": 0.529,
+      "words": [
+        {
+          "text": "I've",
+          "start": 17.44,
+          "end": 17.58,
+          "confidence": 0.309
+        },
+        {
+          "text": "really",
+          "start": 17.58,
+          "end": 18.18,
+          "confidence": 0.763
+        },
+        {
+          "text": "missed",
+          "start": 18.18,
+          "end": 18.68,
+          "confidence": 0.778
+        },
+        {
+          "text": "you.",
+          "start": 18.68,
+          "end": 18.96,
+          "confidence": 0.622
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 0,
+      "start": 19.58,
+      "end": 20.12,
+      "text": " Pops.",
+      "tokens": [
+        51314,
+        430,
+        3370,
+        13,
+        51364
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3579153639546941,
+      "compression_ratio": 1.425414364640884,
+      "no_speech_prob": 0.24429768323898315,
+      "confidence": 0.02,
+      "words": [
+        {
+          "text": "Pops.",
+          "start": 19.58,
+          "end": 20.12,
+          "confidence": 0.02
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/corner_cases/large-v2.efficient_gloria.mp3.words.json b/tests/expected/corner_cases/large-v2.efficient_gloria.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..01b1c82f79a532c844d5b50fb036a4d1ce190ef2
--- /dev/null
+++ b/tests/expected/corner_cases/large-v2.efficient_gloria.mp3.words.json
@@ -0,0 +1,564 @@
+{
+  "text": " Ella, my glorious love. How are you? Oh, I'm okay. I will be. I said she could stay with us tomorrow, just until she feels better. Of course she can. No, this won't be for long. Well, if you can stay as long as you want, my love. I really missed you. I agree.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.0,
+      "end": 4.02,
+      "text": " Ella, my glorious love.",
+      "tokens": [
+        50364,
+        29261,
+        11,
+        452,
+        24026,
+        959,
+        13,
+        50564
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36081909347366503,
+      "compression_ratio": 1.446927374301676,
+      "no_speech_prob": 0.244294673204422,
+      "confidence": 0.477,
+      "words": [
+        {
+          "text": "Ella,",
+          "start": 0.0,
+          "end": 1.68,
+          "confidence": 0.128
+        },
+        {
+          "text": "my",
+          "start": 1.92,
+          "end": 2.1,
+          "confidence": 0.733
+        },
+        {
+          "text": "glorious",
+          "start": 2.1,
+          "end": 3.36,
+          "confidence": 0.625
+        },
+        {
+          "text": "love.",
+          "start": 3.36,
+          "end": 4.02,
+          "confidence": 0.883
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 5.46,
+      "end": 6.24,
+      "text": " How are you?",
+      "tokens": [
+        50564,
+        1012,
+        366,
+        291,
+        30,
+        50664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36081909347366503,
+      "compression_ratio": 1.446927374301676,
+      "no_speech_prob": 0.244294673204422,
+      "confidence": 0.682,
+      "words": [
+        {
+          "text": "How",
+          "start": 5.46,
+          "end": 5.62,
+          "confidence": 0.454
+        },
+        {
+          "text": "are",
+          "start": 5.62,
+          "end": 6.02,
+          "confidence": 0.893
+        },
+        {
+          "text": "you?",
+          "start": 6.02,
+          "end": 6.24,
+          "confidence": 0.783
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 6.32,
+      "end": 9.12,
+      "text": " Oh, I'm okay. I will be.",
+      "tokens": [
+        50664,
+        876,
+        11,
+        286,
+        478,
+        1392,
+        13,
+        286,
+        486,
+        312,
+        13,
+        50814
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36081909347366503,
+      "compression_ratio": 1.446927374301676,
+      "no_speech_prob": 0.244294673204422,
+      "confidence": 0.73,
+      "words": [
+        {
+          "text": "Oh,",
+          "start": 6.32,
+          "end": 6.66,
+          "confidence": 0.479
+        },
+        {
+          "text": "I'm",
+          "start": 6.74,
+          "end": 7.02,
+          "confidence": 0.971
+        },
+        {
+          "text": "okay.",
+          "start": 7.02,
+          "end": 7.7,
+          "confidence": 0.476
+        },
+        {
+          "text": "I",
+          "start": 8.14,
+          "end": 8.56,
+          "confidence": 0.714
+        },
+        {
+          "text": "will",
+          "start": 8.56,
+          "end": 8.82,
+          "confidence": 0.795
+        },
+        {
+          "text": "be.",
+          "start": 8.82,
+          "end": 9.12,
+          "confidence": 0.906
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 9.32,
+      "end": 11.42,
+      "text": " I said she could stay with us tomorrow, just until she feels better.",
+      "tokens": [
+        50814,
+        286,
+        848,
+        750,
+        727,
+        1754,
+        365,
+        505,
+        4153,
+        11,
+        445,
+        1826,
+        750,
+        3417,
+        1101,
+        13,
+        50914
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36081909347366503,
+      "compression_ratio": 1.446927374301676,
+      "no_speech_prob": 0.244294673204422,
+      "confidence": 0.723,
+      "words": [
+        {
+          "text": "I",
+          "start": 9.32,
+          "end": 9.48,
+          "confidence": 0.878
+        },
+        {
+          "text": "said",
+          "start": 9.48,
+          "end": 9.62,
+          "confidence": 0.862
+        },
+        {
+          "text": "she",
+          "start": 9.62,
+          "end": 9.76,
+          "confidence": 0.762
+        },
+        {
+          "text": "could",
+          "start": 9.76,
+          "end": 9.88,
+          "confidence": 0.801
+        },
+        {
+          "text": "stay",
+          "start": 9.88,
+          "end": 10.08,
+          "confidence": 0.921
+        },
+        {
+          "text": "with",
+          "start": 10.08,
+          "end": 10.22,
+          "confidence": 0.812
+        },
+        {
+          "text": "us",
+          "start": 10.22,
+          "end": 10.36,
+          "confidence": 0.848
+        },
+        {
+          "text": "tomorrow,",
+          "start": 10.36,
+          "end": 10.56,
+          "confidence": 0.515
+        },
+        {
+          "text": "just",
+          "start": 10.74,
+          "end": 10.76,
+          "confidence": 0.433
+        },
+        {
+          "text": "until",
+          "start": 10.76,
+          "end": 10.86,
+          "confidence": 0.439
+        },
+        {
+          "text": "she",
+          "start": 10.86,
+          "end": 10.98,
+          "confidence": 0.809
+        },
+        {
+          "text": "feels",
+          "start": 10.98,
+          "end": 11.16,
+          "confidence": 0.777
+        },
+        {
+          "text": "better.",
+          "start": 11.16,
+          "end": 11.42,
+          "confidence": 0.822
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 11.9,
+      "end": 13.06,
+      "text": " Of course she can.",
+      "tokens": [
+        50914,
+        2720,
+        1164,
+        750,
+        393,
+        13,
+        51014
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36081909347366503,
+      "compression_ratio": 1.446927374301676,
+      "no_speech_prob": 0.244294673204422,
+      "confidence": 0.761,
+      "words": [
+        {
+          "text": "Of",
+          "start": 11.9,
+          "end": 12.16,
+          "confidence": 0.562
+        },
+        {
+          "text": "course",
+          "start": 12.16,
+          "end": 12.54,
+          "confidence": 0.875
+        },
+        {
+          "text": "she",
+          "start": 12.54,
+          "end": 12.8,
+          "confidence": 0.758
+        },
+        {
+          "text": "can.",
+          "start": 12.8,
+          "end": 13.06,
+          "confidence": 0.899
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 0,
+      "start": 13.7,
+      "end": 15.2,
+      "text": " No, this won't be for long.",
+      "tokens": [
+        51014,
+        883,
+        11,
+        341,
+        1582,
+        380,
+        312,
+        337,
+        938,
+        13,
+        51114
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36081909347366503,
+      "compression_ratio": 1.446927374301676,
+      "no_speech_prob": 0.244294673204422,
+      "confidence": 0.774,
+      "words": [
+        {
+          "text": "No,",
+          "start": 13.7,
+          "end": 13.72,
+          "confidence": 0.381
+        },
+        {
+          "text": "this",
+          "start": 13.92,
+          "end": 14.26,
+          "confidence": 0.702
+        },
+        {
+          "text": "won't",
+          "start": 14.26,
+          "end": 14.54,
+          "confidence": 0.943
+        },
+        {
+          "text": "be",
+          "start": 14.54,
+          "end": 14.68,
+          "confidence": 0.898
+        },
+        {
+          "text": "for",
+          "start": 14.68,
+          "end": 14.86,
+          "confidence": 0.891
+        },
+        {
+          "text": "long.",
+          "start": 14.86,
+          "end": 15.2,
+          "confidence": 0.877
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 0,
+      "start": 15.3,
+      "end": 17.48,
+      "text": " Well, if you can stay as long as you want, my love.",
+      "tokens": [
+        51114,
+        1042,
+        11,
+        498,
+        291,
+        393,
+        1754,
+        382,
+        938,
+        382,
+        291,
+        528,
+        11,
+        452,
+        959,
+        13,
+        51214
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36081909347366503,
+      "compression_ratio": 1.446927374301676,
+      "no_speech_prob": 0.244294673204422,
+      "confidence": 0.836,
+      "words": [
+        {
+          "text": "Well,",
+          "start": 15.3,
+          "end": 15.46,
+          "confidence": 0.647
+        },
+        {
+          "text": "if",
+          "start": 15.52,
+          "end": 15.6,
+          "confidence": 0.615
+        },
+        {
+          "text": "you",
+          "start": 15.6,
+          "end": 15.68,
+          "confidence": 0.896
+        },
+        {
+          "text": "can",
+          "start": 15.68,
+          "end": 15.82,
+          "confidence": 0.851
+        },
+        {
+          "text": "stay",
+          "start": 15.82,
+          "end": 16.04,
+          "confidence": 0.924
+        },
+        {
+          "text": "as",
+          "start": 16.04,
+          "end": 16.2,
+          "confidence": 0.885
+        },
+        {
+          "text": "long",
+          "start": 16.2,
+          "end": 16.32,
+          "confidence": 0.883
+        },
+        {
+          "text": "as",
+          "start": 16.32,
+          "end": 16.48,
+          "confidence": 0.907
+        },
+        {
+          "text": "you",
+          "start": 16.48,
+          "end": 16.58,
+          "confidence": 0.899
+        },
+        {
+          "text": "want,",
+          "start": 16.58,
+          "end": 16.76,
+          "confidence": 0.81
+        },
+        {
+          "text": "my",
+          "start": 16.9,
+          "end": 17.02,
+          "confidence": 0.901
+        },
+        {
+          "text": "love.",
+          "start": 17.02,
+          "end": 17.48,
+          "confidence": 0.896
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 0,
+      "start": 17.66,
+      "end": 18.96,
+      "text": " I really missed you.",
+      "tokens": [
+        51214,
+        286,
+        534,
+        6721,
+        291,
+        13,
+        51314
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36081909347366503,
+      "compression_ratio": 1.446927374301676,
+      "no_speech_prob": 0.244294673204422,
+      "confidence": 0.479,
+      "words": [
+        {
+          "text": "I",
+          "start": 17.66,
+          "end": 17.86,
+          "confidence": 0.252
+        },
+        {
+          "text": "really",
+          "start": 17.86,
+          "end": 18.22,
+          "confidence": 0.447
+        },
+        {
+          "text": "missed",
+          "start": 18.22,
+          "end": 18.7,
+          "confidence": 0.653
+        },
+        {
+          "text": "you.",
+          "start": 18.7,
+          "end": 18.96,
+          "confidence": 0.717
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 0,
+      "start": 19.58,
+      "end": 20.6,
+      "text": " I agree.",
+      "tokens": [
+        51314,
+        286,
+        3986,
+        13,
+        51414
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36081909347366503,
+      "compression_ratio": 1.446927374301676,
+      "no_speech_prob": 0.244294673204422,
+      "confidence": 0.421,
+      "words": [
+        {
+          "text": "I",
+          "start": 19.58,
+          "end": 20.4,
+          "confidence": 0.403
+        },
+        {
+          "text": "agree.",
+          "start": 20.4,
+          "end": 20.6,
+          "confidence": 0.439
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/corner_cases/large_apollo11.mp3.words.json b/tests/expected/corner_cases/large_apollo11.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..c3a47745197c8551a120143206ea1eebd2b93ac2
--- /dev/null
+++ b/tests/expected/corner_cases/large_apollo11.mp3.words.json
@@ -0,0 +1,1208 @@
+{
+  "text": " Apollo 11, Houston. We got a recommendation for you on your DOJ's E-A limb, E-G-E-A's, over. Go ahead. Okay, we'd like to have, say, a selected one or two on the helmet. We're going to have an B1. And you could put the other one on Mike's helmet, we're still seeing the bleepers. Over. with a cover I tried it already. Okay fine, we weren't sure that this was a suggestion. We thought we'd uh... you could check it out. How much you've already done that. So uh... I guess whatever you can come up with, just let us know and... Okay there's no problem. Okay, there's no problem. We'll let you know where they end up. Nice.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.36,
+      "end": 6.96,
+      "text": " Apollo 11, Houston. We got a recommendation for you on your DOJ's E-A limb, E-G-E-A's, over.",
+      "tokens": [
+        50364,
+        25187,
+        2975,
+        11,
+        18717,
+        13,
+        492,
+        658,
+        257,
+        11879,
+        337,
+        291,
+        322,
+        428,
+        10699,
+        41,
+        311,
+        462,
+        12,
+        32,
+        30390,
+        11,
+        462,
+        12,
+        38,
+        12,
+        36,
+        12,
+        32,
+        311,
+        11,
+        670,
+        13,
+        50714
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6033297837382615,
+      "compression_ratio": 1.425,
+      "no_speech_prob": 0.3341304659843445,
+      "confidence": 0.595,
+      "words": [
+        {
+          "text": "Apollo",
+          "start": 0.36,
+          "end": 0.92,
+          "confidence": 0.79
+        },
+        {
+          "text": "11,",
+          "start": 0.92,
+          "end": 1.32,
+          "confidence": 0.877
+        },
+        {
+          "text": "Houston.",
+          "start": 1.5,
+          "end": 1.74,
+          "confidence": 0.827
+        },
+        {
+          "text": "We",
+          "start": 1.9,
+          "end": 1.94,
+          "confidence": 0.836
+        },
+        {
+          "text": "got",
+          "start": 1.94,
+          "end": 2.1,
+          "confidence": 0.639
+        },
+        {
+          "text": "a",
+          "start": 2.1,
+          "end": 2.3,
+          "confidence": 0.995
+        },
+        {
+          "text": "recommendation",
+          "start": 2.3,
+          "end": 3.08,
+          "confidence": 0.709
+        },
+        {
+          "text": "for",
+          "start": 3.08,
+          "end": 3.46,
+          "confidence": 0.856
+        },
+        {
+          "text": "you",
+          "start": 3.46,
+          "end": 3.62,
+          "confidence": 0.859
+        },
+        {
+          "text": "on",
+          "start": 3.62,
+          "end": 3.76,
+          "confidence": 0.87
+        },
+        {
+          "text": "your",
+          "start": 3.76,
+          "end": 4.06,
+          "confidence": 0.767
+        },
+        {
+          "text": "DOJ's",
+          "start": 4.06,
+          "end": 4.88,
+          "confidence": 0.163
+        },
+        {
+          "text": "E-A",
+          "start": 4.88,
+          "end": 5.3,
+          "confidence": 0.408
+        },
+        {
+          "text": "limb,",
+          "start": 5.3,
+          "end": 5.62,
+          "confidence": 0.264
+        },
+        {
+          "text": "E-G-E-A's,",
+          "start": 5.76,
+          "end": 6.8,
+          "confidence": 0.768
+        },
+        {
+          "text": "over.",
+          "start": 6.82,
+          "end": 6.96,
+          "confidence": 0.817
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 10.74,
+      "end": 11.14,
+      "text": " Go ahead.",
+      "tokens": [
+        50864,
+        1037,
+        2286,
+        13,
+        50914
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6033297837382615,
+      "compression_ratio": 1.425,
+      "no_speech_prob": 0.3341304659843445,
+      "confidence": 0.85,
+      "words": [
+        {
+          "text": "Go",
+          "start": 10.74,
+          "end": 10.98,
+          "confidence": 0.842
+        },
+        {
+          "text": "ahead.",
+          "start": 10.98,
+          "end": 11.14,
+          "confidence": 0.858
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 11.88,
+      "end": 17.3,
+      "text": " Okay, we'd like to have, say, a selected one or two on the helmet.",
+      "tokens": [
+        50914,
+        1033,
+        11,
+        321,
+        1116,
+        411,
+        281,
+        362,
+        11,
+        584,
+        11,
+        257,
+        8209,
+        472,
+        420,
+        732,
+        322,
+        264,
+        15922,
+        13,
+        51214
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6033297837382615,
+      "compression_ratio": 1.425,
+      "no_speech_prob": 0.3341304659843445,
+      "confidence": 0.428,
+      "words": [
+        {
+          "text": "Okay,",
+          "start": 11.88,
+          "end": 12.28,
+          "confidence": 0.507
+        },
+        {
+          "text": "we'd",
+          "start": 12.5,
+          "end": 13.16,
+          "confidence": 0.623
+        },
+        {
+          "text": "like",
+          "start": 13.16,
+          "end": 13.32,
+          "confidence": 0.876
+        },
+        {
+          "text": "to",
+          "start": 13.32,
+          "end": 13.56,
+          "confidence": 0.737
+        },
+        {
+          "text": "have,",
+          "start": 13.56,
+          "end": 14.24,
+          "confidence": 0.124
+        },
+        {
+          "text": "say,",
+          "start": 14.74,
+          "end": 15.0,
+          "confidence": 0.153
+        },
+        {
+          "text": "a",
+          "start": 15.1,
+          "end": 15.16,
+          "confidence": 0.061
+        },
+        {
+          "text": "selected",
+          "start": 15.16,
+          "end": 15.76,
+          "confidence": 0.143
+        },
+        {
+          "text": "one",
+          "start": 15.76,
+          "end": 16.08,
+          "confidence": 0.754
+        },
+        {
+          "text": "or",
+          "start": 16.08,
+          "end": 16.22,
+          "confidence": 0.67
+        },
+        {
+          "text": "two",
+          "start": 16.22,
+          "end": 16.36,
+          "confidence": 0.6
+        },
+        {
+          "text": "on",
+          "start": 16.36,
+          "end": 16.6,
+          "confidence": 0.875
+        },
+        {
+          "text": "the",
+          "start": 16.6,
+          "end": 16.82,
+          "confidence": 0.809
+        },
+        {
+          "text": "helmet.",
+          "start": 16.82,
+          "end": 17.3,
+          "confidence": 0.651
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 17.32,
+      "end": 19.12,
+      "text": " We're going to have an B1.",
+      "tokens": [
+        51214,
+        492,
+        434,
+        516,
+        281,
+        362,
+        364,
+        363,
+        16,
+        13,
+        51314
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6033297837382615,
+      "compression_ratio": 1.425,
+      "no_speech_prob": 0.3341304659843445,
+      "confidence": 0.545,
+      "words": [
+        {
+          "text": "We're",
+          "start": 17.32,
+          "end": 17.78,
+          "confidence": 0.7
+        },
+        {
+          "text": "going",
+          "start": 17.78,
+          "end": 17.94,
+          "confidence": 0.505
+        },
+        {
+          "text": "to",
+          "start": 17.94,
+          "end": 18.06,
+          "confidence": 0.899
+        },
+        {
+          "text": "have",
+          "start": 18.06,
+          "end": 18.22,
+          "confidence": 0.848
+        },
+        {
+          "text": "an",
+          "start": 18.22,
+          "end": 18.4,
+          "confidence": 0.264
+        },
+        {
+          "text": "B1.",
+          "start": 18.4,
+          "end": 19.12,
+          "confidence": 0.395
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 20.08,
+      "end": 24.32,
+      "text": " And you could put the other one on Mike's helmet, we're still seeing the bleepers.",
+      "tokens": [
+        51314,
+        400,
+        291,
+        727,
+        829,
+        264,
+        661,
+        472,
+        322,
+        6602,
+        311,
+        15922,
+        11,
+        321,
+        434,
+        920,
+        2577,
+        264,
+        5408,
+        595,
+        433,
+        13,
+        51564
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6033297837382615,
+      "compression_ratio": 1.425,
+      "no_speech_prob": 0.3341304659843445,
+      "confidence": 0.528,
+      "words": [
+        {
+          "text": "And",
+          "start": 20.08,
+          "end": 20.22,
+          "confidence": 0.796
+        },
+        {
+          "text": "you",
+          "start": 20.22,
+          "end": 20.34,
+          "confidence": 0.885
+        },
+        {
+          "text": "could",
+          "start": 20.34,
+          "end": 20.48,
+          "confidence": 0.415
+        },
+        {
+          "text": "put",
+          "start": 20.48,
+          "end": 20.66,
+          "confidence": 0.894
+        },
+        {
+          "text": "the",
+          "start": 20.66,
+          "end": 20.84,
+          "confidence": 0.813
+        },
+        {
+          "text": "other",
+          "start": 20.84,
+          "end": 21.02,
+          "confidence": 0.774
+        },
+        {
+          "text": "one",
+          "start": 21.02,
+          "end": 21.22,
+          "confidence": 0.779
+        },
+        {
+          "text": "on",
+          "start": 21.22,
+          "end": 21.46,
+          "confidence": 0.906
+        },
+        {
+          "text": "Mike's",
+          "start": 21.46,
+          "end": 22.72,
+          "confidence": 0.831
+        },
+        {
+          "text": "helmet,",
+          "start": 22.72,
+          "end": 22.86,
+          "confidence": 0.791
+        },
+        {
+          "text": "we're",
+          "start": 23.06,
+          "end": 23.14,
+          "confidence": 0.354
+        },
+        {
+          "text": "still",
+          "start": 23.14,
+          "end": 23.34,
+          "confidence": 0.792
+        },
+        {
+          "text": "seeing",
+          "start": 23.34,
+          "end": 23.64,
+          "confidence": 0.728
+        },
+        {
+          "text": "the",
+          "start": 23.64,
+          "end": 23.88,
+          "confidence": 0.099
+        },
+        {
+          "text": "bleepers.",
+          "start": 23.88,
+          "end": 24.32,
+          "confidence": 0.228
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 0,
+      "start": 24.86,
+      "end": 25.1,
+      "text": " Over.",
+      "tokens": [
+        51564,
+        4886,
+        13,
+        51614
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6033297837382615,
+      "compression_ratio": 1.425,
+      "no_speech_prob": 0.3341304659843445,
+      "confidence": 0.616,
+      "words": [
+        {
+          "text": "Over.",
+          "start": 24.86,
+          "end": 25.1,
+          "confidence": 0.616
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 6000,
+      "start": 60.0,
+      "end": 61.9,
+      "text": " with a cover I tried it already.",
+      "tokens": [
+        50364,
+        365,
+        257,
+        2060,
+        286,
+        3031,
+        309,
+        1217,
+        13,
+        50474
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6061306174741973,
+      "compression_ratio": 1.5876777251184835,
+      "no_speech_prob": 0.0662694051861763,
+      "confidence": 0.442,
+      "words": [
+        {
+          "text": "with",
+          "start": 60.0,
+          "end": 60.2,
+          "confidence": 0.119
+        },
+        {
+          "text": "a",
+          "start": 60.2,
+          "end": 60.38,
+          "confidence": 0.457
+        },
+        {
+          "text": "cover",
+          "start": 60.38,
+          "end": 61.04,
+          "confidence": 0.558
+        },
+        {
+          "text": "I",
+          "start": 61.04,
+          "end": 61.22,
+          "confidence": 0.278
+        },
+        {
+          "text": "tried",
+          "start": 61.22,
+          "end": 61.48,
+          "confidence": 0.625
+        },
+        {
+          "text": "it",
+          "start": 61.48,
+          "end": 61.64,
+          "confidence": 0.802
+        },
+        {
+          "text": "already.",
+          "start": 61.64,
+          "end": 61.9,
+          "confidence": 0.772
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 6000,
+      "start": 62.42,
+      "end": 65.18,
+      "text": " Okay fine, we weren't sure that this was a suggestion.",
+      "tokens": [
+        50474,
+        1033,
+        2489,
+        11,
+        321,
+        4999,
+        380,
+        988,
+        300,
+        341,
+        390,
+        257,
+        16541,
+        13,
+        50629
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6061306174741973,
+      "compression_ratio": 1.5876777251184835,
+      "no_speech_prob": 0.0662694051861763,
+      "confidence": 0.666,
+      "words": [
+        {
+          "text": "Okay",
+          "start": 62.42,
+          "end": 62.82,
+          "confidence": 0.414
+        },
+        {
+          "text": "fine,",
+          "start": 62.82,
+          "end": 63.1,
+          "confidence": 0.467
+        },
+        {
+          "text": "we",
+          "start": 63.22,
+          "end": 63.3,
+          "confidence": 0.846
+        },
+        {
+          "text": "weren't",
+          "start": 63.3,
+          "end": 63.56,
+          "confidence": 0.886
+        },
+        {
+          "text": "sure",
+          "start": 63.56,
+          "end": 63.74,
+          "confidence": 0.809
+        },
+        {
+          "text": "that",
+          "start": 63.74,
+          "end": 64.1,
+          "confidence": 0.513
+        },
+        {
+          "text": "this",
+          "start": 64.1,
+          "end": 64.58,
+          "confidence": 0.59
+        },
+        {
+          "text": "was",
+          "start": 64.58,
+          "end": 64.76,
+          "confidence": 0.787
+        },
+        {
+          "text": "a",
+          "start": 64.76,
+          "end": 64.88,
+          "confidence": 0.769
+        },
+        {
+          "text": "suggestion.",
+          "start": 64.88,
+          "end": 65.18,
+          "confidence": 0.605
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 6000,
+      "start": 65.22,
+      "end": 66.76,
+      "text": " We thought we'd uh...",
+      "tokens": [
+        50629,
+        492,
+        1194,
+        321,
+        1116,
+        2232,
+        485,
+        50699
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6061306174741973,
+      "compression_ratio": 1.5876777251184835,
+      "no_speech_prob": 0.0662694051861763,
+      "confidence": 0.604,
+      "words": [
+        {
+          "text": "We",
+          "start": 65.22,
+          "end": 65.4,
+          "confidence": 0.876
+        },
+        {
+          "text": "thought",
+          "start": 65.4,
+          "end": 65.56,
+          "confidence": 0.816
+        },
+        {
+          "text": "we'd",
+          "start": 65.56,
+          "end": 65.88,
+          "confidence": 0.561
+        },
+        {
+          "text": "uh...",
+          "start": 65.88,
+          "end": 66.76,
+          "confidence": 0.356
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 6000,
+      "start": 66.76,
+      "end": 67.82,
+      "text": " you could check it out.",
+      "tokens": [
+        50699,
+        291,
+        727,
+        1520,
+        309,
+        484,
+        13,
+        50769
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6061306174741973,
+      "compression_ratio": 1.5876777251184835,
+      "no_speech_prob": 0.0662694051861763,
+      "confidence": 0.599,
+      "words": [
+        {
+          "text": "you",
+          "start": 66.76,
+          "end": 67.04,
+          "confidence": 0.191
+        },
+        {
+          "text": "could",
+          "start": 67.04,
+          "end": 67.22,
+          "confidence": 0.698
+        },
+        {
+          "text": "check",
+          "start": 67.22,
+          "end": 67.44,
+          "confidence": 0.792
+        },
+        {
+          "text": "it",
+          "start": 67.44,
+          "end": 67.58,
+          "confidence": 0.901
+        },
+        {
+          "text": "out.",
+          "start": 67.58,
+          "end": 67.82,
+          "confidence": 0.811
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 6000,
+      "start": 68.18,
+      "end": 69.3,
+      "text": " How much you've already done that.",
+      "tokens": [
+        50769,
+        1012,
+        709,
+        291,
+        600,
+        1217,
+        1096,
+        300,
+        13,
+        50834
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6061306174741973,
+      "compression_ratio": 1.5876777251184835,
+      "no_speech_prob": 0.0662694051861763,
+      "confidence": 0.617,
+      "words": [
+        {
+          "text": "How",
+          "start": 68.18,
+          "end": 68.42,
+          "confidence": 0.234
+        },
+        {
+          "text": "much",
+          "start": 68.42,
+          "end": 68.6,
+          "confidence": 0.806
+        },
+        {
+          "text": "you've",
+          "start": 68.6,
+          "end": 68.76,
+          "confidence": 0.575
+        },
+        {
+          "text": "already",
+          "start": 68.76,
+          "end": 68.88,
+          "confidence": 0.814
+        },
+        {
+          "text": "done",
+          "start": 68.88,
+          "end": 69.1,
+          "confidence": 0.779
+        },
+        {
+          "text": "that.",
+          "start": 69.1,
+          "end": 69.3,
+          "confidence": 0.861
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 6000,
+      "start": 69.36,
+      "end": 70.26,
+      "text": " So uh...",
+      "tokens": [
+        50834,
+        407,
+        2232,
+        485,
+        50879
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6061306174741973,
+      "compression_ratio": 1.5876777251184835,
+      "no_speech_prob": 0.0662694051861763,
+      "confidence": 0.644,
+      "words": [
+        {
+          "text": "So",
+          "start": 69.36,
+          "end": 69.66,
+          "confidence": 0.883
+        },
+        {
+          "text": "uh...",
+          "start": 69.66,
+          "end": 70.26,
+          "confidence": 0.469
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 6000,
+      "start": 70.32,
+      "end": 71.8,
+      "text": " I guess whatever you can come up with,",
+      "tokens": [
+        50879,
+        286,
+        2041,
+        2035,
+        291,
+        393,
+        808,
+        493,
+        365,
+        11,
+        50954
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6061306174741973,
+      "compression_ratio": 1.5876777251184835,
+      "no_speech_prob": 0.0662694051861763,
+      "confidence": 0.632,
+      "words": [
+        {
+          "text": "I",
+          "start": 70.32,
+          "end": 70.5,
+          "confidence": 0.992
+        },
+        {
+          "text": "guess",
+          "start": 70.5,
+          "end": 70.7,
+          "confidence": 0.905
+        },
+        {
+          "text": "whatever",
+          "start": 70.7,
+          "end": 71.12,
+          "confidence": 0.201
+        },
+        {
+          "text": "you",
+          "start": 71.12,
+          "end": 71.26,
+          "confidence": 0.884
+        },
+        {
+          "text": "can",
+          "start": 71.26,
+          "end": 71.32,
+          "confidence": 0.281
+        },
+        {
+          "text": "come",
+          "start": 71.32,
+          "end": 71.46,
+          "confidence": 0.777
+        },
+        {
+          "text": "up",
+          "start": 71.46,
+          "end": 71.62,
+          "confidence": 0.898
+        },
+        {
+          "text": "with,",
+          "start": 71.62,
+          "end": 71.8,
+          "confidence": 0.817
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 6000,
+      "start": 71.8,
+      "end": 72.76,
+      "text": " just let us know and...",
+      "tokens": [
+        50954,
+        445,
+        718,
+        505,
+        458,
+        293,
+        485,
+        51004
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6061306174741973,
+      "compression_ratio": 1.5876777251184835,
+      "no_speech_prob": 0.0662694051861763,
+      "confidence": 0.721,
+      "words": [
+        {
+          "text": "just",
+          "start": 71.8,
+          "end": 71.98,
+          "confidence": 0.866
+        },
+        {
+          "text": "let",
+          "start": 71.98,
+          "end": 72.12,
+          "confidence": 0.905
+        },
+        {
+          "text": "us",
+          "start": 72.12,
+          "end": 72.26,
+          "confidence": 0.904
+        },
+        {
+          "text": "know",
+          "start": 72.26,
+          "end": 72.42,
+          "confidence": 0.798
+        },
+        {
+          "text": "and...",
+          "start": 72.42,
+          "end": 72.76,
+          "confidence": 0.346
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 6000,
+      "start": 74.16,
+      "end": 75.24,
+      "text": " Okay there's no problem.",
+      "tokens": [
+        51004,
+        1033,
+        456,
+        311,
+        572,
+        1154,
+        13,
+        51129
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6061306174741973,
+      "compression_ratio": 1.5876777251184835,
+      "no_speech_prob": 0.0662694051861763,
+      "confidence": 0.558,
+      "words": [
+        {
+          "text": "Okay",
+          "start": 74.16,
+          "end": 74.44,
+          "confidence": 0.335
+        },
+        {
+          "text": "there's",
+          "start": 74.44,
+          "end": 74.74,
+          "confidence": 0.486
+        },
+        {
+          "text": "no",
+          "start": 74.74,
+          "end": 74.88,
+          "confidence": 0.888
+        },
+        {
+          "text": "problem.",
+          "start": 74.88,
+          "end": 75.24,
+          "confidence": 0.771
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 6000,
+      "start": 75.32,
+      "end": 76.56,
+      "text": " Okay, there's no problem.",
+      "tokens": [
+        51129,
+        1033,
+        11,
+        456,
+        311,
+        572,
+        1154,
+        13,
+        51194
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6061306174741973,
+      "compression_ratio": 1.5876777251184835,
+      "no_speech_prob": 0.0662694051861763,
+      "confidence": 0.777,
+      "words": [
+        {
+          "text": "Okay,",
+          "start": 75.32,
+          "end": 75.84,
+          "confidence": 0.784
+        },
+        {
+          "text": "there's",
+          "start": 76.0,
+          "end": 76.08,
+          "confidence": 0.712
+        },
+        {
+          "text": "no",
+          "start": 76.08,
+          "end": 76.22,
+          "confidence": 0.898
+        },
+        {
+          "text": "problem.",
+          "start": 76.22,
+          "end": 76.56,
+          "confidence": 0.793
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 6000,
+      "start": 76.6,
+      "end": 77.8,
+      "text": " We'll let you know where they end up.",
+      "tokens": [
+        51194,
+        492,
+        603,
+        718,
+        291,
+        458,
+        689,
+        436,
+        917,
+        493,
+        13,
+        51259
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6061306174741973,
+      "compression_ratio": 1.5876777251184835,
+      "no_speech_prob": 0.0662694051861763,
+      "confidence": 0.723,
+      "words": [
+        {
+          "text": "We'll",
+          "start": 76.6,
+          "end": 76.82,
+          "confidence": 0.834
+        },
+        {
+          "text": "let",
+          "start": 76.82,
+          "end": 76.96,
+          "confidence": 0.885
+        },
+        {
+          "text": "you",
+          "start": 76.96,
+          "end": 77.04,
+          "confidence": 0.764
+        },
+        {
+          "text": "know",
+          "start": 77.04,
+          "end": 77.2,
+          "confidence": 0.815
+        },
+        {
+          "text": "where",
+          "start": 77.2,
+          "end": 77.32,
+          "confidence": 0.6
+        },
+        {
+          "text": "they",
+          "start": 77.32,
+          "end": 77.42,
+          "confidence": 0.33
+        },
+        {
+          "text": "end",
+          "start": 77.42,
+          "end": 77.54,
+          "confidence": 0.787
+        },
+        {
+          "text": "up.",
+          "start": 77.54,
+          "end": 77.8,
+          "confidence": 0.905
+        }
+      ]
+    },
+    {
+      "id": 17,
+      "seek": 6000,
+      "start": 77.94,
+      "end": 78.32,
+      "text": " Nice.",
+      "tokens": [
+        51259,
+        5490,
+        13,
+        51299
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.6061306174741973,
+      "compression_ratio": 1.5876777251184835,
+      "no_speech_prob": 0.0662694051861763,
+      "confidence": 0.495,
+      "words": [
+        {
+          "text": "Nice.",
+          "start": 77.94,
+          "end": 78.32,
+          "confidence": 0.495
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/corner_cases/medium.accurate_gloria.mp3.words.json b/tests/expected/corner_cases/medium.accurate_gloria.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..afa758f8da5b91ba2d7cb5705d796df78040207f
--- /dev/null
+++ b/tests/expected/corner_cases/medium.accurate_gloria.mp3.words.json
@@ -0,0 +1,544 @@
+{
+  "text": " Hello. How are you? How are you? Oh, I'm okay. I will be. I said she could stay with us tomorrow until she feels better. Of course she can. This won't be for long. Well, you can stay as long as you want, my love. I really miss you.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 1.32,
+      "end": 1.82,
+      "text": " Hello.",
+      "tokens": [
+        50364,
+        2425,
+        13,
+        50464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.21371329812442555,
+      "compression_ratio": 1.4713375796178343,
+      "no_speech_prob": 0.050164904445409775,
+      "confidence": 0.189,
+      "words": [
+        {
+          "text": "Hello.",
+          "start": 1.32,
+          "end": 1.82,
+          "confidence": 0.189
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 1.94,
+      "end": 3.54,
+      "text": " How are you?",
+      "tokens": [
+        50464,
+        1012,
+        366,
+        291,
+        30,
+        50564
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.21371329812442555,
+      "compression_ratio": 1.4713375796178343,
+      "no_speech_prob": 0.050164904445409775,
+      "confidence": 0.157,
+      "words": [
+        {
+          "text": "How",
+          "start": 1.94,
+          "end": 2.6,
+          "confidence": 0.004
+        },
+        {
+          "text": "are",
+          "start": 2.6,
+          "end": 3.1,
+          "confidence": 0.238
+        },
+        {
+          "text": "you?",
+          "start": 3.1,
+          "end": 3.54,
+          "confidence": 0.809
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 3.7,
+      "end": 6.38,
+      "text": " How are you?",
+      "tokens": [
+        50564,
+        1012,
+        366,
+        291,
+        30,
+        50664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.21371329812442555,
+      "compression_ratio": 1.4713375796178343,
+      "no_speech_prob": 0.050164904445409775,
+      "confidence": 0.353,
+      "words": [
+        {
+          "text": "How",
+          "start": 3.7,
+          "end": 4.3,
+          "confidence": 0.021
+        },
+        {
+          "text": "are",
+          "start": 4.3,
+          "end": 6.12,
+          "confidence": 0.93
+        },
+        {
+          "text": "you?",
+          "start": 6.12,
+          "end": 6.38,
+          "confidence": 0.897
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 6.38,
+      "end": 7.74,
+      "text": " Oh, I'm okay.",
+      "tokens": [
+        50664,
+        876,
+        11,
+        286,
+        478,
+        1392,
+        13,
+        50764
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.21371329812442555,
+      "compression_ratio": 1.4713375796178343,
+      "no_speech_prob": 0.050164904445409775,
+      "confidence": 0.63,
+      "words": [
+        {
+          "text": "Oh,",
+          "start": 6.38,
+          "end": 6.66,
+          "confidence": 0.37
+        },
+        {
+          "text": "I'm",
+          "start": 6.76,
+          "end": 7.18,
+          "confidence": 0.979
+        },
+        {
+          "text": "okay.",
+          "start": 7.18,
+          "end": 7.74,
+          "confidence": 0.692
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 7.74,
+      "end": 9.2,
+      "text": " I will be.",
+      "tokens": [
+        50764,
+        286,
+        486,
+        312,
+        13,
+        50864
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.21371329812442555,
+      "compression_ratio": 1.4713375796178343,
+      "no_speech_prob": 0.050164904445409775,
+      "confidence": 0.543,
+      "words": [
+        {
+          "text": "I",
+          "start": 7.74,
+          "end": 8.64,
+          "confidence": 0.467
+        },
+        {
+          "text": "will",
+          "start": 8.64,
+          "end": 8.88,
+          "confidence": 0.582
+        },
+        {
+          "text": "be.",
+          "start": 8.88,
+          "end": 9.2,
+          "confidence": 0.565
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 0,
+      "start": 9.5,
+      "end": 11.56,
+      "text": " I said she could stay with us tomorrow until she feels better.",
+      "tokens": [
+        50864,
+        286,
+        848,
+        750,
+        727,
+        1754,
+        365,
+        505,
+        4153,
+        1826,
+        750,
+        3417,
+        1101,
+        13,
+        50964
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.21371329812442555,
+      "compression_ratio": 1.4713375796178343,
+      "no_speech_prob": 0.050164904445409775,
+      "confidence": 0.494,
+      "words": [
+        {
+          "text": "I",
+          "start": 9.5,
+          "end": 9.52,
+          "confidence": 0.283
+        },
+        {
+          "text": "said",
+          "start": 9.52,
+          "end": 9.64,
+          "confidence": 0.561
+        },
+        {
+          "text": "she",
+          "start": 9.64,
+          "end": 9.78,
+          "confidence": 0.919
+        },
+        {
+          "text": "could",
+          "start": 9.78,
+          "end": 9.98,
+          "confidence": 0.898
+        },
+        {
+          "text": "stay",
+          "start": 9.98,
+          "end": 10.16,
+          "confidence": 0.993
+        },
+        {
+          "text": "with",
+          "start": 10.16,
+          "end": 10.28,
+          "confidence": 0.991
+        },
+        {
+          "text": "us",
+          "start": 10.28,
+          "end": 10.46,
+          "confidence": 0.966
+        },
+        {
+          "text": "tomorrow",
+          "start": 10.46,
+          "end": 10.68,
+          "confidence": 0.004
+        },
+        {
+          "text": "until",
+          "start": 10.68,
+          "end": 10.84,
+          "confidence": 0.312
+        },
+        {
+          "text": "she",
+          "start": 10.84,
+          "end": 10.98,
+          "confidence": 0.997
+        },
+        {
+          "text": "feels",
+          "start": 10.98,
+          "end": 11.2,
+          "confidence": 0.988
+        },
+        {
+          "text": "better.",
+          "start": 11.2,
+          "end": 11.56,
+          "confidence": 0.825
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 0,
+      "start": 11.56,
+      "end": 13.42,
+      "text": " Of course she can.",
+      "tokens": [
+        50964,
+        2720,
+        1164,
+        750,
+        393,
+        13,
+        51064
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.21371329812442555,
+      "compression_ratio": 1.4713375796178343,
+      "no_speech_prob": 0.050164904445409775,
+      "confidence": 0.31,
+      "words": [
+        {
+          "text": "Of",
+          "start": 11.56,
+          "end": 12.54,
+          "confidence": 0.09
+        },
+        {
+          "text": "course",
+          "start": 12.54,
+          "end": 12.72,
+          "confidence": 0.985
+        },
+        {
+          "text": "she",
+          "start": 12.72,
+          "end": 13.04,
+          "confidence": 0.208
+        },
+        {
+          "text": "can.",
+          "start": 13.04,
+          "end": 13.42,
+          "confidence": 0.392
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 0,
+      "start": 13.54,
+      "end": 15.24,
+      "text": " This won't be for long.",
+      "tokens": [
+        51064,
+        639,
+        1582,
+        380,
+        312,
+        337,
+        938,
+        13,
+        51164
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.21371329812442555,
+      "compression_ratio": 1.4713375796178343,
+      "no_speech_prob": 0.050164904445409775,
+      "confidence": 0.444,
+      "words": [
+        {
+          "text": "This",
+          "start": 13.54,
+          "end": 14.16,
+          "confidence": 0.007
+        },
+        {
+          "text": "won't",
+          "start": 14.16,
+          "end": 14.58,
+          "confidence": 0.926
+        },
+        {
+          "text": "be",
+          "start": 14.58,
+          "end": 14.8,
+          "confidence": 0.99
+        },
+        {
+          "text": "for",
+          "start": 14.8,
+          "end": 14.98,
+          "confidence": 0.978
+        },
+        {
+          "text": "long.",
+          "start": 14.98,
+          "end": 15.24,
+          "confidence": 0.764
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 0,
+      "start": 15.5,
+      "end": 17.62,
+      "text": " Well, you can stay as long as you want, my love.",
+      "tokens": [
+        51164,
+        1042,
+        11,
+        291,
+        393,
+        1754,
+        382,
+        938,
+        382,
+        291,
+        528,
+        11,
+        452,
+        959,
+        13,
+        51264
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.21371329812442555,
+      "compression_ratio": 1.4713375796178343,
+      "no_speech_prob": 0.050164904445409775,
+      "confidence": 0.587,
+      "words": [
+        {
+          "text": "Well,",
+          "start": 15.5,
+          "end": 15.52,
+          "confidence": 0.073
+        },
+        {
+          "text": "you",
+          "start": 15.52,
+          "end": 15.66,
+          "confidence": 0.491
+        },
+        {
+          "text": "can",
+          "start": 15.66,
+          "end": 15.88,
+          "confidence": 0.876
+        },
+        {
+          "text": "stay",
+          "start": 15.88,
+          "end": 16.12,
+          "confidence": 0.932
+        },
+        {
+          "text": "as",
+          "start": 16.12,
+          "end": 16.28,
+          "confidence": 0.979
+        },
+        {
+          "text": "long",
+          "start": 16.28,
+          "end": 16.4,
+          "confidence": 0.995
+        },
+        {
+          "text": "as",
+          "start": 16.4,
+          "end": 16.54,
+          "confidence": 0.995
+        },
+        {
+          "text": "you",
+          "start": 16.54,
+          "end": 16.62,
+          "confidence": 0.995
+        },
+        {
+          "text": "want,",
+          "start": 16.62,
+          "end": 16.8,
+          "confidence": 0.643
+        },
+        {
+          "text": "my",
+          "start": 16.98,
+          "end": 17.2,
+          "confidence": 0.958
+        },
+        {
+          "text": "love.",
+          "start": 17.2,
+          "end": 17.62,
+          "confidence": 0.835
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 0,
+      "start": 17.62,
+      "end": 19.52,
+      "text": " I really miss you.",
+      "tokens": [
+        51264,
+        286,
+        534,
+        1713,
+        291,
+        13,
+        51364
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.21371329812442555,
+      "compression_ratio": 1.4713375796178343,
+      "no_speech_prob": 0.050164904445409775,
+      "confidence": 0.477,
+      "words": [
+        {
+          "text": "I",
+          "start": 17.62,
+          "end": 17.94,
+          "confidence": 0.495
+        },
+        {
+          "text": "really",
+          "start": 17.94,
+          "end": 18.3,
+          "confidence": 0.89
+        },
+        {
+          "text": "miss",
+          "start": 18.3,
+          "end": 18.78,
+          "confidence": 0.338
+        },
+        {
+          "text": "you.",
+          "start": 18.78,
+          "end": 19.52,
+          "confidence": 0.408
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/corner_cases/medium.efficient_gloria.mp3.words.json b/tests/expected/corner_cases/medium.efficient_gloria.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..439728f2cd4ff2aadde1461f93aefbddeff1861a
--- /dev/null
+++ b/tests/expected/corner_cases/medium.efficient_gloria.mp3.words.json
@@ -0,0 +1,538 @@
+{
+  "text": " Hello. How are you? Love. How are you? I'm okay. I will be. I said she could stay with us tomorrow, she feels better. Of course she can. This won't be for long. Well, you can stay as long as you want, my love. I really miss you.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 1.4,
+      "end": 1.74,
+      "text": " Hello.",
+      "tokens": [
+        50364,
+        2425,
+        13,
+        50464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23879062428193934,
+      "compression_ratio": 1.4615384615384615,
+      "no_speech_prob": 0.05016394704580307,
+      "confidence": 0.285,
+      "words": [
+        {
+          "text": "Hello.",
+          "start": 1.4,
+          "end": 1.74,
+          "confidence": 0.285
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 2.32,
+      "end": 3.5,
+      "text": " How are you?",
+      "tokens": [
+        50464,
+        1012,
+        366,
+        291,
+        30,
+        50564
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23879062428193934,
+      "compression_ratio": 1.4615384615384615,
+      "no_speech_prob": 0.05016394704580307,
+      "confidence": 0.786,
+      "words": [
+        {
+          "text": "How",
+          "start": 2.32,
+          "end": 2.82,
+          "confidence": 0.551
+        },
+        {
+          "text": "are",
+          "start": 2.82,
+          "end": 3.24,
+          "confidence": 0.989
+        },
+        {
+          "text": "you?",
+          "start": 3.24,
+          "end": 3.5,
+          "confidence": 0.893
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 3.5,
+      "end": 4.26,
+      "text": " Love.",
+      "tokens": [
+        50564,
+        5956,
+        13,
+        50664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23879062428193934,
+      "compression_ratio": 1.4615384615384615,
+      "no_speech_prob": 0.05016394704580307,
+      "confidence": 0.244,
+      "words": [
+        {
+          "text": "Love.",
+          "start": 3.5,
+          "end": 4.26,
+          "confidence": 0.244
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 5.5,
+      "end": 6.38,
+      "text": " How are you?",
+      "tokens": [
+        50664,
+        1012,
+        366,
+        291,
+        30,
+        50764
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23879062428193934,
+      "compression_ratio": 1.4615384615384615,
+      "no_speech_prob": 0.05016394704580307,
+      "confidence": 0.926,
+      "words": [
+        {
+          "text": "How",
+          "start": 5.5,
+          "end": 5.68,
+          "confidence": 0.851
+        },
+        {
+          "text": "are",
+          "start": 5.68,
+          "end": 6.08,
+          "confidence": 0.998
+        },
+        {
+          "text": "you?",
+          "start": 6.08,
+          "end": 6.38,
+          "confidence": 0.935
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 7.5,
+      "end": 9.18,
+      "text": " I'm okay. I will be.",
+      "tokens": [
+        50764,
+        286,
+        478,
+        1392,
+        13,
+        286,
+        486,
+        312,
+        13,
+        50864
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23879062428193934,
+      "compression_ratio": 1.4615384615384615,
+      "no_speech_prob": 0.05016394704580307,
+      "confidence": 0.77,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 7.5,
+          "end": 7.52,
+          "confidence": 0.767
+        },
+        {
+          "text": "okay.",
+          "start": 7.52,
+          "end": 8.22,
+          "confidence": 0.488
+        },
+        {
+          "text": "I",
+          "start": 8.42,
+          "end": 8.64,
+          "confidence": 0.767
+        },
+        {
+          "text": "will",
+          "start": 8.64,
+          "end": 8.94,
+          "confidence": 0.949
+        },
+        {
+          "text": "be.",
+          "start": 8.94,
+          "end": 9.18,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 0,
+      "start": 9.5,
+      "end": 11.52,
+      "text": " I said she could stay with us tomorrow, she feels better.",
+      "tokens": [
+        50864,
+        286,
+        848,
+        750,
+        727,
+        1754,
+        365,
+        505,
+        4153,
+        11,
+        750,
+        3417,
+        1101,
+        13,
+        50964
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23879062428193934,
+      "compression_ratio": 1.4615384615384615,
+      "no_speech_prob": 0.05016394704580307,
+      "confidence": 0.786,
+      "words": [
+        {
+          "text": "I",
+          "start": 9.5,
+          "end": 9.52,
+          "confidence": 0.883
+        },
+        {
+          "text": "said",
+          "start": 9.52,
+          "end": 9.64,
+          "confidence": 0.856
+        },
+        {
+          "text": "she",
+          "start": 9.64,
+          "end": 9.78,
+          "confidence": 0.928
+        },
+        {
+          "text": "could",
+          "start": 9.78,
+          "end": 9.96,
+          "confidence": 0.909
+        },
+        {
+          "text": "stay",
+          "start": 9.96,
+          "end": 10.16,
+          "confidence": 0.994
+        },
+        {
+          "text": "with",
+          "start": 10.16,
+          "end": 10.28,
+          "confidence": 0.977
+        },
+        {
+          "text": "us",
+          "start": 10.28,
+          "end": 10.46,
+          "confidence": 0.993
+        },
+        {
+          "text": "tomorrow,",
+          "start": 10.46,
+          "end": 10.66,
+          "confidence": 0.514
+        },
+        {
+          "text": "she",
+          "start": 10.72,
+          "end": 10.86,
+          "confidence": 0.279
+        },
+        {
+          "text": "feels",
+          "start": 10.86,
+          "end": 11.16,
+          "confidence": 0.809
+        },
+        {
+          "text": "better.",
+          "start": 11.16,
+          "end": 11.52,
+          "confidence": 0.992
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 0,
+      "start": 12.06,
+      "end": 13.36,
+      "text": " Of course she can.",
+      "tokens": [
+        50964,
+        2720,
+        1164,
+        750,
+        393,
+        13,
+        51064
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23879062428193934,
+      "compression_ratio": 1.4615384615384615,
+      "no_speech_prob": 0.05016394704580307,
+      "confidence": 0.928,
+      "words": [
+        {
+          "text": "Of",
+          "start": 12.06,
+          "end": 12.34,
+          "confidence": 0.788
+        },
+        {
+          "text": "course",
+          "start": 12.34,
+          "end": 12.56,
+          "confidence": 0.989
+        },
+        {
+          "text": "she",
+          "start": 12.56,
+          "end": 12.88,
+          "confidence": 0.958
+        },
+        {
+          "text": "can.",
+          "start": 12.88,
+          "end": 13.36,
+          "confidence": 0.993
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 0,
+      "start": 13.5,
+      "end": 15.26,
+      "text": " This won't be for long.",
+      "tokens": [
+        51064,
+        639,
+        1582,
+        380,
+        312,
+        337,
+        938,
+        13,
+        51164
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23879062428193934,
+      "compression_ratio": 1.4615384615384615,
+      "no_speech_prob": 0.05016394704580307,
+      "confidence": 0.892,
+      "words": [
+        {
+          "text": "This",
+          "start": 13.5,
+          "end": 14.28,
+          "confidence": 0.543
+        },
+        {
+          "text": "won't",
+          "start": 14.28,
+          "end": 14.6,
+          "confidence": 0.975
+        },
+        {
+          "text": "be",
+          "start": 14.6,
+          "end": 14.8,
+          "confidence": 0.996
+        },
+        {
+          "text": "for",
+          "start": 14.8,
+          "end": 14.96,
+          "confidence": 0.984
+        },
+        {
+          "text": "long.",
+          "start": 14.96,
+          "end": 15.26,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 0,
+      "start": 15.5,
+      "end": 17.62,
+      "text": " Well, you can stay as long as you want, my love.",
+      "tokens": [
+        51164,
+        1042,
+        11,
+        291,
+        393,
+        1754,
+        382,
+        938,
+        382,
+        291,
+        528,
+        11,
+        452,
+        959,
+        13,
+        51264
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23879062428193934,
+      "compression_ratio": 1.4615384615384615,
+      "no_speech_prob": 0.05016394704580307,
+      "confidence": 0.927,
+      "words": [
+        {
+          "text": "Well,",
+          "start": 15.5,
+          "end": 15.56,
+          "confidence": 0.675
+        },
+        {
+          "text": "you",
+          "start": 15.68,
+          "end": 15.7,
+          "confidence": 0.744
+        },
+        {
+          "text": "can",
+          "start": 15.7,
+          "end": 15.94,
+          "confidence": 0.982
+        },
+        {
+          "text": "stay",
+          "start": 15.94,
+          "end": 16.14,
+          "confidence": 0.985
+        },
+        {
+          "text": "as",
+          "start": 16.14,
+          "end": 16.28,
+          "confidence": 0.972
+        },
+        {
+          "text": "long",
+          "start": 16.28,
+          "end": 16.4,
+          "confidence": 0.994
+        },
+        {
+          "text": "as",
+          "start": 16.4,
+          "end": 16.48,
+          "confidence": 0.996
+        },
+        {
+          "text": "you",
+          "start": 16.48,
+          "end": 16.62,
+          "confidence": 0.995
+        },
+        {
+          "text": "want,",
+          "start": 16.62,
+          "end": 16.8,
+          "confidence": 0.995
+        },
+        {
+          "text": "my",
+          "start": 16.88,
+          "end": 17.22,
+          "confidence": 0.95
+        },
+        {
+          "text": "love.",
+          "start": 17.22,
+          "end": 17.62,
+          "confidence": 0.993
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 0,
+      "start": 17.76,
+      "end": 19.26,
+      "text": " I really miss you.",
+      "tokens": [
+        51264,
+        286,
+        534,
+        1713,
+        291,
+        13,
+        51364
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23879062428193934,
+      "compression_ratio": 1.4615384615384615,
+      "no_speech_prob": 0.05016394704580307,
+      "confidence": 0.792,
+      "words": [
+        {
+          "text": "I",
+          "start": 17.76,
+          "end": 17.98,
+          "confidence": 0.587
+        },
+        {
+          "text": "really",
+          "start": 17.98,
+          "end": 18.36,
+          "confidence": 0.944
+        },
+        {
+          "text": "miss",
+          "start": 18.36,
+          "end": 18.78,
+          "confidence": 0.905
+        },
+        {
+          "text": "you.",
+          "start": 18.78,
+          "end": 19.26,
+          "confidence": 0.787
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/corner_cases/nocond.random_music.mp4.words.json b/tests/expected/corner_cases/nocond.random_music.mp4.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..f06d275035a63608dd63d45f0e1f4a80d5424924
--- /dev/null
+++ b/tests/expected/corner_cases/nocond.random_music.mp4.words.json
@@ -0,0 +1,2847 @@
+{
+  "text": " I As you're praying for my phone And the laughter in the holes And the names that I've been called I stack it in my mind And I'm waiting for the time When I show you what it's like To be worse than in a mine Tell you, you're the greatest But once you turn they hate us Oh, the misery Everybody wants to be my enemy I smell the sympathy Everybody wants to be my enemy Look out for yourself My enemy Look out for yourself Look, okay, I'm Hoping that somebody pray for me I'm praying that somebody vote for me I'm staying where nobody's supposed to be I propose to be in a wreck of emotions Ready to go whenever she let me know The road is long so put the pedal into the flow The enemy on my trail, my energy unavailable I'ma tell the master the way go Hey, when I'm flat on my track to the top I been out of shape, thinking that I'm a box of an astronaut Blasted off the planet, rocked the cars, catastrophic And it matters more because I had it, now I had it I thought about wreaking havoc on an opposition Kinda shockin', they want it static, with precision I'm automatic, quarterback, I ain't talkin' second Pack it, pack it up, I don't panic, better batter up Who the baddest, it don't matter cause we is your Everybody wants to be my enemy Spare the sympathy Everybody wants to be my enemy Oh, the misery Everybody wants to be my enemy Spell the sympathy Everybody wants to be my enemy Everywhere I swear I'll never be a saint Nowhere my enemy Everywhere I swear I'll never be a saint Look out for yourself",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 2.24,
+      "end": 2.36,
+      "text": " I",
+      "tokens": [
+        50364,
+        286,
+        50464
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.9355003237724304,
+      "compression_ratio": 0.1111111111111111,
+      "no_speech_prob": 0.7811808586120605,
+      "confidence": 0.032,
+      "words": [
+        {
+          "text": "I",
+          "start": 2.24,
+          "end": 2.36,
+          "confidence": 0.032
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 9000,
+      "start": 90.18,
+      "end": 91.7,
+      "text": " As you're praying for my phone",
+      "tokens": [
+        50364,
+        1018,
+        291,
+        434,
+        15611,
+        337,
+        452,
+        2593,
+        50446
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.41540291383094397,
+      "compression_ratio": 1.5369458128078817,
+      "no_speech_prob": 0.7202673554420471,
+      "confidence": 0.716,
+      "words": [
+        {
+          "text": "As",
+          "start": 90.18,
+          "end": 90.32,
+          "confidence": 0.357
+        },
+        {
+          "text": "you're",
+          "start": 90.32,
+          "end": 90.46,
+          "confidence": 0.893
+        },
+        {
+          "text": "praying",
+          "start": 90.46,
+          "end": 90.88,
+          "confidence": 0.966
+        },
+        {
+          "text": "for",
+          "start": 90.88,
+          "end": 91.12,
+          "confidence": 0.994
+        },
+        {
+          "text": "my",
+          "start": 91.12,
+          "end": 91.3,
+          "confidence": 0.997
+        },
+        {
+          "text": "phone",
+          "start": 91.3,
+          "end": 91.7,
+          "confidence": 0.353
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 9000,
+      "start": 91.78,
+      "end": 93.22,
+      "text": " And the laughter in the holes",
+      "tokens": [
+        50446,
+        400,
+        264,
+        13092,
+        294,
+        264,
+        8118,
+        50524
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.41540291383094397,
+      "compression_ratio": 1.5369458128078817,
+      "no_speech_prob": 0.7202673554420471,
+      "confidence": 0.864,
+      "words": [
+        {
+          "text": "And",
+          "start": 91.78,
+          "end": 91.92,
+          "confidence": 0.885
+        },
+        {
+          "text": "the",
+          "start": 91.92,
+          "end": 92.1,
+          "confidence": 0.99
+        },
+        {
+          "text": "laughter",
+          "start": 92.1,
+          "end": 92.5,
+          "confidence": 0.993
+        },
+        {
+          "text": "in",
+          "start": 92.5,
+          "end": 92.78,
+          "confidence": 0.895
+        },
+        {
+          "text": "the",
+          "start": 92.78,
+          "end": 92.92,
+          "confidence": 0.995
+        },
+        {
+          "text": "holes",
+          "start": 92.92,
+          "end": 93.22,
+          "confidence": 0.538
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 9000,
+      "start": 93.34,
+      "end": 94.76,
+      "text": " And the names that I've been called",
+      "tokens": [
+        50524,
+        400,
+        264,
+        5288,
+        300,
+        286,
+        600,
+        668,
+        1219,
+        50604
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.41540291383094397,
+      "compression_ratio": 1.5369458128078817,
+      "no_speech_prob": 0.7202673554420471,
+      "confidence": 0.97,
+      "words": [
+        {
+          "text": "And",
+          "start": 93.34,
+          "end": 93.48,
+          "confidence": 0.956
+        },
+        {
+          "text": "the",
+          "start": 93.48,
+          "end": 93.6,
+          "confidence": 0.994
+        },
+        {
+          "text": "names",
+          "start": 93.6,
+          "end": 93.86,
+          "confidence": 0.989
+        },
+        {
+          "text": "that",
+          "start": 93.86,
+          "end": 94.14,
+          "confidence": 0.982
+        },
+        {
+          "text": "I've",
+          "start": 94.14,
+          "end": 94.32,
+          "confidence": 0.946
+        },
+        {
+          "text": "been",
+          "start": 94.32,
+          "end": 94.5,
+          "confidence": 0.998
+        },
+        {
+          "text": "called",
+          "start": 94.5,
+          "end": 94.76,
+          "confidence": 0.955
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 9000,
+      "start": 94.98,
+      "end": 96.38,
+      "text": " I stack it in my mind",
+      "tokens": [
+        50604,
+        286,
+        8630,
+        309,
+        294,
+        452,
+        1575,
+        50681
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.41540291383094397,
+      "compression_ratio": 1.5369458128078817,
+      "no_speech_prob": 0.7202673554420471,
+      "confidence": 0.96,
+      "words": [
+        {
+          "text": "I",
+          "start": 94.98,
+          "end": 95.14,
+          "confidence": 0.991
+        },
+        {
+          "text": "stack",
+          "start": 95.14,
+          "end": 95.46,
+          "confidence": 0.802
+        },
+        {
+          "text": "it",
+          "start": 95.46,
+          "end": 95.72,
+          "confidence": 0.996
+        },
+        {
+          "text": "in",
+          "start": 95.72,
+          "end": 95.8,
+          "confidence": 0.996
+        },
+        {
+          "text": "my",
+          "start": 95.8,
+          "end": 96.1,
+          "confidence": 0.995
+        },
+        {
+          "text": "mind",
+          "start": 96.1,
+          "end": 96.38,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 9000,
+      "start": 96.48,
+      "end": 97.82,
+      "text": " And I'm waiting for the time",
+      "tokens": [
+        50681,
+        400,
+        286,
+        478,
+        3806,
+        337,
+        264,
+        565,
+        50756
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.41540291383094397,
+      "compression_ratio": 1.5369458128078817,
+      "no_speech_prob": 0.7202673554420471,
+      "confidence": 0.989,
+      "words": [
+        {
+          "text": "And",
+          "start": 96.48,
+          "end": 96.6,
+          "confidence": 0.971
+        },
+        {
+          "text": "I'm",
+          "start": 96.6,
+          "end": 96.74,
+          "confidence": 0.994
+        },
+        {
+          "text": "waiting",
+          "start": 96.74,
+          "end": 97.14,
+          "confidence": 0.978
+        },
+        {
+          "text": "for",
+          "start": 97.14,
+          "end": 97.34,
+          "confidence": 0.997
+        },
+        {
+          "text": "the",
+          "start": 97.34,
+          "end": 97.54,
+          "confidence": 0.996
+        },
+        {
+          "text": "time",
+          "start": 97.54,
+          "end": 97.82,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 9000,
+      "start": 98.0,
+      "end": 99.44,
+      "text": " When I show you what it's like",
+      "tokens": [
+        50756,
+        1133,
+        286,
+        855,
+        291,
+        437,
+        309,
+        311,
+        411,
+        50834
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.41540291383094397,
+      "compression_ratio": 1.5369458128078817,
+      "no_speech_prob": 0.7202673554420471,
+      "confidence": 0.98,
+      "words": [
+        {
+          "text": "When",
+          "start": 98.0,
+          "end": 98.14,
+          "confidence": 0.968
+        },
+        {
+          "text": "I",
+          "start": 98.14,
+          "end": 98.32,
+          "confidence": 0.996
+        },
+        {
+          "text": "show",
+          "start": 98.32,
+          "end": 98.5,
+          "confidence": 0.907
+        },
+        {
+          "text": "you",
+          "start": 98.5,
+          "end": 98.76,
+          "confidence": 0.994
+        },
+        {
+          "text": "what",
+          "start": 98.76,
+          "end": 98.94,
+          "confidence": 0.994
+        },
+        {
+          "text": "it's",
+          "start": 98.94,
+          "end": 99.24,
+          "confidence": 0.991
+        },
+        {
+          "text": "like",
+          "start": 99.24,
+          "end": 99.44,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 9000,
+      "start": 99.52,
+      "end": 101.26,
+      "text": " To be worse than in a mine",
+      "tokens": [
+        50834,
+        1407,
+        312,
+        5324,
+        813,
+        294,
+        257,
+        3892,
+        50923
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.41540291383094397,
+      "compression_ratio": 1.5369458128078817,
+      "no_speech_prob": 0.7202673554420471,
+      "confidence": 0.481,
+      "words": [
+        {
+          "text": "To",
+          "start": 99.52,
+          "end": 99.72,
+          "confidence": 0.987
+        },
+        {
+          "text": "be",
+          "start": 99.72,
+          "end": 99.84,
+          "confidence": 0.999
+        },
+        {
+          "text": "worse",
+          "start": 99.84,
+          "end": 100.1,
+          "confidence": 0.472
+        },
+        {
+          "text": "than",
+          "start": 100.1,
+          "end": 100.38,
+          "confidence": 0.188
+        },
+        {
+          "text": "in",
+          "start": 100.38,
+          "end": 100.56,
+          "confidence": 0.284
+        },
+        {
+          "text": "a",
+          "start": 100.56,
+          "end": 100.9,
+          "confidence": 0.407
+        },
+        {
+          "text": "mine",
+          "start": 100.9,
+          "end": 101.26,
+          "confidence": 0.591
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 9000,
+      "start": 101.36,
+      "end": 106.82,
+      "text": " Tell you, you're the greatest",
+      "tokens": [
+        50923,
+        5115,
+        291,
+        11,
+        291,
+        434,
+        264,
+        6636,
+        51215
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.41540291383094397,
+      "compression_ratio": 1.5369458128078817,
+      "no_speech_prob": 0.7202673554420471,
+      "confidence": 0.962,
+      "words": [
+        {
+          "text": "Tell",
+          "start": 101.36,
+          "end": 102.24,
+          "confidence": 0.898
+        },
+        {
+          "text": "you,",
+          "start": 102.24,
+          "end": 102.92,
+          "confidence": 0.993
+        },
+        {
+          "text": "you're",
+          "start": 102.92,
+          "end": 103.82,
+          "confidence": 0.971
+        },
+        {
+          "text": "the",
+          "start": 103.82,
+          "end": 104.34,
+          "confidence": 0.969
+        },
+        {
+          "text": "greatest",
+          "start": 104.34,
+          "end": 106.82,
+          "confidence": 0.973
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 9000,
+      "start": 107.22,
+      "end": 113.02,
+      "text": " But once you turn they hate us",
+      "tokens": [
+        51215,
+        583,
+        1564,
+        291,
+        1261,
+        436,
+        4700,
+        505,
+        51520
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.41540291383094397,
+      "compression_ratio": 1.5369458128078817,
+      "no_speech_prob": 0.7202673554420471,
+      "confidence": 0.862,
+      "words": [
+        {
+          "text": "But",
+          "start": 107.22,
+          "end": 107.62,
+          "confidence": 0.996
+        },
+        {
+          "text": "once",
+          "start": 107.62,
+          "end": 108.44,
+          "confidence": 0.826
+        },
+        {
+          "text": "you",
+          "start": 108.44,
+          "end": 109.2,
+          "confidence": 0.998
+        },
+        {
+          "text": "turn",
+          "start": 109.2,
+          "end": 109.9,
+          "confidence": 0.908
+        },
+        {
+          "text": "they",
+          "start": 109.9,
+          "end": 110.38,
+          "confidence": 0.481
+        },
+        {
+          "text": "hate",
+          "start": 110.38,
+          "end": 111.92,
+          "confidence": 0.988
+        },
+        {
+          "text": "us",
+          "start": 111.92,
+          "end": 113.02,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 9000,
+      "start": 114.64,
+      "end": 116.2,
+      "text": " Oh, the misery",
+      "tokens": [
+        51585,
+        876,
+        11,
+        264,
+        32309,
+        51700
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.41540291383094397,
+      "compression_ratio": 1.5369458128078817,
+      "no_speech_prob": 0.7202673554420471,
+      "confidence": 0.967,
+      "words": [
+        {
+          "text": "Oh,",
+          "start": 114.64,
+          "end": 115.16,
+          "confidence": 0.912
+        },
+        {
+          "text": "the",
+          "start": 115.22,
+          "end": 115.44,
+          "confidence": 0.993
+        },
+        {
+          "text": "misery",
+          "start": 115.44,
+          "end": 116.2,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 9000,
+      "start": 116.84,
+      "end": 119.3,
+      "text": " Everybody wants to be my enemy",
+      "tokens": [
+        51700,
+        7646,
+        2738,
+        281,
+        312,
+        452,
+        5945,
+        51860
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.41540291383094397,
+      "compression_ratio": 1.5369458128078817,
+      "no_speech_prob": 0.7202673554420471,
+      "confidence": 0.944,
+      "words": [
+        {
+          "text": "Everybody",
+          "start": 116.84,
+          "end": 117.6,
+          "confidence": 0.724
+        },
+        {
+          "text": "wants",
+          "start": 117.6,
+          "end": 117.96,
+          "confidence": 0.993
+        },
+        {
+          "text": "to",
+          "start": 117.96,
+          "end": 118.14,
+          "confidence": 0.998
+        },
+        {
+          "text": "be",
+          "start": 118.14,
+          "end": 118.26,
+          "confidence": 0.999
+        },
+        {
+          "text": "my",
+          "start": 118.26,
+          "end": 118.62,
+          "confidence": 0.997
+        },
+        {
+          "text": "enemy",
+          "start": 118.62,
+          "end": 119.3,
+          "confidence": 0.988
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 11992,
+      "start": 119.96,
+      "end": 126.26,
+      "text": " I smell the sympathy Everybody wants to be my enemy",
+      "tokens": [
+        50364,
+        286,
+        4316,
+        264,
+        33240,
+        7646,
+        2738,
+        281,
+        312,
+        452,
+        5945,
+        50686
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.38010619236872745,
+      "compression_ratio": 1.755458515283843,
+      "no_speech_prob": 0.7215486168861389,
+      "confidence": 0.725,
+      "words": [
+        {
+          "text": "I",
+          "start": 119.96,
+          "end": 120.78,
+          "confidence": 0.324
+        },
+        {
+          "text": "smell",
+          "start": 120.78,
+          "end": 121.42,
+          "confidence": 0.796
+        },
+        {
+          "text": "the",
+          "start": 121.42,
+          "end": 121.72,
+          "confidence": 0.857
+        },
+        {
+          "text": "sympathy",
+          "start": 121.72,
+          "end": 122.54,
+          "confidence": 0.981
+        },
+        {
+          "text": "Everybody",
+          "start": 122.54,
+          "end": 123.8,
+          "confidence": 0.265
+        },
+        {
+          "text": "wants",
+          "start": 123.8,
+          "end": 124.18,
+          "confidence": 0.984
+        },
+        {
+          "text": "to",
+          "start": 124.18,
+          "end": 124.48,
+          "confidence": 0.994
+        },
+        {
+          "text": "be",
+          "start": 124.48,
+          "end": 124.86,
+          "confidence": 0.994
+        },
+        {
+          "text": "my",
+          "start": 124.86,
+          "end": 125.58,
+          "confidence": 0.747
+        },
+        {
+          "text": "enemy",
+          "start": 125.58,
+          "end": 126.26,
+          "confidence": 0.967
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 11992,
+      "start": 126.6,
+      "end": 132.52,
+      "text": " Look out for yourself My enemy",
+      "tokens": [
+        50686,
+        2053,
+        484,
+        337,
+        1803,
+        1222,
+        5945,
+        50994
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.38010619236872745,
+      "compression_ratio": 1.755458515283843,
+      "no_speech_prob": 0.7215486168861389,
+      "confidence": 0.712,
+      "words": [
+        {
+          "text": "Look",
+          "start": 126.6,
+          "end": 130.08,
+          "confidence": 0.463
+        },
+        {
+          "text": "out",
+          "start": 130.08,
+          "end": 130.26,
+          "confidence": 0.74
+        },
+        {
+          "text": "for",
+          "start": 130.26,
+          "end": 130.48,
+          "confidence": 0.993
+        },
+        {
+          "text": "yourself",
+          "start": 130.48,
+          "end": 130.98,
+          "confidence": 0.983
+        },
+        {
+          "text": "My",
+          "start": 130.98,
+          "end": 131.78,
+          "confidence": 0.399
+        },
+        {
+          "text": "enemy",
+          "start": 131.78,
+          "end": 132.52,
+          "confidence": 0.978
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 11992,
+      "start": 133.92,
+      "end": 137.26,
+      "text": " Look out for yourself",
+      "tokens": [
+        50994,
+        2053,
+        484,
+        337,
+        1803,
+        51230
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.38010619236872745,
+      "compression_ratio": 1.755458515283843,
+      "no_speech_prob": 0.7215486168861389,
+      "confidence": 0.977,
+      "words": [
+        {
+          "text": "Look",
+          "start": 133.92,
+          "end": 134.06,
+          "confidence": 0.923
+        },
+        {
+          "text": "out",
+          "start": 134.06,
+          "end": 136.56,
+          "confidence": 0.989
+        },
+        {
+          "text": "for",
+          "start": 136.56,
+          "end": 136.74,
+          "confidence": 0.999
+        },
+        {
+          "text": "yourself",
+          "start": 136.74,
+          "end": 137.26,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 11992,
+      "start": 137.62,
+      "end": 140.18,
+      "text": " Look, okay, I'm Hoping that somebody pray for me",
+      "tokens": [
+        51230,
+        2053,
+        11,
+        1392,
+        11,
+        286,
+        478,
+        13438,
+        278,
+        300,
+        2618,
+        3690,
+        337,
+        385,
+        51374
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.38010619236872745,
+      "compression_ratio": 1.755458515283843,
+      "no_speech_prob": 0.7215486168861389,
+      "confidence": 0.779,
+      "words": [
+        {
+          "text": "Look,",
+          "start": 137.62,
+          "end": 137.88,
+          "confidence": 0.774
+        },
+        {
+          "text": "okay,",
+          "start": 138.44,
+          "end": 138.58,
+          "confidence": 0.665
+        },
+        {
+          "text": "I'm",
+          "start": 138.76,
+          "end": 138.94,
+          "confidence": 0.965
+        },
+        {
+          "text": "Hoping",
+          "start": 138.94,
+          "end": 139.22,
+          "confidence": 0.414
+        },
+        {
+          "text": "that",
+          "start": 139.22,
+          "end": 139.34,
+          "confidence": 0.967
+        },
+        {
+          "text": "somebody",
+          "start": 139.34,
+          "end": 139.58,
+          "confidence": 0.985
+        },
+        {
+          "text": "pray",
+          "start": 139.58,
+          "end": 139.86,
+          "confidence": 0.855
+        },
+        {
+          "text": "for",
+          "start": 139.86,
+          "end": 140.02,
+          "confidence": 0.959
+        },
+        {
+          "text": "me",
+          "start": 140.02,
+          "end": 140.18,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 11992,
+      "start": 140.36,
+      "end": 143.2,
+      "text": " I'm praying that somebody vote for me I'm staying where nobody's supposed to be",
+      "tokens": [
+        51374,
+        286,
+        478,
+        15611,
+        300,
+        2618,
+        4740,
+        337,
+        385,
+        286,
+        478,
+        7939,
+        689,
+        5079,
+        311,
+        3442,
+        281,
+        312,
+        51524
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.38010619236872745,
+      "compression_ratio": 1.755458515283843,
+      "no_speech_prob": 0.7215486168861389,
+      "confidence": 0.846,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 140.36,
+          "end": 140.48,
+          "confidence": 0.788
+        },
+        {
+          "text": "praying",
+          "start": 140.48,
+          "end": 140.64,
+          "confidence": 0.869
+        },
+        {
+          "text": "that",
+          "start": 140.64,
+          "end": 140.84,
+          "confidence": 0.97
+        },
+        {
+          "text": "somebody",
+          "start": 140.84,
+          "end": 141.1,
+          "confidence": 0.996
+        },
+        {
+          "text": "vote",
+          "start": 141.1,
+          "end": 141.34,
+          "confidence": 0.372
+        },
+        {
+          "text": "for",
+          "start": 141.34,
+          "end": 141.5,
+          "confidence": 0.999
+        },
+        {
+          "text": "me",
+          "start": 141.5,
+          "end": 141.7,
+          "confidence": 0.999
+        },
+        {
+          "text": "I'm",
+          "start": 141.7,
+          "end": 141.96,
+          "confidence": 0.902
+        },
+        {
+          "text": "staying",
+          "start": 141.96,
+          "end": 142.16,
+          "confidence": 0.696
+        },
+        {
+          "text": "where",
+          "start": 142.16,
+          "end": 142.34,
+          "confidence": 0.964
+        },
+        {
+          "text": "nobody's",
+          "start": 142.34,
+          "end": 142.68,
+          "confidence": 0.768
+        },
+        {
+          "text": "supposed",
+          "start": 142.68,
+          "end": 142.96,
+          "confidence": 0.97
+        },
+        {
+          "text": "to",
+          "start": 142.96,
+          "end": 143.1,
+          "confidence": 0.996
+        },
+        {
+          "text": "be",
+          "start": 143.1,
+          "end": 143.2,
+          "confidence": 0.975
+        }
+      ]
+    },
+    {
+      "id": 17,
+      "seek": 11992,
+      "start": 143.24,
+      "end": 146.29,
+      "text": " I propose to be in a wreck of emotions Ready to go whenever she let me know",
+      "tokens": [
+        51524,
+        286,
+        17421,
+        281,
+        312,
+        294,
+        257,
+        21478,
+        295,
+        8462,
+        9944,
+        281,
+        352,
+        5699,
+        750,
+        718,
+        385,
+        458,
+        51684
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.38010619236872745,
+      "compression_ratio": 1.755458515283843,
+      "no_speech_prob": 0.7215486168861389,
+      "confidence": 0.711,
+      "words": [
+        {
+          "text": "I",
+          "start": 143.24,
+          "end": 143.4,
+          "confidence": 0.432
+        },
+        {
+          "text": "propose",
+          "start": 143.4,
+          "end": 143.72,
+          "confidence": 0.301
+        },
+        {
+          "text": "to",
+          "start": 143.72,
+          "end": 143.9,
+          "confidence": 0.838
+        },
+        {
+          "text": "be",
+          "start": 143.9,
+          "end": 144.04,
+          "confidence": 0.545
+        },
+        {
+          "text": "in",
+          "start": 144.04,
+          "end": 144.18,
+          "confidence": 0.741
+        },
+        {
+          "text": "a",
+          "start": 144.18,
+          "end": 144.3,
+          "confidence": 0.678
+        },
+        {
+          "text": "wreck",
+          "start": 144.3,
+          "end": 144.4,
+          "confidence": 0.392
+        },
+        {
+          "text": "of",
+          "start": 144.4,
+          "end": 144.54,
+          "confidence": 0.983
+        },
+        {
+          "text": "emotions",
+          "start": 144.54,
+          "end": 145.0,
+          "confidence": 0.916
+        },
+        {
+          "text": "Ready",
+          "start": 145.0,
+          "end": 145.3,
+          "confidence": 0.864
+        },
+        {
+          "text": "to",
+          "start": 145.3,
+          "end": 145.46,
+          "confidence": 0.994
+        },
+        {
+          "text": "go",
+          "start": 145.46,
+          "end": 145.6,
+          "confidence": 0.996
+        },
+        {
+          "text": "whenever",
+          "start": 145.6,
+          "end": 145.8,
+          "confidence": 0.844
+        },
+        {
+          "text": "she",
+          "start": 145.8,
+          "end": 145.96,
+          "confidence": 0.428
+        },
+        {
+          "text": "let",
+          "start": 145.96,
+          "end": 146.08,
+          "confidence": 0.954
+        },
+        {
+          "text": "me",
+          "start": 146.08,
+          "end": 146.16,
+          "confidence": 0.999
+        },
+        {
+          "text": "know",
+          "start": 146.16,
+          "end": 146.29,
+          "confidence": 0.977
+        }
+      ]
+    },
+    {
+      "id": 18,
+      "seek": 11992,
+      "start": 146.29,
+      "end": 149.78,
+      "text": " The road is long so put the pedal into the flow The enemy on my trail, my energy unavailable",
+      "tokens": [
+        51684,
+        440,
+        3060,
+        307,
+        938,
+        370,
+        829,
+        264,
+        19122,
+        666,
+        264,
+        3095,
+        440,
+        5945,
+        322,
+        452,
+        9924,
+        11,
+        452,
+        2281,
+        36541,
+        32699,
+        51860
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.38010619236872745,
+      "compression_ratio": 1.755458515283843,
+      "no_speech_prob": 0.7215486168861389,
+      "confidence": 0.912,
+      "words": [
+        {
+          "text": "The",
+          "start": 146.29,
+          "end": 146.52,
+          "confidence": 0.897
+        },
+        {
+          "text": "road",
+          "start": 146.52,
+          "end": 146.68,
+          "confidence": 0.986
+        },
+        {
+          "text": "is",
+          "start": 146.68,
+          "end": 146.78,
+          "confidence": 0.971
+        },
+        {
+          "text": "long",
+          "start": 146.78,
+          "end": 146.92,
+          "confidence": 0.913
+        },
+        {
+          "text": "so",
+          "start": 146.92,
+          "end": 147.04,
+          "confidence": 0.67
+        },
+        {
+          "text": "put",
+          "start": 147.04,
+          "end": 147.16,
+          "confidence": 0.954
+        },
+        {
+          "text": "the",
+          "start": 147.16,
+          "end": 147.28,
+          "confidence": 0.975
+        },
+        {
+          "text": "pedal",
+          "start": 147.28,
+          "end": 147.42,
+          "confidence": 0.924
+        },
+        {
+          "text": "into",
+          "start": 147.42,
+          "end": 147.6,
+          "confidence": 0.946
+        },
+        {
+          "text": "the",
+          "start": 147.6,
+          "end": 147.74,
+          "confidence": 0.992
+        },
+        {
+          "text": "flow",
+          "start": 147.74,
+          "end": 147.88,
+          "confidence": 0.844
+        },
+        {
+          "text": "The",
+          "start": 147.88,
+          "end": 148.08,
+          "confidence": 0.71
+        },
+        {
+          "text": "enemy",
+          "start": 148.08,
+          "end": 148.26,
+          "confidence": 0.887
+        },
+        {
+          "text": "on",
+          "start": 148.26,
+          "end": 148.38,
+          "confidence": 0.969
+        },
+        {
+          "text": "my",
+          "start": 148.38,
+          "end": 148.5,
+          "confidence": 0.982
+        },
+        {
+          "text": "trail,",
+          "start": 148.5,
+          "end": 148.64,
+          "confidence": 0.992
+        },
+        {
+          "text": "my",
+          "start": 148.72,
+          "end": 148.86,
+          "confidence": 0.99
+        },
+        {
+          "text": "energy",
+          "start": 148.86,
+          "end": 149.1,
+          "confidence": 0.992
+        },
+        {
+          "text": "unavailable",
+          "start": 149.1,
+          "end": 149.78,
+          "confidence": 0.875
+        }
+      ]
+    },
+    {
+      "id": 19,
+      "seek": 14984,
+      "start": 150.02,
+      "end": 151.18,
+      "text": " I'ma tell the master the way go",
+      "tokens": [
+        50364,
+        286,
+        478,
+        64,
+        980,
+        264,
+        4505,
+        264,
+        636,
+        352,
+        50436
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.45425062569958424,
+      "compression_ratio": 1.7374631268436578,
+      "no_speech_prob": 0.7155851125717163,
+      "confidence": 0.592,
+      "words": [
+        {
+          "text": "I'ma",
+          "start": 150.02,
+          "end": 150.24,
+          "confidence": 0.68
+        },
+        {
+          "text": "tell",
+          "start": 150.24,
+          "end": 150.36,
+          "confidence": 0.983
+        },
+        {
+          "text": "the",
+          "start": 150.36,
+          "end": 150.46,
+          "confidence": 0.248
+        },
+        {
+          "text": "master",
+          "start": 150.46,
+          "end": 150.68,
+          "confidence": 0.223
+        },
+        {
+          "text": "the",
+          "start": 150.68,
+          "end": 150.9,
+          "confidence": 0.783
+        },
+        {
+          "text": "way",
+          "start": 150.9,
+          "end": 151.0,
+          "confidence": 0.991
+        },
+        {
+          "text": "go",
+          "start": 151.0,
+          "end": 151.18,
+          "confidence": 0.673
+        }
+      ]
+    },
+    {
+      "id": 20,
+      "seek": 14984,
+      "start": 151.2,
+      "end": 152.54,
+      "text": " Hey, when I'm flat on my track to the top",
+      "tokens": [
+        50436,
+        1911,
+        11,
+        562,
+        286,
+        478,
+        4962,
+        322,
+        452,
+        2837,
+        281,
+        264,
+        1192,
+        50500
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.45425062569958424,
+      "compression_ratio": 1.7374631268436578,
+      "no_speech_prob": 0.7155851125717163,
+      "confidence": 0.589,
+      "words": [
+        {
+          "text": "Hey,",
+          "start": 151.2,
+          "end": 151.4,
+          "confidence": 0.215
+        },
+        {
+          "text": "when",
+          "start": 151.46,
+          "end": 151.56,
+          "confidence": 0.811
+        },
+        {
+          "text": "I'm",
+          "start": 151.56,
+          "end": 151.72,
+          "confidence": 0.523
+        },
+        {
+          "text": "flat",
+          "start": 151.72,
+          "end": 151.8,
+          "confidence": 0.241
+        },
+        {
+          "text": "on",
+          "start": 151.8,
+          "end": 151.9,
+          "confidence": 0.636
+        },
+        {
+          "text": "my",
+          "start": 151.9,
+          "end": 152.02,
+          "confidence": 0.961
+        },
+        {
+          "text": "track",
+          "start": 152.02,
+          "end": 152.16,
+          "confidence": 0.482
+        },
+        {
+          "text": "to",
+          "start": 152.16,
+          "end": 152.32,
+          "confidence": 0.874
+        },
+        {
+          "text": "the",
+          "start": 152.32,
+          "end": 152.42,
+          "confidence": 0.996
+        },
+        {
+          "text": "top",
+          "start": 152.42,
+          "end": 152.54,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 21,
+      "seek": 14984,
+      "start": 152.54,
+      "end": 154.34,
+      "text": " I been out of shape, thinking that I'm a box of an astronaut",
+      "tokens": [
+        50500,
+        286,
+        668,
+        484,
+        295,
+        3909,
+        11,
+        1953,
+        300,
+        286,
+        478,
+        257,
+        2424,
+        295,
+        364,
+        18516,
+        50592
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.45425062569958424,
+      "compression_ratio": 1.7374631268436578,
+      "no_speech_prob": 0.7155851125717163,
+      "confidence": 0.725,
+      "words": [
+        {
+          "text": "I",
+          "start": 152.54,
+          "end": 152.7,
+          "confidence": 0.988
+        },
+        {
+          "text": "been",
+          "start": 152.7,
+          "end": 152.76,
+          "confidence": 0.617
+        },
+        {
+          "text": "out",
+          "start": 152.76,
+          "end": 152.9,
+          "confidence": 0.679
+        },
+        {
+          "text": "of",
+          "start": 152.9,
+          "end": 153.02,
+          "confidence": 0.959
+        },
+        {
+          "text": "shape,",
+          "start": 153.02,
+          "end": 153.1,
+          "confidence": 0.999
+        },
+        {
+          "text": "thinking",
+          "start": 153.16,
+          "end": 153.32,
+          "confidence": 0.667
+        },
+        {
+          "text": "that",
+          "start": 153.32,
+          "end": 153.46,
+          "confidence": 0.261
+        },
+        {
+          "text": "I'm",
+          "start": 153.46,
+          "end": 153.62,
+          "confidence": 0.736
+        },
+        {
+          "text": "a",
+          "start": 153.62,
+          "end": 153.72,
+          "confidence": 0.725
+        },
+        {
+          "text": "box",
+          "start": 153.72,
+          "end": 153.76,
+          "confidence": 0.878
+        },
+        {
+          "text": "of",
+          "start": 153.76,
+          "end": 153.9,
+          "confidence": 0.483
+        },
+        {
+          "text": "an",
+          "start": 153.9,
+          "end": 154.04,
+          "confidence": 0.986
+        },
+        {
+          "text": "astronaut",
+          "start": 154.04,
+          "end": 154.34,
+          "confidence": 0.984
+        }
+      ]
+    },
+    {
+      "id": 22,
+      "seek": 14984,
+      "start": 154.5,
+      "end": 156.42,
+      "text": " Blasted off the planet, rocked the cars, catastrophic",
+      "tokens": [
+        50592,
+        2177,
+        34440,
+        766,
+        264,
+        5054,
+        11,
+        3727,
+        292,
+        264,
+        5163,
+        11,
+        34915,
+        50692
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.45425062569958424,
+      "compression_ratio": 1.7374631268436578,
+      "no_speech_prob": 0.7155851125717163,
+      "confidence": 0.742,
+      "words": [
+        {
+          "text": "Blasted",
+          "start": 154.5,
+          "end": 154.82,
+          "confidence": 0.817
+        },
+        {
+          "text": "off",
+          "start": 154.82,
+          "end": 155.02,
+          "confidence": 0.981
+        },
+        {
+          "text": "the",
+          "start": 155.02,
+          "end": 155.18,
+          "confidence": 0.95
+        },
+        {
+          "text": "planet,",
+          "start": 155.18,
+          "end": 155.36,
+          "confidence": 0.994
+        },
+        {
+          "text": "rocked",
+          "start": 155.44,
+          "end": 155.66,
+          "confidence": 0.691
+        },
+        {
+          "text": "the",
+          "start": 155.66,
+          "end": 155.74,
+          "confidence": 0.801
+        },
+        {
+          "text": "cars,",
+          "start": 155.74,
+          "end": 155.9,
+          "confidence": 0.308
+        },
+        {
+          "text": "catastrophic",
+          "start": 155.9,
+          "end": 156.42,
+          "confidence": 0.693
+        }
+      ]
+    },
+    {
+      "id": 23,
+      "seek": 14984,
+      "start": 156.44,
+      "end": 158.18,
+      "text": " And it matters more because I had it, now I had it",
+      "tokens": [
+        50692,
+        400,
+        309,
+        7001,
+        544,
+        570,
+        286,
+        632,
+        309,
+        11,
+        586,
+        286,
+        632,
+        309,
+        50777
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.45425062569958424,
+      "compression_ratio": 1.7374631268436578,
+      "no_speech_prob": 0.7155851125717163,
+      "confidence": 0.787,
+      "words": [
+        {
+          "text": "And",
+          "start": 156.44,
+          "end": 156.64,
+          "confidence": 0.858
+        },
+        {
+          "text": "it",
+          "start": 156.64,
+          "end": 156.78,
+          "confidence": 0.678
+        },
+        {
+          "text": "matters",
+          "start": 156.78,
+          "end": 156.96,
+          "confidence": 0.996
+        },
+        {
+          "text": "more",
+          "start": 156.96,
+          "end": 157.18,
+          "confidence": 0.981
+        },
+        {
+          "text": "because",
+          "start": 157.18,
+          "end": 157.42,
+          "confidence": 0.749
+        },
+        {
+          "text": "I",
+          "start": 157.42,
+          "end": 157.56,
+          "confidence": 0.703
+        },
+        {
+          "text": "had",
+          "start": 157.56,
+          "end": 157.66,
+          "confidence": 0.951
+        },
+        {
+          "text": "it,",
+          "start": 157.66,
+          "end": 157.8,
+          "confidence": 0.986
+        },
+        {
+          "text": "now",
+          "start": 157.8,
+          "end": 157.94,
+          "confidence": 0.56
+        },
+        {
+          "text": "I",
+          "start": 157.94,
+          "end": 158.06,
+          "confidence": 0.754
+        },
+        {
+          "text": "had",
+          "start": 158.06,
+          "end": 158.12,
+          "confidence": 0.937
+        },
+        {
+          "text": "it",
+          "start": 158.12,
+          "end": 158.18,
+          "confidence": 0.51
+        }
+      ]
+    },
+    {
+      "id": 24,
+      "seek": 14984,
+      "start": 158.18,
+      "end": 159.84,
+      "text": " I thought about wreaking havoc on an opposition",
+      "tokens": [
+        50777,
+        286,
+        1194,
+        466,
+        46674,
+        2456,
+        47367,
+        322,
+        364,
+        13504,
+        50864
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.45425062569958424,
+      "compression_ratio": 1.7374631268436578,
+      "no_speech_prob": 0.7155851125717163,
+      "confidence": 0.959,
+      "words": [
+        {
+          "text": "I",
+          "start": 158.18,
+          "end": 158.24,
+          "confidence": 0.915
+        },
+        {
+          "text": "thought",
+          "start": 158.24,
+          "end": 158.38,
+          "confidence": 0.982
+        },
+        {
+          "text": "about",
+          "start": 158.38,
+          "end": 158.58,
+          "confidence": 0.981
+        },
+        {
+          "text": "wreaking",
+          "start": 158.58,
+          "end": 158.86,
+          "confidence": 0.978
+        },
+        {
+          "text": "havoc",
+          "start": 158.86,
+          "end": 159.08,
+          "confidence": 1.0
+        },
+        {
+          "text": "on",
+          "start": 159.08,
+          "end": 159.3,
+          "confidence": 0.911
+        },
+        {
+          "text": "an",
+          "start": 159.3,
+          "end": 159.46,
+          "confidence": 0.909
+        },
+        {
+          "text": "opposition",
+          "start": 159.46,
+          "end": 159.84,
+          "confidence": 0.984
+        }
+      ]
+    },
+    {
+      "id": 25,
+      "seek": 14984,
+      "start": 159.86,
+      "end": 161.56,
+      "text": " Kinda shockin', they want it static, with precision",
+      "tokens": [
+        50864,
+        35553,
+        5588,
+        259,
+        6098,
+        436,
+        528,
+        309,
+        13437,
+        11,
+        365,
+        18356,
+        50952
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.45425062569958424,
+      "compression_ratio": 1.7374631268436578,
+      "no_speech_prob": 0.7155851125717163,
+      "confidence": 0.572,
+      "words": [
+        {
+          "text": "Kinda",
+          "start": 159.86,
+          "end": 160.1,
+          "confidence": 0.654
+        },
+        {
+          "text": "shockin',",
+          "start": 160.1,
+          "end": 160.48,
+          "confidence": 0.381
+        },
+        {
+          "text": "they",
+          "start": 160.48,
+          "end": 160.6,
+          "confidence": 0.305
+        },
+        {
+          "text": "want",
+          "start": 160.6,
+          "end": 160.74,
+          "confidence": 0.57
+        },
+        {
+          "text": "it",
+          "start": 160.74,
+          "end": 160.88,
+          "confidence": 0.695
+        },
+        {
+          "text": "static,",
+          "start": 160.88,
+          "end": 161.02,
+          "confidence": 0.986
+        },
+        {
+          "text": "with",
+          "start": 161.14,
+          "end": 161.28,
+          "confidence": 0.733
+        },
+        {
+          "text": "precision",
+          "start": 161.28,
+          "end": 161.56,
+          "confidence": 0.794
+        }
+      ]
+    },
+    {
+      "id": 26,
+      "seek": 14984,
+      "start": 161.62,
+      "end": 163.36,
+      "text": " I'm automatic, quarterback, I ain't talkin' second",
+      "tokens": [
+        50952,
+        286,
+        478,
+        12509,
+        11,
+        31952,
+        11,
+        286,
+        7862,
+        380,
+        39243,
+        6,
+        1150,
+        51043
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.45425062569958424,
+      "compression_ratio": 1.7374631268436578,
+      "no_speech_prob": 0.7155851125717163,
+      "confidence": 0.812,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 161.62,
+          "end": 161.88,
+          "confidence": 0.963
+        },
+        {
+          "text": "automatic,",
+          "start": 161.88,
+          "end": 162.18,
+          "confidence": 0.961
+        },
+        {
+          "text": "quarterback,",
+          "start": 162.56,
+          "end": 162.58,
+          "confidence": 0.667
+        },
+        {
+          "text": "I",
+          "start": 162.66,
+          "end": 162.78,
+          "confidence": 0.727
+        },
+        {
+          "text": "ain't",
+          "start": 162.78,
+          "end": 162.9,
+          "confidence": 0.984
+        },
+        {
+          "text": "talkin'",
+          "start": 162.9,
+          "end": 163.2,
+          "confidence": 0.747
+        },
+        {
+          "text": "second",
+          "start": 163.2,
+          "end": 163.36,
+          "confidence": 0.536
+        }
+      ]
+    },
+    {
+      "id": 27,
+      "seek": 14984,
+      "start": 163.36,
+      "end": 165.2,
+      "text": " Pack it, pack it up, I don't panic, better batter up",
+      "tokens": [
+        51043,
+        18466,
+        309,
+        11,
+        2844,
+        309,
+        493,
+        11,
+        286,
+        500,
+        380,
+        14783,
+        11,
+        1101,
+        4220,
+        493,
+        51132
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.45425062569958424,
+      "compression_ratio": 1.7374631268436578,
+      "no_speech_prob": 0.7155851125717163,
+      "confidence": 0.789,
+      "words": [
+        {
+          "text": "Pack",
+          "start": 163.36,
+          "end": 163.6,
+          "confidence": 0.939
+        },
+        {
+          "text": "it,",
+          "start": 163.6,
+          "end": 163.68,
+          "confidence": 0.893
+        },
+        {
+          "text": "pack",
+          "start": 163.7,
+          "end": 163.88,
+          "confidence": 0.962
+        },
+        {
+          "text": "it",
+          "start": 163.88,
+          "end": 164.02,
+          "confidence": 0.998
+        },
+        {
+          "text": "up,",
+          "start": 164.02,
+          "end": 164.12,
+          "confidence": 0.979
+        },
+        {
+          "text": "I",
+          "start": 164.12,
+          "end": 164.22,
+          "confidence": 0.974
+        },
+        {
+          "text": "don't",
+          "start": 164.22,
+          "end": 164.36,
+          "confidence": 0.888
+        },
+        {
+          "text": "panic,",
+          "start": 164.36,
+          "end": 164.56,
+          "confidence": 0.999
+        },
+        {
+          "text": "better",
+          "start": 164.62,
+          "end": 164.88,
+          "confidence": 0.568
+        },
+        {
+          "text": "batter",
+          "start": 164.88,
+          "end": 165.02,
+          "confidence": 0.176
+        },
+        {
+          "text": "up",
+          "start": 165.02,
+          "end": 165.2,
+          "confidence": 0.963
+        }
+      ]
+    },
+    {
+      "id": 28,
+      "seek": 14984,
+      "start": 165.2,
+      "end": 166.76,
+      "text": " Who the baddest, it don't matter cause we is your",
+      "tokens": [
+        51132,
+        2102,
+        264,
+        1578,
+        23748,
+        11,
+        309,
+        500,
+        380,
+        1871,
+        3082,
+        321,
+        307,
+        428,
+        51210
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.45425062569958424,
+      "compression_ratio": 1.7374631268436578,
+      "no_speech_prob": 0.7155851125717163,
+      "confidence": 0.714,
+      "words": [
+        {
+          "text": "Who",
+          "start": 165.2,
+          "end": 165.4,
+          "confidence": 0.994
+        },
+        {
+          "text": "the",
+          "start": 165.4,
+          "end": 165.54,
+          "confidence": 0.954
+        },
+        {
+          "text": "baddest,",
+          "start": 165.54,
+          "end": 165.78,
+          "confidence": 0.833
+        },
+        {
+          "text": "it",
+          "start": 165.8,
+          "end": 165.9,
+          "confidence": 0.993
+        },
+        {
+          "text": "don't",
+          "start": 165.9,
+          "end": 166.04,
+          "confidence": 0.995
+        },
+        {
+          "text": "matter",
+          "start": 166.04,
+          "end": 166.18,
+          "confidence": 0.999
+        },
+        {
+          "text": "cause",
+          "start": 166.18,
+          "end": 166.38,
+          "confidence": 0.235
+        },
+        {
+          "text": "we",
+          "start": 166.38,
+          "end": 166.56,
+          "confidence": 0.956
+        },
+        {
+          "text": "is",
+          "start": 166.56,
+          "end": 166.64,
+          "confidence": 0.208
+        },
+        {
+          "text": "your",
+          "start": 166.64,
+          "end": 166.76,
+          "confidence": 0.577
+        }
+      ]
+    },
+    {
+      "id": 29,
+      "seek": 14984,
+      "start": 166.86,
+      "end": 169.82,
+      "text": " Everybody wants to be my enemy",
+      "tokens": [
+        51210,
+        7646,
+        2738,
+        281,
+        312,
+        452,
+        5945,
+        51402
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.45425062569958424,
+      "compression_ratio": 1.7374631268436578,
+      "no_speech_prob": 0.7155851125717163,
+      "confidence": 0.976,
+      "words": [
+        {
+          "text": "Everybody",
+          "start": 166.86,
+          "end": 167.44,
+          "confidence": 0.922
+        },
+        {
+          "text": "wants",
+          "start": 167.44,
+          "end": 167.82,
+          "confidence": 0.985
+        },
+        {
+          "text": "to",
+          "start": 167.82,
+          "end": 168.0,
+          "confidence": 0.998
+        },
+        {
+          "text": "be",
+          "start": 168.0,
+          "end": 168.16,
+          "confidence": 0.998
+        },
+        {
+          "text": "my",
+          "start": 168.16,
+          "end": 168.44,
+          "confidence": 0.993
+        },
+        {
+          "text": "enemy",
+          "start": 168.44,
+          "end": 169.82,
+          "confidence": 0.965
+        }
+      ]
+    },
+    {
+      "id": 30,
+      "seek": 14984,
+      "start": 170.62,
+      "end": 172.24,
+      "text": " Spare the sympathy",
+      "tokens": [
+        51402,
+        1738,
+        543,
+        264,
+        33240,
+        51522
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.45425062569958424,
+      "compression_ratio": 1.7374631268436578,
+      "no_speech_prob": 0.7155851125717163,
+      "confidence": 0.815,
+      "words": [
+        {
+          "text": "Spare",
+          "start": 170.62,
+          "end": 171.28,
+          "confidence": 0.711
+        },
+        {
+          "text": "the",
+          "start": 171.28,
+          "end": 171.54,
+          "confidence": 0.974
+        },
+        {
+          "text": "sympathy",
+          "start": 171.54,
+          "end": 172.24,
+          "confidence": 0.896
+        }
+      ]
+    },
+    {
+      "id": 31,
+      "seek": 14984,
+      "start": 173.1,
+      "end": 176.24,
+      "text": " Everybody wants to be my enemy",
+      "tokens": [
+        51522,
+        7646,
+        2738,
+        281,
+        312,
+        452,
+        5945,
+        51720
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.45425062569958424,
+      "compression_ratio": 1.7374631268436578,
+      "no_speech_prob": 0.7155851125717163,
+      "confidence": 0.984,
+      "words": [
+        {
+          "text": "Everybody",
+          "start": 173.1,
+          "end": 173.7,
+          "confidence": 0.994
+        },
+        {
+          "text": "wants",
+          "start": 173.7,
+          "end": 174.06,
+          "confidence": 0.994
+        },
+        {
+          "text": "to",
+          "start": 174.06,
+          "end": 174.36,
+          "confidence": 0.999
+        },
+        {
+          "text": "be",
+          "start": 174.36,
+          "end": 174.72,
+          "confidence": 0.999
+        },
+        {
+          "text": "my",
+          "start": 174.72,
+          "end": 175.46,
+          "confidence": 0.923
+        },
+        {
+          "text": "enemy",
+          "start": 175.46,
+          "end": 176.24,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 32,
+      "seek": 14984,
+      "start": 176.86,
+      "end": 178.48,
+      "text": " Oh, the misery",
+      "tokens": [
+        51720,
+        876,
+        11,
+        264,
+        32309,
+        51834
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.45425062569958424,
+      "compression_ratio": 1.7374631268436578,
+      "no_speech_prob": 0.7155851125717163,
+      "confidence": 0.879,
+      "words": [
+        {
+          "text": "Oh,",
+          "start": 176.86,
+          "end": 177.5,
+          "confidence": 0.692
+        },
+        {
+          "text": "the",
+          "start": 177.56,
+          "end": 177.76,
+          "confidence": 0.984
+        },
+        {
+          "text": "misery",
+          "start": 177.76,
+          "end": 178.48,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 33,
+      "seek": 17924,
+      "start": 179.3,
+      "end": 181.62,
+      "text": " Everybody wants to be my enemy",
+      "tokens": [
+        50364,
+        7646,
+        2738,
+        281,
+        312,
+        452,
+        5945,
+        50514
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.35596295406943873,
+      "compression_ratio": 1.8440366972477065,
+      "no_speech_prob": 0.4185682237148285,
+      "confidence": 0.949,
+      "words": [
+        {
+          "text": "Everybody",
+          "start": 179.3,
+          "end": 179.92,
+          "confidence": 0.776
+        },
+        {
+          "text": "wants",
+          "start": 179.92,
+          "end": 180.3,
+          "confidence": 0.98
+        },
+        {
+          "text": "to",
+          "start": 180.3,
+          "end": 180.48,
+          "confidence": 0.997
+        },
+        {
+          "text": "be",
+          "start": 180.48,
+          "end": 180.62,
+          "confidence": 0.998
+        },
+        {
+          "text": "my",
+          "start": 180.62,
+          "end": 180.92,
+          "confidence": 0.992
+        },
+        {
+          "text": "enemy",
+          "start": 180.92,
+          "end": 181.62,
+          "confidence": 0.973
+        }
+      ]
+    },
+    {
+      "id": 34,
+      "seek": 17924,
+      "start": 183.08,
+      "end": 184.64,
+      "text": " Spell the sympathy",
+      "tokens": [
+        50514,
+        3550,
+        285,
+        264,
+        33240,
+        50664
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.35596295406943873,
+      "compression_ratio": 1.8440366972477065,
+      "no_speech_prob": 0.4185682237148285,
+      "confidence": 0.56,
+      "words": [
+        {
+          "text": "Spell",
+          "start": 183.08,
+          "end": 183.78,
+          "confidence": 0.345
+        },
+        {
+          "text": "the",
+          "start": 183.78,
+          "end": 184.08,
+          "confidence": 0.926
+        },
+        {
+          "text": "sympathy",
+          "start": 184.08,
+          "end": 184.64,
+          "confidence": 0.892
+        }
+      ]
+    },
+    {
+      "id": 35,
+      "seek": 17924,
+      "start": 185.5,
+      "end": 188.48,
+      "text": " Everybody wants to be my enemy",
+      "tokens": [
+        50664,
+        7646,
+        2738,
+        281,
+        312,
+        452,
+        5945,
+        50814
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.35596295406943873,
+      "compression_ratio": 1.8440366972477065,
+      "no_speech_prob": 0.4185682237148285,
+      "confidence": 0.961,
+      "words": [
+        {
+          "text": "Everybody",
+          "start": 185.5,
+          "end": 186.16,
+          "confidence": 0.99
+        },
+        {
+          "text": "wants",
+          "start": 186.16,
+          "end": 186.52,
+          "confidence": 0.988
+        },
+        {
+          "text": "to",
+          "start": 186.52,
+          "end": 186.76,
+          "confidence": 0.999
+        },
+        {
+          "text": "be",
+          "start": 186.76,
+          "end": 187.28,
+          "confidence": 0.999
+        },
+        {
+          "text": "my",
+          "start": 187.28,
+          "end": 187.94,
+          "confidence": 0.811
+        },
+        {
+          "text": "enemy",
+          "start": 187.94,
+          "end": 188.48,
+          "confidence": 0.992
+        }
+      ]
+    },
+    {
+      "id": 36,
+      "seek": 17924,
+      "start": 188.9,
+      "end": 192.06,
+      "text": " Everywhere I swear I'll never be a saint",
+      "tokens": [
+        50814,
+        37322,
+        286,
+        11902,
+        286,
+        603,
+        1128,
+        312,
+        257,
+        28374,
+        51014
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.35596295406943873,
+      "compression_ratio": 1.8440366972477065,
+      "no_speech_prob": 0.4185682237148285,
+      "confidence": 0.558,
+      "words": [
+        {
+          "text": "Everywhere",
+          "start": 188.9,
+          "end": 189.58,
+          "confidence": 0.045
+        },
+        {
+          "text": "I",
+          "start": 189.58,
+          "end": 190.14,
+          "confidence": 0.402
+        },
+        {
+          "text": "swear",
+          "start": 190.14,
+          "end": 190.56,
+          "confidence": 0.99
+        },
+        {
+          "text": "I'll",
+          "start": 190.56,
+          "end": 190.96,
+          "confidence": 0.744
+        },
+        {
+          "text": "never",
+          "start": 190.96,
+          "end": 191.32,
+          "confidence": 0.996
+        },
+        {
+          "text": "be",
+          "start": 191.32,
+          "end": 191.68,
+          "confidence": 0.995
+        },
+        {
+          "text": "a",
+          "start": 191.68,
+          "end": 191.9,
+          "confidence": 0.61
+        },
+        {
+          "text": "saint",
+          "start": 191.9,
+          "end": 192.06,
+          "confidence": 0.87
+        }
+      ]
+    },
+    {
+      "id": 37,
+      "seek": 17924,
+      "start": 192.1,
+      "end": 194.78,
+      "text": " Nowhere my enemy",
+      "tokens": [
+        51014,
+        823,
+        6703,
+        452,
+        5945,
+        51164
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.35596295406943873,
+      "compression_ratio": 1.8440366972477065,
+      "no_speech_prob": 0.4185682237148285,
+      "confidence": 0.679,
+      "words": [
+        {
+          "text": "Nowhere",
+          "start": 192.1,
+          "end": 193.18,
+          "confidence": 0.658
+        },
+        {
+          "text": "my",
+          "start": 193.18,
+          "end": 194.08,
+          "confidence": 0.502
+        },
+        {
+          "text": "enemy",
+          "start": 194.08,
+          "end": 194.78,
+          "confidence": 0.979
+        }
+      ]
+    },
+    {
+      "id": 38,
+      "seek": 17924,
+      "start": 195.14,
+      "end": 198.36,
+      "text": " Everywhere I swear I'll never be a saint",
+      "tokens": [
+        51164,
+        37322,
+        286,
+        11902,
+        286,
+        603,
+        1128,
+        312,
+        257,
+        28374,
+        51314
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.35596295406943873,
+      "compression_ratio": 1.8440366972477065,
+      "no_speech_prob": 0.4185682237148285,
+      "confidence": 0.994,
+      "words": [
+        {
+          "text": "Everywhere",
+          "start": 195.14,
+          "end": 196.06,
+          "confidence": 0.973
+        },
+        {
+          "text": "I",
+          "start": 196.06,
+          "end": 196.5,
+          "confidence": 0.994
+        },
+        {
+          "text": "swear",
+          "start": 196.5,
+          "end": 196.78,
+          "confidence": 0.997
+        },
+        {
+          "text": "I'll",
+          "start": 196.78,
+          "end": 197.34,
+          "confidence": 0.995
+        },
+        {
+          "text": "never",
+          "start": 197.34,
+          "end": 197.56,
+          "confidence": 0.999
+        },
+        {
+          "text": "be",
+          "start": 197.56,
+          "end": 197.92,
+          "confidence": 0.999
+        },
+        {
+          "text": "a",
+          "start": 197.92,
+          "end": 198.12,
+          "confidence": 0.998
+        },
+        {
+          "text": "saint",
+          "start": 198.12,
+          "end": 198.36,
+          "confidence": 0.993
+        }
+      ]
+    },
+    {
+      "id": 39,
+      "seek": 17924,
+      "start": 198.5,
+      "end": 199.44,
+      "text": " Look out for yourself",
+      "tokens": [
+        51314,
+        2053,
+        484,
+        337,
+        1803,
+        51414
+      ],
+      "temperature": 0.4,
+      "avg_logprob": -0.35596295406943873,
+      "compression_ratio": 1.8440366972477065,
+      "no_speech_prob": 0.4185682237148285,
+      "confidence": 0.754,
+      "words": [
+        {
+          "text": "Look",
+          "start": 198.5,
+          "end": 198.74,
+          "confidence": 0.356
+        },
+        {
+          "text": "out",
+          "start": 198.74,
+          "end": 198.92,
+          "confidence": 0.98
+        },
+        {
+          "text": "for",
+          "start": 198.92,
+          "end": 199.12,
+          "confidence": 0.97
+        },
+        {
+          "text": "yourself",
+          "start": 199.12,
+          "end": 199.44,
+          "confidence": 0.956
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/corner_cases/nocond_music.mp4.words.json b/tests/expected/corner_cases/nocond_music.mp4.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..9647c5b07f285b8445d88483e2c9bd612e3d7413
--- /dev/null
+++ b/tests/expected/corner_cases/nocond_music.mp4.words.json
@@ -0,0 +1,2750 @@
+{
+  "text": " I Oh, the misery Everybody wants to be my enemy Spare the sympathy Everybody wants to be my enemy Look out for yourself My enemy Look out for yourself But I'm ready Your words up on the wall as you're praying for my phone And the laughter in the holes and the names that I've been called I stack it in my mind and I'm waiting for the time When I show you what it's like to be worse but in the mind Tell you you're the greatest But once you turn they hate us Oh, the misery Everybody wants to be my enemy Spare the sympathy Everybody wants to be my enemy Look out for yourself My enemy Look out for yourself Look, okay I'm hoping that somebody pray for me I'm praying that somebody hold for me. I'm staying where nobody's supposed to be. I propose to be in a wreck of emotions. Ready to go whenever you let me know. The road is long, so put the pedal into the flow. The enemy on my trail, my energy unavailable. I'ma tell them I said away, go away. When I'm plotting, I'ma drive to the top. I've been out of shape, thinking out of the box. I'm an astronaut, blasted off the planet. Rock the cars, catastrophic, and it matters more because I had it now. Had I thought about wreaking havoc on an opposition. Kind of shocking, they want it static. With precision, I'm automatic. Quarterback, I ain't talking second. Pack it, pack it up. I don't panic, better, better. Up who the baddest. it don't matter cause we is your enemy. I swear I'll never be insane You gotta be insane",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 2.24,
+      "end": 2.36,
+      "text": " I",
+      "tokens": [
+        50364,
+        286,
+        50464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9355003237724304,
+      "compression_ratio": 0.1111111111111111,
+      "no_speech_prob": 0.7811808586120605,
+      "confidence": 0.032,
+      "words": [
+        {
+          "text": "I",
+          "start": 2.24,
+          "end": 2.36,
+          "confidence": 0.032
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 6000,
+      "start": 60.0,
+      "end": 69.92,
+      "text": " Oh, the misery Everybody wants to be my enemy",
+      "tokens": [
+        50364,
+        876,
+        11,
+        264,
+        32309,
+        7646,
+        2738,
+        281,
+        312,
+        452,
+        5945,
+        50866
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.45629865472966974,
+      "compression_ratio": 1.62,
+      "no_speech_prob": 0.8699213266372681,
+      "confidence": 0.669,
+      "words": [
+        {
+          "text": "Oh,",
+          "start": 60.0,
+          "end": 63.4,
+          "confidence": 0.084
+        },
+        {
+          "text": "the",
+          "start": 65.24,
+          "end": 65.5,
+          "confidence": 0.797
+        },
+        {
+          "text": "misery",
+          "start": 65.5,
+          "end": 66.3,
+          "confidence": 0.993
+        },
+        {
+          "text": "Everybody",
+          "start": 66.3,
+          "end": 67.7,
+          "confidence": 0.43
+        },
+        {
+          "text": "wants",
+          "start": 67.7,
+          "end": 68.08,
+          "confidence": 0.983
+        },
+        {
+          "text": "to",
+          "start": 68.08,
+          "end": 68.26,
+          "confidence": 0.993
+        },
+        {
+          "text": "be",
+          "start": 68.26,
+          "end": 68.44,
+          "confidence": 0.996
+        },
+        {
+          "text": "my",
+          "start": 68.44,
+          "end": 68.74,
+          "confidence": 0.983
+        },
+        {
+          "text": "enemy",
+          "start": 68.74,
+          "end": 69.92,
+          "confidence": 0.984
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 6000,
+      "start": 70.88,
+      "end": 76.42,
+      "text": " Spare the sympathy Everybody wants to be my enemy",
+      "tokens": [
+        50866,
+        1738,
+        543,
+        264,
+        33240,
+        7646,
+        2738,
+        281,
+        312,
+        452,
+        5945,
+        51182
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.45629865472966974,
+      "compression_ratio": 1.62,
+      "no_speech_prob": 0.8699213266372681,
+      "confidence": 0.934,
+      "words": [
+        {
+          "text": "Spare",
+          "start": 70.88,
+          "end": 71.54,
+          "confidence": 0.814
+        },
+        {
+          "text": "the",
+          "start": 71.54,
+          "end": 71.8,
+          "confidence": 0.968
+        },
+        {
+          "text": "sympathy",
+          "start": 71.8,
+          "end": 72.64,
+          "confidence": 0.993
+        },
+        {
+          "text": "Everybody",
+          "start": 72.64,
+          "end": 73.96,
+          "confidence": 0.963
+        },
+        {
+          "text": "wants",
+          "start": 73.96,
+          "end": 74.3,
+          "confidence": 0.994
+        },
+        {
+          "text": "to",
+          "start": 74.3,
+          "end": 74.64,
+          "confidence": 0.999
+        },
+        {
+          "text": "be",
+          "start": 74.64,
+          "end": 75.16,
+          "confidence": 0.999
+        },
+        {
+          "text": "my",
+          "start": 75.16,
+          "end": 75.72,
+          "confidence": 0.837
+        },
+        {
+          "text": "enemy",
+          "start": 75.72,
+          "end": 76.42,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 6000,
+      "start": 79.92,
+      "end": 82.68,
+      "text": " Look out for yourself My enemy",
+      "tokens": [
+        51182,
+        2053,
+        484,
+        337,
+        1803,
+        1222,
+        5945,
+        51496
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.45629865472966974,
+      "compression_ratio": 1.62,
+      "no_speech_prob": 0.8699213266372681,
+      "confidence": 0.774,
+      "words": [
+        {
+          "text": "Look",
+          "start": 79.92,
+          "end": 80.24,
+          "confidence": 0.43
+        },
+        {
+          "text": "out",
+          "start": 80.24,
+          "end": 80.46,
+          "confidence": 0.99
+        },
+        {
+          "text": "for",
+          "start": 80.46,
+          "end": 80.68,
+          "confidence": 0.989
+        },
+        {
+          "text": "yourself",
+          "start": 80.68,
+          "end": 81.14,
+          "confidence": 0.97
+        },
+        {
+          "text": "My",
+          "start": 81.14,
+          "end": 81.94,
+          "confidence": 0.536
+        },
+        {
+          "text": "enemy",
+          "start": 81.94,
+          "end": 82.68,
+          "confidence": 0.98
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 6000,
+      "start": 86.14,
+      "end": 88.48,
+      "text": " Look out for yourself But I'm ready",
+      "tokens": [
+        51496,
+        2053,
+        484,
+        337,
+        1803,
+        583,
+        286,
+        478,
+        1919,
+        51792
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.45629865472966974,
+      "compression_ratio": 1.62,
+      "no_speech_prob": 0.8699213266372681,
+      "confidence": 0.928,
+      "words": [
+        {
+          "text": "Look",
+          "start": 86.14,
+          "end": 86.46,
+          "confidence": 0.748
+        },
+        {
+          "text": "out",
+          "start": 86.46,
+          "end": 86.68,
+          "confidence": 0.988
+        },
+        {
+          "text": "for",
+          "start": 86.68,
+          "end": 86.88,
+          "confidence": 0.998
+        },
+        {
+          "text": "yourself",
+          "start": 86.88,
+          "end": 87.56,
+          "confidence": 0.999
+        },
+        {
+          "text": "But",
+          "start": 87.56,
+          "end": 87.92,
+          "confidence": 0.766
+        },
+        {
+          "text": "I'm",
+          "start": 87.92,
+          "end": 88.14,
+          "confidence": 0.989
+        },
+        {
+          "text": "ready",
+          "start": 88.14,
+          "end": 88.48,
+          "confidence": 0.995
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 8856,
+      "start": 88.64,
+      "end": 91.7,
+      "text": " Your words up on the wall as you're praying for my phone",
+      "tokens": [
+        50364,
+        2260,
+        2283,
+        493,
+        322,
+        264,
+        2929,
+        382,
+        291,
+        434,
+        15611,
+        337,
+        452,
+        2593,
+        50520
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2874426958037586,
+      "compression_ratio": 1.5869565217391304,
+      "no_speech_prob": 0.7892544865608215,
+      "confidence": 0.82,
+      "words": [
+        {
+          "text": "Your",
+          "start": 88.64,
+          "end": 88.86,
+          "confidence": 0.548
+        },
+        {
+          "text": "words",
+          "start": 88.86,
+          "end": 89.18,
+          "confidence": 0.92
+        },
+        {
+          "text": "up",
+          "start": 89.18,
+          "end": 89.48,
+          "confidence": 0.964
+        },
+        {
+          "text": "on",
+          "start": 89.48,
+          "end": 89.62,
+          "confidence": 0.995
+        },
+        {
+          "text": "the",
+          "start": 89.62,
+          "end": 89.78,
+          "confidence": 0.991
+        },
+        {
+          "text": "wall",
+          "start": 89.78,
+          "end": 90.14,
+          "confidence": 0.88
+        },
+        {
+          "text": "as",
+          "start": 90.14,
+          "end": 90.32,
+          "confidence": 0.402
+        },
+        {
+          "text": "you're",
+          "start": 90.32,
+          "end": 90.46,
+          "confidence": 0.828
+        },
+        {
+          "text": "praying",
+          "start": 90.46,
+          "end": 90.86,
+          "confidence": 0.967
+        },
+        {
+          "text": "for",
+          "start": 90.86,
+          "end": 91.1,
+          "confidence": 0.97
+        },
+        {
+          "text": "my",
+          "start": 91.1,
+          "end": 91.28,
+          "confidence": 0.989
+        },
+        {
+          "text": "phone",
+          "start": 91.28,
+          "end": 91.7,
+          "confidence": 0.702
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 8856,
+      "start": 91.78,
+      "end": 94.74,
+      "text": " And the laughter in the holes and the names that I've been called",
+      "tokens": [
+        50520,
+        400,
+        264,
+        13092,
+        294,
+        264,
+        8118,
+        293,
+        264,
+        5288,
+        300,
+        286,
+        600,
+        668,
+        1219,
+        50680
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2874426958037586,
+      "compression_ratio": 1.5869565217391304,
+      "no_speech_prob": 0.7892544865608215,
+      "confidence": 0.884,
+      "words": [
+        {
+          "text": "And",
+          "start": 91.78,
+          "end": 91.94,
+          "confidence": 0.844
+        },
+        {
+          "text": "the",
+          "start": 91.94,
+          "end": 92.12,
+          "confidence": 0.987
+        },
+        {
+          "text": "laughter",
+          "start": 92.12,
+          "end": 92.5,
+          "confidence": 0.994
+        },
+        {
+          "text": "in",
+          "start": 92.5,
+          "end": 92.72,
+          "confidence": 0.85
+        },
+        {
+          "text": "the",
+          "start": 92.72,
+          "end": 92.92,
+          "confidence": 0.997
+        },
+        {
+          "text": "holes",
+          "start": 92.92,
+          "end": 93.28,
+          "confidence": 0.607
+        },
+        {
+          "text": "and",
+          "start": 93.28,
+          "end": 93.48,
+          "confidence": 0.595
+        },
+        {
+          "text": "the",
+          "start": 93.48,
+          "end": 93.6,
+          "confidence": 0.991
+        },
+        {
+          "text": "names",
+          "start": 93.6,
+          "end": 93.84,
+          "confidence": 0.991
+        },
+        {
+          "text": "that",
+          "start": 93.84,
+          "end": 94.14,
+          "confidence": 0.957
+        },
+        {
+          "text": "I've",
+          "start": 94.14,
+          "end": 94.34,
+          "confidence": 0.914
+        },
+        {
+          "text": "been",
+          "start": 94.34,
+          "end": 94.46,
+          "confidence": 0.985
+        },
+        {
+          "text": "called",
+          "start": 94.46,
+          "end": 94.74,
+          "confidence": 0.912
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 8856,
+      "start": 95.0,
+      "end": 97.82,
+      "text": " I stack it in my mind and I'm waiting for the time",
+      "tokens": [
+        50680,
+        286,
+        8630,
+        309,
+        294,
+        452,
+        1575,
+        293,
+        286,
+        478,
+        3806,
+        337,
+        264,
+        565,
+        50832
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2874426958037586,
+      "compression_ratio": 1.5869565217391304,
+      "no_speech_prob": 0.7892544865608215,
+      "confidence": 0.959,
+      "words": [
+        {
+          "text": "I",
+          "start": 95.0,
+          "end": 95.14,
+          "confidence": 0.987
+        },
+        {
+          "text": "stack",
+          "start": 95.14,
+          "end": 95.46,
+          "confidence": 0.825
+        },
+        {
+          "text": "it",
+          "start": 95.46,
+          "end": 95.72,
+          "confidence": 0.995
+        },
+        {
+          "text": "in",
+          "start": 95.72,
+          "end": 95.8,
+          "confidence": 0.996
+        },
+        {
+          "text": "my",
+          "start": 95.8,
+          "end": 96.1,
+          "confidence": 0.994
+        },
+        {
+          "text": "mind",
+          "start": 96.1,
+          "end": 96.4,
+          "confidence": 0.999
+        },
+        {
+          "text": "and",
+          "start": 96.4,
+          "end": 96.6,
+          "confidence": 0.759
+        },
+        {
+          "text": "I'm",
+          "start": 96.6,
+          "end": 96.72,
+          "confidence": 0.991
+        },
+        {
+          "text": "waiting",
+          "start": 96.72,
+          "end": 97.14,
+          "confidence": 0.988
+        },
+        {
+          "text": "for",
+          "start": 97.14,
+          "end": 97.36,
+          "confidence": 0.996
+        },
+        {
+          "text": "the",
+          "start": 97.36,
+          "end": 97.54,
+          "confidence": 0.996
+        },
+        {
+          "text": "time",
+          "start": 97.54,
+          "end": 97.82,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 8856,
+      "start": 97.98,
+      "end": 101.26,
+      "text": " When I show you what it's like to be worse but in the mind",
+      "tokens": [
+        50832,
+        1133,
+        286,
+        855,
+        291,
+        437,
+        309,
+        311,
+        411,
+        281,
+        312,
+        5324,
+        457,
+        294,
+        264,
+        1575,
+        51000
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2874426958037586,
+      "compression_ratio": 1.5869565217391304,
+      "no_speech_prob": 0.7892544865608215,
+      "confidence": 0.756,
+      "words": [
+        {
+          "text": "When",
+          "start": 97.98,
+          "end": 98.14,
+          "confidence": 0.922
+        },
+        {
+          "text": "I",
+          "start": 98.14,
+          "end": 98.32,
+          "confidence": 0.993
+        },
+        {
+          "text": "show",
+          "start": 98.32,
+          "end": 98.5,
+          "confidence": 0.958
+        },
+        {
+          "text": "you",
+          "start": 98.5,
+          "end": 98.76,
+          "confidence": 0.994
+        },
+        {
+          "text": "what",
+          "start": 98.76,
+          "end": 98.94,
+          "confidence": 0.996
+        },
+        {
+          "text": "it's",
+          "start": 98.94,
+          "end": 99.24,
+          "confidence": 0.988
+        },
+        {
+          "text": "like",
+          "start": 99.24,
+          "end": 99.46,
+          "confidence": 0.998
+        },
+        {
+          "text": "to",
+          "start": 99.46,
+          "end": 99.7,
+          "confidence": 0.875
+        },
+        {
+          "text": "be",
+          "start": 99.7,
+          "end": 99.84,
+          "confidence": 0.997
+        },
+        {
+          "text": "worse",
+          "start": 99.84,
+          "end": 100.08,
+          "confidence": 0.445
+        },
+        {
+          "text": "but",
+          "start": 100.08,
+          "end": 100.4,
+          "confidence": 0.199
+        },
+        {
+          "text": "in",
+          "start": 100.4,
+          "end": 100.58,
+          "confidence": 0.863
+        },
+        {
+          "text": "the",
+          "start": 100.58,
+          "end": 100.8,
+          "confidence": 0.428
+        },
+        {
+          "text": "mind",
+          "start": 100.8,
+          "end": 101.26,
+          "confidence": 0.622
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 8856,
+      "start": 101.34,
+      "end": 106.84,
+      "text": " Tell you you're the greatest",
+      "tokens": [
+        51000,
+        5115,
+        291,
+        291,
+        434,
+        264,
+        6636,
+        51292
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2874426958037586,
+      "compression_ratio": 1.5869565217391304,
+      "no_speech_prob": 0.7892544865608215,
+      "confidence": 0.94,
+      "words": [
+        {
+          "text": "Tell",
+          "start": 101.34,
+          "end": 102.22,
+          "confidence": 0.937
+        },
+        {
+          "text": "you",
+          "start": 102.22,
+          "end": 102.96,
+          "confidence": 0.993
+        },
+        {
+          "text": "you're",
+          "start": 102.96,
+          "end": 103.94,
+          "confidence": 0.873
+        },
+        {
+          "text": "the",
+          "start": 103.94,
+          "end": 104.36,
+          "confidence": 0.985
+        },
+        {
+          "text": "greatest",
+          "start": 104.36,
+          "end": 106.84,
+          "confidence": 0.986
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 8856,
+      "start": 107.2,
+      "end": 113.02,
+      "text": " But once you turn they hate us",
+      "tokens": [
+        51292,
+        583,
+        1564,
+        291,
+        1261,
+        436,
+        4700,
+        505,
+        51592
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2874426958037586,
+      "compression_ratio": 1.5869565217391304,
+      "no_speech_prob": 0.7892544865608215,
+      "confidence": 0.909,
+      "words": [
+        {
+          "text": "But",
+          "start": 107.2,
+          "end": 107.62,
+          "confidence": 0.963
+        },
+        {
+          "text": "once",
+          "start": 107.62,
+          "end": 108.42,
+          "confidence": 0.786
+        },
+        {
+          "text": "you",
+          "start": 108.42,
+          "end": 109.28,
+          "confidence": 0.998
+        },
+        {
+          "text": "turn",
+          "start": 109.28,
+          "end": 109.86,
+          "confidence": 0.914
+        },
+        {
+          "text": "they",
+          "start": 109.86,
+          "end": 110.38,
+          "confidence": 0.754
+        },
+        {
+          "text": "hate",
+          "start": 110.38,
+          "end": 111.92,
+          "confidence": 0.984
+        },
+        {
+          "text": "us",
+          "start": 111.92,
+          "end": 113.02,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 11312,
+      "start": 113.38,
+      "end": 119.78,
+      "text": " Oh, the misery Everybody wants to be my enemy",
+      "tokens": [
+        50364,
+        876,
+        11,
+        264,
+        32309,
+        7646,
+        2738,
+        281,
+        312,
+        452,
+        5945,
+        50714
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.27150371839415355,
+      "compression_ratio": 1.6610169491525424,
+      "no_speech_prob": 0.865480363368988,
+      "confidence": 0.804,
+      "words": [
+        {
+          "text": "Oh,",
+          "start": 113.38,
+          "end": 114.98,
+          "confidence": 0.317
+        },
+        {
+          "text": "the",
+          "start": 115.02,
+          "end": 115.42,
+          "confidence": 0.964
+        },
+        {
+          "text": "misery",
+          "start": 115.42,
+          "end": 116.26,
+          "confidence": 0.995
+        },
+        {
+          "text": "Everybody",
+          "start": 116.26,
+          "end": 117.58,
+          "confidence": 0.482
+        },
+        {
+          "text": "wants",
+          "start": 117.58,
+          "end": 117.96,
+          "confidence": 0.986
+        },
+        {
+          "text": "to",
+          "start": 117.96,
+          "end": 118.14,
+          "confidence": 0.996
+        },
+        {
+          "text": "be",
+          "start": 118.14,
+          "end": 118.32,
+          "confidence": 0.998
+        },
+        {
+          "text": "my",
+          "start": 118.32,
+          "end": 118.56,
+          "confidence": 0.993
+        },
+        {
+          "text": "enemy",
+          "start": 118.56,
+          "end": 119.78,
+          "confidence": 0.983
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 11312,
+      "start": 120.7,
+      "end": 126.28,
+      "text": " Spare the sympathy Everybody wants to be my enemy",
+      "tokens": [
+        50714,
+        1738,
+        543,
+        264,
+        33240,
+        7646,
+        2738,
+        281,
+        312,
+        452,
+        5945,
+        51014
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.27150371839415355,
+      "compression_ratio": 1.6610169491525424,
+      "no_speech_prob": 0.865480363368988,
+      "confidence": 0.874,
+      "words": [
+        {
+          "text": "Spare",
+          "start": 120.7,
+          "end": 121.4,
+          "confidence": 0.576
+        },
+        {
+          "text": "the",
+          "start": 121.4,
+          "end": 121.7,
+          "confidence": 0.985
+        },
+        {
+          "text": "sympathy",
+          "start": 121.7,
+          "end": 122.5,
+          "confidence": 0.994
+        },
+        {
+          "text": "Everybody",
+          "start": 122.5,
+          "end": 123.84,
+          "confidence": 0.969
+        },
+        {
+          "text": "wants",
+          "start": 123.84,
+          "end": 124.18,
+          "confidence": 0.994
+        },
+        {
+          "text": "to",
+          "start": 124.18,
+          "end": 124.42,
+          "confidence": 0.999
+        },
+        {
+          "text": "be",
+          "start": 124.42,
+          "end": 125.24,
+          "confidence": 0.999
+        },
+        {
+          "text": "my",
+          "start": 125.24,
+          "end": 125.62,
+          "confidence": 0.836
+        },
+        {
+          "text": "enemy",
+          "start": 125.62,
+          "end": 126.28,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 11312,
+      "start": 126.62,
+      "end": 132.44,
+      "text": " Look out for yourself My enemy",
+      "tokens": [
+        51014,
+        2053,
+        484,
+        337,
+        1803,
+        1222,
+        5945,
+        51314
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.27150371839415355,
+      "compression_ratio": 1.6610169491525424,
+      "no_speech_prob": 0.865480363368988,
+      "confidence": 0.794,
+      "words": [
+        {
+          "text": "Look",
+          "start": 126.62,
+          "end": 130.12,
+          "confidence": 0.593
+        },
+        {
+          "text": "out",
+          "start": 130.12,
+          "end": 130.32,
+          "confidence": 0.893
+        },
+        {
+          "text": "for",
+          "start": 130.32,
+          "end": 130.48,
+          "confidence": 0.978
+        },
+        {
+          "text": "yourself",
+          "start": 130.48,
+          "end": 130.94,
+          "confidence": 0.988
+        },
+        {
+          "text": "My",
+          "start": 130.94,
+          "end": 131.78,
+          "confidence": 0.496
+        },
+        {
+          "text": "enemy",
+          "start": 131.78,
+          "end": 132.44,
+          "confidence": 0.989
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 11312,
+      "start": 133.72,
+      "end": 137.14,
+      "text": " Look out for yourself",
+      "tokens": [
+        51314,
+        2053,
+        484,
+        337,
+        1803,
+        51564
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.27150371839415355,
+      "compression_ratio": 1.6610169491525424,
+      "no_speech_prob": 0.865480363368988,
+      "confidence": 0.97,
+      "words": [
+        {
+          "text": "Look",
+          "start": 133.72,
+          "end": 134.66,
+          "confidence": 0.906
+        },
+        {
+          "text": "out",
+          "start": 134.66,
+          "end": 136.54,
+          "confidence": 0.978
+        },
+        {
+          "text": "for",
+          "start": 136.54,
+          "end": 136.74,
+          "confidence": 0.999
+        },
+        {
+          "text": "yourself",
+          "start": 136.74,
+          "end": 137.14,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 11312,
+      "start": 137.6,
+      "end": 140.24,
+      "text": " Look, okay I'm hoping that somebody pray for me",
+      "tokens": [
+        51564,
+        2053,
+        11,
+        1392,
+        286,
+        478,
+        7159,
+        300,
+        2618,
+        3690,
+        337,
+        385,
+        51714
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.27150371839415355,
+      "compression_ratio": 1.6610169491525424,
+      "no_speech_prob": 0.865480363368988,
+      "confidence": 0.786,
+      "words": [
+        {
+          "text": "Look,",
+          "start": 137.6,
+          "end": 137.88,
+          "confidence": 0.728
+        },
+        {
+          "text": "okay",
+          "start": 138.4,
+          "end": 138.6,
+          "confidence": 0.728
+        },
+        {
+          "text": "I'm",
+          "start": 138.6,
+          "end": 138.94,
+          "confidence": 0.699
+        },
+        {
+          "text": "hoping",
+          "start": 138.94,
+          "end": 139.16,
+          "confidence": 0.502
+        },
+        {
+          "text": "that",
+          "start": 139.16,
+          "end": 139.34,
+          "confidence": 0.959
+        },
+        {
+          "text": "somebody",
+          "start": 139.34,
+          "end": 139.58,
+          "confidence": 0.981
+        },
+        {
+          "text": "pray",
+          "start": 139.58,
+          "end": 139.84,
+          "confidence": 0.821
+        },
+        {
+          "text": "for",
+          "start": 139.84,
+          "end": 140.02,
+          "confidence": 0.901
+        },
+        {
+          "text": "me",
+          "start": 140.02,
+          "end": 140.24,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 14012,
+      "start": 140.34,
+      "end": 141.7,
+      "text": " I'm praying that somebody hold for me.",
+      "tokens": [
+        50364,
+        286,
+        478,
+        15611,
+        300,
+        2618,
+        1797,
+        337,
+        385,
+        13,
+        50439
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36420179578993056,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7754144668579102,
+      "confidence": 0.794,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 140.34,
+          "end": 140.44,
+          "confidence": 0.819
+        },
+        {
+          "text": "praying",
+          "start": 140.44,
+          "end": 140.66,
+          "confidence": 0.694
+        },
+        {
+          "text": "that",
+          "start": 140.66,
+          "end": 140.84,
+          "confidence": 0.787
+        },
+        {
+          "text": "somebody",
+          "start": 140.84,
+          "end": 141.1,
+          "confidence": 0.985
+        },
+        {
+          "text": "hold",
+          "start": 141.1,
+          "end": 141.36,
+          "confidence": 0.442
+        },
+        {
+          "text": "for",
+          "start": 141.36,
+          "end": 141.52,
+          "confidence": 0.992
+        },
+        {
+          "text": "me.",
+          "start": 141.52,
+          "end": 141.7,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 17,
+      "seek": 14012,
+      "start": 141.76,
+      "end": 143.2,
+      "text": " I'm staying where nobody's supposed to be.",
+      "tokens": [
+        50439,
+        286,
+        478,
+        7939,
+        689,
+        5079,
+        311,
+        3442,
+        281,
+        312,
+        13,
+        50516
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36420179578993056,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7754144668579102,
+      "confidence": 0.853,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 141.76,
+          "end": 141.98,
+          "confidence": 0.976
+        },
+        {
+          "text": "staying",
+          "start": 141.98,
+          "end": 142.16,
+          "confidence": 0.708
+        },
+        {
+          "text": "where",
+          "start": 142.16,
+          "end": 142.34,
+          "confidence": 0.906
+        },
+        {
+          "text": "nobody's",
+          "start": 142.34,
+          "end": 142.68,
+          "confidence": 0.655
+        },
+        {
+          "text": "supposed",
+          "start": 142.68,
+          "end": 142.94,
+          "confidence": 0.923
+        },
+        {
+          "text": "to",
+          "start": 142.94,
+          "end": 143.1,
+          "confidence": 0.992
+        },
+        {
+          "text": "be.",
+          "start": 143.1,
+          "end": 143.2,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 18,
+      "seek": 14012,
+      "start": 143.24,
+      "end": 144.98,
+      "text": " I propose to be in a wreck of emotions.",
+      "tokens": [
+        50516,
+        286,
+        17421,
+        281,
+        312,
+        294,
+        257,
+        21478,
+        295,
+        8462,
+        13,
+        50610
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36420179578993056,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7754144668579102,
+      "confidence": 0.646,
+      "words": [
+        {
+          "text": "I",
+          "start": 143.24,
+          "end": 143.42,
+          "confidence": 0.492
+        },
+        {
+          "text": "propose",
+          "start": 143.42,
+          "end": 143.72,
+          "confidence": 0.333
+        },
+        {
+          "text": "to",
+          "start": 143.72,
+          "end": 143.88,
+          "confidence": 0.778
+        },
+        {
+          "text": "be",
+          "start": 143.88,
+          "end": 144.02,
+          "confidence": 0.442
+        },
+        {
+          "text": "in",
+          "start": 144.02,
+          "end": 144.18,
+          "confidence": 0.812
+        },
+        {
+          "text": "a",
+          "start": 144.18,
+          "end": 144.28,
+          "confidence": 0.559
+        },
+        {
+          "text": "wreck",
+          "start": 144.28,
+          "end": 144.4,
+          "confidence": 0.811
+        },
+        {
+          "text": "of",
+          "start": 144.4,
+          "end": 144.54,
+          "confidence": 0.99
+        },
+        {
+          "text": "emotions.",
+          "start": 144.54,
+          "end": 144.98,
+          "confidence": 0.953
+        }
+      ]
+    },
+    {
+      "id": 19,
+      "seek": 14012,
+      "start": 145.06,
+      "end": 146.3,
+      "text": " Ready to go whenever you let me know.",
+      "tokens": [
+        50610,
+        9944,
+        281,
+        352,
+        5699,
+        291,
+        718,
+        385,
+        458,
+        13,
+        50672
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36420179578993056,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7754144668579102,
+      "confidence": 0.834,
+      "words": [
+        {
+          "text": "Ready",
+          "start": 145.06,
+          "end": 145.3,
+          "confidence": 0.951
+        },
+        {
+          "text": "to",
+          "start": 145.3,
+          "end": 145.46,
+          "confidence": 0.997
+        },
+        {
+          "text": "go",
+          "start": 145.46,
+          "end": 145.6,
+          "confidence": 0.997
+        },
+        {
+          "text": "whenever",
+          "start": 145.6,
+          "end": 145.78,
+          "confidence": 0.661
+        },
+        {
+          "text": "you",
+          "start": 145.78,
+          "end": 145.94,
+          "confidence": 0.403
+        },
+        {
+          "text": "let",
+          "start": 145.94,
+          "end": 146.08,
+          "confidence": 0.952
+        },
+        {
+          "text": "me",
+          "start": 146.08,
+          "end": 146.18,
+          "confidence": 0.998
+        },
+        {
+          "text": "know.",
+          "start": 146.18,
+          "end": 146.3,
+          "confidence": 0.977
+        }
+      ]
+    },
+    {
+      "id": 20,
+      "seek": 14012,
+      "start": 146.36,
+      "end": 147.88,
+      "text": " The road is long, so put the pedal into the flow.",
+      "tokens": [
+        50672,
+        440,
+        3060,
+        307,
+        938,
+        11,
+        370,
+        829,
+        264,
+        19122,
+        666,
+        264,
+        3095,
+        13,
+        50749
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36420179578993056,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7754144668579102,
+      "confidence": 0.959,
+      "words": [
+        {
+          "text": "The",
+          "start": 146.36,
+          "end": 146.52,
+          "confidence": 0.99
+        },
+        {
+          "text": "road",
+          "start": 146.52,
+          "end": 146.68,
+          "confidence": 0.99
+        },
+        {
+          "text": "is",
+          "start": 146.68,
+          "end": 146.78,
+          "confidence": 0.987
+        },
+        {
+          "text": "long,",
+          "start": 146.78,
+          "end": 146.9,
+          "confidence": 0.961
+        },
+        {
+          "text": "so",
+          "start": 146.92,
+          "end": 147.02,
+          "confidence": 0.968
+        },
+        {
+          "text": "put",
+          "start": 147.02,
+          "end": 147.16,
+          "confidence": 0.954
+        },
+        {
+          "text": "the",
+          "start": 147.16,
+          "end": 147.28,
+          "confidence": 0.972
+        },
+        {
+          "text": "pedal",
+          "start": 147.28,
+          "end": 147.4,
+          "confidence": 0.993
+        },
+        {
+          "text": "into",
+          "start": 147.4,
+          "end": 147.6,
+          "confidence": 0.9
+        },
+        {
+          "text": "the",
+          "start": 147.6,
+          "end": 147.76,
+          "confidence": 0.992
+        },
+        {
+          "text": "flow.",
+          "start": 147.76,
+          "end": 147.88,
+          "confidence": 0.856
+        }
+      ]
+    },
+    {
+      "id": 21,
+      "seek": 14012,
+      "start": 147.94,
+      "end": 149.78,
+      "text": " The enemy on my trail, my energy unavailable.",
+      "tokens": [
+        50749,
+        440,
+        5945,
+        322,
+        452,
+        9924,
+        11,
+        452,
+        2281,
+        36541,
+        32699,
+        13,
+        50856
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36420179578993056,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7754144668579102,
+      "confidence": 0.948,
+      "words": [
+        {
+          "text": "The",
+          "start": 147.94,
+          "end": 148.08,
+          "confidence": 0.968
+        },
+        {
+          "text": "enemy",
+          "start": 148.08,
+          "end": 148.26,
+          "confidence": 0.726
+        },
+        {
+          "text": "on",
+          "start": 148.26,
+          "end": 148.38,
+          "confidence": 0.974
+        },
+        {
+          "text": "my",
+          "start": 148.38,
+          "end": 148.5,
+          "confidence": 0.974
+        },
+        {
+          "text": "trail,",
+          "start": 148.5,
+          "end": 148.64,
+          "confidence": 0.986
+        },
+        {
+          "text": "my",
+          "start": 148.68,
+          "end": 148.86,
+          "confidence": 0.99
+        },
+        {
+          "text": "energy",
+          "start": 148.86,
+          "end": 149.1,
+          "confidence": 0.996
+        },
+        {
+          "text": "unavailable.",
+          "start": 149.1,
+          "end": 149.78,
+          "confidence": 0.978
+        }
+      ]
+    },
+    {
+      "id": 22,
+      "seek": 14012,
+      "start": 150.0,
+      "end": 151.35,
+      "text": " I'ma tell them I said away, go away.",
+      "tokens": [
+        50856,
+        286,
+        478,
+        64,
+        980,
+        552,
+        286,
+        848,
+        1314,
+        11,
+        352,
+        1314,
+        13,
+        50924
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36420179578993056,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7754144668579102,
+      "confidence": 0.571,
+      "words": [
+        {
+          "text": "I'ma",
+          "start": 150.0,
+          "end": 150.26,
+          "confidence": 0.765
+        },
+        {
+          "text": "tell",
+          "start": 150.26,
+          "end": 150.36,
+          "confidence": 0.989
+        },
+        {
+          "text": "them",
+          "start": 150.36,
+          "end": 150.5,
+          "confidence": 0.335
+        },
+        {
+          "text": "I",
+          "start": 150.5,
+          "end": 150.62,
+          "confidence": 0.359
+        },
+        {
+          "text": "said",
+          "start": 150.62,
+          "end": 150.76,
+          "confidence": 0.3
+        },
+        {
+          "text": "away,",
+          "start": 150.76,
+          "end": 151.0,
+          "confidence": 0.325
+        },
+        {
+          "text": "go",
+          "start": 151.14,
+          "end": 151.18,
+          "confidence": 0.911
+        },
+        {
+          "text": "away.",
+          "start": 151.18,
+          "end": 151.35,
+          "confidence": 0.781
+        }
+      ]
+    },
+    {
+      "id": 23,
+      "seek": 14012,
+      "start": 151.35,
+      "end": 152.55,
+      "text": " When I'm plotting, I'ma drive to the top.",
+      "tokens": [
+        50924,
+        1133,
+        286,
+        478,
+        41178,
+        11,
+        286,
+        478,
+        64,
+        3332,
+        281,
+        264,
+        1192,
+        13,
+        50985
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36420179578993056,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7754144668579102,
+      "confidence": 0.644,
+      "words": [
+        {
+          "text": "When",
+          "start": 151.35,
+          "end": 151.56,
+          "confidence": 0.886
+        },
+        {
+          "text": "I'm",
+          "start": 151.56,
+          "end": 151.72,
+          "confidence": 0.592
+        },
+        {
+          "text": "plotting,",
+          "start": 151.72,
+          "end": 151.82,
+          "confidence": 0.365
+        },
+        {
+          "text": "I'ma",
+          "start": 151.84,
+          "end": 152.0,
+          "confidence": 0.487
+        },
+        {
+          "text": "drive",
+          "start": 152.0,
+          "end": 152.16,
+          "confidence": 0.622
+        },
+        {
+          "text": "to",
+          "start": 152.16,
+          "end": 152.3,
+          "confidence": 0.984
+        },
+        {
+          "text": "the",
+          "start": 152.3,
+          "end": 152.42,
+          "confidence": 0.997
+        },
+        {
+          "text": "top.",
+          "start": 152.42,
+          "end": 152.55,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 24,
+      "seek": 14012,
+      "start": 152.55,
+      "end": 153.74,
+      "text": " I've been out of shape, thinking out of the box.",
+      "tokens": [
+        50985,
+        286,
+        600,
+        668,
+        484,
+        295,
+        3909,
+        11,
+        1953,
+        484,
+        295,
+        264,
+        2424,
+        13,
+        51043
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36420179578993056,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7754144668579102,
+      "confidence": 0.769,
+      "words": [
+        {
+          "text": "I've",
+          "start": 152.55,
+          "end": 152.7,
+          "confidence": 0.723
+        },
+        {
+          "text": "been",
+          "start": 152.7,
+          "end": 152.78,
+          "confidence": 0.998
+        },
+        {
+          "text": "out",
+          "start": 152.78,
+          "end": 152.9,
+          "confidence": 0.905
+        },
+        {
+          "text": "of",
+          "start": 152.9,
+          "end": 153.02,
+          "confidence": 0.986
+        },
+        {
+          "text": "shape,",
+          "start": 153.02,
+          "end": 153.1,
+          "confidence": 0.998
+        },
+        {
+          "text": "thinking",
+          "start": 153.26,
+          "end": 153.32,
+          "confidence": 0.842
+        },
+        {
+          "text": "out",
+          "start": 153.32,
+          "end": 153.46,
+          "confidence": 0.343
+        },
+        {
+          "text": "of",
+          "start": 153.46,
+          "end": 153.56,
+          "confidence": 0.505
+        },
+        {
+          "text": "the",
+          "start": 153.56,
+          "end": 153.62,
+          "confidence": 0.82
+        },
+        {
+          "text": "box.",
+          "start": 153.62,
+          "end": 153.74,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 25,
+      "seek": 14012,
+      "start": 153.74,
+      "end": 155.34,
+      "text": " I'm an astronaut, blasted off the planet.",
+      "tokens": [
+        51043,
+        286,
+        478,
+        364,
+        18516,
+        11,
+        12035,
+        292,
+        766,
+        264,
+        5054,
+        13,
+        51124
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36420179578993056,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7754144668579102,
+      "confidence": 0.967,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 153.74,
+          "end": 153.92,
+          "confidence": 0.996
+        },
+        {
+          "text": "an",
+          "start": 153.92,
+          "end": 154.06,
+          "confidence": 0.996
+        },
+        {
+          "text": "astronaut,",
+          "start": 154.06,
+          "end": 154.4,
+          "confidence": 0.991
+        },
+        {
+          "text": "blasted",
+          "start": 154.54,
+          "end": 154.88,
+          "confidence": 0.895
+        },
+        {
+          "text": "off",
+          "start": 154.88,
+          "end": 155.02,
+          "confidence": 0.987
+        },
+        {
+          "text": "the",
+          "start": 155.02,
+          "end": 155.18,
+          "confidence": 0.959
+        },
+        {
+          "text": "planet.",
+          "start": 155.18,
+          "end": 155.34,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 26,
+      "seek": 14012,
+      "start": 155.4,
+      "end": 157.18,
+      "text": " Rock the cars, catastrophic, and it matters more",
+      "tokens": [
+        51124,
+        6922,
+        264,
+        5163,
+        11,
+        34915,
+        11,
+        293,
+        309,
+        7001,
+        544,
+        51212
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36420179578993056,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7754144668579102,
+      "confidence": 0.703,
+      "words": [
+        {
+          "text": "Rock",
+          "start": 155.4,
+          "end": 155.6,
+          "confidence": 0.564
+        },
+        {
+          "text": "the",
+          "start": 155.6,
+          "end": 155.74,
+          "confidence": 0.505
+        },
+        {
+          "text": "cars,",
+          "start": 155.74,
+          "end": 155.88,
+          "confidence": 0.47
+        },
+        {
+          "text": "catastrophic,",
+          "start": 155.9,
+          "end": 156.4,
+          "confidence": 0.771
+        },
+        {
+          "text": "and",
+          "start": 156.46,
+          "end": 156.62,
+          "confidence": 0.925
+        },
+        {
+          "text": "it",
+          "start": 156.62,
+          "end": 156.76,
+          "confidence": 0.733
+        },
+        {
+          "text": "matters",
+          "start": 156.76,
+          "end": 156.94,
+          "confidence": 0.878
+        },
+        {
+          "text": "more",
+          "start": 156.94,
+          "end": 157.18,
+          "confidence": 0.974
+        }
+      ]
+    },
+    {
+      "id": 27,
+      "seek": 14012,
+      "start": 157.18,
+      "end": 157.91,
+      "text": " because I had it now.",
+      "tokens": [
+        51212,
+        570,
+        286,
+        632,
+        309,
+        586,
+        13,
+        51254
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36420179578993056,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7754144668579102,
+      "confidence": 0.649,
+      "words": [
+        {
+          "text": "because",
+          "start": 157.18,
+          "end": 157.42,
+          "confidence": 0.99
+        },
+        {
+          "text": "I",
+          "start": 157.42,
+          "end": 157.56,
+          "confidence": 0.532
+        },
+        {
+          "text": "had",
+          "start": 157.56,
+          "end": 157.66,
+          "confidence": 0.936
+        },
+        {
+          "text": "it",
+          "start": 157.66,
+          "end": 157.82,
+          "confidence": 0.984
+        },
+        {
+          "text": "now.",
+          "start": 157.82,
+          "end": 157.91,
+          "confidence": 0.237
+        }
+      ]
+    },
+    {
+      "id": 28,
+      "seek": 14012,
+      "start": 157.91,
+      "end": 159.84,
+      "text": " Had I thought about wreaking havoc on an opposition.",
+      "tokens": [
+        51254,
+        12298,
+        286,
+        1194,
+        466,
+        46674,
+        2456,
+        47367,
+        322,
+        364,
+        13504,
+        13,
+        51350
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36420179578993056,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7754144668579102,
+      "confidence": 0.954,
+      "words": [
+        {
+          "text": "Had",
+          "start": 157.91,
+          "end": 158.12,
+          "confidence": 0.843
+        },
+        {
+          "text": "I",
+          "start": 158.12,
+          "end": 158.2,
+          "confidence": 0.971
+        },
+        {
+          "text": "thought",
+          "start": 158.2,
+          "end": 158.38,
+          "confidence": 0.991
+        },
+        {
+          "text": "about",
+          "start": 158.38,
+          "end": 158.58,
+          "confidence": 0.995
+        },
+        {
+          "text": "wreaking",
+          "start": 158.58,
+          "end": 158.86,
+          "confidence": 0.996
+        },
+        {
+          "text": "havoc",
+          "start": 158.86,
+          "end": 159.08,
+          "confidence": 1.0
+        },
+        {
+          "text": "on",
+          "start": 159.08,
+          "end": 159.32,
+          "confidence": 0.862
+        },
+        {
+          "text": "an",
+          "start": 159.32,
+          "end": 159.46,
+          "confidence": 0.913
+        },
+        {
+          "text": "opposition.",
+          "start": 159.46,
+          "end": 159.84,
+          "confidence": 0.991
+        }
+      ]
+    },
+    {
+      "id": 29,
+      "seek": 14012,
+      "start": 159.86,
+      "end": 161.02,
+      "text": " Kind of shocking, they want it static.",
+      "tokens": [
+        51350,
+        9242,
+        295,
+        18776,
+        11,
+        436,
+        528,
+        309,
+        13437,
+        13,
+        51410
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36420179578993056,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7754144668579102,
+      "confidence": 0.667,
+      "words": [
+        {
+          "text": "Kind",
+          "start": 159.86,
+          "end": 160.06,
+          "confidence": 0.661
+        },
+        {
+          "text": "of",
+          "start": 160.06,
+          "end": 160.18,
+          "confidence": 0.995
+        },
+        {
+          "text": "shocking,",
+          "start": 160.18,
+          "end": 160.38,
+          "confidence": 0.656
+        },
+        {
+          "text": "they",
+          "start": 160.52,
+          "end": 160.6,
+          "confidence": 0.366
+        },
+        {
+          "text": "want",
+          "start": 160.6,
+          "end": 160.74,
+          "confidence": 0.574
+        },
+        {
+          "text": "it",
+          "start": 160.74,
+          "end": 160.88,
+          "confidence": 0.651
+        },
+        {
+          "text": "static.",
+          "start": 160.88,
+          "end": 161.02,
+          "confidence": 0.993
+        }
+      ]
+    },
+    {
+      "id": 30,
+      "seek": 14012,
+      "start": 161.08,
+      "end": 162.18,
+      "text": " With precision, I'm automatic.",
+      "tokens": [
+        51410,
+        2022,
+        18356,
+        11,
+        286,
+        478,
+        12509,
+        13,
+        51468
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36420179578993056,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7754144668579102,
+      "confidence": 0.874,
+      "words": [
+        {
+          "text": "With",
+          "start": 161.08,
+          "end": 161.28,
+          "confidence": 0.587
+        },
+        {
+          "text": "precision,",
+          "start": 161.28,
+          "end": 161.58,
+          "confidence": 0.904
+        },
+        {
+          "text": "I'm",
+          "start": 161.68,
+          "end": 161.88,
+          "confidence": 0.987
+        },
+        {
+          "text": "automatic.",
+          "start": 161.88,
+          "end": 162.18,
+          "confidence": 0.987
+        }
+      ]
+    },
+    {
+      "id": 31,
+      "seek": 14012,
+      "start": 162.24,
+      "end": 163.34,
+      "text": " Quarterback, I ain't talking second.",
+      "tokens": [
+        51468,
+        43794,
+        3207,
+        11,
+        286,
+        7862,
+        380,
+        1417,
+        1150,
+        13,
+        51527
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36420179578993056,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7754144668579102,
+      "confidence": 0.687,
+      "words": [
+        {
+          "text": "Quarterback,",
+          "start": 162.24,
+          "end": 162.66,
+          "confidence": 0.511
+        },
+        {
+          "text": "I",
+          "start": 162.66,
+          "end": 162.78,
+          "confidence": 0.964
+        },
+        {
+          "text": "ain't",
+          "start": 162.78,
+          "end": 162.9,
+          "confidence": 0.99
+        },
+        {
+          "text": "talking",
+          "start": 162.9,
+          "end": 163.1,
+          "confidence": 0.891
+        },
+        {
+          "text": "second.",
+          "start": 163.1,
+          "end": 163.34,
+          "confidence": 0.327
+        }
+      ]
+    },
+    {
+      "id": 32,
+      "seek": 14012,
+      "start": 163.36,
+      "end": 164.12,
+      "text": " Pack it, pack it up.",
+      "tokens": [
+        51527,
+        18466,
+        309,
+        11,
+        2844,
+        309,
+        493,
+        13,
+        51562
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36420179578993056,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7754144668579102,
+      "confidence": 0.973,
+      "words": [
+        {
+          "text": "Pack",
+          "start": 163.36,
+          "end": 163.62,
+          "confidence": 0.967
+        },
+        {
+          "text": "it,",
+          "start": 163.62,
+          "end": 163.68,
+          "confidence": 0.937
+        },
+        {
+          "text": "pack",
+          "start": 163.68,
+          "end": 163.88,
+          "confidence": 0.986
+        },
+        {
+          "text": "it",
+          "start": 163.88,
+          "end": 164.0,
+          "confidence": 0.999
+        },
+        {
+          "text": "up.",
+          "start": 164.0,
+          "end": 164.12,
+          "confidence": 0.979
+        }
+      ]
+    },
+    {
+      "id": 33,
+      "seek": 14012,
+      "start": 164.12,
+      "end": 165.04,
+      "text": " I don't panic, better, better.",
+      "tokens": [
+        51562,
+        286,
+        500,
+        380,
+        14783,
+        11,
+        1101,
+        11,
+        1101,
+        13,
+        51612
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36420179578993056,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7754144668579102,
+      "confidence": 0.76,
+      "words": [
+        {
+          "text": "I",
+          "start": 164.12,
+          "end": 164.18,
+          "confidence": 0.984
+        },
+        {
+          "text": "don't",
+          "start": 164.18,
+          "end": 164.34,
+          "confidence": 0.912
+        },
+        {
+          "text": "panic,",
+          "start": 164.34,
+          "end": 164.58,
+          "confidence": 0.999
+        },
+        {
+          "text": "better,",
+          "start": 164.6,
+          "end": 164.86,
+          "confidence": 0.424
+        },
+        {
+          "text": "better.",
+          "start": 164.86,
+          "end": 165.04,
+          "confidence": 0.555
+        }
+      ]
+    },
+    {
+      "id": 34,
+      "seek": 14012,
+      "start": 165.14,
+      "end": 165.74,
+      "text": " Up who the baddest.",
+      "tokens": [
+        51612,
+        5858,
+        567,
+        264,
+        1578,
+        23748,
+        13,
+        51644
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.36420179578993056,
+      "compression_ratio": 1.7333333333333334,
+      "no_speech_prob": 0.7754144668579102,
+      "confidence": 0.75,
+      "words": [
+        {
+          "text": "Up",
+          "start": 165.14,
+          "end": 165.28,
+          "confidence": 0.517
+        },
+        {
+          "text": "who",
+          "start": 165.28,
+          "end": 165.4,
+          "confidence": 0.747
+        },
+        {
+          "text": "the",
+          "start": 165.4,
+          "end": 165.54,
+          "confidence": 0.926
+        },
+        {
+          "text": "baddest.",
+          "start": 165.54,
+          "end": 165.74,
+          "confidence": 0.816
+        }
+      ]
+    },
+    {
+      "id": 35,
+      "seek": 16572,
+      "start": 165.74,
+      "end": 166.84,
+      "text": " it don't matter cause we is your enemy.",
+      "tokens": [
+        50364,
+        309,
+        500,
+        380,
+        1871,
+        3082,
+        321,
+        307,
+        428,
+        5945,
+        13,
+        50414
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9108315981351413,
+      "compression_ratio": 0.8297872340425532,
+      "no_speech_prob": 0.6954025626182556,
+      "confidence": 0.447,
+      "words": [
+        {
+          "text": "it",
+          "start": 165.74,
+          "end": 165.88,
+          "confidence": 0.125
+        },
+        {
+          "text": "don't",
+          "start": 165.88,
+          "end": 166.06,
+          "confidence": 0.825
+        },
+        {
+          "text": "matter",
+          "start": 166.06,
+          "end": 166.22,
+          "confidence": 0.996
+        },
+        {
+          "text": "cause",
+          "start": 166.22,
+          "end": 166.4,
+          "confidence": 0.287
+        },
+        {
+          "text": "we",
+          "start": 166.4,
+          "end": 166.56,
+          "confidence": 0.889
+        },
+        {
+          "text": "is",
+          "start": 166.56,
+          "end": 166.66,
+          "confidence": 0.229
+        },
+        {
+          "text": "your",
+          "start": 166.66,
+          "end": 166.76,
+          "confidence": 0.561
+        },
+        {
+          "text": "enemy.",
+          "start": 166.76,
+          "end": 166.84,
+          "confidence": 0.257
+        }
+      ]
+    },
+    {
+      "id": 36,
+      "seek": 19572,
+      "start": 195.72,
+      "end": 198.2,
+      "text": " I swear I'll never be insane",
+      "tokens": [
+        50364,
+        286,
+        11902,
+        286,
+        603,
+        1128,
+        312,
+        10838,
+        50464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5534874200820923,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.6747308969497681,
+      "confidence": 0.773,
+      "words": [
+        {
+          "text": "I",
+          "start": 195.72,
+          "end": 196.38,
+          "confidence": 0.745
+        },
+        {
+          "text": "swear",
+          "start": 196.38,
+          "end": 196.74,
+          "confidence": 0.963
+        },
+        {
+          "text": "I'll",
+          "start": 196.74,
+          "end": 197.18,
+          "confidence": 0.665
+        },
+        {
+          "text": "never",
+          "start": 197.18,
+          "end": 197.58,
+          "confidence": 0.997
+        },
+        {
+          "text": "be",
+          "start": 197.58,
+          "end": 197.92,
+          "confidence": 0.994
+        },
+        {
+          "text": "insane",
+          "start": 197.92,
+          "end": 198.2,
+          "confidence": 0.525
+        }
+      ]
+    },
+    {
+      "id": 37,
+      "seek": 19572,
+      "start": 198.5,
+      "end": 199.38,
+      "text": " You gotta be insane",
+      "tokens": [
+        50464,
+        509,
+        3428,
+        312,
+        10838,
+        50564
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5534874200820923,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.6747308969497681,
+      "confidence": 0.492,
+      "words": [
+        {
+          "text": "You",
+          "start": 198.5,
+          "end": 198.7,
+          "confidence": 0.4
+        },
+        {
+          "text": "gotta",
+          "start": 198.7,
+          "end": 198.88,
+          "confidence": 0.268
+        },
+        {
+          "text": "be",
+          "start": 198.88,
+          "end": 199.12,
+          "confidence": 0.959
+        },
+        {
+          "text": "insane",
+          "start": 199.12,
+          "end": 199.38,
+          "confidence": 0.568
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/corner_cases/random.nocond_apollo11.mp3.words.json b/tests/expected/corner_cases/random.nocond_apollo11.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..6d0775c1c9b63b2413a5180c6c157f59125fe90b
--- /dev/null
+++ b/tests/expected/corner_cases/random.nocond_apollo11.mp3.words.json
@@ -0,0 +1,2003 @@
+{
+  "text": " Apollo 11, Houston we got a recommendation for you on your Soyuz-VA GLEME GVA. Alright, okay, we like the... Yeah, I'll put that there, my friend. They make the one that's on the helmet we were going to have in B1. And you can put the other one on the mic helmet with those GVA flipper strings. I got them. I got them. They're the better now. They're the one that got the one right there. They're going to the leak reshaping. We got them in there. I got them in bags. And I just... Yeah. I got them in the album bags. At least it's in the album bags. Right here. Right here. Yeah, we're taking Nick and me out. Yeah, we're thinking next week on a... You know, we were... We were going to hang with the cover, I tried it already. Okay, fine, we weren't sure of that, just a suggestion. We thought we'd... you could check it out. I'm not sure if you've already done that. So, I guess we're going to come up with this, let us know. Okay, no problem. Okay, no problem. We'll let you know when the end of the... ...sun. Bye.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.52,
+      "end": 6.54,
+      "text": " Apollo 11, Houston we got a recommendation for you on your Soyuz-VA GLEME GVA.",
+      "tokens": [
+        50364,
+        25187,
+        2975,
+        11,
+        18717,
+        321,
+        658,
+        257,
+        11879,
+        337,
+        291,
+        322,
+        428,
+        24758,
+        3334,
+        12,
+        20914,
+        460,
+        2634,
+        15454,
+        460,
+        20914,
+        13,
+        50714
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.7576699998643663,
+      "compression_ratio": 1.4202898550724639,
+      "no_speech_prob": 0.44998496770858765,
+      "confidence": 0.541,
+      "words": [
+        {
+          "text": "Apollo",
+          "start": 0.52,
+          "end": 0.88,
+          "confidence": 0.155
+        },
+        {
+          "text": "11,",
+          "start": 0.88,
+          "end": 1.26,
+          "confidence": 0.977
+        },
+        {
+          "text": "Houston",
+          "start": 1.52,
+          "end": 1.72,
+          "confidence": 0.986
+        },
+        {
+          "text": "we",
+          "start": 1.72,
+          "end": 1.94,
+          "confidence": 0.518
+        },
+        {
+          "text": "got",
+          "start": 1.94,
+          "end": 2.1,
+          "confidence": 0.823
+        },
+        {
+          "text": "a",
+          "start": 2.1,
+          "end": 2.26,
+          "confidence": 0.989
+        },
+        {
+          "text": "recommendation",
+          "start": 2.26,
+          "end": 2.86,
+          "confidence": 0.968
+        },
+        {
+          "text": "for",
+          "start": 2.86,
+          "end": 3.44,
+          "confidence": 0.946
+        },
+        {
+          "text": "you",
+          "start": 3.44,
+          "end": 3.6,
+          "confidence": 0.984
+        },
+        {
+          "text": "on",
+          "start": 3.6,
+          "end": 3.72,
+          "confidence": 0.909
+        },
+        {
+          "text": "your",
+          "start": 3.72,
+          "end": 3.92,
+          "confidence": 0.971
+        },
+        {
+          "text": "Soyuz-VA",
+          "start": 3.92,
+          "end": 5.16,
+          "confidence": 0.26
+        },
+        {
+          "text": "GLEME",
+          "start": 5.16,
+          "end": 5.74,
+          "confidence": 0.475
+        },
+        {
+          "text": "GVA.",
+          "start": 5.74,
+          "end": 6.54,
+          "confidence": 0.435
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 10.8,
+      "end": 13.48,
+      "text": " Alright, okay, we like the...",
+      "tokens": [
+        50714,
+        2798,
+        11,
+        1392,
+        11,
+        321,
+        411,
+        264,
+        485,
+        51014
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.7576699998643663,
+      "compression_ratio": 1.4202898550724639,
+      "no_speech_prob": 0.44998496770858765,
+      "confidence": 0.412,
+      "words": [
+        {
+          "text": "Alright,",
+          "start": 10.8,
+          "end": 11.04,
+          "confidence": 0.31
+        },
+        {
+          "text": "okay,",
+          "start": 11.68,
+          "end": 12.22,
+          "confidence": 0.504
+        },
+        {
+          "text": "we",
+          "start": 12.5,
+          "end": 12.98,
+          "confidence": 0.609
+        },
+        {
+          "text": "like",
+          "start": 12.98,
+          "end": 13.26,
+          "confidence": 0.505
+        },
+        {
+          "text": "the...",
+          "start": 13.26,
+          "end": 13.48,
+          "confidence": 0.247
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 13.48,
+      "end": 14.6,
+      "text": " Yeah, I'll put that there, my friend.",
+      "tokens": [
+        51014,
+        865,
+        11,
+        286,
+        603,
+        829,
+        300,
+        456,
+        11,
+        452,
+        1277,
+        13,
+        51114
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.7576699998643663,
+      "compression_ratio": 1.4202898550724639,
+      "no_speech_prob": 0.44998496770858765,
+      "confidence": 0.218,
+      "words": [
+        {
+          "text": "Yeah,",
+          "start": 13.48,
+          "end": 13.5,
+          "confidence": 0.281
+        },
+        {
+          "text": "I'll",
+          "start": 13.5,
+          "end": 13.78,
+          "confidence": 0.195
+        },
+        {
+          "text": "put",
+          "start": 13.78,
+          "end": 13.96,
+          "confidence": 0.206
+        },
+        {
+          "text": "that",
+          "start": 13.96,
+          "end": 14.12,
+          "confidence": 0.86
+        },
+        {
+          "text": "there,",
+          "start": 14.12,
+          "end": 14.38,
+          "confidence": 0.325
+        },
+        {
+          "text": "my",
+          "start": 14.4,
+          "end": 14.54,
+          "confidence": 0.095
+        },
+        {
+          "text": "friend.",
+          "start": 14.54,
+          "end": 14.6,
+          "confidence": 0.088
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 14.6,
+      "end": 19.08,
+      "text": " They make the one that's on the helmet we were going to have in B1.",
+      "tokens": [
+        51114,
+        814,
+        652,
+        264,
+        472,
+        300,
+        311,
+        322,
+        264,
+        15922,
+        321,
+        645,
+        516,
+        281,
+        362,
+        294,
+        363,
+        16,
+        13,
+        51314
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.7576699998643663,
+      "compression_ratio": 1.4202898550724639,
+      "no_speech_prob": 0.44998496770858765,
+      "confidence": 0.6,
+      "words": [
+        {
+          "text": "They",
+          "start": 14.6,
+          "end": 15.46,
+          "confidence": 0.366
+        },
+        {
+          "text": "make",
+          "start": 15.46,
+          "end": 15.68,
+          "confidence": 0.458
+        },
+        {
+          "text": "the",
+          "start": 15.68,
+          "end": 15.84,
+          "confidence": 0.354
+        },
+        {
+          "text": "one",
+          "start": 15.84,
+          "end": 16.06,
+          "confidence": 0.71
+        },
+        {
+          "text": "that's",
+          "start": 16.06,
+          "end": 16.28,
+          "confidence": 0.572
+        },
+        {
+          "text": "on",
+          "start": 16.28,
+          "end": 16.48,
+          "confidence": 0.636
+        },
+        {
+          "text": "the",
+          "start": 16.48,
+          "end": 16.78,
+          "confidence": 0.858
+        },
+        {
+          "text": "helmet",
+          "start": 16.78,
+          "end": 17.26,
+          "confidence": 0.892
+        },
+        {
+          "text": "we",
+          "start": 17.26,
+          "end": 17.52,
+          "confidence": 0.185
+        },
+        {
+          "text": "were",
+          "start": 17.52,
+          "end": 17.78,
+          "confidence": 0.529
+        },
+        {
+          "text": "going",
+          "start": 17.78,
+          "end": 17.92,
+          "confidence": 0.55
+        },
+        {
+          "text": "to",
+          "start": 17.92,
+          "end": 17.98,
+          "confidence": 0.984
+        },
+        {
+          "text": "have",
+          "start": 17.98,
+          "end": 18.2,
+          "confidence": 0.958
+        },
+        {
+          "text": "in",
+          "start": 18.2,
+          "end": 18.38,
+          "confidence": 0.844
+        },
+        {
+          "text": "B1.",
+          "start": 18.38,
+          "end": 19.08,
+          "confidence": 0.765
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 20.12,
+      "end": 24.52,
+      "text": " And you can put the other one on the mic helmet with those GVA flipper strings.",
+      "tokens": [
+        51314,
+        400,
+        291,
+        393,
+        829,
+        264,
+        661,
+        472,
+        322,
+        264,
+        3123,
+        15922,
+        365,
+        729,
+        460,
+        20914,
+        932,
+        15124,
+        13985,
+        13,
+        51614
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.7576699998643663,
+      "compression_ratio": 1.4202898550724639,
+      "no_speech_prob": 0.44998496770858765,
+      "confidence": 0.468,
+      "words": [
+        {
+          "text": "And",
+          "start": 20.12,
+          "end": 20.16,
+          "confidence": 0.534
+        },
+        {
+          "text": "you",
+          "start": 20.16,
+          "end": 20.32,
+          "confidence": 0.942
+        },
+        {
+          "text": "can",
+          "start": 20.32,
+          "end": 20.48,
+          "confidence": 0.74
+        },
+        {
+          "text": "put",
+          "start": 20.48,
+          "end": 20.64,
+          "confidence": 0.992
+        },
+        {
+          "text": "the",
+          "start": 20.64,
+          "end": 20.84,
+          "confidence": 0.99
+        },
+        {
+          "text": "other",
+          "start": 20.84,
+          "end": 21.0,
+          "confidence": 0.993
+        },
+        {
+          "text": "one",
+          "start": 21.0,
+          "end": 21.18,
+          "confidence": 0.982
+        },
+        {
+          "text": "on",
+          "start": 21.18,
+          "end": 21.42,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 21.42,
+          "end": 21.94,
+          "confidence": 0.462
+        },
+        {
+          "text": "mic",
+          "start": 21.94,
+          "end": 22.48,
+          "confidence": 0.384
+        },
+        {
+          "text": "helmet",
+          "start": 22.48,
+          "end": 22.8,
+          "confidence": 0.89
+        },
+        {
+          "text": "with",
+          "start": 22.8,
+          "end": 23.06,
+          "confidence": 0.436
+        },
+        {
+          "text": "those",
+          "start": 23.06,
+          "end": 23.3,
+          "confidence": 0.45
+        },
+        {
+          "text": "GVA",
+          "start": 23.3,
+          "end": 23.74,
+          "confidence": 0.222
+        },
+        {
+          "text": "flipper",
+          "start": 23.74,
+          "end": 24.18,
+          "confidence": 0.103
+        },
+        {
+          "text": "strings.",
+          "start": 24.18,
+          "end": 24.52,
+          "confidence": 0.207
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 2500,
+      "start": 31.32,
+      "end": 34.03,
+      "text": " I got them. I got them. They're the better now.",
+      "tokens": [
+        50364,
+        286,
+        658,
+        552,
+        13,
+        286,
+        658,
+        552,
+        13,
+        814,
+        434,
+        264,
+        1101,
+        586,
+        13,
+        50814
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.7381767340465984,
+      "compression_ratio": 1.920731707317073,
+      "no_speech_prob": 0.8235840797424316,
+      "confidence": 0.45,
+      "words": [
+        {
+          "text": "I",
+          "start": 31.32,
+          "end": 31.52,
+          "confidence": 0.121
+        },
+        {
+          "text": "got",
+          "start": 31.52,
+          "end": 31.82,
+          "confidence": 0.464
+        },
+        {
+          "text": "them.",
+          "start": 31.82,
+          "end": 32.12,
+          "confidence": 0.264
+        },
+        {
+          "text": "I",
+          "start": 32.44,
+          "end": 32.84,
+          "confidence": 0.385
+        },
+        {
+          "text": "got",
+          "start": 32.84,
+          "end": 33.16,
+          "confidence": 0.967
+        },
+        {
+          "text": "them.",
+          "start": 33.16,
+          "end": 33.44,
+          "confidence": 0.958
+        },
+        {
+          "text": "They're",
+          "start": 33.44,
+          "end": 33.5,
+          "confidence": 0.389
+        },
+        {
+          "text": "the",
+          "start": 33.5,
+          "end": 33.56,
+          "confidence": 0.312
+        },
+        {
+          "text": "better",
+          "start": 33.56,
+          "end": 33.76,
+          "confidence": 0.763
+        },
+        {
+          "text": "now.",
+          "start": 33.76,
+          "end": 34.03,
+          "confidence": 0.795
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 2500,
+      "start": 34.03,
+      "end": 36.36,
+      "text": " They're the one that got the one right there.",
+      "tokens": [
+        50814,
+        814,
+        434,
+        264,
+        472,
+        300,
+        658,
+        264,
+        472,
+        558,
+        456,
+        13,
+        50964
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.7381767340465984,
+      "compression_ratio": 1.920731707317073,
+      "no_speech_prob": 0.8235840797424316,
+      "confidence": 0.275,
+      "words": [
+        {
+          "text": "They're",
+          "start": 34.03,
+          "end": 34.38,
+          "confidence": 0.243
+        },
+        {
+          "text": "the",
+          "start": 34.38,
+          "end": 34.58,
+          "confidence": 0.738
+        },
+        {
+          "text": "one",
+          "start": 34.58,
+          "end": 34.94,
+          "confidence": 0.279
+        },
+        {
+          "text": "that",
+          "start": 34.94,
+          "end": 35.28,
+          "confidence": 0.456
+        },
+        {
+          "text": "got",
+          "start": 35.28,
+          "end": 35.48,
+          "confidence": 0.186
+        },
+        {
+          "text": "the",
+          "start": 35.48,
+          "end": 35.68,
+          "confidence": 0.439
+        },
+        {
+          "text": "one",
+          "start": 35.68,
+          "end": 35.76,
+          "confidence": 0.154
+        },
+        {
+          "text": "right",
+          "start": 35.76,
+          "end": 36.04,
+          "confidence": 0.08
+        },
+        {
+          "text": "there.",
+          "start": 36.04,
+          "end": 36.36,
+          "confidence": 0.454
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 2500,
+      "start": 37.62,
+      "end": 39.38,
+      "text": " They're going to the leak reshaping.",
+      "tokens": [
+        50964,
+        814,
+        434,
+        516,
+        281,
+        264,
+        17143,
+        725,
+        71,
+        569,
+        278,
+        13,
+        51114
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.7381767340465984,
+      "compression_ratio": 1.920731707317073,
+      "no_speech_prob": 0.8235840797424316,
+      "confidence": 0.287,
+      "words": [
+        {
+          "text": "They're",
+          "start": 37.62,
+          "end": 37.96,
+          "confidence": 0.506
+        },
+        {
+          "text": "going",
+          "start": 37.96,
+          "end": 38.12,
+          "confidence": 0.907
+        },
+        {
+          "text": "to",
+          "start": 38.12,
+          "end": 38.36,
+          "confidence": 0.282
+        },
+        {
+          "text": "the",
+          "start": 38.36,
+          "end": 38.48,
+          "confidence": 0.145
+        },
+        {
+          "text": "leak",
+          "start": 38.48,
+          "end": 38.76,
+          "confidence": 0.068
+        },
+        {
+          "text": "reshaping.",
+          "start": 38.76,
+          "end": 39.38,
+          "confidence": 0.275
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 2500,
+      "start": 39.88,
+      "end": 40.98,
+      "text": " We got them in there.",
+      "tokens": [
+        51114,
+        492,
+        658,
+        552,
+        294,
+        456,
+        13,
+        51164
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.7381767340465984,
+      "compression_ratio": 1.920731707317073,
+      "no_speech_prob": 0.8235840797424316,
+      "confidence": 0.722,
+      "words": [
+        {
+          "text": "We",
+          "start": 39.88,
+          "end": 40.22,
+          "confidence": 0.62
+        },
+        {
+          "text": "got",
+          "start": 40.22,
+          "end": 40.48,
+          "confidence": 0.571
+        },
+        {
+          "text": "them",
+          "start": 40.48,
+          "end": 40.64,
+          "confidence": 0.956
+        },
+        {
+          "text": "in",
+          "start": 40.64,
+          "end": 40.74,
+          "confidence": 0.946
+        },
+        {
+          "text": "there.",
+          "start": 40.74,
+          "end": 40.98,
+          "confidence": 0.612
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 2500,
+      "start": 41.22,
+      "end": 41.98,
+      "text": " I got them in bags.",
+      "tokens": [
+        51164,
+        286,
+        658,
+        552,
+        294,
+        10405,
+        13,
+        51264
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.7381767340465984,
+      "compression_ratio": 1.920731707317073,
+      "no_speech_prob": 0.8235840797424316,
+      "confidence": 0.397,
+      "words": [
+        {
+          "text": "I",
+          "start": 41.22,
+          "end": 41.32,
+          "confidence": 0.236
+        },
+        {
+          "text": "got",
+          "start": 41.32,
+          "end": 41.5,
+          "confidence": 0.153
+        },
+        {
+          "text": "them",
+          "start": 41.5,
+          "end": 41.56,
+          "confidence": 0.852
+        },
+        {
+          "text": "in",
+          "start": 41.56,
+          "end": 41.72,
+          "confidence": 0.861
+        },
+        {
+          "text": "bags.",
+          "start": 41.72,
+          "end": 41.98,
+          "confidence": 0.374
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 2500,
+      "start": 43.1,
+      "end": 44.48,
+      "text": " And I just...",
+      "tokens": [
+        51264,
+        400,
+        286,
+        445,
+        485,
+        51364
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.7381767340465984,
+      "compression_ratio": 1.920731707317073,
+      "no_speech_prob": 0.8235840797424316,
+      "confidence": 0.367,
+      "words": [
+        {
+          "text": "And",
+          "start": 43.1,
+          "end": 43.36,
+          "confidence": 0.573
+        },
+        {
+          "text": "I",
+          "start": 43.36,
+          "end": 44.0,
+          "confidence": 0.332
+        },
+        {
+          "text": "just...",
+          "start": 44.0,
+          "end": 44.48,
+          "confidence": 0.26
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 2500,
+      "start": 45.22,
+      "end": 45.4,
+      "text": " Yeah.",
+      "tokens": [
+        51364,
+        865,
+        13,
+        51414
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.7381767340465984,
+      "compression_ratio": 1.920731707317073,
+      "no_speech_prob": 0.8235840797424316,
+      "confidence": 0.283,
+      "words": [
+        {
+          "text": "Yeah.",
+          "start": 45.22,
+          "end": 45.4,
+          "confidence": 0.283
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 2500,
+      "start": 46.2,
+      "end": 47.4,
+      "text": " I got them in the album bags.",
+      "tokens": [
+        51414,
+        286,
+        658,
+        552,
+        294,
+        264,
+        6030,
+        10405,
+        13,
+        51514
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.7381767340465984,
+      "compression_ratio": 1.920731707317073,
+      "no_speech_prob": 0.8235840797424316,
+      "confidence": 0.445,
+      "words": [
+        {
+          "text": "I",
+          "start": 46.2,
+          "end": 46.38,
+          "confidence": 0.297
+        },
+        {
+          "text": "got",
+          "start": 46.38,
+          "end": 46.46,
+          "confidence": 0.548
+        },
+        {
+          "text": "them",
+          "start": 46.46,
+          "end": 46.5,
+          "confidence": 0.959
+        },
+        {
+          "text": "in",
+          "start": 46.5,
+          "end": 46.74,
+          "confidence": 0.906
+        },
+        {
+          "text": "the",
+          "start": 46.74,
+          "end": 46.92,
+          "confidence": 0.453
+        },
+        {
+          "text": "album",
+          "start": 46.92,
+          "end": 47.06,
+          "confidence": 0.22
+        },
+        {
+          "text": "bags.",
+          "start": 47.06,
+          "end": 47.4,
+          "confidence": 0.246
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 2500,
+      "start": 48.22,
+      "end": 49.58,
+      "text": " At least it's in the album bags.",
+      "tokens": [
+        51514,
+        1711,
+        1935,
+        309,
+        311,
+        294,
+        264,
+        6030,
+        10405,
+        13,
+        51614
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.7381767340465984,
+      "compression_ratio": 1.920731707317073,
+      "no_speech_prob": 0.8235840797424316,
+      "confidence": 0.606,
+      "words": [
+        {
+          "text": "At",
+          "start": 48.22,
+          "end": 48.34,
+          "confidence": 0.184
+        },
+        {
+          "text": "least",
+          "start": 48.34,
+          "end": 48.6,
+          "confidence": 0.907
+        },
+        {
+          "text": "it's",
+          "start": 48.6,
+          "end": 48.86,
+          "confidence": 0.567
+        },
+        {
+          "text": "in",
+          "start": 48.86,
+          "end": 48.96,
+          "confidence": 0.802
+        },
+        {
+          "text": "the",
+          "start": 48.96,
+          "end": 49.1,
+          "confidence": 0.586
+        },
+        {
+          "text": "album",
+          "start": 49.1,
+          "end": 49.22,
+          "confidence": 0.862
+        },
+        {
+          "text": "bags.",
+          "start": 49.22,
+          "end": 49.58,
+          "confidence": 0.837
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 2500,
+      "start": 50.1,
+      "end": 50.6,
+      "text": " Right here.",
+      "tokens": [
+        51614,
+        1779,
+        510,
+        13,
+        51664
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.7381767340465984,
+      "compression_ratio": 1.920731707317073,
+      "no_speech_prob": 0.8235840797424316,
+      "confidence": 0.308,
+      "words": [
+        {
+          "text": "Right",
+          "start": 50.1,
+          "end": 50.4,
+          "confidence": 0.29
+        },
+        {
+          "text": "here.",
+          "start": 50.4,
+          "end": 50.6,
+          "confidence": 0.327
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 2500,
+      "start": 51.46,
+      "end": 51.83,
+      "text": " Right here.",
+      "tokens": [
+        51664,
+        1779,
+        510,
+        13,
+        51714
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.7381767340465984,
+      "compression_ratio": 1.920731707317073,
+      "no_speech_prob": 0.8235840797424316,
+      "confidence": 0.82,
+      "words": [
+        {
+          "text": "Right",
+          "start": 51.46,
+          "end": 51.74,
+          "confidence": 0.73
+        },
+        {
+          "text": "here.",
+          "start": 51.74,
+          "end": 51.83,
+          "confidence": 0.921
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 2500,
+      "start": 51.83,
+      "end": 52.88,
+      "text": " Yeah, we're taking Nick and me out.",
+      "tokens": [
+        51714,
+        865,
+        11,
+        321,
+        434,
+        1940,
+        9449,
+        293,
+        385,
+        484,
+        13,
+        51764
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.7381767340465984,
+      "compression_ratio": 1.920731707317073,
+      "no_speech_prob": 0.8235840797424316,
+      "confidence": 0.395,
+      "words": [
+        {
+          "text": "Yeah,",
+          "start": 51.83,
+          "end": 52.16,
+          "confidence": 0.158
+        },
+        {
+          "text": "we're",
+          "start": 52.16,
+          "end": 52.26,
+          "confidence": 0.635
+        },
+        {
+          "text": "taking",
+          "start": 52.26,
+          "end": 52.28,
+          "confidence": 0.611
+        },
+        {
+          "text": "Nick",
+          "start": 52.28,
+          "end": 52.52,
+          "confidence": 0.185
+        },
+        {
+          "text": "and",
+          "start": 52.52,
+          "end": 52.64,
+          "confidence": 0.143
+        },
+        {
+          "text": "me",
+          "start": 52.64,
+          "end": 52.74,
+          "confidence": 0.683
+        },
+        {
+          "text": "out.",
+          "start": 52.74,
+          "end": 52.88,
+          "confidence": 0.837
+        }
+      ]
+    },
+    {
+      "id": 17,
+      "seek": 5300,
+      "start": 53.1,
+      "end": 54.57,
+      "text": " Yeah, we're thinking next week on a...",
+      "tokens": [
+        50364,
+        865,
+        11,
+        321,
+        434,
+        1953,
+        958,
+        1243,
+        322,
+        257,
+        485,
+        50464
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.519427408698861,
+      "compression_ratio": 1.7004219409282701,
+      "no_speech_prob": 0.4345245361328125,
+      "confidence": 0.419,
+      "words": [
+        {
+          "text": "Yeah,",
+          "start": 53.1,
+          "end": 53.26,
+          "confidence": 0.657
+        },
+        {
+          "text": "we're",
+          "start": 53.34,
+          "end": 53.44,
+          "confidence": 0.583
+        },
+        {
+          "text": "thinking",
+          "start": 53.44,
+          "end": 53.62,
+          "confidence": 0.593
+        },
+        {
+          "text": "next",
+          "start": 53.62,
+          "end": 53.86,
+          "confidence": 0.343
+        },
+        {
+          "text": "week",
+          "start": 53.86,
+          "end": 54.06,
+          "confidence": 0.383
+        },
+        {
+          "text": "on",
+          "start": 54.06,
+          "end": 54.22,
+          "confidence": 0.251
+        },
+        {
+          "text": "a...",
+          "start": 54.22,
+          "end": 54.57,
+          "confidence": 0.216
+        }
+      ]
+    },
+    {
+      "id": 18,
+      "seek": 5300,
+      "start": 54.57,
+      "end": 57.34,
+      "text": " You know, we were...",
+      "tokens": [
+        50464,
+        509,
+        458,
+        11,
+        321,
+        645,
+        485,
+        50564
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.519427408698861,
+      "compression_ratio": 1.7004219409282701,
+      "no_speech_prob": 0.4345245361328125,
+      "confidence": 0.463,
+      "words": [
+        {
+          "text": "You",
+          "start": 54.57,
+          "end": 55.08,
+          "confidence": 0.18
+        },
+        {
+          "text": "know,",
+          "start": 55.08,
+          "end": 55.2,
+          "confidence": 0.915
+        },
+        {
+          "text": "we",
+          "start": 56.36,
+          "end": 56.62,
+          "confidence": 0.392
+        },
+        {
+          "text": "were...",
+          "start": 56.62,
+          "end": 57.34,
+          "confidence": 0.71
+        }
+      ]
+    },
+    {
+      "id": 19,
+      "seek": 5300,
+      "start": 57.86,
+      "end": 61.8,
+      "text": " We were going to hang with the cover, I tried it already.",
+      "tokens": [
+        50564,
+        492,
+        645,
+        516,
+        281,
+        3967,
+        365,
+        264,
+        2060,
+        11,
+        286,
+        3031,
+        309,
+        1217,
+        13,
+        50814
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.519427408698861,
+      "compression_ratio": 1.7004219409282701,
+      "no_speech_prob": 0.4345245361328125,
+      "confidence": 0.421,
+      "words": [
+        {
+          "text": "We",
+          "start": 57.86,
+          "end": 58.0,
+          "confidence": 0.388
+        },
+        {
+          "text": "were",
+          "start": 58.0,
+          "end": 58.4,
+          "confidence": 0.245
+        },
+        {
+          "text": "going",
+          "start": 58.4,
+          "end": 58.54,
+          "confidence": 0.258
+        },
+        {
+          "text": "to",
+          "start": 58.54,
+          "end": 58.7,
+          "confidence": 0.935
+        },
+        {
+          "text": "hang",
+          "start": 58.7,
+          "end": 58.72,
+          "confidence": 0.406
+        },
+        {
+          "text": "with",
+          "start": 58.72,
+          "end": 59.22,
+          "confidence": 0.25
+        },
+        {
+          "text": "the",
+          "start": 59.22,
+          "end": 59.5,
+          "confidence": 0.191
+        },
+        {
+          "text": "cover,",
+          "start": 59.5,
+          "end": 61.02,
+          "confidence": 0.352
+        },
+        {
+          "text": "I",
+          "start": 61.18,
+          "end": 61.24,
+          "confidence": 0.573
+        },
+        {
+          "text": "tried",
+          "start": 61.24,
+          "end": 61.44,
+          "confidence": 0.644
+        },
+        {
+          "text": "it",
+          "start": 61.44,
+          "end": 61.62,
+          "confidence": 0.602
+        },
+        {
+          "text": "already.",
+          "start": 61.62,
+          "end": 61.8,
+          "confidence": 0.896
+        }
+      ]
+    },
+    {
+      "id": 20,
+      "seek": 5300,
+      "start": 62.52,
+      "end": 65.12,
+      "text": " Okay, fine, we weren't sure of that, just a suggestion.",
+      "tokens": [
+        50814,
+        1033,
+        11,
+        2489,
+        11,
+        321,
+        4999,
+        380,
+        988,
+        295,
+        300,
+        11,
+        445,
+        257,
+        16541,
+        13,
+        50964
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.519427408698861,
+      "compression_ratio": 1.7004219409282701,
+      "no_speech_prob": 0.4345245361328125,
+      "confidence": 0.86,
+      "words": [
+        {
+          "text": "Okay,",
+          "start": 62.52,
+          "end": 62.78,
+          "confidence": 0.731
+        },
+        {
+          "text": "fine,",
+          "start": 62.9,
+          "end": 63.06,
+          "confidence": 0.955
+        },
+        {
+          "text": "we",
+          "start": 63.16,
+          "end": 63.3,
+          "confidence": 0.968
+        },
+        {
+          "text": "weren't",
+          "start": 63.3,
+          "end": 63.56,
+          "confidence": 0.993
+        },
+        {
+          "text": "sure",
+          "start": 63.56,
+          "end": 63.72,
+          "confidence": 0.974
+        },
+        {
+          "text": "of",
+          "start": 63.72,
+          "end": 63.86,
+          "confidence": 0.598
+        },
+        {
+          "text": "that,",
+          "start": 63.86,
+          "end": 63.98,
+          "confidence": 0.993
+        },
+        {
+          "text": "just",
+          "start": 64.1,
+          "end": 64.56,
+          "confidence": 0.637
+        },
+        {
+          "text": "a",
+          "start": 64.56,
+          "end": 64.74,
+          "confidence": 0.779
+        },
+        {
+          "text": "suggestion.",
+          "start": 64.74,
+          "end": 65.12,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 21,
+      "seek": 5300,
+      "start": 65.22,
+      "end": 67.7,
+      "text": " We thought we'd... you could check it out.",
+      "tokens": [
+        50964,
+        492,
+        1194,
+        321,
+        1116,
+        485,
+        291,
+        727,
+        1520,
+        309,
+        484,
+        13,
+        51114
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.519427408698861,
+      "compression_ratio": 1.7004219409282701,
+      "no_speech_prob": 0.4345245361328125,
+      "confidence": 0.794,
+      "words": [
+        {
+          "text": "We",
+          "start": 65.22,
+          "end": 65.42,
+          "confidence": 0.896
+        },
+        {
+          "text": "thought",
+          "start": 65.42,
+          "end": 65.54,
+          "confidence": 0.983
+        },
+        {
+          "text": "we'd...",
+          "start": 65.54,
+          "end": 66.06,
+          "confidence": 0.818
+        },
+        {
+          "text": "you",
+          "start": 66.06,
+          "end": 67.04,
+          "confidence": 0.308
+        },
+        {
+          "text": "could",
+          "start": 67.04,
+          "end": 67.2,
+          "confidence": 0.777
+        },
+        {
+          "text": "check",
+          "start": 67.2,
+          "end": 67.38,
+          "confidence": 0.888
+        },
+        {
+          "text": "it",
+          "start": 67.38,
+          "end": 67.54,
+          "confidence": 0.996
+        },
+        {
+          "text": "out.",
+          "start": 67.54,
+          "end": 67.7,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 22,
+      "seek": 5300,
+      "start": 68.2,
+      "end": 69.26,
+      "text": " I'm not sure if you've already done that.",
+      "tokens": [
+        51114,
+        286,
+        478,
+        406,
+        988,
+        498,
+        291,
+        600,
+        1217,
+        1096,
+        300,
+        13,
+        51214
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.519427408698861,
+      "compression_ratio": 1.7004219409282701,
+      "no_speech_prob": 0.4345245361328125,
+      "confidence": 0.465,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 68.2,
+          "end": 68.44,
+          "confidence": 0.341
+        },
+        {
+          "text": "not",
+          "start": 68.44,
+          "end": 68.5,
+          "confidence": 0.399
+        },
+        {
+          "text": "sure",
+          "start": 68.5,
+          "end": 68.64,
+          "confidence": 0.854
+        },
+        {
+          "text": "if",
+          "start": 68.64,
+          "end": 68.66,
+          "confidence": 0.463
+        },
+        {
+          "text": "you've",
+          "start": 68.66,
+          "end": 68.72,
+          "confidence": 0.384
+        },
+        {
+          "text": "already",
+          "start": 68.72,
+          "end": 68.86,
+          "confidence": 0.427
+        },
+        {
+          "text": "done",
+          "start": 68.86,
+          "end": 69.06,
+          "confidence": 0.408
+        },
+        {
+          "text": "that.",
+          "start": 69.06,
+          "end": 69.26,
+          "confidence": 0.993
+        }
+      ]
+    },
+    {
+      "id": 23,
+      "seek": 5300,
+      "start": 69.5,
+      "end": 72.44,
+      "text": " So, I guess we're going to come up with this, let us know.",
+      "tokens": [
+        51214,
+        407,
+        11,
+        286,
+        2041,
+        321,
+        434,
+        516,
+        281,
+        808,
+        493,
+        365,
+        341,
+        11,
+        718,
+        505,
+        458,
+        13,
+        51364
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.519427408698861,
+      "compression_ratio": 1.7004219409282701,
+      "no_speech_prob": 0.4345245361328125,
+      "confidence": 0.746,
+      "words": [
+        {
+          "text": "So,",
+          "start": 69.5,
+          "end": 69.6,
+          "confidence": 0.664
+        },
+        {
+          "text": "I",
+          "start": 69.7,
+          "end": 69.88,
+          "confidence": 0.812
+        },
+        {
+          "text": "guess",
+          "start": 69.88,
+          "end": 70.62,
+          "confidence": 0.99
+        },
+        {
+          "text": "we're",
+          "start": 70.62,
+          "end": 71.08,
+          "confidence": 0.743
+        },
+        {
+          "text": "going",
+          "start": 71.08,
+          "end": 71.22,
+          "confidence": 0.542
+        },
+        {
+          "text": "to",
+          "start": 71.22,
+          "end": 71.28,
+          "confidence": 0.989
+        },
+        {
+          "text": "come",
+          "start": 71.28,
+          "end": 71.42,
+          "confidence": 0.936
+        },
+        {
+          "text": "up",
+          "start": 71.42,
+          "end": 71.6,
+          "confidence": 0.676
+        },
+        {
+          "text": "with",
+          "start": 71.6,
+          "end": 71.76,
+          "confidence": 0.966
+        },
+        {
+          "text": "this,",
+          "start": 71.76,
+          "end": 71.9,
+          "confidence": 0.239
+        },
+        {
+          "text": "let",
+          "start": 72.1,
+          "end": 72.12,
+          "confidence": 0.718
+        },
+        {
+          "text": "us",
+          "start": 72.12,
+          "end": 72.24,
+          "confidence": 0.997
+        },
+        {
+          "text": "know.",
+          "start": 72.24,
+          "end": 72.44,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 24,
+      "seek": 5300,
+      "start": 74.22,
+      "end": 75.16,
+      "text": " Okay, no problem.",
+      "tokens": [
+        51414,
+        1033,
+        11,
+        572,
+        1154,
+        13,
+        51464
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.519427408698861,
+      "compression_ratio": 1.7004219409282701,
+      "no_speech_prob": 0.4345245361328125,
+      "confidence": 0.903,
+      "words": [
+        {
+          "text": "Okay,",
+          "start": 74.22,
+          "end": 74.48,
+          "confidence": 0.835
+        },
+        {
+          "text": "no",
+          "start": 74.58,
+          "end": 74.82,
+          "confidence": 0.913
+        },
+        {
+          "text": "problem.",
+          "start": 74.82,
+          "end": 75.16,
+          "confidence": 0.968
+        }
+      ]
+    },
+    {
+      "id": 25,
+      "seek": 5300,
+      "start": 75.2,
+      "end": 76.48,
+      "text": " Okay, no problem.",
+      "tokens": [
+        51464,
+        1033,
+        11,
+        572,
+        1154,
+        13,
+        51514
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.519427408698861,
+      "compression_ratio": 1.7004219409282701,
+      "no_speech_prob": 0.4345245361328125,
+      "confidence": 0.819,
+      "words": [
+        {
+          "text": "Okay,",
+          "start": 75.2,
+          "end": 75.8,
+          "confidence": 0.607
+        },
+        {
+          "text": "no",
+          "start": 75.92,
+          "end": 76.14,
+          "confidence": 0.908
+        },
+        {
+          "text": "problem.",
+          "start": 76.14,
+          "end": 76.48,
+          "confidence": 0.995
+        }
+      ]
+    },
+    {
+      "id": 26,
+      "seek": 5300,
+      "start": 76.54,
+      "end": 77.86,
+      "text": " We'll let you know when the end of the...",
+      "tokens": [
+        51514,
+        492,
+        603,
+        718,
+        291,
+        458,
+        562,
+        264,
+        917,
+        295,
+        264,
+        485,
+        51614
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.519427408698861,
+      "compression_ratio": 1.7004219409282701,
+      "no_speech_prob": 0.4345245361328125,
+      "confidence": 0.739,
+      "words": [
+        {
+          "text": "We'll",
+          "start": 76.54,
+          "end": 76.8,
+          "confidence": 0.755
+        },
+        {
+          "text": "let",
+          "start": 76.8,
+          "end": 76.92,
+          "confidence": 0.955
+        },
+        {
+          "text": "you",
+          "start": 76.92,
+          "end": 77.0,
+          "confidence": 0.628
+        },
+        {
+          "text": "know",
+          "start": 77.0,
+          "end": 77.16,
+          "confidence": 0.997
+        },
+        {
+          "text": "when",
+          "start": 77.16,
+          "end": 77.32,
+          "confidence": 0.421
+        },
+        {
+          "text": "the",
+          "start": 77.32,
+          "end": 77.4,
+          "confidence": 0.856
+        },
+        {
+          "text": "end",
+          "start": 77.4,
+          "end": 77.52,
+          "confidence": 0.978
+        },
+        {
+          "text": "of",
+          "start": 77.52,
+          "end": 77.64,
+          "confidence": 0.98
+        },
+        {
+          "text": "the...",
+          "start": 77.64,
+          "end": 77.86,
+          "confidence": 0.413
+        }
+      ]
+    },
+    {
+      "id": 27,
+      "seek": 5300,
+      "start": 78.02,
+      "end": 78.24,
+      "text": " ...sun.",
+      "tokens": [
+        51614,
+        1097,
+        11314,
+        13,
+        51664
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -0.519427408698861,
+      "compression_ratio": 1.7004219409282701,
+      "no_speech_prob": 0.4345245361328125,
+      "confidence": 0.158,
+      "words": [
+        {
+          "text": "...sun.",
+          "start": 78.02,
+          "end": 78.24,
+          "confidence": 0.158
+        }
+      ]
+    },
+    {
+      "id": 28,
+      "seek": 8300,
+      "start": 88.8,
+      "end": 88.82,
+      "text": " Bye.",
+      "tokens": [
+        50364,
+        4621,
+        13,
+        50664
+      ],
+      "temperature": 0.1,
+      "avg_logprob": -1.232518768310547,
+      "compression_ratio": 0.3333333333333333,
+      "no_speech_prob": 0.592905580997467,
+      "confidence": 0.069,
+      "words": [
+        {
+          "text": "Bye.",
+          "start": 88.8,
+          "end": 88.82,
+          "confidence": 0.069
+        }
+      ]
+    }
+  ],
+  "language": "English"
+}
\ No newline at end of file
diff --git a/tests/expected/corner_cases/random_apollo11.mp3.words.json b/tests/expected/corner_cases/random_apollo11.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..b4390210f6149284e2dcb88c6a807e9f9cdd3769
--- /dev/null
+++ b/tests/expected/corner_cases/random_apollo11.mp3.words.json
@@ -0,0 +1,1812 @@
+{
+  "text": " Apollo 11, Houston we got a recommendation for you on your Soyuz-EA GLEME GVA. Alright, okay. Yeah, let's take that camera. They make it want to go on the helmet. We're going to have a B1 and you can put the other one on the mic helmet with those GVA. Over. Alright, got them. Alright, got them. They're the better helmet that C1 has. They got the one mic that makes going through the leak reshapes. We got them in there helmet bags. And uh, we got the helmet in there helmet bags. The leak system, the leak of the bag. Right, yeah. Yeah, we're taking the leak to the auto, see you later. Hey, we were going to hang with the cover on the right side already. Okay, fine. We weren't sure of that, just a suggestion. We thought we'd, uh, you could check it out. It's not much of a hard to turn on, so uh, I guess we're going to come up with just let us know. Okay, no problem. Okay, no problem. We'll let you know when the end of the sun. Hello.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.52,
+      "end": 6.54,
+      "text": " Apollo 11, Houston we got a recommendation for you on your Soyuz-EA GLEME GVA.",
+      "tokens": [
+        50364,
+        25187,
+        2975,
+        11,
+        18717,
+        321,
+        658,
+        257,
+        11879,
+        337,
+        291,
+        322,
+        428,
+        24758,
+        3334,
+        12,
+        36,
+        32,
+        460,
+        2634,
+        15454,
+        460,
+        20914,
+        13,
+        50714
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.6685471307663691,
+      "compression_ratio": 1.3597883597883598,
+      "no_speech_prob": 0.44998496770858765,
+      "confidence": 0.548,
+      "words": [
+        {
+          "text": "Apollo",
+          "start": 0.52,
+          "end": 0.88,
+          "confidence": 0.155
+        },
+        {
+          "text": "11,",
+          "start": 0.88,
+          "end": 1.26,
+          "confidence": 0.977
+        },
+        {
+          "text": "Houston",
+          "start": 1.52,
+          "end": 1.72,
+          "confidence": 0.986
+        },
+        {
+          "text": "we",
+          "start": 1.72,
+          "end": 1.94,
+          "confidence": 0.518
+        },
+        {
+          "text": "got",
+          "start": 1.94,
+          "end": 2.1,
+          "confidence": 0.823
+        },
+        {
+          "text": "a",
+          "start": 2.1,
+          "end": 2.26,
+          "confidence": 0.989
+        },
+        {
+          "text": "recommendation",
+          "start": 2.26,
+          "end": 2.86,
+          "confidence": 0.968
+        },
+        {
+          "text": "for",
+          "start": 2.86,
+          "end": 3.44,
+          "confidence": 0.946
+        },
+        {
+          "text": "you",
+          "start": 3.44,
+          "end": 3.6,
+          "confidence": 0.984
+        },
+        {
+          "text": "on",
+          "start": 3.6,
+          "end": 3.72,
+          "confidence": 0.909
+        },
+        {
+          "text": "your",
+          "start": 3.72,
+          "end": 3.92,
+          "confidence": 0.971
+        },
+        {
+          "text": "Soyuz-EA",
+          "start": 3.92,
+          "end": 5.26,
+          "confidence": 0.321
+        },
+        {
+          "text": "GLEME",
+          "start": 5.26,
+          "end": 5.74,
+          "confidence": 0.558
+        },
+        {
+          "text": "GVA.",
+          "start": 5.74,
+          "end": 6.54,
+          "confidence": 0.336
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 10.8,
+      "end": 12.2,
+      "text": " Alright, okay.",
+      "tokens": [
+        50914,
+        2798,
+        11,
+        1392,
+        13,
+        50964
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.6685471307663691,
+      "compression_ratio": 1.3597883597883598,
+      "no_speech_prob": 0.44998496770858765,
+      "confidence": 0.366,
+      "words": [
+        {
+          "text": "Alright,",
+          "start": 10.8,
+          "end": 11.08,
+          "confidence": 0.282
+        },
+        {
+          "text": "okay.",
+          "start": 11.68,
+          "end": 12.2,
+          "confidence": 0.476
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 12.82,
+      "end": 14.4,
+      "text": " Yeah, let's take that camera.",
+      "tokens": [
+        51014,
+        865,
+        11,
+        718,
+        311,
+        747,
+        300,
+        2799,
+        13,
+        51064
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.6685471307663691,
+      "compression_ratio": 1.3597883597883598,
+      "no_speech_prob": 0.44998496770858765,
+      "confidence": 0.357,
+      "words": [
+        {
+          "text": "Yeah,",
+          "start": 12.82,
+          "end": 13.0,
+          "confidence": 0.167
+        },
+        {
+          "text": "let's",
+          "start": 13.04,
+          "end": 13.38,
+          "confidence": 0.277
+        },
+        {
+          "text": "take",
+          "start": 13.38,
+          "end": 14.02,
+          "confidence": 0.398
+        },
+        {
+          "text": "that",
+          "start": 14.02,
+          "end": 14.26,
+          "confidence": 0.478
+        },
+        {
+          "text": "camera.",
+          "start": 14.26,
+          "end": 14.4,
+          "confidence": 0.849
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 14.84,
+      "end": 17.26,
+      "text": " They make it want to go on the helmet.",
+      "tokens": [
+        51114,
+        814,
+        652,
+        309,
+        528,
+        281,
+        352,
+        322,
+        264,
+        15922,
+        13,
+        51214
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.6685471307663691,
+      "compression_ratio": 1.3597883597883598,
+      "no_speech_prob": 0.44998496770858765,
+      "confidence": 0.551,
+      "words": [
+        {
+          "text": "They",
+          "start": 14.84,
+          "end": 15.48,
+          "confidence": 0.397
+        },
+        {
+          "text": "make",
+          "start": 15.48,
+          "end": 15.68,
+          "confidence": 0.428
+        },
+        {
+          "text": "it",
+          "start": 15.68,
+          "end": 15.86,
+          "confidence": 0.21
+        },
+        {
+          "text": "want",
+          "start": 15.86,
+          "end": 16.06,
+          "confidence": 0.24
+        },
+        {
+          "text": "to",
+          "start": 16.06,
+          "end": 16.2,
+          "confidence": 0.965
+        },
+        {
+          "text": "go",
+          "start": 16.2,
+          "end": 16.38,
+          "confidence": 0.904
+        },
+        {
+          "text": "on",
+          "start": 16.38,
+          "end": 16.6,
+          "confidence": 0.952
+        },
+        {
+          "text": "the",
+          "start": 16.6,
+          "end": 16.8,
+          "confidence": 0.889
+        },
+        {
+          "text": "helmet.",
+          "start": 16.8,
+          "end": 17.26,
+          "confidence": 0.745
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 17.62,
+      "end": 23.74,
+      "text": " We're going to have a B1 and you can put the other one on the mic helmet with those GVA.",
+      "tokens": [
+        51264,
+        492,
+        434,
+        516,
+        281,
+        362,
+        257,
+        363,
+        16,
+        293,
+        291,
+        393,
+        829,
+        264,
+        661,
+        472,
+        322,
+        264,
+        3123,
+        15922,
+        365,
+        729,
+        460,
+        20914,
+        13,
+        51564
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.6685471307663691,
+      "compression_ratio": 1.3597883597883598,
+      "no_speech_prob": 0.44998496770858765,
+      "confidence": 0.672,
+      "words": [
+        {
+          "text": "We're",
+          "start": 17.62,
+          "end": 17.8,
+          "confidence": 0.779
+        },
+        {
+          "text": "going",
+          "start": 17.8,
+          "end": 17.92,
+          "confidence": 0.633
+        },
+        {
+          "text": "to",
+          "start": 17.92,
+          "end": 17.98,
+          "confidence": 0.992
+        },
+        {
+          "text": "have",
+          "start": 17.98,
+          "end": 18.2,
+          "confidence": 0.953
+        },
+        {
+          "text": "a",
+          "start": 18.2,
+          "end": 18.38,
+          "confidence": 0.36
+        },
+        {
+          "text": "B1",
+          "start": 18.38,
+          "end": 19.08,
+          "confidence": 0.836
+        },
+        {
+          "text": "and",
+          "start": 19.08,
+          "end": 20.16,
+          "confidence": 0.42
+        },
+        {
+          "text": "you",
+          "start": 20.16,
+          "end": 20.32,
+          "confidence": 0.865
+        },
+        {
+          "text": "can",
+          "start": 20.32,
+          "end": 20.48,
+          "confidence": 0.699
+        },
+        {
+          "text": "put",
+          "start": 20.48,
+          "end": 20.64,
+          "confidence": 0.971
+        },
+        {
+          "text": "the",
+          "start": 20.64,
+          "end": 20.84,
+          "confidence": 0.976
+        },
+        {
+          "text": "other",
+          "start": 20.84,
+          "end": 21.0,
+          "confidence": 0.995
+        },
+        {
+          "text": "one",
+          "start": 21.0,
+          "end": 21.18,
+          "confidence": 0.97
+        },
+        {
+          "text": "on",
+          "start": 21.18,
+          "end": 21.42,
+          "confidence": 0.988
+        },
+        {
+          "text": "the",
+          "start": 21.42,
+          "end": 21.94,
+          "confidence": 0.627
+        },
+        {
+          "text": "mic",
+          "start": 21.94,
+          "end": 22.48,
+          "confidence": 0.391
+        },
+        {
+          "text": "helmet",
+          "start": 22.48,
+          "end": 22.8,
+          "confidence": 0.935
+        },
+        {
+          "text": "with",
+          "start": 22.8,
+          "end": 23.06,
+          "confidence": 0.466
+        },
+        {
+          "text": "those",
+          "start": 23.06,
+          "end": 23.3,
+          "confidence": 0.358
+        },
+        {
+          "text": "GVA.",
+          "start": 23.3,
+          "end": 23.74,
+          "confidence": 0.363
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 0,
+      "start": 24.88,
+      "end": 25.12,
+      "text": " Over.",
+      "tokens": [
+        51614,
+        4886,
+        13,
+        51664
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.6685471307663691,
+      "compression_ratio": 1.3597883597883598,
+      "no_speech_prob": 0.44998496770858765,
+      "confidence": 0.29,
+      "words": [
+        {
+          "text": "Over.",
+          "start": 24.88,
+          "end": 25.12,
+          "confidence": 0.29
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 3000,
+      "start": 31.28,
+      "end": 32.12,
+      "text": " Alright, got them.",
+      "tokens": [
+        50414,
+        2798,
+        11,
+        658,
+        552,
+        13,
+        50464
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.7122965494791667,
+      "compression_ratio": 1.8131868131868132,
+      "no_speech_prob": 0.07163436710834503,
+      "confidence": 0.531,
+      "words": [
+        {
+          "text": "Alright,",
+          "start": 31.28,
+          "end": 31.56,
+          "confidence": 0.866
+        },
+        {
+          "text": "got",
+          "start": 31.82,
+          "end": 31.86,
+          "confidence": 0.43
+        },
+        {
+          "text": "them.",
+          "start": 31.86,
+          "end": 32.12,
+          "confidence": 0.402
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 3000,
+      "start": 32.74,
+      "end": 33.44,
+      "text": " Alright, got them.",
+      "tokens": [
+        50514,
+        2798,
+        11,
+        658,
+        552,
+        13,
+        50564
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.7122965494791667,
+      "compression_ratio": 1.8131868131868132,
+      "no_speech_prob": 0.07163436710834503,
+      "confidence": 0.879,
+      "words": [
+        {
+          "text": "Alright,",
+          "start": 32.74,
+          "end": 32.92,
+          "confidence": 0.74
+        },
+        {
+          "text": "got",
+          "start": 33.12,
+          "end": 33.18,
+          "confidence": 0.939
+        },
+        {
+          "text": "them.",
+          "start": 33.18,
+          "end": 33.44,
+          "confidence": 0.976
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 3000,
+      "start": 34.5,
+      "end": 35.3,
+      "text": " They're the better helmet that C1 has.",
+      "tokens": [
+        50614,
+        814,
+        434,
+        264,
+        1101,
+        15922,
+        300,
+        383,
+        16,
+        575,
+        13,
+        50664
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.7122965494791667,
+      "compression_ratio": 1.8131868131868132,
+      "no_speech_prob": 0.07163436710834503,
+      "confidence": 0.373,
+      "words": [
+        {
+          "text": "They're",
+          "start": 34.5,
+          "end": 34.52,
+          "confidence": 0.222
+        },
+        {
+          "text": "the",
+          "start": 34.52,
+          "end": 34.54,
+          "confidence": 0.185
+        },
+        {
+          "text": "better",
+          "start": 34.54,
+          "end": 34.56,
+          "confidence": 0.512
+        },
+        {
+          "text": "helmet",
+          "start": 34.56,
+          "end": 34.58,
+          "confidence": 0.699
+        },
+        {
+          "text": "that",
+          "start": 34.58,
+          "end": 34.6,
+          "confidence": 0.247
+        },
+        {
+          "text": "C1",
+          "start": 34.6,
+          "end": 34.92,
+          "confidence": 0.464
+        },
+        {
+          "text": "has.",
+          "start": 34.92,
+          "end": 35.3,
+          "confidence": 0.799
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 3000,
+      "start": 37.58,
+      "end": 39.34,
+      "text": " They got the one mic that makes going through the leak reshapes.",
+      "tokens": [
+        50714,
+        814,
+        658,
+        264,
+        472,
+        3123,
+        300,
+        1669,
+        516,
+        807,
+        264,
+        17143,
+        725,
+        71,
+        569,
+        279,
+        13,
+        50814
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.7122965494791667,
+      "compression_ratio": 1.8131868131868132,
+      "no_speech_prob": 0.07163436710834503,
+      "confidence": 0.362,
+      "words": [
+        {
+          "text": "They",
+          "start": 37.58,
+          "end": 37.8,
+          "confidence": 0.355
+        },
+        {
+          "text": "got",
+          "start": 37.8,
+          "end": 37.9,
+          "confidence": 0.372
+        },
+        {
+          "text": "the",
+          "start": 37.9,
+          "end": 37.92,
+          "confidence": 0.702
+        },
+        {
+          "text": "one",
+          "start": 37.92,
+          "end": 37.94,
+          "confidence": 0.721
+        },
+        {
+          "text": "mic",
+          "start": 37.94,
+          "end": 37.96,
+          "confidence": 0.632
+        },
+        {
+          "text": "that",
+          "start": 37.96,
+          "end": 37.98,
+          "confidence": 0.117
+        },
+        {
+          "text": "makes",
+          "start": 37.98,
+          "end": 38.0,
+          "confidence": 0.191
+        },
+        {
+          "text": "going",
+          "start": 38.0,
+          "end": 38.12,
+          "confidence": 0.749
+        },
+        {
+          "text": "through",
+          "start": 38.12,
+          "end": 38.34,
+          "confidence": 0.305
+        },
+        {
+          "text": "the",
+          "start": 38.34,
+          "end": 38.5,
+          "confidence": 0.397
+        },
+        {
+          "text": "leak",
+          "start": 38.5,
+          "end": 38.76,
+          "confidence": 0.41
+        },
+        {
+          "text": "reshapes.",
+          "start": 38.76,
+          "end": 39.34,
+          "confidence": 0.288
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 3000,
+      "start": 39.9,
+      "end": 41.94,
+      "text": " We got them in there helmet bags.",
+      "tokens": [
+        50864,
+        492,
+        658,
+        552,
+        294,
+        456,
+        15922,
+        10405,
+        13,
+        50964
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.7122965494791667,
+      "compression_ratio": 1.8131868131868132,
+      "no_speech_prob": 0.07163436710834503,
+      "confidence": 0.576,
+      "words": [
+        {
+          "text": "We",
+          "start": 39.9,
+          "end": 40.2,
+          "confidence": 0.487
+        },
+        {
+          "text": "got",
+          "start": 40.2,
+          "end": 40.48,
+          "confidence": 0.582
+        },
+        {
+          "text": "them",
+          "start": 40.48,
+          "end": 40.64,
+          "confidence": 0.881
+        },
+        {
+          "text": "in",
+          "start": 40.64,
+          "end": 40.74,
+          "confidence": 0.917
+        },
+        {
+          "text": "there",
+          "start": 40.74,
+          "end": 40.96,
+          "confidence": 0.418
+        },
+        {
+          "text": "helmet",
+          "start": 40.96,
+          "end": 41.52,
+          "confidence": 0.654
+        },
+        {
+          "text": "bags.",
+          "start": 41.52,
+          "end": 41.94,
+          "confidence": 0.336
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 3000,
+      "start": 43.02,
+      "end": 47.4,
+      "text": " And uh, we got the helmet in there helmet bags.",
+      "tokens": [
+        51014,
+        400,
+        2232,
+        11,
+        321,
+        658,
+        264,
+        15922,
+        294,
+        456,
+        15922,
+        10405,
+        13,
+        51264
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.7122965494791667,
+      "compression_ratio": 1.8131868131868132,
+      "no_speech_prob": 0.07163436710834503,
+      "confidence": 0.431,
+      "words": [
+        {
+          "text": "And",
+          "start": 43.02,
+          "end": 43.34,
+          "confidence": 0.575
+        },
+        {
+          "text": "uh,",
+          "start": 43.34,
+          "end": 43.74,
+          "confidence": 0.208
+        },
+        {
+          "text": "we",
+          "start": 43.86,
+          "end": 44.04,
+          "confidence": 0.423
+        },
+        {
+          "text": "got",
+          "start": 44.04,
+          "end": 44.2,
+          "confidence": 0.549
+        },
+        {
+          "text": "the",
+          "start": 44.2,
+          "end": 44.5,
+          "confidence": 0.209
+        },
+        {
+          "text": "helmet",
+          "start": 44.5,
+          "end": 46.46,
+          "confidence": 0.845
+        },
+        {
+          "text": "in",
+          "start": 46.46,
+          "end": 46.72,
+          "confidence": 0.188
+        },
+        {
+          "text": "there",
+          "start": 46.72,
+          "end": 47.06,
+          "confidence": 0.391
+        },
+        {
+          "text": "helmet",
+          "start": 47.06,
+          "end": 47.08,
+          "confidence": 0.69
+        },
+        {
+          "text": "bags.",
+          "start": 47.08,
+          "end": 47.4,
+          "confidence": 0.889
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 3000,
+      "start": 48.5,
+      "end": 49.58,
+      "text": " The leak system, the leak of the bag.",
+      "tokens": [
+        51314,
+        440,
+        17143,
+        1185,
+        11,
+        264,
+        17143,
+        295,
+        264,
+        3411,
+        13,
+        51364
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.7122965494791667,
+      "compression_ratio": 1.8131868131868132,
+      "no_speech_prob": 0.07163436710834503,
+      "confidence": 0.499,
+      "words": [
+        {
+          "text": "The",
+          "start": 48.5,
+          "end": 48.52,
+          "confidence": 0.266
+        },
+        {
+          "text": "leak",
+          "start": 48.52,
+          "end": 48.6,
+          "confidence": 0.299
+        },
+        {
+          "text": "system,",
+          "start": 48.6,
+          "end": 48.86,
+          "confidence": 0.54
+        },
+        {
+          "text": "the",
+          "start": 49.06,
+          "end": 49.14,
+          "confidence": 0.589
+        },
+        {
+          "text": "leak",
+          "start": 49.14,
+          "end": 49.22,
+          "confidence": 0.962
+        },
+        {
+          "text": "of",
+          "start": 49.22,
+          "end": 49.32,
+          "confidence": 0.244
+        },
+        {
+          "text": "the",
+          "start": 49.32,
+          "end": 49.4,
+          "confidence": 0.941
+        },
+        {
+          "text": "bag.",
+          "start": 49.4,
+          "end": 49.58,
+          "confidence": 0.689
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 3000,
+      "start": 51.34,
+      "end": 51.94,
+      "text": " Right, yeah.",
+      "tokens": [
+        51414,
+        1779,
+        11,
+        1338,
+        13,
+        51464
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.7122965494791667,
+      "compression_ratio": 1.8131868131868132,
+      "no_speech_prob": 0.07163436710834503,
+      "confidence": 0.369,
+      "words": [
+        {
+          "text": "Right,",
+          "start": 51.34,
+          "end": 51.72,
+          "confidence": 0.187
+        },
+        {
+          "text": "yeah.",
+          "start": 51.82,
+          "end": 51.94,
+          "confidence": 0.73
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 3000,
+      "start": 53.06,
+      "end": 55.22,
+      "text": " Yeah, we're taking the leak to the auto, see you later.",
+      "tokens": [
+        51514,
+        865,
+        11,
+        321,
+        434,
+        1940,
+        264,
+        17143,
+        281,
+        264,
+        8399,
+        11,
+        536,
+        291,
+        1780,
+        13,
+        51614
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.7122965494791667,
+      "compression_ratio": 1.8131868131868132,
+      "no_speech_prob": 0.07163436710834503,
+      "confidence": 0.425,
+      "words": [
+        {
+          "text": "Yeah,",
+          "start": 53.06,
+          "end": 53.26,
+          "confidence": 0.561
+        },
+        {
+          "text": "we're",
+          "start": 53.34,
+          "end": 53.42,
+          "confidence": 0.725
+        },
+        {
+          "text": "taking",
+          "start": 53.42,
+          "end": 53.62,
+          "confidence": 0.683
+        },
+        {
+          "text": "the",
+          "start": 53.62,
+          "end": 53.8,
+          "confidence": 0.661
+        },
+        {
+          "text": "leak",
+          "start": 53.8,
+          "end": 53.88,
+          "confidence": 0.396
+        },
+        {
+          "text": "to",
+          "start": 53.88,
+          "end": 54.02,
+          "confidence": 0.08
+        },
+        {
+          "text": "the",
+          "start": 54.02,
+          "end": 54.08,
+          "confidence": 0.935
+        },
+        {
+          "text": "auto,",
+          "start": 54.08,
+          "end": 54.26,
+          "confidence": 0.228
+        },
+        {
+          "text": "see",
+          "start": 54.46,
+          "end": 54.58,
+          "confidence": 0.191
+        },
+        {
+          "text": "you",
+          "start": 54.58,
+          "end": 55.14,
+          "confidence": 0.401
+        },
+        {
+          "text": "later.",
+          "start": 55.14,
+          "end": 55.22,
+          "confidence": 0.503
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 5500,
+      "start": 56.4,
+      "end": 61.48,
+      "text": " Hey, we were going to hang with the cover on the right side already.",
+      "tokens": [
+        50414,
+        1911,
+        11,
+        321,
+        645,
+        516,
+        281,
+        3967,
+        365,
+        264,
+        2060,
+        322,
+        264,
+        558,
+        1252,
+        1217,
+        13,
+        50664
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.4537031500189154,
+      "compression_ratio": 1.6168224299065421,
+      "no_speech_prob": 0.3397921025753021,
+      "confidence": 0.371,
+      "words": [
+        {
+          "text": "Hey,",
+          "start": 56.4,
+          "end": 56.6,
+          "confidence": 0.195
+        },
+        {
+          "text": "we",
+          "start": 56.62,
+          "end": 56.74,
+          "confidence": 0.949
+        },
+        {
+          "text": "were",
+          "start": 56.74,
+          "end": 56.9,
+          "confidence": 0.526
+        },
+        {
+          "text": "going",
+          "start": 56.9,
+          "end": 57.1,
+          "confidence": 0.184
+        },
+        {
+          "text": "to",
+          "start": 57.1,
+          "end": 57.22,
+          "confidence": 0.938
+        },
+        {
+          "text": "hang",
+          "start": 57.22,
+          "end": 57.38,
+          "confidence": 0.255
+        },
+        {
+          "text": "with",
+          "start": 57.38,
+          "end": 59.24,
+          "confidence": 0.252
+        },
+        {
+          "text": "the",
+          "start": 59.24,
+          "end": 60.24,
+          "confidence": 0.529
+        },
+        {
+          "text": "cover",
+          "start": 60.24,
+          "end": 61.02,
+          "confidence": 0.737
+        },
+        {
+          "text": "on",
+          "start": 61.02,
+          "end": 61.22,
+          "confidence": 0.324
+        },
+        {
+          "text": "the",
+          "start": 61.22,
+          "end": 61.28,
+          "confidence": 0.44
+        },
+        {
+          "text": "right",
+          "start": 61.28,
+          "end": 61.3,
+          "confidence": 0.088
+        },
+        {
+          "text": "side",
+          "start": 61.3,
+          "end": 61.4,
+          "confidence": 0.4
+        },
+        {
+          "text": "already.",
+          "start": 61.4,
+          "end": 61.48,
+          "confidence": 0.447
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 5500,
+      "start": 62.52,
+      "end": 63.02,
+      "text": " Okay, fine.",
+      "tokens": [
+        50714,
+        1033,
+        11,
+        2489,
+        13,
+        50764
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.4537031500189154,
+      "compression_ratio": 1.6168224299065421,
+      "no_speech_prob": 0.3397921025753021,
+      "confidence": 0.91,
+      "words": [
+        {
+          "text": "Okay,",
+          "start": 62.52,
+          "end": 62.78,
+          "confidence": 0.914
+        },
+        {
+          "text": "fine.",
+          "start": 62.88,
+          "end": 63.02,
+          "confidence": 0.905
+        }
+      ]
+    },
+    {
+      "id": 17,
+      "seek": 5500,
+      "start": 63.02,
+      "end": 65.1,
+      "text": " We weren't sure of that, just a suggestion.",
+      "tokens": [
+        50764,
+        492,
+        4999,
+        380,
+        988,
+        295,
+        300,
+        11,
+        445,
+        257,
+        16541,
+        13,
+        50864
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.4537031500189154,
+      "compression_ratio": 1.6168224299065421,
+      "no_speech_prob": 0.3397921025753021,
+      "confidence": 0.842,
+      "words": [
+        {
+          "text": "We",
+          "start": 63.02,
+          "end": 63.3,
+          "confidence": 0.937
+        },
+        {
+          "text": "weren't",
+          "start": 63.3,
+          "end": 63.56,
+          "confidence": 0.976
+        },
+        {
+          "text": "sure",
+          "start": 63.56,
+          "end": 63.72,
+          "confidence": 0.929
+        },
+        {
+          "text": "of",
+          "start": 63.72,
+          "end": 63.84,
+          "confidence": 0.502
+        },
+        {
+          "text": "that,",
+          "start": 63.84,
+          "end": 63.98,
+          "confidence": 0.986
+        },
+        {
+          "text": "just",
+          "start": 64.12,
+          "end": 64.56,
+          "confidence": 0.772
+        },
+        {
+          "text": "a",
+          "start": 64.56,
+          "end": 64.72,
+          "confidence": 0.675
+        },
+        {
+          "text": "suggestion.",
+          "start": 64.72,
+          "end": 65.1,
+          "confidence": 0.994
+        }
+      ]
+    },
+    {
+      "id": 18,
+      "seek": 5500,
+      "start": 65.2,
+      "end": 67.5,
+      "text": " We thought we'd, uh, you could check it out.",
+      "tokens": [
+        50864,
+        492,
+        1194,
+        321,
+        1116,
+        11,
+        2232,
+        11,
+        291,
+        727,
+        1520,
+        309,
+        484,
+        13,
+        50964
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.4537031500189154,
+      "compression_ratio": 1.6168224299065421,
+      "no_speech_prob": 0.3397921025753021,
+      "confidence": 0.754,
+      "words": [
+        {
+          "text": "We",
+          "start": 65.2,
+          "end": 65.4,
+          "confidence": 0.915
+        },
+        {
+          "text": "thought",
+          "start": 65.4,
+          "end": 65.54,
+          "confidence": 0.972
+        },
+        {
+          "text": "we'd,",
+          "start": 65.54,
+          "end": 65.9,
+          "confidence": 0.679
+        },
+        {
+          "text": "uh,",
+          "start": 65.96,
+          "end": 66.02,
+          "confidence": 0.597
+        },
+        {
+          "text": "you",
+          "start": 66.78,
+          "end": 67.04,
+          "confidence": 0.408
+        },
+        {
+          "text": "could",
+          "start": 67.04,
+          "end": 67.2,
+          "confidence": 0.808
+        },
+        {
+          "text": "check",
+          "start": 67.2,
+          "end": 67.36,
+          "confidence": 0.751
+        },
+        {
+          "text": "it",
+          "start": 67.36,
+          "end": 67.48,
+          "confidence": 0.984
+        },
+        {
+          "text": "out.",
+          "start": 67.48,
+          "end": 67.5,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 19,
+      "seek": 5500,
+      "start": 68.2,
+      "end": 72.4,
+      "text": " It's not much of a hard to turn on, so uh, I guess we're going to come up with just let us know.",
+      "tokens": [
+        51014,
+        467,
+        311,
+        406,
+        709,
+        295,
+        257,
+        1152,
+        281,
+        1261,
+        322,
+        11,
+        370,
+        2232,
+        11,
+        286,
+        2041,
+        321,
+        434,
+        516,
+        281,
+        808,
+        493,
+        365,
+        445,
+        718,
+        505,
+        458,
+        13,
+        51214
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.4537031500189154,
+      "compression_ratio": 1.6168224299065421,
+      "no_speech_prob": 0.3397921025753021,
+      "confidence": 0.608,
+      "words": [
+        {
+          "text": "It's",
+          "start": 68.2,
+          "end": 68.3,
+          "confidence": 0.411
+        },
+        {
+          "text": "not",
+          "start": 68.3,
+          "end": 68.4,
+          "confidence": 0.946
+        },
+        {
+          "text": "much",
+          "start": 68.4,
+          "end": 68.56,
+          "confidence": 0.902
+        },
+        {
+          "text": "of",
+          "start": 68.56,
+          "end": 68.7,
+          "confidence": 0.574
+        },
+        {
+          "text": "a",
+          "start": 68.7,
+          "end": 68.72,
+          "confidence": 0.719
+        },
+        {
+          "text": "hard",
+          "start": 68.72,
+          "end": 68.84,
+          "confidence": 0.144
+        },
+        {
+          "text": "to",
+          "start": 68.84,
+          "end": 68.98,
+          "confidence": 0.405
+        },
+        {
+          "text": "turn",
+          "start": 68.98,
+          "end": 69.1,
+          "confidence": 0.673
+        },
+        {
+          "text": "on,",
+          "start": 69.1,
+          "end": 69.22,
+          "confidence": 0.157
+        },
+        {
+          "text": "so",
+          "start": 69.26,
+          "end": 69.56,
+          "confidence": 0.845
+        },
+        {
+          "text": "uh,",
+          "start": 69.56,
+          "end": 69.84,
+          "confidence": 0.31
+        },
+        {
+          "text": "I",
+          "start": 70.34,
+          "end": 70.5,
+          "confidence": 0.786
+        },
+        {
+          "text": "guess",
+          "start": 70.5,
+          "end": 70.64,
+          "confidence": 0.993
+        },
+        {
+          "text": "we're",
+          "start": 70.64,
+          "end": 71.08,
+          "confidence": 0.562
+        },
+        {
+          "text": "going",
+          "start": 71.08,
+          "end": 71.2,
+          "confidence": 0.781
+        },
+        {
+          "text": "to",
+          "start": 71.2,
+          "end": 71.28,
+          "confidence": 0.991
+        },
+        {
+          "text": "come",
+          "start": 71.28,
+          "end": 71.42,
+          "confidence": 0.964
+        },
+        {
+          "text": "up",
+          "start": 71.42,
+          "end": 71.6,
+          "confidence": 0.952
+        },
+        {
+          "text": "with",
+          "start": 71.6,
+          "end": 71.76,
+          "confidence": 0.954
+        },
+        {
+          "text": "just",
+          "start": 71.76,
+          "end": 71.94,
+          "confidence": 0.316
+        },
+        {
+          "text": "let",
+          "start": 71.94,
+          "end": 72.1,
+          "confidence": 0.811
+        },
+        {
+          "text": "us",
+          "start": 72.1,
+          "end": 72.24,
+          "confidence": 0.977
+        },
+        {
+          "text": "know.",
+          "start": 72.24,
+          "end": 72.4,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 20,
+      "seek": 5500,
+      "start": 74.22,
+      "end": 75.03,
+      "text": " Okay, no problem.",
+      "tokens": [
+        51314,
+        1033,
+        11,
+        572,
+        1154,
+        13,
+        51364
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.4537031500189154,
+      "compression_ratio": 1.6168224299065421,
+      "no_speech_prob": 0.3397921025753021,
+      "confidence": 0.912,
+      "words": [
+        {
+          "text": "Okay,",
+          "start": 74.22,
+          "end": 74.48,
+          "confidence": 0.833
+        },
+        {
+          "text": "no",
+          "start": 74.62,
+          "end": 74.84,
+          "confidence": 0.935
+        },
+        {
+          "text": "problem.",
+          "start": 74.84,
+          "end": 75.03,
+          "confidence": 0.974
+        }
+      ]
+    },
+    {
+      "id": 21,
+      "seek": 5500,
+      "start": 75.03,
+      "end": 76.48,
+      "text": " Okay, no problem.",
+      "tokens": [
+        51364,
+        1033,
+        11,
+        572,
+        1154,
+        13,
+        51414
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.4537031500189154,
+      "compression_ratio": 1.6168224299065421,
+      "no_speech_prob": 0.3397921025753021,
+      "confidence": 0.839,
+      "words": [
+        {
+          "text": "Okay,",
+          "start": 75.03,
+          "end": 75.78,
+          "confidence": 0.629
+        },
+        {
+          "text": "no",
+          "start": 75.94,
+          "end": 76.14,
+          "confidence": 0.946
+        },
+        {
+          "text": "problem.",
+          "start": 76.14,
+          "end": 76.48,
+          "confidence": 0.991
+        }
+      ]
+    },
+    {
+      "id": 22,
+      "seek": 5500,
+      "start": 76.48,
+      "end": 78.22,
+      "text": " We'll let you know when the end of the sun.",
+      "tokens": [
+        51414,
+        492,
+        603,
+        718,
+        291,
+        458,
+        562,
+        264,
+        917,
+        295,
+        264,
+        3295,
+        13,
+        51514
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.4537031500189154,
+      "compression_ratio": 1.6168224299065421,
+      "no_speech_prob": 0.3397921025753021,
+      "confidence": 0.607,
+      "words": [
+        {
+          "text": "We'll",
+          "start": 76.48,
+          "end": 76.8,
+          "confidence": 0.667
+        },
+        {
+          "text": "let",
+          "start": 76.8,
+          "end": 76.92,
+          "confidence": 0.949
+        },
+        {
+          "text": "you",
+          "start": 76.92,
+          "end": 77.08,
+          "confidence": 0.544
+        },
+        {
+          "text": "know",
+          "start": 77.08,
+          "end": 77.18,
+          "confidence": 0.998
+        },
+        {
+          "text": "when",
+          "start": 77.18,
+          "end": 77.3,
+          "confidence": 0.533
+        },
+        {
+          "text": "the",
+          "start": 77.3,
+          "end": 77.4,
+          "confidence": 0.894
+        },
+        {
+          "text": "end",
+          "start": 77.4,
+          "end": 77.52,
+          "confidence": 0.97
+        },
+        {
+          "text": "of",
+          "start": 77.52,
+          "end": 77.64,
+          "confidence": 0.976
+        },
+        {
+          "text": "the",
+          "start": 77.64,
+          "end": 78.02,
+          "confidence": 0.527
+        },
+        {
+          "text": "sun.",
+          "start": 78.02,
+          "end": 78.22,
+          "confidence": 0.075
+        }
+      ]
+    },
+    {
+      "id": 23,
+      "seek": 8500,
+      "start": 85.22,
+      "end": 85.4,
+      "text": " Hello.",
+      "tokens": [
+        50364,
+        2425,
+        13,
+        50414
+      ],
+      "temperature": 0.2,
+      "avg_logprob": -0.6903002738952637,
+      "compression_ratio": 0.42857142857142855,
+      "no_speech_prob": 0.9557693600654602,
+      "confidence": 0.216,
+      "words": [
+        {
+          "text": "Hello.",
+          "start": 85.22,
+          "end": 85.4,
+          "confidence": 0.216
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/corner_cases/stucked_lm_apollo11.mp3.words.json b/tests/expected/corner_cases/stucked_lm_apollo11.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..ab5aefe27e14ec694737a5182311b067430f6cde
--- /dev/null
+++ b/tests/expected/corner_cases/stucked_lm_apollo11.mp3.words.json
@@ -0,0 +1,3820 @@
+{
+  "text": " Apollo 11, Houston we got a recommendation for you on your Soyuz-VA GLEME GVA. Alright, okay, we like to say that they make the one that's on the helmet we're going to have in B1. And you can put the other one on the mic helmet with those GVA blizzard frames. Alright, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.52,
+      "end": 6.54,
+      "text": " Apollo 11, Houston we got a recommendation for you on your Soyuz-VA GLEME GVA.",
+      "tokens": [
+        50364,
+        25187,
+        2975,
+        11,
+        18717,
+        321,
+        658,
+        257,
+        11879,
+        337,
+        291,
+        322,
+        428,
+        24758,
+        3334,
+        12,
+        20914,
+        460,
+        2634,
+        15454,
+        460,
+        20914,
+        13,
+        50714
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7225757398103413,
+      "compression_ratio": 1.39247311827957,
+      "no_speech_prob": 0.44998496770858765,
+      "confidence": 0.541,
+      "words": [
+        {
+          "text": "Apollo",
+          "start": 0.52,
+          "end": 0.88,
+          "confidence": 0.155
+        },
+        {
+          "text": "11,",
+          "start": 0.88,
+          "end": 1.26,
+          "confidence": 0.977
+        },
+        {
+          "text": "Houston",
+          "start": 1.52,
+          "end": 1.72,
+          "confidence": 0.986
+        },
+        {
+          "text": "we",
+          "start": 1.72,
+          "end": 1.94,
+          "confidence": 0.518
+        },
+        {
+          "text": "got",
+          "start": 1.94,
+          "end": 2.1,
+          "confidence": 0.823
+        },
+        {
+          "text": "a",
+          "start": 2.1,
+          "end": 2.26,
+          "confidence": 0.989
+        },
+        {
+          "text": "recommendation",
+          "start": 2.26,
+          "end": 2.86,
+          "confidence": 0.968
+        },
+        {
+          "text": "for",
+          "start": 2.86,
+          "end": 3.44,
+          "confidence": 0.946
+        },
+        {
+          "text": "you",
+          "start": 3.44,
+          "end": 3.6,
+          "confidence": 0.984
+        },
+        {
+          "text": "on",
+          "start": 3.6,
+          "end": 3.72,
+          "confidence": 0.909
+        },
+        {
+          "text": "your",
+          "start": 3.72,
+          "end": 3.92,
+          "confidence": 0.971
+        },
+        {
+          "text": "Soyuz-VA",
+          "start": 3.92,
+          "end": 5.16,
+          "confidence": 0.26
+        },
+        {
+          "text": "GLEME",
+          "start": 5.16,
+          "end": 5.74,
+          "confidence": 0.475
+        },
+        {
+          "text": "GVA.",
+          "start": 5.74,
+          "end": 6.54,
+          "confidence": 0.435
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 10.8,
+      "end": 19.06,
+      "text": " Alright, okay, we like to say that they make the one that's on the helmet we're going to have in B1.",
+      "tokens": [
+        50714,
+        2798,
+        11,
+        1392,
+        11,
+        321,
+        411,
+        281,
+        584,
+        300,
+        436,
+        652,
+        264,
+        472,
+        300,
+        311,
+        322,
+        264,
+        15922,
+        321,
+        434,
+        516,
+        281,
+        362,
+        294,
+        363,
+        16,
+        13,
+        51314
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7225757398103413,
+      "compression_ratio": 1.39247311827957,
+      "no_speech_prob": 0.44998496770858765,
+      "confidence": 0.468,
+      "words": [
+        {
+          "text": "Alright,",
+          "start": 10.8,
+          "end": 11.04,
+          "confidence": 0.31
+        },
+        {
+          "text": "okay,",
+          "start": 11.68,
+          "end": 12.22,
+          "confidence": 0.504
+        },
+        {
+          "text": "we",
+          "start": 12.52,
+          "end": 12.96,
+          "confidence": 0.609
+        },
+        {
+          "text": "like",
+          "start": 12.96,
+          "end": 13.28,
+          "confidence": 0.505
+        },
+        {
+          "text": "to",
+          "start": 13.28,
+          "end": 13.54,
+          "confidence": 0.263
+        },
+        {
+          "text": "say",
+          "start": 13.54,
+          "end": 14.9,
+          "confidence": 0.138
+        },
+        {
+          "text": "that",
+          "start": 14.9,
+          "end": 15.38,
+          "confidence": 0.199
+        },
+        {
+          "text": "they",
+          "start": 15.38,
+          "end": 15.44,
+          "confidence": 0.417
+        },
+        {
+          "text": "make",
+          "start": 15.44,
+          "end": 15.68,
+          "confidence": 0.402
+        },
+        {
+          "text": "the",
+          "start": 15.68,
+          "end": 15.84,
+          "confidence": 0.253
+        },
+        {
+          "text": "one",
+          "start": 15.84,
+          "end": 16.06,
+          "confidence": 0.609
+        },
+        {
+          "text": "that's",
+          "start": 16.06,
+          "end": 16.28,
+          "confidence": 0.442
+        },
+        {
+          "text": "on",
+          "start": 16.28,
+          "end": 16.48,
+          "confidence": 0.595
+        },
+        {
+          "text": "the",
+          "start": 16.48,
+          "end": 16.78,
+          "confidence": 0.872
+        },
+        {
+          "text": "helmet",
+          "start": 16.78,
+          "end": 17.26,
+          "confidence": 0.856
+        },
+        {
+          "text": "we're",
+          "start": 17.26,
+          "end": 17.76,
+          "confidence": 0.299
+        },
+        {
+          "text": "going",
+          "start": 17.76,
+          "end": 17.92,
+          "confidence": 0.598
+        },
+        {
+          "text": "to",
+          "start": 17.92,
+          "end": 18.06,
+          "confidence": 0.822
+        },
+        {
+          "text": "have",
+          "start": 18.06,
+          "end": 18.2,
+          "confidence": 0.835
+        },
+        {
+          "text": "in",
+          "start": 18.2,
+          "end": 18.36,
+          "confidence": 0.717
+        },
+        {
+          "text": "B1.",
+          "start": 18.36,
+          "end": 19.06,
+          "confidence": 0.764
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 19.36,
+      "end": 24.52,
+      "text": " And you can put the other one on the mic helmet with those GVA blizzard frames.",
+      "tokens": [
+        51314,
+        400,
+        291,
+        393,
+        829,
+        264,
+        661,
+        472,
+        322,
+        264,
+        3123,
+        15922,
+        365,
+        729,
+        460,
+        20914,
+        888,
+        31062,
+        12083,
+        13,
+        51614
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7225757398103413,
+      "compression_ratio": 1.39247311827957,
+      "no_speech_prob": 0.44998496770858765,
+      "confidence": 0.485,
+      "words": [
+        {
+          "text": "And",
+          "start": 19.36,
+          "end": 20.2,
+          "confidence": 0.668
+        },
+        {
+          "text": "you",
+          "start": 20.2,
+          "end": 20.32,
+          "confidence": 0.948
+        },
+        {
+          "text": "can",
+          "start": 20.32,
+          "end": 20.48,
+          "confidence": 0.725
+        },
+        {
+          "text": "put",
+          "start": 20.48,
+          "end": 20.64,
+          "confidence": 0.98
+        },
+        {
+          "text": "the",
+          "start": 20.64,
+          "end": 20.84,
+          "confidence": 0.989
+        },
+        {
+          "text": "other",
+          "start": 20.84,
+          "end": 21.0,
+          "confidence": 0.991
+        },
+        {
+          "text": "one",
+          "start": 21.0,
+          "end": 21.18,
+          "confidence": 0.978
+        },
+        {
+          "text": "on",
+          "start": 21.18,
+          "end": 21.4,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 21.4,
+          "end": 21.94,
+          "confidence": 0.522
+        },
+        {
+          "text": "mic",
+          "start": 21.94,
+          "end": 22.48,
+          "confidence": 0.414
+        },
+        {
+          "text": "helmet",
+          "start": 22.48,
+          "end": 22.8,
+          "confidence": 0.882
+        },
+        {
+          "text": "with",
+          "start": 22.8,
+          "end": 23.06,
+          "confidence": 0.423
+        },
+        {
+          "text": "those",
+          "start": 23.06,
+          "end": 23.3,
+          "confidence": 0.466
+        },
+        {
+          "text": "GVA",
+          "start": 23.3,
+          "end": 23.74,
+          "confidence": 0.214
+        },
+        {
+          "text": "blizzard",
+          "start": 23.74,
+          "end": 24.18,
+          "confidence": 0.108
+        },
+        {
+          "text": "frames.",
+          "start": 24.18,
+          "end": 24.52,
+          "confidence": 0.255
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 2500,
+      "start": 31.34,
+      "end": 54.98,
+      "text": " Alright, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them",
+      "tokens": [
+        50364,
+        2798,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.11148937649197048,
+      "compression_ratio": 24.096774193548388,
+      "no_speech_prob": 0.4302051365375519,
+      "confidence": 0.93,
+      "words": [
+        {
+          "text": "Alright,",
+          "start": 31.34,
+          "end": 31.52,
+          "confidence": 0.066
+        },
+        {
+          "text": "got",
+          "start": 31.82,
+          "end": 31.84,
+          "confidence": 0.335
+        },
+        {
+          "text": "them,",
+          "start": 31.84,
+          "end": 32.12,
+          "confidence": 0.274
+        },
+        {
+          "text": "got",
+          "start": 32.38,
+          "end": 32.9,
+          "confidence": 0.568
+        },
+        {
+          "text": "them,",
+          "start": 32.9,
+          "end": 33.46,
+          "confidence": 0.941
+        },
+        {
+          "text": "got",
+          "start": 33.74,
+          "end": 33.76,
+          "confidence": 0.581
+        },
+        {
+          "text": "them,",
+          "start": 33.76,
+          "end": 33.78,
+          "confidence": 0.925
+        },
+        {
+          "text": "got",
+          "start": 33.78,
+          "end": 33.8,
+          "confidence": 0.523
+        },
+        {
+          "text": "them,",
+          "start": 33.8,
+          "end": 33.9,
+          "confidence": 0.906
+        },
+        {
+          "text": "got",
+          "start": 34.12,
+          "end": 34.14,
+          "confidence": 0.635
+        },
+        {
+          "text": "them,",
+          "start": 34.14,
+          "end": 34.5,
+          "confidence": 0.92
+        },
+        {
+          "text": "got",
+          "start": 34.5,
+          "end": 34.6,
+          "confidence": 0.688
+        },
+        {
+          "text": "them,",
+          "start": 34.6,
+          "end": 34.62,
+          "confidence": 0.946
+        },
+        {
+          "text": "got",
+          "start": 34.62,
+          "end": 34.64,
+          "confidence": 0.771
+        },
+        {
+          "text": "them,",
+          "start": 34.64,
+          "end": 34.66,
+          "confidence": 0.967
+        },
+        {
+          "text": "got",
+          "start": 34.66,
+          "end": 34.68,
+          "confidence": 0.856
+        },
+        {
+          "text": "them,",
+          "start": 34.68,
+          "end": 34.7,
+          "confidence": 0.975
+        },
+        {
+          "text": "got",
+          "start": 34.82,
+          "end": 34.92,
+          "confidence": 0.868
+        },
+        {
+          "text": "them,",
+          "start": 34.92,
+          "end": 34.94,
+          "confidence": 0.981
+        },
+        {
+          "text": "got",
+          "start": 34.94,
+          "end": 34.96,
+          "confidence": 0.909
+        },
+        {
+          "text": "them,",
+          "start": 34.96,
+          "end": 35.1,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 35.1,
+          "end": 35.28,
+          "confidence": 0.931
+        },
+        {
+          "text": "them,",
+          "start": 35.28,
+          "end": 35.62,
+          "confidence": 0.988
+        },
+        {
+          "text": "got",
+          "start": 35.74,
+          "end": 35.76,
+          "confidence": 0.945
+        },
+        {
+          "text": "them,",
+          "start": 35.76,
+          "end": 35.78,
+          "confidence": 0.988
+        },
+        {
+          "text": "got",
+          "start": 36.0,
+          "end": 36.02,
+          "confidence": 0.948
+        },
+        {
+          "text": "them,",
+          "start": 36.02,
+          "end": 36.04,
+          "confidence": 0.988
+        },
+        {
+          "text": "got",
+          "start": 36.04,
+          "end": 36.06,
+          "confidence": 0.947
+        },
+        {
+          "text": "them,",
+          "start": 36.06,
+          "end": 36.08,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 36.08,
+          "end": 36.1,
+          "confidence": 0.948
+        },
+        {
+          "text": "them,",
+          "start": 36.1,
+          "end": 36.12,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 36.12,
+          "end": 36.14,
+          "confidence": 0.949
+        },
+        {
+          "text": "them,",
+          "start": 36.14,
+          "end": 36.16,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 36.16,
+          "end": 36.34,
+          "confidence": 0.95
+        },
+        {
+          "text": "them,",
+          "start": 36.34,
+          "end": 36.74,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 36.74,
+          "end": 37.46,
+          "confidence": 0.952
+        },
+        {
+          "text": "them,",
+          "start": 37.46,
+          "end": 37.82,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 37.82,
+          "end": 37.84,
+          "confidence": 0.953
+        },
+        {
+          "text": "them,",
+          "start": 37.84,
+          "end": 38.12,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 38.12,
+          "end": 38.14,
+          "confidence": 0.955
+        },
+        {
+          "text": "them,",
+          "start": 38.14,
+          "end": 38.5,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 38.5,
+          "end": 38.52,
+          "confidence": 0.957
+        },
+        {
+          "text": "them,",
+          "start": 38.52,
+          "end": 38.54,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 38.54,
+          "end": 38.56,
+          "confidence": 0.958
+        },
+        {
+          "text": "them,",
+          "start": 38.56,
+          "end": 38.58,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 38.58,
+          "end": 38.6,
+          "confidence": 0.96
+        },
+        {
+          "text": "them,",
+          "start": 38.6,
+          "end": 38.62,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 38.62,
+          "end": 38.64,
+          "confidence": 0.961
+        },
+        {
+          "text": "them,",
+          "start": 38.64,
+          "end": 38.66,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 38.66,
+          "end": 38.68,
+          "confidence": 0.962
+        },
+        {
+          "text": "them,",
+          "start": 38.68,
+          "end": 38.7,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 38.7,
+          "end": 38.72,
+          "confidence": 0.963
+        },
+        {
+          "text": "them,",
+          "start": 38.72,
+          "end": 38.74,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 38.74,
+          "end": 38.76,
+          "confidence": 0.963
+        },
+        {
+          "text": "them,",
+          "start": 38.76,
+          "end": 38.78,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 38.78,
+          "end": 38.8,
+          "confidence": 0.963
+        },
+        {
+          "text": "them,",
+          "start": 38.8,
+          "end": 38.82,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 38.82,
+          "end": 38.84,
+          "confidence": 0.964
+        },
+        {
+          "text": "them,",
+          "start": 38.84,
+          "end": 38.86,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 38.86,
+          "end": 38.88,
+          "confidence": 0.964
+        },
+        {
+          "text": "them,",
+          "start": 38.88,
+          "end": 38.9,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 38.9,
+          "end": 38.92,
+          "confidence": 0.965
+        },
+        {
+          "text": "them,",
+          "start": 38.92,
+          "end": 38.94,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 38.94,
+          "end": 38.96,
+          "confidence": 0.965
+        },
+        {
+          "text": "them,",
+          "start": 38.96,
+          "end": 38.98,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 38.98,
+          "end": 39.0,
+          "confidence": 0.967
+        },
+        {
+          "text": "them,",
+          "start": 39.0,
+          "end": 39.02,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 39.02,
+          "end": 39.04,
+          "confidence": 0.968
+        },
+        {
+          "text": "them,",
+          "start": 39.04,
+          "end": 39.06,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 39.06,
+          "end": 39.08,
+          "confidence": 0.97
+        },
+        {
+          "text": "them,",
+          "start": 39.08,
+          "end": 39.1,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 39.1,
+          "end": 39.12,
+          "confidence": 0.97
+        },
+        {
+          "text": "them,",
+          "start": 39.12,
+          "end": 39.14,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 39.14,
+          "end": 39.16,
+          "confidence": 0.972
+        },
+        {
+          "text": "them,",
+          "start": 39.16,
+          "end": 39.18,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 39.18,
+          "end": 39.2,
+          "confidence": 0.972
+        },
+        {
+          "text": "them,",
+          "start": 39.2,
+          "end": 39.22,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 39.22,
+          "end": 39.24,
+          "confidence": 0.974
+        },
+        {
+          "text": "them,",
+          "start": 39.24,
+          "end": 39.26,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 39.26,
+          "end": 39.28,
+          "confidence": 0.976
+        },
+        {
+          "text": "them,",
+          "start": 39.28,
+          "end": 39.3,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 39.3,
+          "end": 39.32,
+          "confidence": 0.977
+        },
+        {
+          "text": "them,",
+          "start": 39.32,
+          "end": 39.34,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 39.34,
+          "end": 39.36,
+          "confidence": 0.978
+        },
+        {
+          "text": "them,",
+          "start": 39.36,
+          "end": 39.38,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.38,
+          "end": 39.4,
+          "confidence": 0.981
+        },
+        {
+          "text": "them,",
+          "start": 39.4,
+          "end": 39.42,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.42,
+          "end": 39.44,
+          "confidence": 0.982
+        },
+        {
+          "text": "them,",
+          "start": 39.44,
+          "end": 39.46,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.46,
+          "end": 39.48,
+          "confidence": 0.983
+        },
+        {
+          "text": "them,",
+          "start": 39.48,
+          "end": 39.5,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.5,
+          "end": 39.52,
+          "confidence": 0.984
+        },
+        {
+          "text": "them,",
+          "start": 39.52,
+          "end": 39.54,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.54,
+          "end": 39.56,
+          "confidence": 0.985
+        },
+        {
+          "text": "them,",
+          "start": 39.56,
+          "end": 39.58,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.58,
+          "end": 39.6,
+          "confidence": 0.986
+        },
+        {
+          "text": "them,",
+          "start": 39.6,
+          "end": 39.62,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.62,
+          "end": 39.64,
+          "confidence": 0.984
+        },
+        {
+          "text": "them,",
+          "start": 39.64,
+          "end": 39.66,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.66,
+          "end": 39.68,
+          "confidence": 0.986
+        },
+        {
+          "text": "them,",
+          "start": 39.68,
+          "end": 39.7,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.7,
+          "end": 39.72,
+          "confidence": 0.987
+        },
+        {
+          "text": "them,",
+          "start": 39.72,
+          "end": 39.74,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.74,
+          "end": 39.76,
+          "confidence": 0.988
+        },
+        {
+          "text": "them,",
+          "start": 39.76,
+          "end": 39.78,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.78,
+          "end": 39.8,
+          "confidence": 0.989
+        },
+        {
+          "text": "them,",
+          "start": 39.8,
+          "end": 39.82,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.82,
+          "end": 39.84,
+          "confidence": 0.989
+        },
+        {
+          "text": "them,",
+          "start": 39.84,
+          "end": 39.86,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.86,
+          "end": 39.88,
+          "confidence": 0.99
+        },
+        {
+          "text": "them,",
+          "start": 39.88,
+          "end": 39.9,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.9,
+          "end": 39.92,
+          "confidence": 0.99
+        },
+        {
+          "text": "them,",
+          "start": 39.92,
+          "end": 39.94,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.94,
+          "end": 39.96,
+          "confidence": 0.991
+        },
+        {
+          "text": "them,",
+          "start": 39.96,
+          "end": 39.98,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 39.98,
+          "end": 40.0,
+          "confidence": 0.991
+        },
+        {
+          "text": "them,",
+          "start": 40.0,
+          "end": 40.02,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 40.02,
+          "end": 40.04,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 40.04,
+          "end": 40.06,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 40.06,
+          "end": 40.08,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 40.08,
+          "end": 40.1,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 40.1,
+          "end": 40.12,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 40.12,
+          "end": 40.14,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 40.14,
+          "end": 40.16,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 40.16,
+          "end": 40.18,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 40.18,
+          "end": 40.2,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 40.2,
+          "end": 40.22,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 40.22,
+          "end": 40.46,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 40.46,
+          "end": 40.76,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 41.02,
+          "end": 41.04,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 41.04,
+          "end": 41.72,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 41.9,
+          "end": 41.92,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 41.92,
+          "end": 43.0,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 43.0,
+          "end": 44.06,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 44.06,
+          "end": 44.88,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 44.94,
+          "end": 45.46,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 45.46,
+          "end": 45.76,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 45.76,
+          "end": 47.06,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 47.06,
+          "end": 47.76,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 47.82,
+          "end": 48.5,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 48.5,
+          "end": 48.9,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 48.9,
+          "end": 49.2,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 49.2,
+          "end": 50.8,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 51.18,
+          "end": 51.74,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 51.74,
+          "end": 52.38,
+          "confidence": 0.997
+        },
+        {
+          "text": "got",
+          "start": 52.44,
+          "end": 53.26,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 53.26,
+          "end": 53.74,
+          "confidence": 0.997
+        },
+        {
+          "text": "got",
+          "start": 53.76,
+          "end": 54.2,
+          "confidence": 0.995
+        },
+        {
+          "text": "them",
+          "start": 54.2,
+          "end": 54.98,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 5500,
+      "start": 55.0,
+      "end": 85.0,
+      "text": " got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them",
+      "tokens": [
+        50364,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.05314932168866487,
+      "compression_ratio": 29.52,
+      "no_speech_prob": 0.2454655021429062,
+      "confidence": 0.948,
+      "words": [
+        {
+          "text": "got",
+          "start": 55.0,
+          "end": 55.1,
+          "confidence": 0.213
+        },
+        {
+          "text": "them,",
+          "start": 55.1,
+          "end": 55.12,
+          "confidence": 0.95
+        },
+        {
+          "text": "got",
+          "start": 55.16,
+          "end": 55.18,
+          "confidence": 0.955
+        },
+        {
+          "text": "them,",
+          "start": 55.18,
+          "end": 55.5,
+          "confidence": 0.997
+        },
+        {
+          "text": "got",
+          "start": 55.56,
+          "end": 57.36,
+          "confidence": 0.963
+        },
+        {
+          "text": "them,",
+          "start": 57.36,
+          "end": 57.52,
+          "confidence": 0.997
+        },
+        {
+          "text": "got",
+          "start": 57.58,
+          "end": 57.68,
+          "confidence": 0.957
+        },
+        {
+          "text": "them,",
+          "start": 57.68,
+          "end": 57.7,
+          "confidence": 0.997
+        },
+        {
+          "text": "got",
+          "start": 57.7,
+          "end": 57.72,
+          "confidence": 0.938
+        },
+        {
+          "text": "them,",
+          "start": 57.72,
+          "end": 57.74,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 57.74,
+          "end": 57.76,
+          "confidence": 0.912
+        },
+        {
+          "text": "them,",
+          "start": 57.76,
+          "end": 57.78,
+          "confidence": 0.988
+        },
+        {
+          "text": "got",
+          "start": 57.78,
+          "end": 57.8,
+          "confidence": 0.872
+        },
+        {
+          "text": "them,",
+          "start": 57.8,
+          "end": 57.82,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 57.82,
+          "end": 57.84,
+          "confidence": 0.862
+        },
+        {
+          "text": "them,",
+          "start": 57.84,
+          "end": 57.86,
+          "confidence": 0.984
+        },
+        {
+          "text": "got",
+          "start": 57.86,
+          "end": 57.88,
+          "confidence": 0.888
+        },
+        {
+          "text": "them,",
+          "start": 57.88,
+          "end": 57.9,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 57.9,
+          "end": 58.98,
+          "confidence": 0.85
+        },
+        {
+          "text": "them,",
+          "start": 58.98,
+          "end": 59.22,
+          "confidence": 0.924
+        },
+        {
+          "text": "got",
+          "start": 60.5,
+          "end": 61.26,
+          "confidence": 0.56
+        },
+        {
+          "text": "them,",
+          "start": 61.26,
+          "end": 61.94,
+          "confidence": 0.958
+        },
+        {
+          "text": "got",
+          "start": 61.94,
+          "end": 61.96,
+          "confidence": 0.81
+        },
+        {
+          "text": "them,",
+          "start": 61.96,
+          "end": 61.98,
+          "confidence": 0.976
+        },
+        {
+          "text": "got",
+          "start": 61.98,
+          "end": 62.0,
+          "confidence": 0.842
+        },
+        {
+          "text": "them,",
+          "start": 62.0,
+          "end": 62.02,
+          "confidence": 0.977
+        },
+        {
+          "text": "got",
+          "start": 62.02,
+          "end": 62.04,
+          "confidence": 0.835
+        },
+        {
+          "text": "them,",
+          "start": 62.04,
+          "end": 62.06,
+          "confidence": 0.977
+        },
+        {
+          "text": "got",
+          "start": 62.06,
+          "end": 62.08,
+          "confidence": 0.835
+        },
+        {
+          "text": "them,",
+          "start": 62.08,
+          "end": 62.1,
+          "confidence": 0.979
+        },
+        {
+          "text": "got",
+          "start": 62.1,
+          "end": 62.12,
+          "confidence": 0.853
+        },
+        {
+          "text": "them,",
+          "start": 62.12,
+          "end": 62.14,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 62.14,
+          "end": 62.16,
+          "confidence": 0.875
+        },
+        {
+          "text": "them,",
+          "start": 62.16,
+          "end": 62.18,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 62.18,
+          "end": 62.2,
+          "confidence": 0.892
+        },
+        {
+          "text": "them,",
+          "start": 62.2,
+          "end": 62.22,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 62.22,
+          "end": 62.24,
+          "confidence": 0.884
+        },
+        {
+          "text": "them,",
+          "start": 62.24,
+          "end": 62.26,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 62.26,
+          "end": 62.28,
+          "confidence": 0.877
+        },
+        {
+          "text": "them,",
+          "start": 62.28,
+          "end": 62.3,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 62.3,
+          "end": 62.32,
+          "confidence": 0.874
+        },
+        {
+          "text": "them,",
+          "start": 62.32,
+          "end": 62.34,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 62.34,
+          "end": 62.36,
+          "confidence": 0.871
+        },
+        {
+          "text": "them,",
+          "start": 62.36,
+          "end": 62.38,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 62.38,
+          "end": 62.4,
+          "confidence": 0.88
+        },
+        {
+          "text": "them,",
+          "start": 62.4,
+          "end": 62.42,
+          "confidence": 0.988
+        },
+        {
+          "text": "got",
+          "start": 62.44,
+          "end": 62.46,
+          "confidence": 0.883
+        },
+        {
+          "text": "them,",
+          "start": 62.46,
+          "end": 62.48,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 62.54,
+          "end": 62.78,
+          "confidence": 0.889
+        },
+        {
+          "text": "them,",
+          "start": 62.78,
+          "end": 62.8,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 62.8,
+          "end": 62.82,
+          "confidence": 0.894
+        },
+        {
+          "text": "them,",
+          "start": 62.82,
+          "end": 62.84,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 62.84,
+          "end": 62.86,
+          "confidence": 0.902
+        },
+        {
+          "text": "them,",
+          "start": 62.86,
+          "end": 62.88,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 62.88,
+          "end": 62.9,
+          "confidence": 0.904
+        },
+        {
+          "text": "them,",
+          "start": 62.9,
+          "end": 62.92,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 62.92,
+          "end": 62.94,
+          "confidence": 0.91
+        },
+        {
+          "text": "them,",
+          "start": 62.94,
+          "end": 62.96,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 62.96,
+          "end": 62.98,
+          "confidence": 0.916
+        },
+        {
+          "text": "them,",
+          "start": 62.98,
+          "end": 63.0,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 63.0,
+          "end": 63.02,
+          "confidence": 0.918
+        },
+        {
+          "text": "them,",
+          "start": 63.02,
+          "end": 63.04,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 63.04,
+          "end": 63.06,
+          "confidence": 0.923
+        },
+        {
+          "text": "them,",
+          "start": 63.06,
+          "end": 63.08,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 63.08,
+          "end": 63.1,
+          "confidence": 0.93
+        },
+        {
+          "text": "them,",
+          "start": 63.1,
+          "end": 63.12,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 63.12,
+          "end": 63.14,
+          "confidence": 0.932
+        },
+        {
+          "text": "them,",
+          "start": 63.14,
+          "end": 63.16,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 63.16,
+          "end": 63.18,
+          "confidence": 0.938
+        },
+        {
+          "text": "them,",
+          "start": 63.18,
+          "end": 63.2,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 63.2,
+          "end": 63.22,
+          "confidence": 0.943
+        },
+        {
+          "text": "them,",
+          "start": 63.22,
+          "end": 63.24,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 63.24,
+          "end": 63.26,
+          "confidence": 0.945
+        },
+        {
+          "text": "them,",
+          "start": 63.26,
+          "end": 63.28,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 63.28,
+          "end": 63.3,
+          "confidence": 0.949
+        },
+        {
+          "text": "them,",
+          "start": 63.3,
+          "end": 63.32,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 63.32,
+          "end": 63.34,
+          "confidence": 0.954
+        },
+        {
+          "text": "them,",
+          "start": 63.34,
+          "end": 63.36,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 63.36,
+          "end": 63.38,
+          "confidence": 0.954
+        },
+        {
+          "text": "them,",
+          "start": 63.38,
+          "end": 63.4,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 63.4,
+          "end": 63.46,
+          "confidence": 0.956
+        },
+        {
+          "text": "them,",
+          "start": 63.46,
+          "end": 63.64,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 63.64,
+          "end": 63.68,
+          "confidence": 0.96
+        },
+        {
+          "text": "them,",
+          "start": 63.68,
+          "end": 63.7,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 63.7,
+          "end": 63.72,
+          "confidence": 0.961
+        },
+        {
+          "text": "them,",
+          "start": 63.72,
+          "end": 63.74,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 63.74,
+          "end": 63.76,
+          "confidence": 0.96
+        },
+        {
+          "text": "them,",
+          "start": 63.76,
+          "end": 63.78,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 63.78,
+          "end": 63.8,
+          "confidence": 0.963
+        },
+        {
+          "text": "them,",
+          "start": 63.8,
+          "end": 63.82,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 63.82,
+          "end": 63.84,
+          "confidence": 0.964
+        },
+        {
+          "text": "them,",
+          "start": 63.84,
+          "end": 64.42,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 64.46,
+          "end": 64.58,
+          "confidence": 0.967
+        },
+        {
+          "text": "them,",
+          "start": 64.58,
+          "end": 64.64,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 64.72,
+          "end": 65.06,
+          "confidence": 0.967
+        },
+        {
+          "text": "them,",
+          "start": 65.06,
+          "end": 65.22,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 65.22,
+          "end": 66.0,
+          "confidence": 0.968
+        },
+        {
+          "text": "them,",
+          "start": 66.0,
+          "end": 66.2,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 66.38,
+          "end": 67.34,
+          "confidence": 0.97
+        },
+        {
+          "text": "them,",
+          "start": 67.34,
+          "end": 67.44,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 67.48,
+          "end": 67.5,
+          "confidence": 0.97
+        },
+        {
+          "text": "them,",
+          "start": 67.5,
+          "end": 67.52,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 67.52,
+          "end": 67.54,
+          "confidence": 0.972
+        },
+        {
+          "text": "them,",
+          "start": 67.54,
+          "end": 67.56,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 67.56,
+          "end": 67.58,
+          "confidence": 0.973
+        },
+        {
+          "text": "them,",
+          "start": 67.58,
+          "end": 67.6,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 67.6,
+          "end": 67.62,
+          "confidence": 0.973
+        },
+        {
+          "text": "them,",
+          "start": 67.62,
+          "end": 67.64,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 67.68,
+          "end": 67.7,
+          "confidence": 0.973
+        },
+        {
+          "text": "them,",
+          "start": 67.7,
+          "end": 67.72,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 67.72,
+          "end": 67.74,
+          "confidence": 0.974
+        },
+        {
+          "text": "them,",
+          "start": 67.74,
+          "end": 67.86,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 68.12,
+          "end": 68.36,
+          "confidence": 0.974
+        },
+        {
+          "text": "them,",
+          "start": 68.36,
+          "end": 68.38,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 68.56,
+          "end": 68.58,
+          "confidence": 0.974
+        },
+        {
+          "text": "them,",
+          "start": 68.58,
+          "end": 68.6,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 68.6,
+          "end": 68.8,
+          "confidence": 0.975
+        },
+        {
+          "text": "them,",
+          "start": 68.8,
+          "end": 69.12,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 69.26,
+          "end": 69.28,
+          "confidence": 0.975
+        },
+        {
+          "text": "them,",
+          "start": 69.28,
+          "end": 69.44,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 69.84,
+          "end": 69.86,
+          "confidence": 0.975
+        },
+        {
+          "text": "them,",
+          "start": 69.86,
+          "end": 70.02,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 70.2,
+          "end": 70.5,
+          "confidence": 0.976
+        },
+        {
+          "text": "them,",
+          "start": 70.5,
+          "end": 71.42,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 71.56,
+          "end": 71.58,
+          "confidence": 0.977
+        },
+        {
+          "text": "them,",
+          "start": 71.58,
+          "end": 71.94,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 71.94,
+          "end": 72.1,
+          "confidence": 0.977
+        },
+        {
+          "text": "them,",
+          "start": 72.1,
+          "end": 72.82,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 72.82,
+          "end": 74.48,
+          "confidence": 0.978
+        },
+        {
+          "text": "them,",
+          "start": 74.48,
+          "end": 74.66,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 74.74,
+          "end": 74.88,
+          "confidence": 0.978
+        },
+        {
+          "text": "them,",
+          "start": 74.88,
+          "end": 74.9,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 74.92,
+          "end": 74.94,
+          "confidence": 0.978
+        },
+        {
+          "text": "them,",
+          "start": 74.94,
+          "end": 74.96,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 75.12,
+          "end": 75.14,
+          "confidence": 0.978
+        },
+        {
+          "text": "them,",
+          "start": 75.14,
+          "end": 75.24,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 75.24,
+          "end": 75.78,
+          "confidence": 0.98
+        },
+        {
+          "text": "them,",
+          "start": 75.78,
+          "end": 76.02,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 76.02,
+          "end": 76.4,
+          "confidence": 0.981
+        },
+        {
+          "text": "them,",
+          "start": 76.4,
+          "end": 76.6,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 76.6,
+          "end": 76.82,
+          "confidence": 0.98
+        },
+        {
+          "text": "them,",
+          "start": 76.82,
+          "end": 77.76,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 78.22,
+          "end": 78.24,
+          "confidence": 0.98
+        },
+        {
+          "text": "them,",
+          "start": 78.24,
+          "end": 78.42,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 80.0,
+          "end": 80.02,
+          "confidence": 0.98
+        },
+        {
+          "text": "them,",
+          "start": 80.02,
+          "end": 82.6,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 82.6,
+          "end": 84.98,
+          "confidence": 0.98
+        },
+        {
+          "text": "them",
+          "start": 84.98,
+          "end": 85.0,
+          "confidence": 0.994
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 8500,
+      "start": 85.0,
+      "end": 115.0,
+      "text": " got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them",
+      "tokens": [
+        50364,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.042715128227199674,
+      "compression_ratio": 29.52,
+      "no_speech_prob": 0.6358686685562134,
+      "confidence": 0.953,
+      "words": [
+        {
+          "text": "got",
+          "start": 85.0,
+          "end": 85.4,
+          "confidence": 0.455
+        },
+        {
+          "text": "them,",
+          "start": 85.4,
+          "end": 85.58,
+          "confidence": 0.951
+        },
+        {
+          "text": "got",
+          "start": 86.12,
+          "end": 86.72,
+          "confidence": 0.965
+        },
+        {
+          "text": "them,",
+          "start": 86.72,
+          "end": 87.12,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 87.24,
+          "end": 87.56,
+          "confidence": 0.964
+        },
+        {
+          "text": "them,",
+          "start": 87.56,
+          "end": 87.94,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 88.08,
+          "end": 88.48,
+          "confidence": 0.955
+        },
+        {
+          "text": "them,",
+          "start": 88.48,
+          "end": 88.5,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 88.5,
+          "end": 88.9,
+          "confidence": 0.94
+        },
+        {
+          "text": "them,",
+          "start": 88.9,
+          "end": 89.02,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 89.06,
+          "end": 89.08,
+          "confidence": 0.92
+        },
+        {
+          "text": "them,",
+          "start": 89.08,
+          "end": 89.1,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 89.1,
+          "end": 89.12,
+          "confidence": 0.908
+        },
+        {
+          "text": "them,",
+          "start": 89.12,
+          "end": 89.14,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 89.58,
+          "end": 89.6,
+          "confidence": 0.907
+        },
+        {
+          "text": "them,",
+          "start": 89.6,
+          "end": 89.62,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 90.06,
+          "end": 90.08,
+          "confidence": 0.915
+        },
+        {
+          "text": "them,",
+          "start": 90.08,
+          "end": 90.1,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 90.68,
+          "end": 90.7,
+          "confidence": 0.91
+        },
+        {
+          "text": "them,",
+          "start": 90.7,
+          "end": 90.72,
+          "confidence": 0.972
+        },
+        {
+          "text": "got",
+          "start": 91.88,
+          "end": 91.9,
+          "confidence": 0.856
+        },
+        {
+          "text": "them,",
+          "start": 91.9,
+          "end": 91.92,
+          "confidence": 0.965
+        },
+        {
+          "text": "got",
+          "start": 91.92,
+          "end": 91.94,
+          "confidence": 0.831
+        },
+        {
+          "text": "them,",
+          "start": 91.94,
+          "end": 91.96,
+          "confidence": 0.968
+        },
+        {
+          "text": "got",
+          "start": 91.96,
+          "end": 91.98,
+          "confidence": 0.855
+        },
+        {
+          "text": "them,",
+          "start": 91.98,
+          "end": 92.0,
+          "confidence": 0.97
+        },
+        {
+          "text": "got",
+          "start": 92.0,
+          "end": 92.02,
+          "confidence": 0.879
+        },
+        {
+          "text": "them,",
+          "start": 92.02,
+          "end": 92.04,
+          "confidence": 0.97
+        },
+        {
+          "text": "got",
+          "start": 92.04,
+          "end": 92.06,
+          "confidence": 0.889
+        },
+        {
+          "text": "them,",
+          "start": 92.06,
+          "end": 92.08,
+          "confidence": 0.97
+        },
+        {
+          "text": "got",
+          "start": 92.08,
+          "end": 92.1,
+          "confidence": 0.892
+        },
+        {
+          "text": "them,",
+          "start": 92.1,
+          "end": 92.12,
+          "confidence": 0.97
+        },
+        {
+          "text": "got",
+          "start": 92.12,
+          "end": 92.14,
+          "confidence": 0.884
+        },
+        {
+          "text": "them,",
+          "start": 92.14,
+          "end": 92.16,
+          "confidence": 0.972
+        },
+        {
+          "text": "got",
+          "start": 92.16,
+          "end": 92.18,
+          "confidence": 0.882
+        },
+        {
+          "text": "them,",
+          "start": 92.18,
+          "end": 92.2,
+          "confidence": 0.972
+        },
+        {
+          "text": "got",
+          "start": 92.2,
+          "end": 92.22,
+          "confidence": 0.88
+        },
+        {
+          "text": "them,",
+          "start": 92.22,
+          "end": 92.24,
+          "confidence": 0.97
+        },
+        {
+          "text": "got",
+          "start": 92.24,
+          "end": 92.26,
+          "confidence": 0.879
+        },
+        {
+          "text": "them,",
+          "start": 92.26,
+          "end": 92.28,
+          "confidence": 0.97
+        },
+        {
+          "text": "got",
+          "start": 92.28,
+          "end": 92.3,
+          "confidence": 0.878
+        },
+        {
+          "text": "them,",
+          "start": 92.3,
+          "end": 92.32,
+          "confidence": 0.971
+        },
+        {
+          "text": "got",
+          "start": 92.32,
+          "end": 92.34,
+          "confidence": 0.874
+        },
+        {
+          "text": "them,",
+          "start": 92.34,
+          "end": 92.36,
+          "confidence": 0.971
+        },
+        {
+          "text": "got",
+          "start": 92.36,
+          "end": 92.38,
+          "confidence": 0.882
+        },
+        {
+          "text": "them,",
+          "start": 92.38,
+          "end": 92.4,
+          "confidence": 0.973
+        },
+        {
+          "text": "got",
+          "start": 92.4,
+          "end": 92.42,
+          "confidence": 0.881
+        },
+        {
+          "text": "them,",
+          "start": 92.42,
+          "end": 92.44,
+          "confidence": 0.973
+        },
+        {
+          "text": "got",
+          "start": 92.44,
+          "end": 92.46,
+          "confidence": 0.881
+        },
+        {
+          "text": "them,",
+          "start": 92.46,
+          "end": 92.48,
+          "confidence": 0.975
+        },
+        {
+          "text": "got",
+          "start": 92.48,
+          "end": 92.5,
+          "confidence": 0.885
+        },
+        {
+          "text": "them,",
+          "start": 92.5,
+          "end": 92.52,
+          "confidence": 0.976
+        },
+        {
+          "text": "got",
+          "start": 92.52,
+          "end": 92.54,
+          "confidence": 0.888
+        },
+        {
+          "text": "them,",
+          "start": 92.54,
+          "end": 92.56,
+          "confidence": 0.977
+        },
+        {
+          "text": "got",
+          "start": 92.56,
+          "end": 92.58,
+          "confidence": 0.888
+        },
+        {
+          "text": "them,",
+          "start": 92.58,
+          "end": 92.6,
+          "confidence": 0.978
+        },
+        {
+          "text": "got",
+          "start": 92.6,
+          "end": 92.62,
+          "confidence": 0.892
+        },
+        {
+          "text": "them,",
+          "start": 92.62,
+          "end": 92.64,
+          "confidence": 0.978
+        },
+        {
+          "text": "got",
+          "start": 92.64,
+          "end": 92.66,
+          "confidence": 0.896
+        },
+        {
+          "text": "them,",
+          "start": 92.66,
+          "end": 92.68,
+          "confidence": 0.979
+        },
+        {
+          "text": "got",
+          "start": 92.68,
+          "end": 92.7,
+          "confidence": 0.895
+        },
+        {
+          "text": "them,",
+          "start": 92.7,
+          "end": 92.72,
+          "confidence": 0.98
+        },
+        {
+          "text": "got",
+          "start": 92.72,
+          "end": 92.74,
+          "confidence": 0.897
+        },
+        {
+          "text": "them,",
+          "start": 92.74,
+          "end": 92.76,
+          "confidence": 0.981
+        },
+        {
+          "text": "got",
+          "start": 92.76,
+          "end": 92.78,
+          "confidence": 0.906
+        },
+        {
+          "text": "them,",
+          "start": 92.78,
+          "end": 92.8,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 92.8,
+          "end": 92.82,
+          "confidence": 0.906
+        },
+        {
+          "text": "them,",
+          "start": 92.82,
+          "end": 92.84,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 92.84,
+          "end": 92.86,
+          "confidence": 0.911
+        },
+        {
+          "text": "them,",
+          "start": 92.86,
+          "end": 92.88,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 92.88,
+          "end": 92.9,
+          "confidence": 0.917
+        },
+        {
+          "text": "them,",
+          "start": 92.9,
+          "end": 92.92,
+          "confidence": 0.984
+        },
+        {
+          "text": "got",
+          "start": 92.92,
+          "end": 92.94,
+          "confidence": 0.916
+        },
+        {
+          "text": "them,",
+          "start": 92.94,
+          "end": 92.96,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 92.96,
+          "end": 92.98,
+          "confidence": 0.924
+        },
+        {
+          "text": "them,",
+          "start": 92.98,
+          "end": 93.0,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 93.26,
+          "end": 93.28,
+          "confidence": 0.929
+        },
+        {
+          "text": "them,",
+          "start": 93.28,
+          "end": 93.3,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 93.3,
+          "end": 93.32,
+          "confidence": 0.931
+        },
+        {
+          "text": "them,",
+          "start": 93.32,
+          "end": 93.34,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 93.34,
+          "end": 93.36,
+          "confidence": 0.934
+        },
+        {
+          "text": "them,",
+          "start": 93.36,
+          "end": 93.38,
+          "confidence": 0.988
+        },
+        {
+          "text": "got",
+          "start": 93.38,
+          "end": 93.4,
+          "confidence": 0.94
+        },
+        {
+          "text": "them,",
+          "start": 93.4,
+          "end": 93.42,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 94.02,
+          "end": 96.72,
+          "confidence": 0.943
+        },
+        {
+          "text": "them,",
+          "start": 96.72,
+          "end": 96.74,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 96.74,
+          "end": 96.76,
+          "confidence": 0.942
+        },
+        {
+          "text": "them,",
+          "start": 96.76,
+          "end": 96.78,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 96.78,
+          "end": 96.8,
+          "confidence": 0.947
+        },
+        {
+          "text": "them,",
+          "start": 96.8,
+          "end": 96.82,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 96.82,
+          "end": 96.84,
+          "confidence": 0.952
+        },
+        {
+          "text": "them,",
+          "start": 96.84,
+          "end": 96.86,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 96.86,
+          "end": 96.88,
+          "confidence": 0.956
+        },
+        {
+          "text": "them,",
+          "start": 96.88,
+          "end": 96.9,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 96.9,
+          "end": 99.68,
+          "confidence": 0.956
+        },
+        {
+          "text": "them,",
+          "start": 99.68,
+          "end": 99.7,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 99.78,
+          "end": 99.8,
+          "confidence": 0.959
+        },
+        {
+          "text": "them,",
+          "start": 99.8,
+          "end": 100.0,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 100.66,
+          "end": 100.68,
+          "confidence": 0.962
+        },
+        {
+          "text": "them,",
+          "start": 100.68,
+          "end": 101.44,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 101.48,
+          "end": 101.5,
+          "confidence": 0.962
+        },
+        {
+          "text": "them,",
+          "start": 101.5,
+          "end": 101.52,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 101.52,
+          "end": 101.54,
+          "confidence": 0.966
+        },
+        {
+          "text": "them,",
+          "start": 101.54,
+          "end": 101.56,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 101.56,
+          "end": 101.58,
+          "confidence": 0.968
+        },
+        {
+          "text": "them,",
+          "start": 101.58,
+          "end": 101.6,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 101.6,
+          "end": 101.62,
+          "confidence": 0.969
+        },
+        {
+          "text": "them,",
+          "start": 101.62,
+          "end": 101.64,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 101.64,
+          "end": 101.66,
+          "confidence": 0.971
+        },
+        {
+          "text": "them,",
+          "start": 101.66,
+          "end": 101.68,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 101.68,
+          "end": 101.7,
+          "confidence": 0.972
+        },
+        {
+          "text": "them,",
+          "start": 101.7,
+          "end": 101.72,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 101.72,
+          "end": 101.74,
+          "confidence": 0.971
+        },
+        {
+          "text": "them,",
+          "start": 101.74,
+          "end": 101.88,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 101.88,
+          "end": 101.9,
+          "confidence": 0.973
+        },
+        {
+          "text": "them,",
+          "start": 101.9,
+          "end": 101.92,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 101.92,
+          "end": 101.94,
+          "confidence": 0.975
+        },
+        {
+          "text": "them,",
+          "start": 101.94,
+          "end": 101.96,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 101.96,
+          "end": 101.98,
+          "confidence": 0.975
+        },
+        {
+          "text": "them,",
+          "start": 101.98,
+          "end": 102.0,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 102.0,
+          "end": 102.02,
+          "confidence": 0.976
+        },
+        {
+          "text": "them,",
+          "start": 102.02,
+          "end": 102.04,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 102.04,
+          "end": 102.06,
+          "confidence": 0.978
+        },
+        {
+          "text": "them,",
+          "start": 102.06,
+          "end": 102.08,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 102.08,
+          "end": 102.1,
+          "confidence": 0.979
+        },
+        {
+          "text": "them,",
+          "start": 102.1,
+          "end": 102.12,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 102.12,
+          "end": 102.14,
+          "confidence": 0.98
+        },
+        {
+          "text": "them,",
+          "start": 102.14,
+          "end": 102.18,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 102.18,
+          "end": 102.2,
+          "confidence": 0.981
+        },
+        {
+          "text": "them,",
+          "start": 102.2,
+          "end": 102.22,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 102.22,
+          "end": 102.24,
+          "confidence": 0.98
+        },
+        {
+          "text": "them,",
+          "start": 102.24,
+          "end": 102.26,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 102.26,
+          "end": 102.28,
+          "confidence": 0.981
+        },
+        {
+          "text": "them,",
+          "start": 102.28,
+          "end": 102.3,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 102.3,
+          "end": 102.32,
+          "confidence": 0.981
+        },
+        {
+          "text": "them,",
+          "start": 102.32,
+          "end": 102.34,
+          "confidence": 0.996
+        },
+        {
+          "text": "got",
+          "start": 102.34,
+          "end": 102.36,
+          "confidence": 0.983
+        },
+        {
+          "text": "them,",
+          "start": 102.36,
+          "end": 103.8,
+          "confidence": 0.997
+        },
+        {
+          "text": "got",
+          "start": 103.8,
+          "end": 103.82,
+          "confidence": 0.983
+        },
+        {
+          "text": "them,",
+          "start": 103.82,
+          "end": 105.08,
+          "confidence": 0.997
+        },
+        {
+          "text": "got",
+          "start": 105.08,
+          "end": 105.1,
+          "confidence": 0.984
+        },
+        {
+          "text": "them,",
+          "start": 105.1,
+          "end": 110.38,
+          "confidence": 0.997
+        },
+        {
+          "text": "got",
+          "start": 110.38,
+          "end": 110.4,
+          "confidence": 0.985
+        },
+        {
+          "text": "them,",
+          "start": 110.4,
+          "end": 111.78,
+          "confidence": 0.997
+        },
+        {
+          "text": "got",
+          "start": 111.78,
+          "end": 111.8,
+          "confidence": 0.985
+        },
+        {
+          "text": "them,",
+          "start": 111.8,
+          "end": 114.74,
+          "confidence": 0.997
+        },
+        {
+          "text": "got",
+          "start": 114.74,
+          "end": 114.98,
+          "confidence": 0.985
+        },
+        {
+          "text": "them",
+          "start": 114.98,
+          "end": 115.0,
+          "confidence": 0.997
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/medium_auto.cpu/empty.mp3.words.json b/tests/expected/medium_auto.cpu/empty.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..4343ff36131a9ff2cd0f90ee1eb0dcace7c2c1e4
--- /dev/null
+++ b/tests/expected/medium_auto.cpu/empty.mp3.words.json
@@ -0,0 +1,46 @@
+{
+  "text": " Thanks for watching!",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.02,
+      "end": 3.06,
+      "text": " Thanks for watching!",
+      "tokens": [
+        50364,
+        2561,
+        337,
+        1976,
+        0,
+        50514
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.8994035720825195,
+      "compression_ratio": 0.7142857142857143,
+      "no_speech_prob": 0.6661779880523682,
+      "confidence": 0.373,
+      "words": [
+        {
+          "text": "Thanks",
+          "start": 0.02,
+          "end": 0.44,
+          "confidence": 0.06
+        },
+        {
+          "text": "for",
+          "start": 0.44,
+          "end": 1.02,
+          "confidence": 0.916
+        },
+        {
+          "text": "watching!",
+          "start": 1.02,
+          "end": 3.06,
+          "confidence": 0.936
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/medium_auto.cpu/radio_short.mp3.words.json b/tests/expected/medium_auto.cpu/radio_short.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..b5ad9acab69d8c24acd10bd904b99b423c6c97ec
--- /dev/null
+++ b/tests/expected/medium_auto.cpu/radio_short.mp3.words.json
@@ -0,0 +1,1616 @@
+{
+  "text": "3212122222222211111111111111111111111111111111111111111111111111111111",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.04,
+      "end": 0.64,
+      "text": "3",
+      "tokens": [
+        18
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.28690400990572845,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8406417965888977,
+      "confidence": 0.029,
+      "words": [
+        {
+          "text": "3",
+          "start": 0.04,
+          "end": 0.64,
+          "confidence": 0.029
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 1.52,
+      "end": 3.0,
+      "text": "2",
+      "tokens": [
+        17
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.28690400990572845,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8406417965888977,
+      "confidence": 0.688,
+      "words": [
+        {
+          "text": "2",
+          "start": 1.52,
+          "end": 3.0,
+          "confidence": 0.688
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 3.68,
+      "end": 5.32,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.28690400990572845,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8406417965888977,
+      "confidence": 0.95,
+      "words": [
+        {
+          "text": "1",
+          "start": 3.68,
+          "end": 5.32,
+          "confidence": 0.95
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 6.5,
+      "end": 7.02,
+      "text": "2",
+      "tokens": [
+        17
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.28690400990572845,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8406417965888977,
+      "confidence": 0.278,
+      "words": [
+        {
+          "text": "2",
+          "start": 6.5,
+          "end": 7.02,
+          "confidence": 0.278
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 8.08,
+      "end": 9.68,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.28690400990572845,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8406417965888977,
+      "confidence": 0.702,
+      "words": [
+        {
+          "text": "1",
+          "start": 8.08,
+          "end": 9.68,
+          "confidence": 0.702
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 0,
+      "start": 10.38,
+      "end": 11.04,
+      "text": "2",
+      "tokens": [
+        17
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.28690400990572845,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8406417965888977,
+      "confidence": 0.919,
+      "words": [
+        {
+          "text": "2",
+          "start": 10.38,
+          "end": 11.04,
+          "confidence": 0.919
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 0,
+      "start": 11.54,
+      "end": 13.04,
+      "text": "2",
+      "tokens": [
+        17
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.28690400990572845,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8406417965888977,
+      "confidence": 0.657,
+      "words": [
+        {
+          "text": "2",
+          "start": 11.54,
+          "end": 13.04,
+          "confidence": 0.657
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 0,
+      "start": 13.52,
+      "end": 15.57,
+      "text": "2",
+      "tokens": [
+        17
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.28690400990572845,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8406417965888977,
+      "confidence": 0.772,
+      "words": [
+        {
+          "text": "2",
+          "start": 13.52,
+          "end": 15.57,
+          "confidence": 0.772
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 0,
+      "start": 15.57,
+      "end": 16.98,
+      "text": "2",
+      "tokens": [
+        17
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.28690400990572845,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8406417965888977,
+      "confidence": 0.905,
+      "words": [
+        {
+          "text": "2",
+          "start": 15.57,
+          "end": 16.98,
+          "confidence": 0.905
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 0,
+      "start": 17.52,
+      "end": 19.22,
+      "text": "2",
+      "tokens": [
+        17
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.28690400990572845,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8406417965888977,
+      "confidence": 0.808,
+      "words": [
+        {
+          "text": "2",
+          "start": 17.52,
+          "end": 19.22,
+          "confidence": 0.808
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 0,
+      "start": 19.62,
+      "end": 20.68,
+      "text": "2",
+      "tokens": [
+        17
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.28690400990572845,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8406417965888977,
+      "confidence": 0.626,
+      "words": [
+        {
+          "text": "2",
+          "start": 19.62,
+          "end": 20.68,
+          "confidence": 0.626
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 0,
+      "start": 22.22,
+      "end": 22.86,
+      "text": "2",
+      "tokens": [
+        17
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.28690400990572845,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8406417965888977,
+      "confidence": 0.835,
+      "words": [
+        {
+          "text": "2",
+          "start": 22.22,
+          "end": 22.86,
+          "confidence": 0.835
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 0,
+      "start": 23.52,
+      "end": 24.68,
+      "text": "2",
+      "tokens": [
+        17
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.28690400990572845,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8406417965888977,
+      "confidence": 0.974,
+      "words": [
+        {
+          "text": "2",
+          "start": 23.52,
+          "end": 24.68,
+          "confidence": 0.974
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 0,
+      "start": 25.7,
+      "end": 27.1,
+      "text": "2",
+      "tokens": [
+        17
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.28690400990572845,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8406417965888977,
+      "confidence": 0.97,
+      "words": [
+        {
+          "text": "2",
+          "start": 25.7,
+          "end": 27.1,
+          "confidence": 0.97
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 2800,
+      "start": 28.02,
+      "end": 28.86,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12449877912347967,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.022917350754141808,
+      "confidence": 0.271,
+      "words": [
+        {
+          "text": "1",
+          "start": 28.02,
+          "end": 28.86,
+          "confidence": 0.271
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 2800,
+      "start": 30.5,
+      "end": 31.12,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12449877912347967,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.022917350754141808,
+      "confidence": 0.504,
+      "words": [
+        {
+          "text": "1",
+          "start": 30.5,
+          "end": 31.12,
+          "confidence": 0.504
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 2800,
+      "start": 31.52,
+      "end": 33.55,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12449877912347967,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.022917350754141808,
+      "confidence": 0.911,
+      "words": [
+        {
+          "text": "1",
+          "start": 31.52,
+          "end": 33.55,
+          "confidence": 0.911
+        }
+      ]
+    },
+    {
+      "id": 17,
+      "seek": 2800,
+      "start": 33.55,
+      "end": 35.02,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12449877912347967,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.022917350754141808,
+      "confidence": 0.894,
+      "words": [
+        {
+          "text": "1",
+          "start": 33.55,
+          "end": 35.02,
+          "confidence": 0.894
+        }
+      ]
+    },
+    {
+      "id": 18,
+      "seek": 2800,
+      "start": 36.24,
+      "end": 37.52,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12449877912347967,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.022917350754141808,
+      "confidence": 0.957,
+      "words": [
+        {
+          "text": "1",
+          "start": 36.24,
+          "end": 37.52,
+          "confidence": 0.957
+        }
+      ]
+    },
+    {
+      "id": 19,
+      "seek": 2800,
+      "start": 37.68,
+      "end": 39.8,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12449877912347967,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.022917350754141808,
+      "confidence": 0.958,
+      "words": [
+        {
+          "text": "1",
+          "start": 37.68,
+          "end": 39.8,
+          "confidence": 0.958
+        }
+      ]
+    },
+    {
+      "id": 20,
+      "seek": 2800,
+      "start": 39.8,
+      "end": 41.2,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12449877912347967,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.022917350754141808,
+      "confidence": 0.967,
+      "words": [
+        {
+          "text": "1",
+          "start": 39.8,
+          "end": 41.2,
+          "confidence": 0.967
+        }
+      ]
+    },
+    {
+      "id": 21,
+      "seek": 2800,
+      "start": 41.52,
+      "end": 44.02,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12449877912347967,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.022917350754141808,
+      "confidence": 0.973,
+      "words": [
+        {
+          "text": "1",
+          "start": 41.52,
+          "end": 44.02,
+          "confidence": 0.973
+        }
+      ]
+    },
+    {
+      "id": 22,
+      "seek": 2800,
+      "start": 44.02,
+      "end": 45.04,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12449877912347967,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.022917350754141808,
+      "confidence": 0.944,
+      "words": [
+        {
+          "text": "1",
+          "start": 44.02,
+          "end": 45.04,
+          "confidence": 0.944
+        }
+      ]
+    },
+    {
+      "id": 23,
+      "seek": 2800,
+      "start": 45.52,
+      "end": 47.53,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12449877912347967,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.022917350754141808,
+      "confidence": 0.959,
+      "words": [
+        {
+          "text": "1",
+          "start": 45.52,
+          "end": 47.53,
+          "confidence": 0.959
+        }
+      ]
+    },
+    {
+      "id": 24,
+      "seek": 2800,
+      "start": 47.53,
+      "end": 48.94,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12449877912347967,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.022917350754141808,
+      "confidence": 0.966,
+      "words": [
+        {
+          "text": "1",
+          "start": 47.53,
+          "end": 48.94,
+          "confidence": 0.966
+        }
+      ]
+    },
+    {
+      "id": 25,
+      "seek": 2800,
+      "start": 50.2,
+      "end": 52.06,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12449877912347967,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.022917350754141808,
+      "confidence": 0.968,
+      "words": [
+        {
+          "text": "1",
+          "start": 50.2,
+          "end": 52.06,
+          "confidence": 0.968
+        }
+      ]
+    },
+    {
+      "id": 26,
+      "seek": 2800,
+      "start": 52.32,
+      "end": 52.84,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12449877912347967,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.022917350754141808,
+      "confidence": 0.964,
+      "words": [
+        {
+          "text": "1",
+          "start": 52.32,
+          "end": 52.84,
+          "confidence": 0.964
+        }
+      ]
+    },
+    {
+      "id": 27,
+      "seek": 2800,
+      "start": 53.64,
+      "end": 54.9,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12449877912347967,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.022917350754141808,
+      "confidence": 0.944,
+      "words": [
+        {
+          "text": "1",
+          "start": 53.64,
+          "end": 54.9,
+          "confidence": 0.944
+        }
+      ]
+    },
+    {
+      "id": 28,
+      "seek": 5600,
+      "start": 56.02,
+      "end": 57.06,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12232361056587913,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.015843844041228294,
+      "confidence": 0.377,
+      "words": [
+        {
+          "text": "1",
+          "start": 56.02,
+          "end": 57.06,
+          "confidence": 0.377
+        }
+      ]
+    },
+    {
+      "id": 29,
+      "seek": 5600,
+      "start": 57.52,
+      "end": 58.8,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12232361056587913,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.015843844041228294,
+      "confidence": 0.763,
+      "words": [
+        {
+          "text": "1",
+          "start": 57.52,
+          "end": 58.8,
+          "confidence": 0.763
+        }
+      ]
+    },
+    {
+      "id": 30,
+      "seek": 5600,
+      "start": 59.8,
+      "end": 61.08,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12232361056587913,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.015843844041228294,
+      "confidence": 0.952,
+      "words": [
+        {
+          "text": "1",
+          "start": 59.8,
+          "end": 61.08,
+          "confidence": 0.952
+        }
+      ]
+    },
+    {
+      "id": 31,
+      "seek": 5600,
+      "start": 61.52,
+      "end": 63.08,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12232361056587913,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.015843844041228294,
+      "confidence": 0.949,
+      "words": [
+        {
+          "text": "1",
+          "start": 61.52,
+          "end": 63.08,
+          "confidence": 0.949
+        }
+      ]
+    },
+    {
+      "id": 32,
+      "seek": 5600,
+      "start": 64.04,
+      "end": 65.18,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12232361056587913,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.015843844041228294,
+      "confidence": 0.954,
+      "words": [
+        {
+          "text": "1",
+          "start": 64.04,
+          "end": 65.18,
+          "confidence": 0.954
+        }
+      ]
+    },
+    {
+      "id": 33,
+      "seek": 5600,
+      "start": 65.52,
+      "end": 66.7,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12232361056587913,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.015843844041228294,
+      "confidence": 0.952,
+      "words": [
+        {
+          "text": "1",
+          "start": 65.52,
+          "end": 66.7,
+          "confidence": 0.952
+        }
+      ]
+    },
+    {
+      "id": 34,
+      "seek": 5600,
+      "start": 67.52,
+      "end": 69.08,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12232361056587913,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.015843844041228294,
+      "confidence": 0.966,
+      "words": [
+        {
+          "text": "1",
+          "start": 67.52,
+          "end": 69.08,
+          "confidence": 0.966
+        }
+      ]
+    },
+    {
+      "id": 35,
+      "seek": 5600,
+      "start": 69.58,
+      "end": 71.65,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12232361056587913,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.015843844041228294,
+      "confidence": 0.958,
+      "words": [
+        {
+          "text": "1",
+          "start": 69.58,
+          "end": 71.65,
+          "confidence": 0.958
+        }
+      ]
+    },
+    {
+      "id": 36,
+      "seek": 5600,
+      "start": 71.65,
+      "end": 73.62,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12232361056587913,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.015843844041228294,
+      "confidence": 0.957,
+      "words": [
+        {
+          "text": "1",
+          "start": 71.65,
+          "end": 73.62,
+          "confidence": 0.957
+        }
+      ]
+    },
+    {
+      "id": 37,
+      "seek": 5600,
+      "start": 73.62,
+      "end": 75.85,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12232361056587913,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.015843844041228294,
+      "confidence": 0.953,
+      "words": [
+        {
+          "text": "1",
+          "start": 73.62,
+          "end": 75.85,
+          "confidence": 0.953
+        }
+      ]
+    },
+    {
+      "id": 38,
+      "seek": 5600,
+      "start": 75.85,
+      "end": 77.12,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12232361056587913,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.015843844041228294,
+      "confidence": 0.942,
+      "words": [
+        {
+          "text": "1",
+          "start": 75.85,
+          "end": 77.12,
+          "confidence": 0.942
+        }
+      ]
+    },
+    {
+      "id": 39,
+      "seek": 5600,
+      "start": 78.22,
+      "end": 78.78,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12232361056587913,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.015843844041228294,
+      "confidence": 0.936,
+      "words": [
+        {
+          "text": "1",
+          "start": 78.22,
+          "end": 78.78,
+          "confidence": 0.936
+        }
+      ]
+    },
+    {
+      "id": 40,
+      "seek": 5600,
+      "start": 80.08,
+      "end": 80.86,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12232361056587913,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.015843844041228294,
+      "confidence": 0.929,
+      "words": [
+        {
+          "text": "1",
+          "start": 80.08,
+          "end": 80.86,
+          "confidence": 0.929
+        }
+      ]
+    },
+    {
+      "id": 41,
+      "seek": 5600,
+      "start": 81.52,
+      "end": 82.7,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12232361056587913,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.015843844041228294,
+      "confidence": 0.903,
+      "words": [
+        {
+          "text": "1",
+          "start": 81.52,
+          "end": 82.7,
+          "confidence": 0.903
+        }
+      ]
+    },
+    {
+      "id": 42,
+      "seek": 8400,
+      "start": 84.88,
+      "end": 85.08,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10775410045276988,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.02908501960337162,
+      "confidence": 0.82,
+      "words": [
+        {
+          "text": "1",
+          "start": 84.88,
+          "end": 85.08,
+          "confidence": 0.82
+        }
+      ]
+    },
+    {
+      "id": 43,
+      "seek": 8400,
+      "start": 85.58,
+      "end": 86.86,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10775410045276988,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.02908501960337162,
+      "confidence": 0.884,
+      "words": [
+        {
+          "text": "1",
+          "start": 85.58,
+          "end": 86.86,
+          "confidence": 0.884
+        }
+      ]
+    },
+    {
+      "id": 44,
+      "seek": 8400,
+      "start": 88.02,
+      "end": 89.2,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10775410045276988,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.02908501960337162,
+      "confidence": 0.957,
+      "words": [
+        {
+          "text": "1",
+          "start": 88.02,
+          "end": 89.2,
+          "confidence": 0.957
+        }
+      ]
+    },
+    {
+      "id": 45,
+      "seek": 8400,
+      "start": 89.52,
+      "end": 90.98,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10775410045276988,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.02908501960337162,
+      "confidence": 0.952,
+      "words": [
+        {
+          "text": "1",
+          "start": 89.52,
+          "end": 90.98,
+          "confidence": 0.952
+        }
+      ]
+    },
+    {
+      "id": 46,
+      "seek": 8400,
+      "start": 92.5,
+      "end": 93.04,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10775410045276988,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.02908501960337162,
+      "confidence": 0.917,
+      "words": [
+        {
+          "text": "1",
+          "start": 92.5,
+          "end": 93.04,
+          "confidence": 0.917
+        }
+      ]
+    },
+    {
+      "id": 47,
+      "seek": 8400,
+      "start": 93.58,
+      "end": 95.56,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10775410045276988,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.02908501960337162,
+      "confidence": 0.947,
+      "words": [
+        {
+          "text": "1",
+          "start": 93.58,
+          "end": 95.56,
+          "confidence": 0.947
+        }
+      ]
+    },
+    {
+      "id": 48,
+      "seek": 8400,
+      "start": 95.6,
+      "end": 97.95,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10775410045276988,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.02908501960337162,
+      "confidence": 0.97,
+      "words": [
+        {
+          "text": "1",
+          "start": 95.6,
+          "end": 97.95,
+          "confidence": 0.97
+        }
+      ]
+    },
+    {
+      "id": 49,
+      "seek": 8400,
+      "start": 97.95,
+      "end": 99.14,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10775410045276988,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.02908501960337162,
+      "confidence": 0.976,
+      "words": [
+        {
+          "text": "1",
+          "start": 97.95,
+          "end": 99.14,
+          "confidence": 0.976
+        }
+      ]
+    },
+    {
+      "id": 50,
+      "seek": 8400,
+      "start": 99.52,
+      "end": 101.08,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10775410045276988,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.02908501960337162,
+      "confidence": 0.984,
+      "words": [
+        {
+          "text": "1",
+          "start": 99.52,
+          "end": 101.08,
+          "confidence": 0.984
+        }
+      ]
+    },
+    {
+      "id": 51,
+      "seek": 8400,
+      "start": 101.52,
+      "end": 103.62,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10775410045276988,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.02908501960337162,
+      "confidence": 0.985,
+      "words": [
+        {
+          "text": "1",
+          "start": 101.52,
+          "end": 103.62,
+          "confidence": 0.985
+        }
+      ]
+    },
+    {
+      "id": 52,
+      "seek": 8400,
+      "start": 103.62,
+      "end": 105.7,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10775410045276988,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.02908501960337162,
+      "confidence": 0.988,
+      "words": [
+        {
+          "text": "1",
+          "start": 103.62,
+          "end": 105.7,
+          "confidence": 0.988
+        }
+      ]
+    },
+    {
+      "id": 53,
+      "seek": 8400,
+      "start": 106.5,
+      "end": 107.12,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10775410045276988,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.02908501960337162,
+      "confidence": 0.957,
+      "words": [
+        {
+          "text": "1",
+          "start": 106.5,
+          "end": 107.12,
+          "confidence": 0.957
+        }
+      ]
+    },
+    {
+      "id": 54,
+      "seek": 8400,
+      "start": 108.5,
+      "end": 109.22,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10775410045276988,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.02908501960337162,
+      "confidence": 0.946,
+      "words": [
+        {
+          "text": "1",
+          "start": 108.5,
+          "end": 109.22,
+          "confidence": 0.946
+        }
+      ]
+    },
+    {
+      "id": 55,
+      "seek": 8400,
+      "start": 109.52,
+      "end": 111.36,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10775410045276988,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.02908501960337162,
+      "confidence": 0.89,
+      "words": [
+        {
+          "text": "1",
+          "start": 109.52,
+          "end": 111.36,
+          "confidence": 0.89
+        }
+      ]
+    },
+    {
+      "id": 56,
+      "seek": 11200,
+      "start": 112.98,
+      "end": 113.34,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10804855823516846,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.04961525276303291,
+      "confidence": 0.895,
+      "words": [
+        {
+          "text": "1",
+          "start": 112.98,
+          "end": 113.34,
+          "confidence": 0.895
+        }
+      ]
+    },
+    {
+      "id": 57,
+      "seek": 11200,
+      "start": 113.88,
+      "end": 114.52,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10804855823516846,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.04961525276303291,
+      "confidence": 0.871,
+      "words": [
+        {
+          "text": "1",
+          "start": 113.88,
+          "end": 114.52,
+          "confidence": 0.871
+        }
+      ]
+    },
+    {
+      "id": 58,
+      "seek": 11200,
+      "start": 115.94,
+      "end": 117.2,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10804855823516846,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.04961525276303291,
+      "confidence": 0.977,
+      "words": [
+        {
+          "text": "1",
+          "start": 115.94,
+          "end": 117.2,
+          "confidence": 0.977
+        }
+      ]
+    },
+    {
+      "id": 59,
+      "seek": 11200,
+      "start": 117.52,
+      "end": 118.64,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10804855823516846,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.04961525276303291,
+      "confidence": 0.975,
+      "words": [
+        {
+          "text": "1",
+          "start": 117.52,
+          "end": 118.64,
+          "confidence": 0.975
+        }
+      ]
+    },
+    {
+      "id": 60,
+      "seek": 11200,
+      "start": 120.5,
+      "end": 120.8,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10804855823516846,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.04961525276303291,
+      "confidence": 0.957,
+      "words": [
+        {
+          "text": "1",
+          "start": 120.5,
+          "end": 120.8,
+          "confidence": 0.957
+        }
+      ]
+    },
+    {
+      "id": 61,
+      "seek": 11200,
+      "start": 121.58,
+      "end": 123.74,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10804855823516846,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.04961525276303291,
+      "confidence": 0.959,
+      "words": [
+        {
+          "text": "1",
+          "start": 121.58,
+          "end": 123.74,
+          "confidence": 0.959
+        }
+      ]
+    },
+    {
+      "id": 62,
+      "seek": 11200,
+      "start": 123.9,
+      "end": 125.56,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10804855823516846,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.04961525276303291,
+      "confidence": 0.967,
+      "words": [
+        {
+          "text": "1",
+          "start": 123.9,
+          "end": 125.56,
+          "confidence": 0.967
+        }
+      ]
+    },
+    {
+      "id": 63,
+      "seek": 11200,
+      "start": 125.56,
+      "end": 127.34,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10804855823516846,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.04961525276303291,
+      "confidence": 0.968,
+      "words": [
+        {
+          "text": "1",
+          "start": 125.56,
+          "end": 127.34,
+          "confidence": 0.968
+        }
+      ]
+    },
+    {
+      "id": 64,
+      "seek": 11200,
+      "start": 127.52,
+      "end": 129.2,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10804855823516846,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.04961525276303291,
+      "confidence": 0.96,
+      "words": [
+        {
+          "text": "1",
+          "start": 127.52,
+          "end": 129.2,
+          "confidence": 0.96
+        }
+      ]
+    },
+    {
+      "id": 65,
+      "seek": 11200,
+      "start": 129.52,
+      "end": 131.06,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10804855823516846,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.04961525276303291,
+      "confidence": 0.965,
+      "words": [
+        {
+          "text": "1",
+          "start": 129.52,
+          "end": 131.06,
+          "confidence": 0.965
+        }
+      ]
+    },
+    {
+      "id": 66,
+      "seek": 11200,
+      "start": 131.52,
+      "end": 133.3,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10804855823516846,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.04961525276303291,
+      "confidence": 0.969,
+      "words": [
+        {
+          "text": "1",
+          "start": 131.52,
+          "end": 133.3,
+          "confidence": 0.969
+        }
+      ]
+    },
+    {
+      "id": 67,
+      "seek": 11200,
+      "start": 133.52,
+      "end": 135.73,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10804855823516846,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.04961525276303291,
+      "confidence": 0.966,
+      "words": [
+        {
+          "text": "1",
+          "start": 133.52,
+          "end": 135.73,
+          "confidence": 0.966
+        }
+      ]
+    },
+    {
+      "id": 68,
+      "seek": 11200,
+      "start": 135.73,
+      "end": 137.34,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10804855823516846,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.04961525276303291,
+      "confidence": 0.971,
+      "words": [
+        {
+          "text": "1",
+          "start": 135.73,
+          "end": 137.34,
+          "confidence": 0.971
+        }
+      ]
+    },
+    {
+      "id": 69,
+      "seek": 11200,
+      "start": 137.52,
+      "end": 139.8,
+      "text": "1",
+      "tokens": [
+        16
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10804855823516846,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.04961525276303291,
+      "confidence": 0.925,
+      "words": [
+        {
+          "text": "1",
+          "start": 137.52,
+          "end": 139.8,
+          "confidence": 0.925
+        }
+      ]
+    }
+  ],
+  "language": "zh"
+}
\ No newline at end of file
diff --git a/tests/expected/medium_auto.cpu/smartphone.mp3.words.json b/tests/expected/medium_auto.cpu/smartphone.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..9faa961d5cf4a38b6ac04b76010aeaddb28cee89
--- /dev/null
+++ b/tests/expected/medium_auto.cpu/smartphone.mp3.words.json
@@ -0,0 +1,4802 @@
+{
+  "text": " C'est évident ce que dit Nicolas, mais je ne me l'étais jamais formulé comme ça. Ce qui fait la force du smartphone, c'est pas seulement l'accumulation des fonctions, mais la manière dont elles interagissent entre elles. Ce qui dit d'ailleurs sur la photo, c'est hyper convaincant. Alors évidemment, il faudrait ajouter les interfaces. L'écran tactile a été beaucoup très souvent mentionné. Mais bon, il faut dire qu'il profite aussi de 20 ans pendant lesquels les ordinateurs nous ont appris à cliquer sur des icônes. Sauf que le smartphone ajoute le toucher, ce qui rend le contact plus direct, plus sensible. Et puis évidemment, il faudrait parler aussi des applications qui permettent de contourner le côté touffu de la navigation web pour aller directement au but. Bref, tout ça, ce sont les conditions qui permettent de créer cet objet dont Nicolas dit qu'il est vraisemblablement inédit dans l'histoire de l'humanité. Mais ça, ça soulève une autre interrogation. Est-ce que le fait que cet objet soit inédit induit que notre rapport à lui est aussi un rapport inédit? Je veux dire, est-ce que le rapport qu'on a au smartphone est comparable à celui qu'on entretenait à d'autres objets techniques comme la voiture ou le téléphone? Il n'y a pas d'équivalent en fait. Et donc cette espèce de nouveauté dans la relation à l'objet, c'est fascinant et terrifiant. Parce qu'on a l'impression, comme le disent les utilisateurs et les services, d'être dépendants de cet objet, d'induire en fait une espèce de relation, de médiation avec le monde qui rend de l'ampleur et qui amène aussi à des formes de rejet. Donc, à objet inédit, rapport inédit. Et ce rapport, si j'en crois Nicolas, serait caractérisé par un mélange de dépendance et de rejet. Bon, en vrai, il faudrait remonter très très finement toute l'histoire des objets techniques et de leur insertion dans nos vies pour déterminer si ce rapport est totalement inédit. Mais j'ai l'impression comme ça que Nicolas ne se trompe pas vraiment. Pour autant que je sache, il y a eu plein de discussions autour de la voiture ou même du téléphone. Mais la dépendance n'était pas du même ordre. Donc le rejet non plus n'était pas du même ordre. On peut adorer sa bagnole, en avoir besoin pour plein de choses. Et bien, le soir, quand on va se coucher, on la laisse. On ne l'a pas dans la main quand on est au lit, on ne l'emmène pas au chiottes. On pouvait être énervé par son môme qui occupait la ligne de téléphone pendant une heure chaque soir pour discuter avec un copain. Mais ça ne ressemblait pas à ce qu'on peut ressentir à voir ce même môme aujourd'hui, continuellement avec son smartphone dans la main, comme si c'était une sorte de pacemaker externe, comme si le lâcher allait entraîner sa mort immédiate. Bon, je dis ça pour le môme, mais c'est évidemment valable pour nous aussi. Donc, rapport inédit. D'accord. Mais pourquoi a-t-on l'impression qu'on n'en sortira jamais? Est-ce qu'il faut en remettre la faute sur les gens qui ont créé cet outil merveilleux et diabolique, et diabolique parce que merveilleux? Les économistes parlent de dépendance du sentier. C'est l'idée qu'on est sur un sentier qui a été établi, soit volontairement en marchant dessus, soit en définissant des bornes, en définissant une signalétique.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.38,
+      "end": 3.62,
+      "text": " C'est évident ce que dit Nicolas, mais je ne me l'étais jamais formulé comme ça.",
+      "tokens": [
+        383,
+        6,
+        377,
+        20090,
+        1078,
+        1769,
+        631,
+        6176,
+        38268,
+        11,
+        2420,
+        1506,
+        408,
+        385,
+        287,
+        6,
+        22824,
+        14540,
+        49990,
+        526,
+        5173,
+        2788,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23666970461409614,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.1567964404821396,
+      "confidence": 0.935,
+      "words": [
+        {
+          "text": "C'est",
+          "start": 0.38,
+          "end": 0.58,
+          "confidence": 0.961
+        },
+        {
+          "text": "évident",
+          "start": 0.58,
+          "end": 0.88,
+          "confidence": 0.984
+        },
+        {
+          "text": "ce",
+          "start": 0.88,
+          "end": 1.02,
+          "confidence": 0.663
+        },
+        {
+          "text": "que",
+          "start": 1.02,
+          "end": 1.08,
+          "confidence": 0.989
+        },
+        {
+          "text": "dit",
+          "start": 1.08,
+          "end": 1.2,
+          "confidence": 0.994
+        },
+        {
+          "text": "Nicolas,",
+          "start": 1.2,
+          "end": 1.78,
+          "confidence": 0.91
+        },
+        {
+          "text": "mais",
+          "start": 1.78,
+          "end": 1.9,
+          "confidence": 0.979
+        },
+        {
+          "text": "je",
+          "start": 1.9,
+          "end": 2.24,
+          "confidence": 0.982
+        },
+        {
+          "text": "ne",
+          "start": 2.24,
+          "end": 2.34,
+          "confidence": 0.835
+        },
+        {
+          "text": "me",
+          "start": 2.34,
+          "end": 2.38,
+          "confidence": 0.82
+        },
+        {
+          "text": "l'étais",
+          "start": 2.38,
+          "end": 2.58,
+          "confidence": 0.971
+        },
+        {
+          "text": "jamais",
+          "start": 2.58,
+          "end": 2.84,
+          "confidence": 0.989
+        },
+        {
+          "text": "formulé",
+          "start": 2.84,
+          "end": 3.26,
+          "confidence": 0.909
+        },
+        {
+          "text": "comme",
+          "start": 3.26,
+          "end": 3.42,
+          "confidence": 0.993
+        },
+        {
+          "text": "ça.",
+          "start": 3.42,
+          "end": 3.62,
+          "confidence": 0.975
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 4.08,
+      "end": 7.92,
+      "text": " Ce qui fait la force du smartphone, c'est pas seulement l'accumulation des fonctions,",
+      "tokens": [
+        8257,
+        1956,
+        3887,
+        635,
+        3464,
+        1581,
+        13307,
+        11,
+        269,
+        6,
+        377,
+        1736,
+        27772,
+        287,
+        6,
+        8476,
+        449,
+        2776,
+        730,
+        17290,
+        3916,
+        11
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23666970461409614,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.1567964404821396,
+      "confidence": 0.93,
+      "words": [
+        {
+          "text": "Ce",
+          "start": 4.08,
+          "end": 4.26,
+          "confidence": 0.952
+        },
+        {
+          "text": "qui",
+          "start": 4.26,
+          "end": 4.34,
+          "confidence": 0.958
+        },
+        {
+          "text": "fait",
+          "start": 4.34,
+          "end": 4.48,
+          "confidence": 0.565
+        },
+        {
+          "text": "la",
+          "start": 4.48,
+          "end": 4.66,
+          "confidence": 0.971
+        },
+        {
+          "text": "force",
+          "start": 4.66,
+          "end": 5.0,
+          "confidence": 0.999
+        },
+        {
+          "text": "du",
+          "start": 5.0,
+          "end": 5.2,
+          "confidence": 0.996
+        },
+        {
+          "text": "smartphone,",
+          "start": 5.2,
+          "end": 5.88,
+          "confidence": 0.911
+        },
+        {
+          "text": "c'est",
+          "start": 5.88,
+          "end": 6.12,
+          "confidence": 0.88
+        },
+        {
+          "text": "pas",
+          "start": 6.12,
+          "end": 6.26,
+          "confidence": 0.992
+        },
+        {
+          "text": "seulement",
+          "start": 6.26,
+          "end": 6.52,
+          "confidence": 0.999
+        },
+        {
+          "text": "l'accumulation",
+          "start": 6.52,
+          "end": 7.38,
+          "confidence": 0.958
+        },
+        {
+          "text": "des",
+          "start": 7.38,
+          "end": 7.56,
+          "confidence": 0.983
+        },
+        {
+          "text": "fonctions,",
+          "start": 7.56,
+          "end": 7.92,
+          "confidence": 0.987
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 8.32,
+      "end": 10.88,
+      "text": " mais la manière dont elles interagissent entre elles.",
+      "tokens": [
+        2420,
+        635,
+        22267,
+        9400,
+        23576,
+        728,
+        559,
+        25450,
+        3962,
+        23576,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23666970461409614,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.1567964404821396,
+      "confidence": 0.977,
+      "words": [
+        {
+          "text": "mais",
+          "start": 8.32,
+          "end": 8.44,
+          "confidence": 0.992
+        },
+        {
+          "text": "la",
+          "start": 8.44,
+          "end": 8.6,
+          "confidence": 0.995
+        },
+        {
+          "text": "manière",
+          "start": 8.6,
+          "end": 8.9,
+          "confidence": 0.999
+        },
+        {
+          "text": "dont",
+          "start": 8.9,
+          "end": 9.1,
+          "confidence": 0.978
+        },
+        {
+          "text": "elles",
+          "start": 9.1,
+          "end": 9.48,
+          "confidence": 0.967
+        },
+        {
+          "text": "interagissent",
+          "start": 9.48,
+          "end": 10.32,
+          "confidence": 0.964
+        },
+        {
+          "text": "entre",
+          "start": 10.32,
+          "end": 10.58,
+          "confidence": 0.956
+        },
+        {
+          "text": "elles.",
+          "start": 10.58,
+          "end": 10.88,
+          "confidence": 0.99
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 10.96,
+      "end": 13.0,
+      "text": " Ce qui dit d'ailleurs sur la photo, c'est hyper convaincant.",
+      "tokens": [
+        8257,
+        1956,
+        6176,
+        274,
+        6,
+        19400,
+        1022,
+        635,
+        5052,
+        11,
+        269,
+        6,
+        377,
+        9848,
+        3754,
+        491,
+        66,
+        394,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23666970461409614,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.1567964404821396,
+      "confidence": 0.906,
+      "words": [
+        {
+          "text": "Ce",
+          "start": 10.96,
+          "end": 11.16,
+          "confidence": 0.607
+        },
+        {
+          "text": "qui",
+          "start": 11.16,
+          "end": 11.22,
+          "confidence": 0.765
+        },
+        {
+          "text": "dit",
+          "start": 11.22,
+          "end": 11.4,
+          "confidence": 0.983
+        },
+        {
+          "text": "d'ailleurs",
+          "start": 11.4,
+          "end": 11.56,
+          "confidence": 0.985
+        },
+        {
+          "text": "sur",
+          "start": 11.56,
+          "end": 11.72,
+          "confidence": 0.477
+        },
+        {
+          "text": "la",
+          "start": 11.72,
+          "end": 11.78,
+          "confidence": 0.984
+        },
+        {
+          "text": "photo,",
+          "start": 11.78,
+          "end": 12.12,
+          "confidence": 0.994
+        },
+        {
+          "text": "c'est",
+          "start": 12.12,
+          "end": 12.2,
+          "confidence": 0.997
+        },
+        {
+          "text": "hyper",
+          "start": 12.2,
+          "end": 12.42,
+          "confidence": 0.993
+        },
+        {
+          "text": "convaincant.",
+          "start": 12.42,
+          "end": 13.0,
+          "confidence": 0.982
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 13.34,
+      "end": 16.02,
+      "text": " Alors évidemment, il faudrait ajouter les interfaces.",
+      "tokens": [
+        9946,
+        24724,
+        11,
+        1930,
+        38694,
+        8645,
+        17680,
+        23985,
+        1512,
+        28416,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23666970461409614,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.1567964404821396,
+      "confidence": 0.913,
+      "words": [
+        {
+          "text": "Alors",
+          "start": 13.34,
+          "end": 13.62,
+          "confidence": 0.585
+        },
+        {
+          "text": "évidemment,",
+          "start": 13.62,
+          "end": 14.34,
+          "confidence": 0.832
+        },
+        {
+          "text": "il",
+          "start": 14.34,
+          "end": 14.38,
+          "confidence": 0.952
+        },
+        {
+          "text": "faudrait",
+          "start": 14.38,
+          "end": 14.74,
+          "confidence": 0.996
+        },
+        {
+          "text": "ajouter",
+          "start": 14.74,
+          "end": 15.16,
+          "confidence": 0.992
+        },
+        {
+          "text": "les",
+          "start": 15.16,
+          "end": 15.52,
+          "confidence": 0.985
+        },
+        {
+          "text": "interfaces.",
+          "start": 15.52,
+          "end": 16.02,
+          "confidence": 0.984
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 0,
+      "start": 16.22,
+      "end": 19.36,
+      "text": " L'écran tactile a été beaucoup très souvent mentionné.",
+      "tokens": [
+        441,
+        6,
+        9062,
+        4257,
+        47319,
+        257,
+        8862,
+        8796,
+        5732,
+        20847,
+        2152,
+        15055,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23666970461409614,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.1567964404821396,
+      "confidence": 0.923,
+      "words": [
+        {
+          "text": "L'écran",
+          "start": 16.22,
+          "end": 16.7,
+          "confidence": 0.996
+        },
+        {
+          "text": "tactile",
+          "start": 16.7,
+          "end": 17.06,
+          "confidence": 0.986
+        },
+        {
+          "text": "a",
+          "start": 17.06,
+          "end": 17.26,
+          "confidence": 0.98
+        },
+        {
+          "text": "été",
+          "start": 17.26,
+          "end": 17.88,
+          "confidence": 0.975
+        },
+        {
+          "text": "beaucoup",
+          "start": 17.88,
+          "end": 18.28,
+          "confidence": 0.976
+        },
+        {
+          "text": "très",
+          "start": 18.28,
+          "end": 18.62,
+          "confidence": 0.447
+        },
+        {
+          "text": "souvent",
+          "start": 18.62,
+          "end": 18.9,
+          "confidence": 0.996
+        },
+        {
+          "text": "mentionné.",
+          "start": 18.9,
+          "end": 19.36,
+          "confidence": 0.978
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 0,
+      "start": 19.84,
+      "end": 25.26,
+      "text": " Mais bon, il faut dire qu'il profite aussi de 20 ans pendant lesquels les ordinateurs nous ont appris à cliquer sur des icônes.",
+      "tokens": [
+        6313,
+        4428,
+        11,
+        1930,
+        8487,
+        1264,
+        421,
+        6,
+        388,
+        1740,
+        642,
+        6212,
+        368,
+        945,
+        1567,
+        17338,
+        1512,
+        358,
+        1625,
+        1512,
+        4792,
+        13923,
+        2156,
+        4666,
+        6592,
+        724,
+        5714,
+        1531,
+        596,
+        23909,
+        1022,
+        730,
+        4376,
+        2851,
+        4081,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23666970461409614,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.1567964404821396,
+      "confidence": 0.92,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 19.84,
+          "end": 20.22,
+          "confidence": 0.944
+        },
+        {
+          "text": "bon,",
+          "start": 20.22,
+          "end": 20.52,
+          "confidence": 0.667
+        },
+        {
+          "text": "il",
+          "start": 20.52,
+          "end": 20.6,
+          "confidence": 0.99
+        },
+        {
+          "text": "faut",
+          "start": 20.6,
+          "end": 20.7,
+          "confidence": 0.99
+        },
+        {
+          "text": "dire",
+          "start": 20.7,
+          "end": 20.84,
+          "confidence": 0.995
+        },
+        {
+          "text": "qu'il",
+          "start": 20.84,
+          "end": 20.96,
+          "confidence": 0.88
+        },
+        {
+          "text": "profite",
+          "start": 20.96,
+          "end": 21.26,
+          "confidence": 0.995
+        },
+        {
+          "text": "aussi",
+          "start": 21.26,
+          "end": 21.68,
+          "confidence": 0.972
+        },
+        {
+          "text": "de",
+          "start": 21.68,
+          "end": 21.9,
+          "confidence": 0.97
+        },
+        {
+          "text": "20",
+          "start": 21.9,
+          "end": 22.1,
+          "confidence": 0.812
+        },
+        {
+          "text": "ans",
+          "start": 22.1,
+          "end": 22.32,
+          "confidence": 0.997
+        },
+        {
+          "text": "pendant",
+          "start": 22.32,
+          "end": 22.48,
+          "confidence": 0.72
+        },
+        {
+          "text": "lesquels",
+          "start": 22.48,
+          "end": 22.92,
+          "confidence": 0.98
+        },
+        {
+          "text": "les",
+          "start": 22.92,
+          "end": 23.04,
+          "confidence": 0.709
+        },
+        {
+          "text": "ordinateurs",
+          "start": 23.04,
+          "end": 23.54,
+          "confidence": 0.965
+        },
+        {
+          "text": "nous",
+          "start": 23.54,
+          "end": 23.72,
+          "confidence": 0.602
+        },
+        {
+          "text": "ont",
+          "start": 23.72,
+          "end": 23.82,
+          "confidence": 0.974
+        },
+        {
+          "text": "appris",
+          "start": 23.82,
+          "end": 24.1,
+          "confidence": 0.991
+        },
+        {
+          "text": "à",
+          "start": 24.1,
+          "end": 24.24,
+          "confidence": 0.829
+        },
+        {
+          "text": "cliquer",
+          "start": 24.24,
+          "end": 24.5,
+          "confidence": 0.989
+        },
+        {
+          "text": "sur",
+          "start": 24.5,
+          "end": 24.66,
+          "confidence": 0.984
+        },
+        {
+          "text": "des",
+          "start": 24.66,
+          "end": 24.94,
+          "confidence": 0.971
+        },
+        {
+          "text": "icônes.",
+          "start": 24.94,
+          "end": 25.26,
+          "confidence": 0.992
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 2534,
+      "start": 25.42,
+      "end": 30.64,
+      "text": " Sauf que le smartphone ajoute le toucher, ce qui rend le contact plus direct, plus sensible.",
+      "tokens": [
+        318,
+        9507,
+        631,
+        476,
+        13307,
+        17680,
+        14040,
+        476,
+        2557,
+        260,
+        11,
+        1769,
+        1956,
+        6125,
+        476,
+        3385,
+        1804,
+        2047,
+        11,
+        1804,
+        25380,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07915337880452473,
+      "compression_ratio": 1.6254416961130742,
+      "no_speech_prob": 3.457161710684886e-06,
+      "confidence": 0.969,
+      "words": [
+        {
+          "text": "Sauf",
+          "start": 25.42,
+          "end": 25.76,
+          "confidence": 0.99
+        },
+        {
+          "text": "que",
+          "start": 25.76,
+          "end": 26.26,
+          "confidence": 0.996
+        },
+        {
+          "text": "le",
+          "start": 26.26,
+          "end": 26.66,
+          "confidence": 0.631
+        },
+        {
+          "text": "smartphone",
+          "start": 26.66,
+          "end": 27.06,
+          "confidence": 0.996
+        },
+        {
+          "text": "ajoute",
+          "start": 27.06,
+          "end": 27.44,
+          "confidence": 0.991
+        },
+        {
+          "text": "le",
+          "start": 27.44,
+          "end": 27.62,
+          "confidence": 0.992
+        },
+        {
+          "text": "toucher,",
+          "start": 27.62,
+          "end": 28.18,
+          "confidence": 0.988
+        },
+        {
+          "text": "ce",
+          "start": 28.18,
+          "end": 28.22,
+          "confidence": 0.99
+        },
+        {
+          "text": "qui",
+          "start": 28.22,
+          "end": 28.28,
+          "confidence": 1.0
+        },
+        {
+          "text": "rend",
+          "start": 28.28,
+          "end": 28.48,
+          "confidence": 0.994
+        },
+        {
+          "text": "le",
+          "start": 28.48,
+          "end": 28.68,
+          "confidence": 0.993
+        },
+        {
+          "text": "contact",
+          "start": 28.68,
+          "end": 29.1,
+          "confidence": 0.999
+        },
+        {
+          "text": "plus",
+          "start": 29.1,
+          "end": 29.46,
+          "confidence": 0.985
+        },
+        {
+          "text": "direct,",
+          "start": 29.46,
+          "end": 30.22,
+          "confidence": 0.995
+        },
+        {
+          "text": "plus",
+          "start": 30.22,
+          "end": 30.26,
+          "confidence": 0.994
+        },
+        {
+          "text": "sensible.",
+          "start": 30.26,
+          "end": 30.64,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 2534,
+      "start": 31.04,
+      "end": 37.82,
+      "text": " Et puis évidemment, il faudrait parler aussi des applications qui permettent de contourner le côté touffu de la navigation web pour aller directement au but.",
+      "tokens": [
+        3790,
+        9093,
+        24724,
+        11,
+        1930,
+        38694,
+        8645,
+        16421,
+        6212,
+        730,
+        5821,
+        1956,
+        21540,
+        317,
+        368,
+        21234,
+        1193,
+        476,
+        18437,
+        10095,
+        602,
+        84,
+        368,
+        635,
+        17346,
+        3670,
+        2016,
+        8722,
+        37297,
+        1609,
+        457,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07915337880452473,
+      "compression_ratio": 1.6254416961130742,
+      "no_speech_prob": 3.457161710684886e-06,
+      "confidence": 0.892,
+      "words": [
+        {
+          "text": "Et",
+          "start": 31.04,
+          "end": 31.22,
+          "confidence": 0.97
+        },
+        {
+          "text": "puis",
+          "start": 31.22,
+          "end": 31.36,
+          "confidence": 0.971
+        },
+        {
+          "text": "évidemment,",
+          "start": 31.36,
+          "end": 31.7,
+          "confidence": 0.875
+        },
+        {
+          "text": "il",
+          "start": 31.7,
+          "end": 31.74,
+          "confidence": 0.993
+        },
+        {
+          "text": "faudrait",
+          "start": 31.74,
+          "end": 31.94,
+          "confidence": 0.995
+        },
+        {
+          "text": "parler",
+          "start": 31.94,
+          "end": 32.12,
+          "confidence": 0.84
+        },
+        {
+          "text": "aussi",
+          "start": 32.12,
+          "end": 32.34,
+          "confidence": 0.977
+        },
+        {
+          "text": "des",
+          "start": 32.34,
+          "end": 32.48,
+          "confidence": 0.994
+        },
+        {
+          "text": "applications",
+          "start": 32.48,
+          "end": 32.9,
+          "confidence": 0.993
+        },
+        {
+          "text": "qui",
+          "start": 32.9,
+          "end": 33.18,
+          "confidence": 0.481
+        },
+        {
+          "text": "permettent",
+          "start": 33.18,
+          "end": 33.74,
+          "confidence": 0.992
+        },
+        {
+          "text": "de",
+          "start": 33.74,
+          "end": 33.96,
+          "confidence": 0.885
+        },
+        {
+          "text": "contourner",
+          "start": 33.96,
+          "end": 34.42,
+          "confidence": 0.958
+        },
+        {
+          "text": "le",
+          "start": 34.42,
+          "end": 34.52,
+          "confidence": 0.775
+        },
+        {
+          "text": "côté",
+          "start": 34.52,
+          "end": 34.8,
+          "confidence": 0.984
+        },
+        {
+          "text": "touffu",
+          "start": 34.8,
+          "end": 35.32,
+          "confidence": 0.741
+        },
+        {
+          "text": "de",
+          "start": 35.32,
+          "end": 35.72,
+          "confidence": 0.882
+        },
+        {
+          "text": "la",
+          "start": 35.72,
+          "end": 35.78,
+          "confidence": 0.992
+        },
+        {
+          "text": "navigation",
+          "start": 35.78,
+          "end": 36.24,
+          "confidence": 0.994
+        },
+        {
+          "text": "web",
+          "start": 36.24,
+          "end": 36.6,
+          "confidence": 0.854
+        },
+        {
+          "text": "pour",
+          "start": 36.6,
+          "end": 36.78,
+          "confidence": 0.585
+        },
+        {
+          "text": "aller",
+          "start": 36.78,
+          "end": 36.98,
+          "confidence": 0.987
+        },
+        {
+          "text": "directement",
+          "start": 36.98,
+          "end": 37.52,
+          "confidence": 0.997
+        },
+        {
+          "text": "au",
+          "start": 37.52,
+          "end": 37.68,
+          "confidence": 0.967
+        },
+        {
+          "text": "but.",
+          "start": 37.68,
+          "end": 37.82,
+          "confidence": 0.995
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 2534,
+      "start": 37.82,
+      "end": 46.54,
+      "text": " Bref, tout ça, ce sont les conditions qui permettent de créer cet objet dont Nicolas dit qu'il est vraisemblablement inédit dans l'histoire de l'humanité.",
+      "tokens": [
+        49957,
+        11,
+        3486,
+        2788,
+        11,
+        1769,
+        4900,
+        1512,
+        4487,
+        1956,
+        21540,
+        317,
+        368,
+        32062,
+        8603,
+        14964,
+        9400,
+        38268,
+        6176,
+        421,
+        6,
+        388,
+        871,
+        6070,
+        271,
+        443,
+        5199,
+        712,
+        518,
+        294,
+        7811,
+        270,
+        2680,
+        287,
+        6,
+        29093,
+        368,
+        287,
+        6,
+        18796,
+        5066,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07915337880452473,
+      "compression_ratio": 1.6254416961130742,
+      "no_speech_prob": 3.457161710684886e-06,
+      "confidence": 0.974,
+      "words": [
+        {
+          "text": "Bref,",
+          "start": 37.82,
+          "end": 38.76,
+          "confidence": 0.987
+        },
+        {
+          "text": "tout",
+          "start": 38.76,
+          "end": 38.98,
+          "confidence": 0.711
+        },
+        {
+          "text": "ça,",
+          "start": 38.98,
+          "end": 39.42,
+          "confidence": 0.995
+        },
+        {
+          "text": "ce",
+          "start": 39.42,
+          "end": 39.7,
+          "confidence": 0.993
+        },
+        {
+          "text": "sont",
+          "start": 39.7,
+          "end": 39.88,
+          "confidence": 0.999
+        },
+        {
+          "text": "les",
+          "start": 39.88,
+          "end": 40.16,
+          "confidence": 0.991
+        },
+        {
+          "text": "conditions",
+          "start": 40.16,
+          "end": 40.68,
+          "confidence": 0.995
+        },
+        {
+          "text": "qui",
+          "start": 40.68,
+          "end": 40.96,
+          "confidence": 0.997
+        },
+        {
+          "text": "permettent",
+          "start": 40.96,
+          "end": 41.46,
+          "confidence": 0.997
+        },
+        {
+          "text": "de",
+          "start": 41.46,
+          "end": 41.6,
+          "confidence": 0.998
+        },
+        {
+          "text": "créer",
+          "start": 41.6,
+          "end": 42.06,
+          "confidence": 0.998
+        },
+        {
+          "text": "cet",
+          "start": 42.06,
+          "end": 42.38,
+          "confidence": 0.998
+        },
+        {
+          "text": "objet",
+          "start": 42.38,
+          "end": 42.6,
+          "confidence": 0.994
+        },
+        {
+          "text": "dont",
+          "start": 42.6,
+          "end": 42.8,
+          "confidence": 0.779
+        },
+        {
+          "text": "Nicolas",
+          "start": 42.8,
+          "end": 43.26,
+          "confidence": 0.989
+        },
+        {
+          "text": "dit",
+          "start": 43.26,
+          "end": 43.5,
+          "confidence": 0.986
+        },
+        {
+          "text": "qu'il",
+          "start": 43.5,
+          "end": 43.7,
+          "confidence": 0.983
+        },
+        {
+          "text": "est",
+          "start": 43.7,
+          "end": 43.88,
+          "confidence": 0.991
+        },
+        {
+          "text": "vraisemblablement",
+          "start": 43.88,
+          "end": 44.98,
+          "confidence": 0.991
+        },
+        {
+          "text": "inédit",
+          "start": 44.98,
+          "end": 45.38,
+          "confidence": 0.98
+        },
+        {
+          "text": "dans",
+          "start": 45.38,
+          "end": 45.7,
+          "confidence": 0.969
+        },
+        {
+          "text": "l'histoire",
+          "start": 45.7,
+          "end": 45.98,
+          "confidence": 0.957
+        },
+        {
+          "text": "de",
+          "start": 45.98,
+          "end": 46.18,
+          "confidence": 0.999
+        },
+        {
+          "text": "l'humanité.",
+          "start": 46.18,
+          "end": 46.54,
+          "confidence": 0.992
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 2534,
+      "start": 46.54,
+      "end": 48.82,
+      "text": " Mais ça, ça soulève une autre interrogation.",
+      "tokens": [
+        6313,
+        2788,
+        11,
+        2788,
+        5133,
+        31397,
+        2251,
+        15081,
+        24871,
+        399,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07915337880452473,
+      "compression_ratio": 1.6254416961130742,
+      "no_speech_prob": 3.457161710684886e-06,
+      "confidence": 0.969,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 46.54,
+          "end": 47.24,
+          "confidence": 0.846
+        },
+        {
+          "text": "ça,",
+          "start": 47.24,
+          "end": 47.72,
+          "confidence": 0.935
+        },
+        {
+          "text": "ça",
+          "start": 47.72,
+          "end": 47.76,
+          "confidence": 0.977
+        },
+        {
+          "text": "soulève",
+          "start": 47.76,
+          "end": 47.84,
+          "confidence": 0.993
+        },
+        {
+          "text": "une",
+          "start": 47.84,
+          "end": 48.02,
+          "confidence": 0.998
+        },
+        {
+          "text": "autre",
+          "start": 48.02,
+          "end": 48.26,
+          "confidence": 0.999
+        },
+        {
+          "text": "interrogation.",
+          "start": 48.26,
+          "end": 48.82,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 4884,
+      "start": 49.22,
+      "end": 55.46,
+      "text": " Est-ce que le fait que cet objet soit inédit induit que notre rapport à lui est aussi un rapport inédit?",
+      "tokens": [
+        4410,
+        12,
+        384,
+        631,
+        476,
+        3887,
+        631,
+        8603,
+        14964,
+        12703,
+        294,
+        7811,
+        270,
+        13716,
+        270,
+        631,
+        10349,
+        18018,
+        1531,
+        8783,
+        871,
+        6212,
+        517,
+        18018,
+        294,
+        7811,
+        270,
+        2506
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10746372298689078,
+      "compression_ratio": 1.662379421221865,
+      "no_speech_prob": 1.3105129255563952e-05,
+      "confidence": 0.988,
+      "words": [
+        {
+          "text": "Est-ce",
+          "start": 49.22,
+          "end": 49.62,
+          "confidence": 0.982
+        },
+        {
+          "text": "que",
+          "start": 49.62,
+          "end": 49.72,
+          "confidence": 0.991
+        },
+        {
+          "text": "le",
+          "start": 49.72,
+          "end": 49.82,
+          "confidence": 0.993
+        },
+        {
+          "text": "fait",
+          "start": 49.82,
+          "end": 49.98,
+          "confidence": 0.999
+        },
+        {
+          "text": "que",
+          "start": 49.98,
+          "end": 50.14,
+          "confidence": 0.991
+        },
+        {
+          "text": "cet",
+          "start": 50.14,
+          "end": 50.32,
+          "confidence": 0.991
+        },
+        {
+          "text": "objet",
+          "start": 50.32,
+          "end": 50.66,
+          "confidence": 0.997
+        },
+        {
+          "text": "soit",
+          "start": 50.66,
+          "end": 51.12,
+          "confidence": 0.995
+        },
+        {
+          "text": "inédit",
+          "start": 51.12,
+          "end": 51.8,
+          "confidence": 0.996
+        },
+        {
+          "text": "induit",
+          "start": 51.8,
+          "end": 52.32,
+          "confidence": 0.977
+        },
+        {
+          "text": "que",
+          "start": 52.32,
+          "end": 52.42,
+          "confidence": 0.983
+        },
+        {
+          "text": "notre",
+          "start": 52.42,
+          "end": 52.72,
+          "confidence": 0.996
+        },
+        {
+          "text": "rapport",
+          "start": 52.72,
+          "end": 53.28,
+          "confidence": 0.997
+        },
+        {
+          "text": "à",
+          "start": 53.28,
+          "end": 53.44,
+          "confidence": 0.978
+        },
+        {
+          "text": "lui",
+          "start": 53.44,
+          "end": 53.66,
+          "confidence": 0.999
+        },
+        {
+          "text": "est",
+          "start": 53.66,
+          "end": 54.02,
+          "confidence": 0.916
+        },
+        {
+          "text": "aussi",
+          "start": 54.02,
+          "end": 54.54,
+          "confidence": 0.995
+        },
+        {
+          "text": "un",
+          "start": 54.54,
+          "end": 54.7,
+          "confidence": 0.995
+        },
+        {
+          "text": "rapport",
+          "start": 54.7,
+          "end": 55.0,
+          "confidence": 0.996
+        },
+        {
+          "text": "inédit?",
+          "start": 55.0,
+          "end": 55.46,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 4884,
+      "start": 55.46,
+      "end": 63.12,
+      "text": " Je veux dire, est-ce que le rapport qu'on a au smartphone est comparable à celui qu'on entretenait à d'autres objets techniques comme la voiture ou le téléphone?",
+      "tokens": [
+        2588,
+        16389,
+        1264,
+        11,
+        871,
+        12,
+        384,
+        631,
+        476,
+        18018,
+        421,
+        6,
+        266,
+        257,
+        1609,
+        13307,
+        871,
+        25323,
+        1531,
+        22829,
+        421,
+        6,
+        266,
+        3962,
+        1147,
+        1001,
+        1531,
+        274,
+        6,
+        16752,
+        1111,
+        25349,
+        7512,
+        5173,
+        635,
+        38859,
+        2820,
+        476,
+        47159,
+        2506
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10746372298689078,
+      "compression_ratio": 1.662379421221865,
+      "no_speech_prob": 1.3105129255563952e-05,
+      "confidence": 0.965,
+      "words": [
+        {
+          "text": "Je",
+          "start": 55.46,
+          "end": 55.9,
+          "confidence": 0.88
+        },
+        {
+          "text": "veux",
+          "start": 55.9,
+          "end": 56.0,
+          "confidence": 0.988
+        },
+        {
+          "text": "dire,",
+          "start": 56.0,
+          "end": 56.24,
+          "confidence": 0.997
+        },
+        {
+          "text": "est-ce",
+          "start": 56.24,
+          "end": 56.36,
+          "confidence": 0.99
+        },
+        {
+          "text": "que",
+          "start": 56.36,
+          "end": 56.42,
+          "confidence": 0.99
+        },
+        {
+          "text": "le",
+          "start": 56.42,
+          "end": 56.58,
+          "confidence": 0.995
+        },
+        {
+          "text": "rapport",
+          "start": 56.58,
+          "end": 56.88,
+          "confidence": 0.998
+        },
+        {
+          "text": "qu'on",
+          "start": 56.88,
+          "end": 57.04,
+          "confidence": 0.986
+        },
+        {
+          "text": "a",
+          "start": 57.04,
+          "end": 57.18,
+          "confidence": 0.989
+        },
+        {
+          "text": "au",
+          "start": 57.18,
+          "end": 57.28,
+          "confidence": 0.968
+        },
+        {
+          "text": "smartphone",
+          "start": 57.28,
+          "end": 57.6,
+          "confidence": 0.994
+        },
+        {
+          "text": "est",
+          "start": 57.6,
+          "end": 57.92,
+          "confidence": 0.95
+        },
+        {
+          "text": "comparable",
+          "start": 57.92,
+          "end": 58.24,
+          "confidence": 0.997
+        },
+        {
+          "text": "à",
+          "start": 58.24,
+          "end": 58.48,
+          "confidence": 0.949
+        },
+        {
+          "text": "celui",
+          "start": 58.48,
+          "end": 58.66,
+          "confidence": 0.998
+        },
+        {
+          "text": "qu'on",
+          "start": 58.66,
+          "end": 58.9,
+          "confidence": 0.989
+        },
+        {
+          "text": "entretenait",
+          "start": 58.9,
+          "end": 59.32,
+          "confidence": 0.929
+        },
+        {
+          "text": "à",
+          "start": 59.32,
+          "end": 59.46,
+          "confidence": 0.958
+        },
+        {
+          "text": "d'autres",
+          "start": 59.46,
+          "end": 59.7,
+          "confidence": 0.997
+        },
+        {
+          "text": "objets",
+          "start": 59.7,
+          "end": 59.96,
+          "confidence": 0.991
+        },
+        {
+          "text": "techniques",
+          "start": 59.96,
+          "end": 60.46,
+          "confidence": 0.983
+        },
+        {
+          "text": "comme",
+          "start": 60.46,
+          "end": 60.88,
+          "confidence": 0.587
+        },
+        {
+          "text": "la",
+          "start": 60.88,
+          "end": 61.5,
+          "confidence": 0.987
+        },
+        {
+          "text": "voiture",
+          "start": 61.5,
+          "end": 62.06,
+          "confidence": 1.0
+        },
+        {
+          "text": "ou",
+          "start": 62.06,
+          "end": 62.36,
+          "confidence": 0.945
+        },
+        {
+          "text": "le",
+          "start": 62.36,
+          "end": 62.68,
+          "confidence": 0.998
+        },
+        {
+          "text": "téléphone?",
+          "start": 62.68,
+          "end": 63.12,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 4884,
+      "start": 63.36,
+      "end": 66.66,
+      "text": " Il n'y a pas d'équivalent en fait.",
+      "tokens": [
+        4416,
+        297,
+        6,
+        88,
+        257,
+        1736,
+        274,
+        6,
+        20183,
+        3576,
+        317,
+        465,
+        3887,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10746372298689078,
+      "compression_ratio": 1.662379421221865,
+      "no_speech_prob": 1.3105129255563952e-05,
+      "confidence": 0.936,
+      "words": [
+        {
+          "text": "Il",
+          "start": 63.36,
+          "end": 65.42,
+          "confidence": 0.779
+        },
+        {
+          "text": "n'y",
+          "start": 65.42,
+          "end": 65.48,
+          "confidence": 0.978
+        },
+        {
+          "text": "a",
+          "start": 65.48,
+          "end": 65.54,
+          "confidence": 0.992
+        },
+        {
+          "text": "pas",
+          "start": 65.54,
+          "end": 65.66,
+          "confidence": 0.999
+        },
+        {
+          "text": "d'équivalent",
+          "start": 65.66,
+          "end": 66.22,
+          "confidence": 0.995
+        },
+        {
+          "text": "en",
+          "start": 66.22,
+          "end": 66.42,
+          "confidence": 0.601
+        },
+        {
+          "text": "fait.",
+          "start": 66.42,
+          "end": 66.66,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 4884,
+      "start": 66.88,
+      "end": 71.52,
+      "text": " Et donc cette espèce de nouveauté dans la relation à l'objet, c'est fascinant et terrifiant.",
+      "tokens": [
+        3790,
+        5926,
+        5550,
+        7089,
+        30236,
+        368,
+        11456,
+        1375,
+        526,
+        2680,
+        635,
+        9721,
+        1531,
+        287,
+        6,
+        996,
+        7108,
+        11,
+        269,
+        6,
+        377,
+        7184,
+        259,
+        394,
+        1030,
+        7245,
+        351,
+        5798,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10746372298689078,
+      "compression_ratio": 1.662379421221865,
+      "no_speech_prob": 1.3105129255563952e-05,
+      "confidence": 0.953,
+      "words": [
+        {
+          "text": "Et",
+          "start": 66.88,
+          "end": 66.98,
+          "confidence": 0.599
+        },
+        {
+          "text": "donc",
+          "start": 66.98,
+          "end": 67.08,
+          "confidence": 0.901
+        },
+        {
+          "text": "cette",
+          "start": 67.08,
+          "end": 67.28,
+          "confidence": 0.71
+        },
+        {
+          "text": "espèce",
+          "start": 67.28,
+          "end": 67.54,
+          "confidence": 0.995
+        },
+        {
+          "text": "de",
+          "start": 67.54,
+          "end": 67.68,
+          "confidence": 0.999
+        },
+        {
+          "text": "nouveauté",
+          "start": 67.68,
+          "end": 68.48,
+          "confidence": 0.979
+        },
+        {
+          "text": "dans",
+          "start": 68.48,
+          "end": 68.66,
+          "confidence": 0.98
+        },
+        {
+          "text": "la",
+          "start": 68.66,
+          "end": 68.94,
+          "confidence": 0.995
+        },
+        {
+          "text": "relation",
+          "start": 68.94,
+          "end": 69.22,
+          "confidence": 0.998
+        },
+        {
+          "text": "à",
+          "start": 69.22,
+          "end": 69.38,
+          "confidence": 0.997
+        },
+        {
+          "text": "l'objet,",
+          "start": 69.38,
+          "end": 70.24,
+          "confidence": 0.997
+        },
+        {
+          "text": "c'est",
+          "start": 70.24,
+          "end": 70.38,
+          "confidence": 0.98
+        },
+        {
+          "text": "fascinant",
+          "start": 70.38,
+          "end": 70.64,
+          "confidence": 0.978
+        },
+        {
+          "text": "et",
+          "start": 70.64,
+          "end": 70.76,
+          "confidence": 0.964
+        },
+        {
+          "text": "terrifiant.",
+          "start": 70.76,
+          "end": 71.52,
+          "confidence": 0.977
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 4884,
+      "start": 71.62,
+      "end": 76.48,
+      "text": " Parce qu'on a l'impression, comme le disent les utilisateurs et les services, d'être dépendants de cet objet,",
+      "tokens": [
+        20429,
+        421,
+        6,
+        266,
+        257,
+        287,
+        6,
+        36107,
+        11,
+        5173,
+        476,
+        37313,
+        1512,
+        33643,
+        25929,
+        1030,
+        1512,
+        3328,
+        11,
+        274,
+        6,
+        9498,
+        45768,
+        1719,
+        368,
+        8603,
+        14964,
+        11
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10746372298689078,
+      "compression_ratio": 1.662379421221865,
+      "no_speech_prob": 1.3105129255563952e-05,
+      "confidence": 0.813,
+      "words": [
+        {
+          "text": "Parce",
+          "start": 71.62,
+          "end": 71.86,
+          "confidence": 0.512
+        },
+        {
+          "text": "qu'on",
+          "start": 71.86,
+          "end": 72.12,
+          "confidence": 0.937
+        },
+        {
+          "text": "a",
+          "start": 72.12,
+          "end": 72.44,
+          "confidence": 0.982
+        },
+        {
+          "text": "l'impression,",
+          "start": 72.44,
+          "end": 73.56,
+          "confidence": 0.998
+        },
+        {
+          "text": "comme",
+          "start": 73.56,
+          "end": 73.84,
+          "confidence": 0.964
+        },
+        {
+          "text": "le",
+          "start": 73.84,
+          "end": 74.0,
+          "confidence": 0.984
+        },
+        {
+          "text": "disent",
+          "start": 74.0,
+          "end": 74.2,
+          "confidence": 0.998
+        },
+        {
+          "text": "les",
+          "start": 74.2,
+          "end": 74.4,
+          "confidence": 0.994
+        },
+        {
+          "text": "utilisateurs",
+          "start": 74.4,
+          "end": 74.84,
+          "confidence": 0.997
+        },
+        {
+          "text": "et",
+          "start": 74.84,
+          "end": 74.96,
+          "confidence": 0.329
+        },
+        {
+          "text": "les",
+          "start": 74.96,
+          "end": 75.0,
+          "confidence": 0.773
+        },
+        {
+          "text": "services,",
+          "start": 75.0,
+          "end": 75.22,
+          "confidence": 0.214
+        },
+        {
+          "text": "d'être",
+          "start": 75.22,
+          "end": 75.42,
+          "confidence": 0.766
+        },
+        {
+          "text": "dépendants",
+          "start": 75.42,
+          "end": 75.96,
+          "confidence": 0.789
+        },
+        {
+          "text": "de",
+          "start": 75.96,
+          "end": 76.08,
+          "confidence": 0.986
+        },
+        {
+          "text": "cet",
+          "start": 76.08,
+          "end": 76.26,
+          "confidence": 0.996
+        },
+        {
+          "text": "objet,",
+          "start": 76.26,
+          "end": 76.48,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 7684,
+      "start": 76.86,
+      "end": 83.26,
+      "text": " d'induire en fait une espèce de relation, de médiation avec le monde qui rend de l'ampleur et qui amène aussi à des formes de rejet.",
+      "tokens": [
+        274,
+        6,
+        471,
+        43612,
+        465,
+        3887,
+        2251,
+        7089,
+        30236,
+        368,
+        9721,
+        11,
+        368,
+        42436,
+        399,
+        4163,
+        476,
+        10431,
+        1956,
+        6125,
+        368,
+        287,
+        6,
+        335,
+        781,
+        374,
+        1030,
+        1956,
+        669,
+        18832,
+        6212,
+        1531,
+        730,
+        1254,
+        279,
+        368,
+        319,
+        7108,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06937986261704389,
+      "compression_ratio": 1.6787003610108304,
+      "no_speech_prob": 5.948771558905719e-06,
+      "confidence": 0.917,
+      "words": [
+        {
+          "text": "d'induire",
+          "start": 76.86,
+          "end": 77.08,
+          "confidence": 0.841
+        },
+        {
+          "text": "en",
+          "start": 77.08,
+          "end": 77.24,
+          "confidence": 0.618
+        },
+        {
+          "text": "fait",
+          "start": 77.24,
+          "end": 77.34,
+          "confidence": 0.994
+        },
+        {
+          "text": "une",
+          "start": 77.34,
+          "end": 77.52,
+          "confidence": 0.983
+        },
+        {
+          "text": "espèce",
+          "start": 77.52,
+          "end": 77.88,
+          "confidence": 0.996
+        },
+        {
+          "text": "de",
+          "start": 77.88,
+          "end": 78.48,
+          "confidence": 0.997
+        },
+        {
+          "text": "relation,",
+          "start": 78.48,
+          "end": 78.6,
+          "confidence": 0.596
+        },
+        {
+          "text": "de",
+          "start": 78.6,
+          "end": 78.94,
+          "confidence": 0.987
+        },
+        {
+          "text": "médiation",
+          "start": 78.94,
+          "end": 79.52,
+          "confidence": 0.997
+        },
+        {
+          "text": "avec",
+          "start": 79.52,
+          "end": 79.74,
+          "confidence": 0.967
+        },
+        {
+          "text": "le",
+          "start": 79.74,
+          "end": 79.92,
+          "confidence": 0.998
+        },
+        {
+          "text": "monde",
+          "start": 79.92,
+          "end": 80.64,
+          "confidence": 0.992
+        },
+        {
+          "text": "qui",
+          "start": 80.64,
+          "end": 81.1,
+          "confidence": 0.696
+        },
+        {
+          "text": "rend",
+          "start": 81.1,
+          "end": 81.64,
+          "confidence": 0.91
+        },
+        {
+          "text": "de",
+          "start": 81.64,
+          "end": 81.78,
+          "confidence": 0.712
+        },
+        {
+          "text": "l'ampleur",
+          "start": 81.78,
+          "end": 82.02,
+          "confidence": 0.987
+        },
+        {
+          "text": "et",
+          "start": 82.02,
+          "end": 82.12,
+          "confidence": 0.931
+        },
+        {
+          "text": "qui",
+          "start": 82.12,
+          "end": 82.24,
+          "confidence": 0.976
+        },
+        {
+          "text": "amène",
+          "start": 82.24,
+          "end": 82.36,
+          "confidence": 0.973
+        },
+        {
+          "text": "aussi",
+          "start": 82.36,
+          "end": 82.56,
+          "confidence": 0.938
+        },
+        {
+          "text": "à",
+          "start": 82.56,
+          "end": 82.62,
+          "confidence": 0.941
+        },
+        {
+          "text": "des",
+          "start": 82.62,
+          "end": 82.72,
+          "confidence": 0.992
+        },
+        {
+          "text": "formes",
+          "start": 82.72,
+          "end": 82.9,
+          "confidence": 0.993
+        },
+        {
+          "text": "de",
+          "start": 82.9,
+          "end": 83.02,
+          "confidence": 0.998
+        },
+        {
+          "text": "rejet.",
+          "start": 83.02,
+          "end": 83.26,
+          "confidence": 0.883
+        }
+      ]
+    },
+    {
+      "id": 17,
+      "seek": 7684,
+      "start": 83.94,
+      "end": 87.8,
+      "text": " Donc, à objet inédit, rapport inédit.",
+      "tokens": [
+        7477,
+        11,
+        1531,
+        14964,
+        294,
+        7811,
+        270,
+        11,
+        18018,
+        294,
+        7811,
+        270,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06937986261704389,
+      "compression_ratio": 1.6787003610108304,
+      "no_speech_prob": 5.948771558905719e-06,
+      "confidence": 0.962,
+      "words": [
+        {
+          "text": "Donc,",
+          "start": 83.94,
+          "end": 84.94,
+          "confidence": 0.971
+        },
+        {
+          "text": "à",
+          "start": 84.94,
+          "end": 84.98,
+          "confidence": 0.88
+        },
+        {
+          "text": "objet",
+          "start": 84.98,
+          "end": 85.36,
+          "confidence": 0.828
+        },
+        {
+          "text": "inédit,",
+          "start": 85.36,
+          "end": 86.56,
+          "confidence": 0.993
+        },
+        {
+          "text": "rapport",
+          "start": 86.56,
+          "end": 87.0,
+          "confidence": 0.981
+        },
+        {
+          "text": "inédit.",
+          "start": 87.0,
+          "end": 87.8,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 18,
+      "seek": 7684,
+      "start": 88.02,
+      "end": 95.14,
+      "text": " Et ce rapport, si j'en crois Nicolas, serait caractérisé par un mélange de dépendance et de rejet.",
+      "tokens": [
+        3790,
+        1769,
+        18018,
+        11,
+        1511,
+        361,
+        6,
+        268,
+        21724,
+        38268,
+        11,
+        23139,
+        1032,
+        578,
+        4198,
+        22118,
+        971,
+        517,
+        41953,
+        933,
+        368,
+        45768,
+        719,
+        1030,
+        368,
+        319,
+        7108,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06937986261704389,
+      "compression_ratio": 1.6787003610108304,
+      "no_speech_prob": 5.948771558905719e-06,
+      "confidence": 0.972,
+      "words": [
+        {
+          "text": "Et",
+          "start": 88.02,
+          "end": 88.48,
+          "confidence": 0.992
+        },
+        {
+          "text": "ce",
+          "start": 88.48,
+          "end": 88.86,
+          "confidence": 0.975
+        },
+        {
+          "text": "rapport,",
+          "start": 88.86,
+          "end": 89.28,
+          "confidence": 0.998
+        },
+        {
+          "text": "si",
+          "start": 89.28,
+          "end": 89.56,
+          "confidence": 0.999
+        },
+        {
+          "text": "j'en",
+          "start": 89.56,
+          "end": 89.84,
+          "confidence": 0.996
+        },
+        {
+          "text": "crois",
+          "start": 89.84,
+          "end": 89.88,
+          "confidence": 0.984
+        },
+        {
+          "text": "Nicolas,",
+          "start": 89.88,
+          "end": 90.54,
+          "confidence": 0.681
+        },
+        {
+          "text": "serait",
+          "start": 90.54,
+          "end": 90.94,
+          "confidence": 0.885
+        },
+        {
+          "text": "caractérisé",
+          "start": 90.94,
+          "end": 91.8,
+          "confidence": 0.993
+        },
+        {
+          "text": "par",
+          "start": 91.8,
+          "end": 92.12,
+          "confidence": 0.997
+        },
+        {
+          "text": "un",
+          "start": 92.12,
+          "end": 92.44,
+          "confidence": 0.997
+        },
+        {
+          "text": "mélange",
+          "start": 92.44,
+          "end": 92.98,
+          "confidence": 0.999
+        },
+        {
+          "text": "de",
+          "start": 92.98,
+          "end": 93.4,
+          "confidence": 0.998
+        },
+        {
+          "text": "dépendance",
+          "start": 93.4,
+          "end": 94.24,
+          "confidence": 0.953
+        },
+        {
+          "text": "et",
+          "start": 94.24,
+          "end": 94.54,
+          "confidence": 0.998
+        },
+        {
+          "text": "de",
+          "start": 94.54,
+          "end": 94.68,
+          "confidence": 0.999
+        },
+        {
+          "text": "rejet.",
+          "start": 94.68,
+          "end": 95.14,
+          "confidence": 0.993
+        }
+      ]
+    },
+    {
+      "id": 19,
+      "seek": 7684,
+      "start": 95.78,
+      "end": 102.86,
+      "text": " Bon, en vrai, il faudrait remonter très très finement toute l'histoire des objets techniques et de leur insertion dans nos vies",
+      "tokens": [
+        7368,
+        11,
+        465,
+        17815,
+        11,
+        1930,
+        38694,
+        8645,
+        890,
+        41806,
+        5732,
+        5732,
+        962,
+        1712,
+        14953,
+        287,
+        6,
+        29093,
+        730,
+        1111,
+        25349,
+        7512,
+        1030,
+        368,
+        9580,
+        8969,
+        313,
+        2680,
+        3269,
+        371,
+        530
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06937986261704389,
+      "compression_ratio": 1.6787003610108304,
+      "no_speech_prob": 5.948771558905719e-06,
+      "confidence": 0.941,
+      "words": [
+        {
+          "text": "Bon,",
+          "start": 95.78,
+          "end": 96.38,
+          "confidence": 0.792
+        },
+        {
+          "text": "en",
+          "start": 96.38,
+          "end": 96.52,
+          "confidence": 0.998
+        },
+        {
+          "text": "vrai,",
+          "start": 96.52,
+          "end": 97.14,
+          "confidence": 0.994
+        },
+        {
+          "text": "il",
+          "start": 97.14,
+          "end": 97.18,
+          "confidence": 0.998
+        },
+        {
+          "text": "faudrait",
+          "start": 97.18,
+          "end": 97.58,
+          "confidence": 0.997
+        },
+        {
+          "text": "remonter",
+          "start": 97.58,
+          "end": 98.08,
+          "confidence": 0.997
+        },
+        {
+          "text": "très",
+          "start": 98.08,
+          "end": 98.6,
+          "confidence": 0.997
+        },
+        {
+          "text": "très",
+          "start": 98.6,
+          "end": 98.7,
+          "confidence": 0.768
+        },
+        {
+          "text": "finement",
+          "start": 98.7,
+          "end": 99.32,
+          "confidence": 0.849
+        },
+        {
+          "text": "toute",
+          "start": 99.32,
+          "end": 99.7,
+          "confidence": 0.984
+        },
+        {
+          "text": "l'histoire",
+          "start": 99.7,
+          "end": 100.06,
+          "confidence": 0.997
+        },
+        {
+          "text": "des",
+          "start": 100.06,
+          "end": 100.24,
+          "confidence": 0.998
+        },
+        {
+          "text": "objets",
+          "start": 100.24,
+          "end": 100.48,
+          "confidence": 0.999
+        },
+        {
+          "text": "techniques",
+          "start": 100.48,
+          "end": 101.02,
+          "confidence": 0.984
+        },
+        {
+          "text": "et",
+          "start": 101.02,
+          "end": 101.48,
+          "confidence": 0.527
+        },
+        {
+          "text": "de",
+          "start": 101.48,
+          "end": 101.68,
+          "confidence": 0.994
+        },
+        {
+          "text": "leur",
+          "start": 101.68,
+          "end": 101.84,
+          "confidence": 0.833
+        },
+        {
+          "text": "insertion",
+          "start": 101.84,
+          "end": 102.32,
+          "confidence": 0.994
+        },
+        {
+          "text": "dans",
+          "start": 102.32,
+          "end": 102.48,
+          "confidence": 0.99
+        },
+        {
+          "text": "nos",
+          "start": 102.48,
+          "end": 102.66,
+          "confidence": 0.998
+        },
+        {
+          "text": "vies",
+          "start": 102.66,
+          "end": 102.86,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 20,
+      "seek": 7684,
+      "start": 102.9,
+      "end": 105.74,
+      "text": " pour déterminer si ce rapport est totalement inédit.",
+      "tokens": [
+        2016,
+        2795,
+        29725,
+        260,
+        1511,
+        1769,
+        18018,
+        871,
+        45203,
+        294,
+        7811,
+        270,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06937986261704389,
+      "compression_ratio": 1.6787003610108304,
+      "no_speech_prob": 5.948771558905719e-06,
+      "confidence": 0.981,
+      "words": [
+        {
+          "text": "pour",
+          "start": 102.9,
+          "end": 103.06,
+          "confidence": 0.822
+        },
+        {
+          "text": "déterminer",
+          "start": 103.06,
+          "end": 103.66,
+          "confidence": 0.997
+        },
+        {
+          "text": "si",
+          "start": 103.66,
+          "end": 103.76,
+          "confidence": 0.992
+        },
+        {
+          "text": "ce",
+          "start": 103.76,
+          "end": 103.94,
+          "confidence": 0.997
+        },
+        {
+          "text": "rapport",
+          "start": 103.94,
+          "end": 104.26,
+          "confidence": 0.997
+        },
+        {
+          "text": "est",
+          "start": 104.26,
+          "end": 104.74,
+          "confidence": 0.998
+        },
+        {
+          "text": "totalement",
+          "start": 104.74,
+          "end": 105.3,
+          "confidence": 0.999
+        },
+        {
+          "text": "inédit.",
+          "start": 105.3,
+          "end": 105.74,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 21,
+      "seek": 10584,
+      "start": 106.1,
+      "end": 109.34,
+      "text": " Mais j'ai l'impression comme ça que Nicolas ne se trompe pas vraiment.",
+      "tokens": [
+        6313,
+        361,
+        6,
+        1301,
+        287,
+        6,
+        36107,
+        5173,
+        2788,
+        631,
+        38268,
+        408,
+        369,
+        504,
+        298,
+        494,
+        1736,
+        8322,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07386374800172571,
+      "compression_ratio": 1.685512367491166,
+      "no_speech_prob": 5.46344235772267e-05,
+      "confidence": 0.94,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 106.1,
+          "end": 106.36,
+          "confidence": 0.947
+        },
+        {
+          "text": "j'ai",
+          "start": 106.36,
+          "end": 106.92,
+          "confidence": 0.941
+        },
+        {
+          "text": "l'impression",
+          "start": 106.92,
+          "end": 107.36,
+          "confidence": 0.996
+        },
+        {
+          "text": "comme",
+          "start": 107.36,
+          "end": 107.56,
+          "confidence": 0.641
+        },
+        {
+          "text": "ça",
+          "start": 107.56,
+          "end": 107.82,
+          "confidence": 0.978
+        },
+        {
+          "text": "que",
+          "start": 107.82,
+          "end": 107.96,
+          "confidence": 0.976
+        },
+        {
+          "text": "Nicolas",
+          "start": 107.96,
+          "end": 108.46,
+          "confidence": 0.985
+        },
+        {
+          "text": "ne",
+          "start": 108.46,
+          "end": 108.66,
+          "confidence": 0.726
+        },
+        {
+          "text": "se",
+          "start": 108.66,
+          "end": 108.7,
+          "confidence": 0.991
+        },
+        {
+          "text": "trompe",
+          "start": 108.7,
+          "end": 108.88,
+          "confidence": 0.995
+        },
+        {
+          "text": "pas",
+          "start": 108.88,
+          "end": 109.08,
+          "confidence": 0.999
+        },
+        {
+          "text": "vraiment.",
+          "start": 109.08,
+          "end": 109.34,
+          "confidence": 0.991
+        }
+      ]
+    },
+    {
+      "id": 22,
+      "seek": 10584,
+      "start": 109.88,
+      "end": 114.98,
+      "text": " Pour autant que je sache, il y a eu plein de discussions autour de la voiture ou même du téléphone.",
+      "tokens": [
+        8732,
+        34081,
+        631,
+        1506,
+        262,
+        6000,
+        11,
+        1930,
+        288,
+        257,
+        2228,
+        21088,
+        368,
+        11088,
+        30249,
+        368,
+        635,
+        38859,
+        2820,
+        5698,
+        1581,
+        47159,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07386374800172571,
+      "compression_ratio": 1.685512367491166,
+      "no_speech_prob": 5.46344235772267e-05,
+      "confidence": 0.969,
+      "words": [
+        {
+          "text": "Pour",
+          "start": 109.88,
+          "end": 110.08,
+          "confidence": 0.997
+        },
+        {
+          "text": "autant",
+          "start": 110.08,
+          "end": 110.24,
+          "confidence": 1.0
+        },
+        {
+          "text": "que",
+          "start": 110.24,
+          "end": 110.42,
+          "confidence": 0.988
+        },
+        {
+          "text": "je",
+          "start": 110.42,
+          "end": 110.52,
+          "confidence": 0.998
+        },
+        {
+          "text": "sache,",
+          "start": 110.52,
+          "end": 111.14,
+          "confidence": 0.963
+        },
+        {
+          "text": "il",
+          "start": 111.14,
+          "end": 111.18,
+          "confidence": 0.997
+        },
+        {
+          "text": "y",
+          "start": 111.18,
+          "end": 111.32,
+          "confidence": 0.992
+        },
+        {
+          "text": "a",
+          "start": 111.32,
+          "end": 111.36,
+          "confidence": 0.993
+        },
+        {
+          "text": "eu",
+          "start": 111.36,
+          "end": 111.68,
+          "confidence": 0.998
+        },
+        {
+          "text": "plein",
+          "start": 111.68,
+          "end": 111.88,
+          "confidence": 0.974
+        },
+        {
+          "text": "de",
+          "start": 111.88,
+          "end": 112.06,
+          "confidence": 0.997
+        },
+        {
+          "text": "discussions",
+          "start": 112.06,
+          "end": 112.6,
+          "confidence": 0.799
+        },
+        {
+          "text": "autour",
+          "start": 112.6,
+          "end": 112.94,
+          "confidence": 0.995
+        },
+        {
+          "text": "de",
+          "start": 112.94,
+          "end": 113.46,
+          "confidence": 0.997
+        },
+        {
+          "text": "la",
+          "start": 113.46,
+          "end": 113.52,
+          "confidence": 0.998
+        },
+        {
+          "text": "voiture",
+          "start": 113.52,
+          "end": 113.86,
+          "confidence": 1.0
+        },
+        {
+          "text": "ou",
+          "start": 113.86,
+          "end": 114.06,
+          "confidence": 0.765
+        },
+        {
+          "text": "même",
+          "start": 114.06,
+          "end": 114.44,
+          "confidence": 0.996
+        },
+        {
+          "text": "du",
+          "start": 114.44,
+          "end": 114.6,
+          "confidence": 0.995
+        },
+        {
+          "text": "téléphone.",
+          "start": 114.6,
+          "end": 114.98,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 23,
+      "seek": 10584,
+      "start": 115.34,
+      "end": 119.84,
+      "text": " Mais la dépendance n'était pas du même ordre. Donc le rejet non plus n'était pas du même ordre.",
+      "tokens": [
+        6313,
+        635,
+        45768,
+        719,
+        297,
+        6,
+        9743,
+        1736,
+        1581,
+        5698,
+        4792,
+        265,
+        13,
+        7477,
+        476,
+        319,
+        7108,
+        2107,
+        1804,
+        297,
+        6,
+        9743,
+        1736,
+        1581,
+        5698,
+        4792,
+        265,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07386374800172571,
+      "compression_ratio": 1.685512367491166,
+      "no_speech_prob": 5.46344235772267e-05,
+      "confidence": 0.972,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 115.34,
+          "end": 115.72,
+          "confidence": 0.994
+        },
+        {
+          "text": "la",
+          "start": 115.72,
+          "end": 116.02,
+          "confidence": 0.937
+        },
+        {
+          "text": "dépendance",
+          "start": 116.02,
+          "end": 116.4,
+          "confidence": 0.997
+        },
+        {
+          "text": "n'était",
+          "start": 116.4,
+          "end": 116.62,
+          "confidence": 0.994
+        },
+        {
+          "text": "pas",
+          "start": 116.62,
+          "end": 117.0,
+          "confidence": 0.998
+        },
+        {
+          "text": "du",
+          "start": 117.0,
+          "end": 117.16,
+          "confidence": 0.995
+        },
+        {
+          "text": "même",
+          "start": 117.16,
+          "end": 117.46,
+          "confidence": 0.999
+        },
+        {
+          "text": "ordre.",
+          "start": 117.46,
+          "end": 117.78,
+          "confidence": 0.999
+        },
+        {
+          "text": "Donc",
+          "start": 117.78,
+          "end": 117.98,
+          "confidence": 0.804
+        },
+        {
+          "text": "le",
+          "start": 117.98,
+          "end": 118.34,
+          "confidence": 0.715
+        },
+        {
+          "text": "rejet",
+          "start": 118.34,
+          "end": 118.62,
+          "confidence": 0.999
+        },
+        {
+          "text": "non",
+          "start": 118.62,
+          "end": 118.78,
+          "confidence": 0.975
+        },
+        {
+          "text": "plus",
+          "start": 118.78,
+          "end": 118.94,
+          "confidence": 0.996
+        },
+        {
+          "text": "n'était",
+          "start": 118.94,
+          "end": 119.12,
+          "confidence": 0.987
+        },
+        {
+          "text": "pas",
+          "start": 119.12,
+          "end": 119.3,
+          "confidence": 0.998
+        },
+        {
+          "text": "du",
+          "start": 119.3,
+          "end": 119.38,
+          "confidence": 0.995
+        },
+        {
+          "text": "même",
+          "start": 119.38,
+          "end": 119.56,
+          "confidence": 0.999
+        },
+        {
+          "text": "ordre.",
+          "start": 119.56,
+          "end": 119.84,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 24,
+      "seek": 10584,
+      "start": 119.98,
+      "end": 123.02,
+      "text": " On peut adorer sa bagnole, en avoir besoin pour plein de choses.",
+      "tokens": [
+        1282,
+        5977,
+        614,
+        17618,
+        601,
+        3411,
+        1771,
+        306,
+        11,
+        465,
+        10853,
+        19207,
+        2016,
+        21088,
+        368,
+        14488,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07386374800172571,
+      "compression_ratio": 1.685512367491166,
+      "no_speech_prob": 5.46344235772267e-05,
+      "confidence": 0.991,
+      "words": [
+        {
+          "text": "On",
+          "start": 119.98,
+          "end": 120.18,
+          "confidence": 0.996
+        },
+        {
+          "text": "peut",
+          "start": 120.18,
+          "end": 120.38,
+          "confidence": 0.997
+        },
+        {
+          "text": "adorer",
+          "start": 120.38,
+          "end": 120.66,
+          "confidence": 0.99
+        },
+        {
+          "text": "sa",
+          "start": 120.66,
+          "end": 120.88,
+          "confidence": 0.985
+        },
+        {
+          "text": "bagnole,",
+          "start": 120.88,
+          "end": 121.46,
+          "confidence": 0.984
+        },
+        {
+          "text": "en",
+          "start": 121.46,
+          "end": 121.56,
+          "confidence": 0.989
+        },
+        {
+          "text": "avoir",
+          "start": 121.56,
+          "end": 121.74,
+          "confidence": 0.998
+        },
+        {
+          "text": "besoin",
+          "start": 121.74,
+          "end": 122.1,
+          "confidence": 0.999
+        },
+        {
+          "text": "pour",
+          "start": 122.1,
+          "end": 122.34,
+          "confidence": 0.987
+        },
+        {
+          "text": "plein",
+          "start": 122.34,
+          "end": 122.68,
+          "confidence": 0.989
+        },
+        {
+          "text": "de",
+          "start": 122.68,
+          "end": 122.8,
+          "confidence": 0.998
+        },
+        {
+          "text": "choses.",
+          "start": 122.8,
+          "end": 123.02,
+          "confidence": 0.989
+        }
+      ]
+    },
+    {
+      "id": 25,
+      "seek": 10584,
+      "start": 123.28,
+      "end": 126.36,
+      "text": " Et bien, le soir, quand on va se coucher, on la laisse.",
+      "tokens": [
+        3790,
+        3610,
+        11,
+        476,
+        27105,
+        11,
+        6932,
+        322,
+        2773,
+        369,
+        1384,
+        6759,
+        11,
+        322,
+        635,
+        30969,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07386374800172571,
+      "compression_ratio": 1.685512367491166,
+      "no_speech_prob": 5.46344235772267e-05,
+      "confidence": 0.895,
+      "words": [
+        {
+          "text": "Et",
+          "start": 123.28,
+          "end": 123.46,
+          "confidence": 0.667
+        },
+        {
+          "text": "bien,",
+          "start": 123.46,
+          "end": 123.86,
+          "confidence": 0.469
+        },
+        {
+          "text": "le",
+          "start": 123.86,
+          "end": 123.98,
+          "confidence": 0.996
+        },
+        {
+          "text": "soir,",
+          "start": 123.98,
+          "end": 124.68,
+          "confidence": 0.999
+        },
+        {
+          "text": "quand",
+          "start": 124.68,
+          "end": 124.9,
+          "confidence": 0.997
+        },
+        {
+          "text": "on",
+          "start": 124.9,
+          "end": 125.02,
+          "confidence": 0.998
+        },
+        {
+          "text": "va",
+          "start": 125.02,
+          "end": 125.14,
+          "confidence": 0.996
+        },
+        {
+          "text": "se",
+          "start": 125.14,
+          "end": 125.38,
+          "confidence": 0.988
+        },
+        {
+          "text": "coucher,",
+          "start": 125.38,
+          "end": 125.8,
+          "confidence": 0.987
+        },
+        {
+          "text": "on",
+          "start": 125.8,
+          "end": 126.02,
+          "confidence": 0.995
+        },
+        {
+          "text": "la",
+          "start": 126.02,
+          "end": 126.22,
+          "confidence": 0.802
+        },
+        {
+          "text": "laisse.",
+          "start": 126.22,
+          "end": 126.36,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 26,
+      "seek": 10584,
+      "start": 126.98,
+      "end": 130.48,
+      "text": " On ne l'a pas dans la main quand on est au lit, on ne l'emmène pas au chiottes.",
+      "tokens": [
+        1282,
+        408,
+        287,
+        6,
+        64,
+        1736,
+        2680,
+        635,
+        2135,
+        6932,
+        322,
+        871,
+        1609,
+        7997,
+        11,
+        322,
+        408,
+        287,
+        6,
+        443,
+        76,
+        18832,
+        1736,
+        1609,
+        13228,
+        1521,
+        279,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07386374800172571,
+      "compression_ratio": 1.685512367491166,
+      "no_speech_prob": 5.46344235772267e-05,
+      "confidence": 0.914,
+      "words": [
+        {
+          "text": "On",
+          "start": 126.98,
+          "end": 127.32,
+          "confidence": 0.954
+        },
+        {
+          "text": "ne",
+          "start": 127.32,
+          "end": 127.36,
+          "confidence": 0.803
+        },
+        {
+          "text": "l'a",
+          "start": 127.36,
+          "end": 127.48,
+          "confidence": 0.974
+        },
+        {
+          "text": "pas",
+          "start": 127.48,
+          "end": 127.68,
+          "confidence": 0.999
+        },
+        {
+          "text": "dans",
+          "start": 127.68,
+          "end": 127.8,
+          "confidence": 0.996
+        },
+        {
+          "text": "la",
+          "start": 127.8,
+          "end": 128.06,
+          "confidence": 0.994
+        },
+        {
+          "text": "main",
+          "start": 128.06,
+          "end": 128.26,
+          "confidence": 0.999
+        },
+        {
+          "text": "quand",
+          "start": 128.26,
+          "end": 128.44,
+          "confidence": 0.935
+        },
+        {
+          "text": "on",
+          "start": 128.44,
+          "end": 128.62,
+          "confidence": 0.997
+        },
+        {
+          "text": "est",
+          "start": 128.62,
+          "end": 128.68,
+          "confidence": 0.993
+        },
+        {
+          "text": "au",
+          "start": 128.68,
+          "end": 129.04,
+          "confidence": 0.984
+        },
+        {
+          "text": "lit,",
+          "start": 129.04,
+          "end": 129.14,
+          "confidence": 0.999
+        },
+        {
+          "text": "on",
+          "start": 129.14,
+          "end": 129.26,
+          "confidence": 0.427
+        },
+        {
+          "text": "ne",
+          "start": 129.26,
+          "end": 129.3,
+          "confidence": 0.963
+        },
+        {
+          "text": "l'emmène",
+          "start": 129.3,
+          "end": 129.5,
+          "confidence": 0.992
+        },
+        {
+          "text": "pas",
+          "start": 129.5,
+          "end": 129.68,
+          "confidence": 0.997
+        },
+        {
+          "text": "au",
+          "start": 129.68,
+          "end": 129.86,
+          "confidence": 0.674
+        },
+        {
+          "text": "chiottes.",
+          "start": 129.86,
+          "end": 130.48,
+          "confidence": 0.828
+        }
+      ]
+    },
+    {
+      "id": 27,
+      "seek": 13084,
+      "start": 130.86,
+      "end": 136.9,
+      "text": " On pouvait être énervé par son môme qui occupait la ligne de téléphone pendant une heure chaque soir pour discuter avec un copain.",
+      "tokens": [
+        1282,
+        45913,
+        7418,
+        45045,
+        15797,
+        971,
+        1872,
+        275,
+        2851,
+        1398,
+        1956,
+        8073,
+        1001,
+        635,
+        34207,
+        368,
+        47159,
+        17338,
+        2251,
+        30027,
+        18920,
+        27105,
+        2016,
+        2983,
+        20314,
+        4163,
+        517,
+        2971,
+        491,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06199159333200166,
+      "compression_ratio": 1.6127167630057804,
+      "no_speech_prob": 1.6126719856401905e-05,
+      "confidence": 0.955,
+      "words": [
+        {
+          "text": "On",
+          "start": 130.86,
+          "end": 131.04,
+          "confidence": 0.983
+        },
+        {
+          "text": "pouvait",
+          "start": 131.04,
+          "end": 131.28,
+          "confidence": 0.989
+        },
+        {
+          "text": "être",
+          "start": 131.28,
+          "end": 131.48,
+          "confidence": 0.996
+        },
+        {
+          "text": "énervé",
+          "start": 131.48,
+          "end": 132.22,
+          "confidence": 0.906
+        },
+        {
+          "text": "par",
+          "start": 132.22,
+          "end": 132.44,
+          "confidence": 0.991
+        },
+        {
+          "text": "son",
+          "start": 132.44,
+          "end": 132.7,
+          "confidence": 0.998
+        },
+        {
+          "text": "môme",
+          "start": 132.7,
+          "end": 133.1,
+          "confidence": 0.832
+        },
+        {
+          "text": "qui",
+          "start": 133.1,
+          "end": 133.34,
+          "confidence": 0.919
+        },
+        {
+          "text": "occupait",
+          "start": 133.34,
+          "end": 133.76,
+          "confidence": 0.991
+        },
+        {
+          "text": "la",
+          "start": 133.76,
+          "end": 133.8,
+          "confidence": 0.992
+        },
+        {
+          "text": "ligne",
+          "start": 133.8,
+          "end": 134.08,
+          "confidence": 0.999
+        },
+        {
+          "text": "de",
+          "start": 134.08,
+          "end": 134.14,
+          "confidence": 0.997
+        },
+        {
+          "text": "téléphone",
+          "start": 134.14,
+          "end": 134.6,
+          "confidence": 0.985
+        },
+        {
+          "text": "pendant",
+          "start": 134.6,
+          "end": 134.82,
+          "confidence": 0.981
+        },
+        {
+          "text": "une",
+          "start": 134.82,
+          "end": 135.2,
+          "confidence": 0.87
+        },
+        {
+          "text": "heure",
+          "start": 135.2,
+          "end": 135.36,
+          "confidence": 0.998
+        },
+        {
+          "text": "chaque",
+          "start": 135.36,
+          "end": 135.54,
+          "confidence": 0.991
+        },
+        {
+          "text": "soir",
+          "start": 135.54,
+          "end": 135.8,
+          "confidence": 0.996
+        },
+        {
+          "text": "pour",
+          "start": 135.8,
+          "end": 135.96,
+          "confidence": 0.79
+        },
+        {
+          "text": "discuter",
+          "start": 135.96,
+          "end": 136.28,
+          "confidence": 0.997
+        },
+        {
+          "text": "avec",
+          "start": 136.28,
+          "end": 136.48,
+          "confidence": 0.996
+        },
+        {
+          "text": "un",
+          "start": 136.48,
+          "end": 136.6,
+          "confidence": 0.999
+        },
+        {
+          "text": "copain.",
+          "start": 136.6,
+          "end": 136.9,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 28,
+      "seek": 13084,
+      "start": 137.28,
+      "end": 141.88,
+      "text": " Mais ça ne ressemblait pas à ce qu'on peut ressentir à voir ce même môme aujourd'hui,",
+      "tokens": [
+        6313,
+        2788,
+        408,
+        725,
+        15750,
+        35235,
+        1736,
+        1531,
+        1769,
+        421,
+        6,
+        266,
+        5977,
+        24689,
+        317,
+        347,
+        1531,
+        10695,
+        1769,
+        5698,
+        275,
+        2851,
+        1398,
+        14023,
+        6,
+        10556,
+        11
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06199159333200166,
+      "compression_ratio": 1.6127167630057804,
+      "no_speech_prob": 1.6126719856401905e-05,
+      "confidence": 0.959,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 137.28,
+          "end": 137.46,
+          "confidence": 0.993
+        },
+        {
+          "text": "ça",
+          "start": 137.46,
+          "end": 137.68,
+          "confidence": 0.938
+        },
+        {
+          "text": "ne",
+          "start": 137.68,
+          "end": 137.94,
+          "confidence": 0.998
+        },
+        {
+          "text": "ressemblait",
+          "start": 137.94,
+          "end": 138.4,
+          "confidence": 0.991
+        },
+        {
+          "text": "pas",
+          "start": 138.4,
+          "end": 138.76,
+          "confidence": 0.995
+        },
+        {
+          "text": "à",
+          "start": 138.76,
+          "end": 138.94,
+          "confidence": 0.988
+        },
+        {
+          "text": "ce",
+          "start": 138.94,
+          "end": 138.98,
+          "confidence": 0.998
+        },
+        {
+          "text": "qu'on",
+          "start": 138.98,
+          "end": 139.1,
+          "confidence": 0.986
+        },
+        {
+          "text": "peut",
+          "start": 139.1,
+          "end": 139.48,
+          "confidence": 0.988
+        },
+        {
+          "text": "ressentir",
+          "start": 139.48,
+          "end": 140.12,
+          "confidence": 0.997
+        },
+        {
+          "text": "à",
+          "start": 140.12,
+          "end": 140.32,
+          "confidence": 0.498
+        },
+        {
+          "text": "voir",
+          "start": 140.32,
+          "end": 140.46,
+          "confidence": 0.855
+        },
+        {
+          "text": "ce",
+          "start": 140.46,
+          "end": 140.68,
+          "confidence": 0.989
+        },
+        {
+          "text": "même",
+          "start": 140.68,
+          "end": 140.94,
+          "confidence": 0.984
+        },
+        {
+          "text": "môme",
+          "start": 140.94,
+          "end": 141.34,
+          "confidence": 0.998
+        },
+        {
+          "text": "aujourd'hui,",
+          "start": 141.34,
+          "end": 141.88,
+          "confidence": 0.988
+        }
+      ]
+    },
+    {
+      "id": 29,
+      "seek": 13084,
+      "start": 142.14,
+      "end": 146.3,
+      "text": " continuellement avec son smartphone dans la main, comme si c'était une sorte de pacemaker externe,",
+      "tokens": [
+        2354,
+        285,
+        1712,
+        4163,
+        1872,
+        13307,
+        2680,
+        635,
+        2135,
+        11,
+        5173,
+        1511,
+        269,
+        6,
+        9743,
+        2251,
+        25559,
+        368,
+        15165,
+        49523,
+        454,
+        391,
+        716,
+        11
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06199159333200166,
+      "compression_ratio": 1.6127167630057804,
+      "no_speech_prob": 1.6126719856401905e-05,
+      "confidence": 0.963,
+      "words": [
+        {
+          "text": "continuellement",
+          "start": 142.14,
+          "end": 142.94,
+          "confidence": 0.971
+        },
+        {
+          "text": "avec",
+          "start": 142.94,
+          "end": 143.18,
+          "confidence": 0.805
+        },
+        {
+          "text": "son",
+          "start": 143.18,
+          "end": 143.38,
+          "confidence": 0.995
+        },
+        {
+          "text": "smartphone",
+          "start": 143.38,
+          "end": 143.76,
+          "confidence": 0.978
+        },
+        {
+          "text": "dans",
+          "start": 143.76,
+          "end": 143.94,
+          "confidence": 0.979
+        },
+        {
+          "text": "la",
+          "start": 143.94,
+          "end": 144.0,
+          "confidence": 0.996
+        },
+        {
+          "text": "main,",
+          "start": 144.0,
+          "end": 144.36,
+          "confidence": 0.998
+        },
+        {
+          "text": "comme",
+          "start": 144.36,
+          "end": 144.52,
+          "confidence": 0.835
+        },
+        {
+          "text": "si",
+          "start": 144.52,
+          "end": 144.64,
+          "confidence": 0.975
+        },
+        {
+          "text": "c'était",
+          "start": 144.64,
+          "end": 144.82,
+          "confidence": 0.991
+        },
+        {
+          "text": "une",
+          "start": 144.82,
+          "end": 145.06,
+          "confidence": 0.989
+        },
+        {
+          "text": "sorte",
+          "start": 145.06,
+          "end": 145.22,
+          "confidence": 0.997
+        },
+        {
+          "text": "de",
+          "start": 145.22,
+          "end": 145.3,
+          "confidence": 0.982
+        },
+        {
+          "text": "pacemaker",
+          "start": 145.3,
+          "end": 145.82,
+          "confidence": 0.917
+        },
+        {
+          "text": "externe,",
+          "start": 145.82,
+          "end": 146.3,
+          "confidence": 0.992
+        }
+      ]
+    },
+    {
+      "id": 30,
+      "seek": 13084,
+      "start": 146.34,
+      "end": 148.84,
+      "text": " comme si le lâcher allait entraîner sa mort immédiate.",
+      "tokens": [
+        5173,
+        1511,
+        476,
+        48835,
+        6759,
+        439,
+        1001,
+        22284,
+        7517,
+        1193,
+        601,
+        6599,
+        3397,
+        526,
+        4504,
+        473,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06199159333200166,
+      "compression_ratio": 1.6127167630057804,
+      "no_speech_prob": 1.6126719856401905e-05,
+      "confidence": 0.989,
+      "words": [
+        {
+          "text": "comme",
+          "start": 146.34,
+          "end": 146.58,
+          "confidence": 0.996
+        },
+        {
+          "text": "si",
+          "start": 146.58,
+          "end": 146.76,
+          "confidence": 0.994
+        },
+        {
+          "text": "le",
+          "start": 146.76,
+          "end": 146.84,
+          "confidence": 0.997
+        },
+        {
+          "text": "lâcher",
+          "start": 146.84,
+          "end": 147.36,
+          "confidence": 0.969
+        },
+        {
+          "text": "allait",
+          "start": 147.36,
+          "end": 147.56,
+          "confidence": 0.993
+        },
+        {
+          "text": "entraîner",
+          "start": 147.56,
+          "end": 147.86,
+          "confidence": 0.978
+        },
+        {
+          "text": "sa",
+          "start": 147.86,
+          "end": 148.0,
+          "confidence": 0.999
+        },
+        {
+          "text": "mort",
+          "start": 148.0,
+          "end": 148.22,
+          "confidence": 0.998
+        },
+        {
+          "text": "immédiate.",
+          "start": 148.22,
+          "end": 148.84,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 31,
+      "seek": 13084,
+      "start": 149.04,
+      "end": 151.96,
+      "text": " Bon, je dis ça pour le môme, mais c'est évidemment valable pour nous aussi.",
+      "tokens": [
+        7368,
+        11,
+        1506,
+        717,
+        2788,
+        2016,
+        476,
+        275,
+        2851,
+        1398,
+        11,
+        2420,
+        269,
+        6,
+        377,
+        24724,
+        1323,
+        712,
+        2016,
+        4666,
+        6212,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06199159333200166,
+      "compression_ratio": 1.6127167630057804,
+      "no_speech_prob": 1.6126719856401905e-05,
+      "confidence": 0.974,
+      "words": [
+        {
+          "text": "Bon,",
+          "start": 149.04,
+          "end": 149.28,
+          "confidence": 0.918
+        },
+        {
+          "text": "je",
+          "start": 149.28,
+          "end": 149.32,
+          "confidence": 0.934
+        },
+        {
+          "text": "dis",
+          "start": 149.32,
+          "end": 149.46,
+          "confidence": 0.988
+        },
+        {
+          "text": "ça",
+          "start": 149.46,
+          "end": 149.64,
+          "confidence": 0.994
+        },
+        {
+          "text": "pour",
+          "start": 149.64,
+          "end": 149.74,
+          "confidence": 0.997
+        },
+        {
+          "text": "le",
+          "start": 149.74,
+          "end": 149.88,
+          "confidence": 0.995
+        },
+        {
+          "text": "môme,",
+          "start": 149.88,
+          "end": 150.32,
+          "confidence": 0.998
+        },
+        {
+          "text": "mais",
+          "start": 150.32,
+          "end": 150.52,
+          "confidence": 0.791
+        },
+        {
+          "text": "c'est",
+          "start": 150.52,
+          "end": 150.82,
+          "confidence": 0.981
+        },
+        {
+          "text": "évidemment",
+          "start": 150.82,
+          "end": 151.14,
+          "confidence": 0.98
+        },
+        {
+          "text": "valable",
+          "start": 151.14,
+          "end": 151.48,
+          "confidence": 0.998
+        },
+        {
+          "text": "pour",
+          "start": 151.48,
+          "end": 151.62,
+          "confidence": 0.997
+        },
+        {
+          "text": "nous",
+          "start": 151.62,
+          "end": 151.76,
+          "confidence": 0.999
+        },
+        {
+          "text": "aussi.",
+          "start": 151.76,
+          "end": 151.96,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 32,
+      "seek": 13084,
+      "start": 152.34,
+      "end": 158.22,
+      "text": " Donc, rapport inédit. D'accord. Mais pourquoi a-t-on l'impression qu'on n'en sortira jamais?",
+      "tokens": [
+        7477,
+        11,
+        18018,
+        294,
+        7811,
+        270,
+        13,
+        413,
+        6,
+        19947,
+        13,
+        6313,
+        19934,
+        257,
+        12,
+        83,
+        12,
+        266,
+        287,
+        6,
+        36107,
+        421,
+        6,
+        266,
+        297,
+        6,
+        268,
+        1333,
+        4271,
+        14540,
+        2506
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06199159333200166,
+      "compression_ratio": 1.6127167630057804,
+      "no_speech_prob": 1.6126719856401905e-05,
+      "confidence": 0.948,
+      "words": [
+        {
+          "text": "Donc,",
+          "start": 152.34,
+          "end": 153.46,
+          "confidence": 0.991
+        },
+        {
+          "text": "rapport",
+          "start": 153.46,
+          "end": 153.66,
+          "confidence": 0.976
+        },
+        {
+          "text": "inédit.",
+          "start": 153.66,
+          "end": 154.24,
+          "confidence": 0.996
+        },
+        {
+          "text": "D'accord.",
+          "start": 154.24,
+          "end": 155.48,
+          "confidence": 0.978
+        },
+        {
+          "text": "Mais",
+          "start": 155.48,
+          "end": 155.82,
+          "confidence": 0.557
+        },
+        {
+          "text": "pourquoi",
+          "start": 155.82,
+          "end": 156.32,
+          "confidence": 0.994
+        },
+        {
+          "text": "a-t-on",
+          "start": 156.32,
+          "end": 156.68,
+          "confidence": 0.94
+        },
+        {
+          "text": "l'impression",
+          "start": 156.68,
+          "end": 157.06,
+          "confidence": 0.999
+        },
+        {
+          "text": "qu'on",
+          "start": 157.06,
+          "end": 157.26,
+          "confidence": 0.995
+        },
+        {
+          "text": "n'en",
+          "start": 157.26,
+          "end": 157.44,
+          "confidence": 0.878
+        },
+        {
+          "text": "sortira",
+          "start": 157.44,
+          "end": 157.9,
+          "confidence": 0.989
+        },
+        {
+          "text": "jamais?",
+          "start": 157.9,
+          "end": 158.22,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 33,
+      "seek": 15884,
+      "start": 158.86,
+      "end": 165.32,
+      "text": " Est-ce qu'il faut en remettre la faute sur les gens qui ont créé cet outil merveilleux et diabolique, et diabolique parce que merveilleux?",
+      "tokens": [
+        4410,
+        12,
+        384,
+        421,
+        6,
+        388,
+        8487,
+        465,
+        890,
+        40681,
+        635,
+        2050,
+        1169,
+        1022,
+        1512,
+        10668,
+        1956,
+        6592,
+        15609,
+        526,
+        8603,
+        484,
+        388,
+        3551,
+        303,
+        3409,
+        2449,
+        1030,
+        1026,
+        14923,
+        1925,
+        11,
+        1030,
+        1026,
+        14923,
+        1925,
+        6992,
+        631,
+        3551,
+        303,
+        3409,
+        2449,
+        2506
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.079788723507443,
+      "compression_ratio": 1.6517857142857142,
+      "no_speech_prob": 5.4980162531137466e-05,
+      "confidence": 0.962,
+      "words": [
+        {
+          "text": "Est-ce",
+          "start": 158.86,
+          "end": 159.34,
+          "confidence": 0.981
+        },
+        {
+          "text": "qu'il",
+          "start": 159.34,
+          "end": 159.46,
+          "confidence": 0.997
+        },
+        {
+          "text": "faut",
+          "start": 159.46,
+          "end": 159.62,
+          "confidence": 0.999
+        },
+        {
+          "text": "en",
+          "start": 159.62,
+          "end": 159.78,
+          "confidence": 0.97
+        },
+        {
+          "text": "remettre",
+          "start": 159.78,
+          "end": 160.12,
+          "confidence": 0.999
+        },
+        {
+          "text": "la",
+          "start": 160.12,
+          "end": 160.34,
+          "confidence": 0.998
+        },
+        {
+          "text": "faute",
+          "start": 160.34,
+          "end": 160.66,
+          "confidence": 0.986
+        },
+        {
+          "text": "sur",
+          "start": 160.66,
+          "end": 160.94,
+          "confidence": 0.995
+        },
+        {
+          "text": "les",
+          "start": 160.94,
+          "end": 161.28,
+          "confidence": 0.995
+        },
+        {
+          "text": "gens",
+          "start": 161.28,
+          "end": 161.44,
+          "confidence": 1.0
+        },
+        {
+          "text": "qui",
+          "start": 161.44,
+          "end": 161.58,
+          "confidence": 0.984
+        },
+        {
+          "text": "ont",
+          "start": 161.58,
+          "end": 161.72,
+          "confidence": 0.998
+        },
+        {
+          "text": "créé",
+          "start": 161.72,
+          "end": 162.3,
+          "confidence": 0.99
+        },
+        {
+          "text": "cet",
+          "start": 162.3,
+          "end": 162.46,
+          "confidence": 0.852
+        },
+        {
+          "text": "outil",
+          "start": 162.46,
+          "end": 162.78,
+          "confidence": 0.99
+        },
+        {
+          "text": "merveilleux",
+          "start": 162.78,
+          "end": 163.34,
+          "confidence": 0.994
+        },
+        {
+          "text": "et",
+          "start": 163.34,
+          "end": 163.5,
+          "confidence": 0.954
+        },
+        {
+          "text": "diabolique,",
+          "start": 163.5,
+          "end": 163.86,
+          "confidence": 0.992
+        },
+        {
+          "text": "et",
+          "start": 163.86,
+          "end": 163.92,
+          "confidence": 0.54
+        },
+        {
+          "text": "diabolique",
+          "start": 163.92,
+          "end": 164.4,
+          "confidence": 0.951
+        },
+        {
+          "text": "parce",
+          "start": 164.4,
+          "end": 164.66,
+          "confidence": 0.703
+        },
+        {
+          "text": "que",
+          "start": 164.66,
+          "end": 164.84,
+          "confidence": 0.99
+        },
+        {
+          "text": "merveilleux?",
+          "start": 164.84,
+          "end": 165.32,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 34,
+      "seek": 15884,
+      "start": 166.34,
+      "end": 168.82,
+      "text": " Les économistes parlent de dépendance du sentier.",
+      "tokens": [
+        6965,
+        31171,
+        22368,
+        13734,
+        317,
+        368,
+        45768,
+        719,
+        1581,
+        2279,
+        811,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.079788723507443,
+      "compression_ratio": 1.6517857142857142,
+      "no_speech_prob": 5.4980162531137466e-05,
+      "confidence": 0.984,
+      "words": [
+        {
+          "text": "Les",
+          "start": 166.34,
+          "end": 167.04,
+          "confidence": 0.926
+        },
+        {
+          "text": "économistes",
+          "start": 167.04,
+          "end": 167.48,
+          "confidence": 0.998
+        },
+        {
+          "text": "parlent",
+          "start": 167.48,
+          "end": 167.68,
+          "confidence": 0.995
+        },
+        {
+          "text": "de",
+          "start": 167.68,
+          "end": 167.82,
+          "confidence": 0.995
+        },
+        {
+          "text": "dépendance",
+          "start": 167.82,
+          "end": 168.36,
+          "confidence": 0.985
+        },
+        {
+          "text": "du",
+          "start": 168.36,
+          "end": 168.5,
+          "confidence": 0.997
+        },
+        {
+          "text": "sentier.",
+          "start": 168.5,
+          "end": 168.82,
+          "confidence": 0.978
+        }
+      ]
+    },
+    {
+      "id": 35,
+      "seek": 16884,
+      "start": 168.86,
+      "end": 177.42,
+      "text": " C'est l'idée qu'on est sur un sentier qui a été établi, soit volontairement en marchant dessus, soit en définissant des bornes, en définissant une signalétique.",
+      "tokens": [
+        50364,
+        383,
+        6,
+        377,
+        287,
+        6,
+        34281,
+        421,
+        6,
+        266,
+        871,
+        1022,
+        517,
+        2279,
+        811,
+        1956,
+        257,
+        8862,
+        4823,
+        455,
+        2081,
+        11,
+        12703,
+        40005,
+        9020,
+        518,
+        465,
+        8368,
+        394,
+        30677,
+        11,
+        12703,
+        465,
+        40763,
+        29492,
+        730,
+        4232,
+        279,
+        11,
+        465,
+        40763,
+        29492,
+        2251,
+        6358,
+        42379,
+        13,
+        51414
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10415018598238628,
+      "compression_ratio": 1.3916666666666666,
+      "no_speech_prob": 3.958350498578511e-05,
+      "confidence": 0.93,
+      "words": [
+        {
+          "text": "C'est",
+          "start": 168.86,
+          "end": 169.1,
+          "confidence": 0.952
+        },
+        {
+          "text": "l'idée",
+          "start": 169.1,
+          "end": 169.34,
+          "confidence": 0.992
+        },
+        {
+          "text": "qu'on",
+          "start": 169.34,
+          "end": 169.7,
+          "confidence": 0.825
+        },
+        {
+          "text": "est",
+          "start": 169.7,
+          "end": 169.88,
+          "confidence": 0.631
+        },
+        {
+          "text": "sur",
+          "start": 169.88,
+          "end": 170.0,
+          "confidence": 0.993
+        },
+        {
+          "text": "un",
+          "start": 170.0,
+          "end": 170.54,
+          "confidence": 0.998
+        },
+        {
+          "text": "sentier",
+          "start": 170.54,
+          "end": 170.78,
+          "confidence": 0.99
+        },
+        {
+          "text": "qui",
+          "start": 170.78,
+          "end": 170.84,
+          "confidence": 0.961
+        },
+        {
+          "text": "a",
+          "start": 170.84,
+          "end": 170.94,
+          "confidence": 0.98
+        },
+        {
+          "text": "été",
+          "start": 170.94,
+          "end": 171.12,
+          "confidence": 0.996
+        },
+        {
+          "text": "établi,",
+          "start": 171.12,
+          "end": 171.9,
+          "confidence": 0.995
+        },
+        {
+          "text": "soit",
+          "start": 171.9,
+          "end": 172.12,
+          "confidence": 0.989
+        },
+        {
+          "text": "volontairement",
+          "start": 172.12,
+          "end": 172.72,
+          "confidence": 0.965
+        },
+        {
+          "text": "en",
+          "start": 172.72,
+          "end": 172.8,
+          "confidence": 0.941
+        },
+        {
+          "text": "marchant",
+          "start": 172.8,
+          "end": 173.06,
+          "confidence": 0.997
+        },
+        {
+          "text": "dessus,",
+          "start": 173.06,
+          "end": 174.24,
+          "confidence": 0.972
+        },
+        {
+          "text": "soit",
+          "start": 174.24,
+          "end": 174.92,
+          "confidence": 0.996
+        },
+        {
+          "text": "en",
+          "start": 174.92,
+          "end": 175.36,
+          "confidence": 0.991
+        },
+        {
+          "text": "définissant",
+          "start": 175.36,
+          "end": 175.5,
+          "confidence": 0.983
+        },
+        {
+          "text": "des",
+          "start": 175.5,
+          "end": 175.76,
+          "confidence": 0.984
+        },
+        {
+          "text": "bornes,",
+          "start": 175.76,
+          "end": 176.04,
+          "confidence": 0.975
+        },
+        {
+          "text": "en",
+          "start": 176.04,
+          "end": 176.08,
+          "confidence": 0.68
+        },
+        {
+          "text": "définissant",
+          "start": 176.08,
+          "end": 176.58,
+          "confidence": 0.997
+        },
+        {
+          "text": "une",
+          "start": 176.58,
+          "end": 176.82,
+          "confidence": 0.944
+        },
+        {
+          "text": "signalétique.",
+          "start": 176.82,
+          "end": 177.42,
+          "confidence": 0.642
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/medium_auto/bonjour.wav.words.json b/tests/expected/medium_auto/bonjour.wav.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..da3af389c96084e047ab79e6e6e78b0436b0bff3
--- /dev/null
+++ b/tests/expected/medium_auto/bonjour.wav.words.json
@@ -0,0 +1,133 @@
+{
+  "text": " Bonjour !",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.14,
+      "end": 0.94,
+      "text": " Bonjour !",
+      "tokens": [
+        50364,
+        25431,
+        2298,
+        50402
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7046648502349854,
+      "compression_ratio": 0.5294117647058824,
+      "no_speech_prob": 0.08610370755195618,
+      "confidence": 0.964,
+      "words": [
+        {
+          "text": "Bonjour !",
+          "start": 0.14,
+          "end": 0.94,
+          "confidence": 0.964
+        }
+      ]
+    }
+  ],
+  "language": "fr",
+  "language_probs": {
+    "en": 0.010910450480878353,
+    "zh": 0.009780064225196838,
+    "de": 0.0010308112250640988,
+    "es": 0.00041648533078841865,
+    "ru": 0.0012629760894924402,
+    "ko": 0.0024727871641516685,
+    "fr": 0.9519104361534119,
+    "ja": 0.003029722487553954,
+    "pt": 0.007736667525023222,
+    "tr": 0.00019368366338312626,
+    "pl": 0.0013871078845113516,
+    "ca": 8.248044650827069e-06,
+    "nl": 0.0005183243192732334,
+    "ar": 0.0015965515049174428,
+    "sv": 0.00013311671500559896,
+    "it": 0.0024727871641516685,
+    "id": 7.948761049192399e-05,
+    "hi": 0.00010696228127926588,
+    "fi": 1.1814779099950101e-05,
+    "vi": 0.00038518596556968987,
+    "he": 7.351402746280655e-05,
+    "uk": 3.112779450020753e-05,
+    "el": 0.0002486947341822088,
+    "ms": 0.0003095056163147092,
+    "cs": 2.621223575260956e-05,
+    "ro": 4.9742080591386184e-05,
+    "da": 5.161494755157037e-06,
+    "hu": 1.5652040019631386e-05,
+    "ta": 2.540577042964287e-05,
+    "no": 6.423583727155346e-06,
+    "th": 0.00017361690697725862,
+    "ur": 2.3866510673542507e-05,
+    "hr": 3.603303866839269e-06,
+    "bg": 6.323995876300614e-06,
+    "lt": 2.4140632604030543e-07,
+    "la": 0.000605982553679496,
+    "mi": 9.43938794080168e-05,
+    "ml": 4.925132543576183e-06,
+    "cy": 0.0011864564148709178,
+    "sk": 6.562104317708872e-07,
+    "te": 6.627490620303433e-06,
+    "fa": 2.5011888283188455e-05,
+    "lv": 8.474158619264927e-08,
+    "bn": 2.8953361379535636e-06,
+    "sr": 7.596187145963995e-08,
+    "az": 6.497363358448638e-08,
+    "sl": 8.377933227166068e-06,
+    "kn": 2.687426103875623e-08,
+    "et": 7.596187145963995e-08,
+    "mk": 5.4287504269723286e-08,
+    "br": 0.0003294670023024082,
+    "eu": 1.1338299827912124e-06,
+    "is": 2.693082308269368e-07,
+    "hy": 1.5586363133479608e-07,
+    "ne": 1.0712341236285283e-07,
+    "mn": 4.876541765952425e-07,
+    "bs": 1.169821643998148e-06,
+    "kk": 5.915916645449215e-08,
+    "sq": 7.960735359802129e-08,
+    "sw": 9.346260412712581e-06,
+    "gl": 1.3180339010432363e-05,
+    "mr": 1.2523994996627152e-07,
+    "pa": 2.7785696943283256e-07,
+    "si": 7.628194452991011e-06,
+    "km": 0.00011565379827516153,
+    "sn": 8.073935896391049e-05,
+    "yo": 1.0105716683028731e-05,
+    "so": 8.132403195304505e-09,
+    "af": 6.36020956790162e-07,
+    "oc": 2.424235390208196e-05,
+    "ka": 9.433752445886512e-09,
+    "be": 6.524740911117988e-06,
+    "tg": 5.37519051491131e-09,
+    "sd": 3.2996334198287514e-07,
+    "gu": 2.5444039764010995e-08,
+    "am": 2.193413273232636e-08,
+    "yi": 6.261604426072154e-07,
+    "lo": 1.4110742085904349e-06,
+    "uz": 8.115323413271369e-10,
+    "fo": 2.0013287382880662e-07,
+    "ht": 3.547440201145946e-06,
+    "ps": 2.555125320213847e-06,
+    "tk": 4.633703643008857e-09,
+    "nn": 0.0005782325752079487,
+    "mt": 2.5643599244062898e-08,
+    "sa": 1.9479279217193834e-05,
+    "lb": 5.089128674029553e-09,
+    "my": 3.603303866839269e-06,
+    "bo": 1.7561102367835701e-06,
+    "tl": 2.7470186978462152e-05,
+    "mg": 1.2303933871748995e-08,
+    "as": 2.092969531020117e-08,
+    "tt": 1.5889033422311627e-09,
+    "haw": 0.00013521297660190612,
+    "ln": 5.272798944133683e-07,
+    "ha": 1.004217775602001e-08,
+    "ba": 5.949793546733417e-09,
+    "jw": 0.0002448391169309616,
+    "su": 6.848170475137749e-09
+  }
+}
\ No newline at end of file
diff --git a/tests/expected/medium_auto/bonjour_vous_allez_bien.mp3.words.json b/tests/expected/medium_auto/bonjour_vous_allez_bien.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..3685a9bb214825ee9e95617a328fb5cb9a0eb3e4
--- /dev/null
+++ b/tests/expected/medium_auto/bonjour_vous_allez_bien.mp3.words.json
@@ -0,0 +1,235 @@
+{
+  "text": " Bonjour ! Est-ce que vous allez bien ? Bonjour ! Est-ce que vous allez bien ?",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.42,
+      "end": 3.46,
+      "text": " Bonjour ! Est-ce que vous allez bien ?",
+      "tokens": [
+        50364,
+        25431,
+        2298,
+        4410,
+        12,
+        384,
+        631,
+        2630,
+        18146,
+        3610,
+        2506,
+        50564
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3616434610806979,
+      "compression_ratio": 0.8260869565217391,
+      "no_speech_prob": 0.07169149070978165,
+      "confidence": 0.936,
+      "words": [
+        {
+          "text": "Bonjour !",
+          "start": 0.42,
+          "end": 1.92,
+          "confidence": 0.874
+        },
+        {
+          "text": "Est-ce",
+          "start": 1.92,
+          "end": 2.16,
+          "confidence": 0.885
+        },
+        {
+          "text": "que",
+          "start": 2.16,
+          "end": 2.24,
+          "confidence": 0.988
+        },
+        {
+          "text": "vous",
+          "start": 2.24,
+          "end": 2.38,
+          "confidence": 0.996
+        },
+        {
+          "text": "allez",
+          "start": 2.38,
+          "end": 2.58,
+          "confidence": 0.99
+        },
+        {
+          "text": "bien ?",
+          "start": 2.58,
+          "end": 3.46,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 3000,
+      "start": 32.94,
+      "end": 35.86,
+      "text": " Bonjour ! Est-ce que vous allez bien ?",
+      "tokens": [
+        50364,
+        25431,
+        2298,
+        4410,
+        12,
+        384,
+        631,
+        2630,
+        18146,
+        3610,
+        2506,
+        50664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.30651259422302246,
+      "compression_ratio": 0.8260869565217391,
+      "no_speech_prob": 0.40451279282569885,
+      "confidence": 0.933,
+      "words": [
+        {
+          "text": "Bonjour !",
+          "start": 32.94,
+          "end": 34.44,
+          "confidence": 0.741
+        },
+        {
+          "text": "Est-ce",
+          "start": 34.44,
+          "end": 34.7,
+          "confidence": 0.921
+        },
+        {
+          "text": "que",
+          "start": 34.7,
+          "end": 34.76,
+          "confidence": 0.996
+        },
+        {
+          "text": "vous",
+          "start": 34.76,
+          "end": 34.9,
+          "confidence": 0.998
+        },
+        {
+          "text": "allez",
+          "start": 34.9,
+          "end": 35.1,
+          "confidence": 0.997
+        },
+        {
+          "text": "bien ?",
+          "start": 35.1,
+          "end": 35.86,
+          "confidence": 0.999
+        }
+      ]
+    }
+  ],
+  "language": "fr",
+  "language_probs": {
+    "en": 0.06090574339032173,
+    "zh": 0.003715273691341281,
+    "de": 0.005754328332841396,
+    "es": 0.007161377463489771,
+    "ru": 0.0019886428490281105,
+    "ko": 0.0026760115288197994,
+    "fr": 0.7536683082580566,
+    "ja": 0.002848599338904023,
+    "pt": 0.0049219378270208836,
+    "tr": 0.0009844496380537748,
+    "pl": 0.0036009668838232756,
+    "ca": 2.1080166334286332e-05,
+    "nl": 0.002848599338904023,
+    "ar": 0.00263452366925776,
+    "sv": 0.00025680899852886796,
+    "it": 0.0036576741840690374,
+    "id": 0.00012321829854045063,
+    "hi": 0.00041684217285364866,
+    "fi": 8.468662417726591e-05,
+    "vi": 0.0002489078033249825,
+    "he": 4.325369809521362e-05,
+    "uk": 4.0003127651289105e-05,
+    "el": 7.591259782202542e-05,
+    "ms": 0.0007202387205325067,
+    "cs": 0.0002955853415187448,
+    "ro": 9.596251766197383e-05,
+    "da": 4.2583109461702406e-05,
+    "hu": 7.357701542787254e-05,
+    "ta": 7.634730536665302e-06,
+    "no": 5.383009556680918e-05,
+    "th": 0.00013745995238423347,
+    "ur": 7.243630534503609e-05,
+    "hr": 2.8528902475954965e-06,
+    "bg": 1.1824902685475536e-05,
+    "lt": 5.035650474383147e-07,
+    "la": 0.02311721071600914,
+    "mi": 0.00021966038912069052,
+    "ml": 1.4948076568543911e-05,
+    "cy": 0.006319893989712,
+    "sk": 8.255112334154546e-06,
+    "te": 1.980298475245945e-05,
+    "fa": 0.00011575288226595148,
+    "lv": 8.700824309926247e-07,
+    "bn": 1.1641573109955061e-05,
+    "sr": 9.02842458572195e-08,
+    "az": 3.33536695507064e-06,
+    "sl": 1.7205131371156313e-05,
+    "kn": 3.46094878977965e-07,
+    "et": 1.6255279433607939e-06,
+    "mk": 6.452324186057012e-08,
+    "br": 0.013589906506240368,
+    "eu": 2.0114837752771564e-05,
+    "is": 4.929352144245058e-06,
+    "hy": 1.0660472753443173e-06,
+    "ne": 2.0548598058667267e-06,
+    "mn": 5.0568687584018335e-05,
+    "bs": 3.441242597546079e-06,
+    "kk": 4.957580586051336e-07,
+    "sq": 1.9719890076430602e-07,
+    "sw": 7.754960279271472e-06,
+    "gl": 7.02076795278117e-05,
+    "mr": 1.785293193279358e-06,
+    "pa": 4.558905857265927e-06,
+    "si": 6.0051803302485496e-05,
+    "km": 0.001573145855218172,
+    "sn": 0.0003915869747288525,
+    "yo": 0.00011575288226595148,
+    "so": 1.5969655464687094e-07,
+    "af": 8.001128662726842e-06,
+    "oc": 0.0006356084486469626,
+    "ka": 1.0150930052077456e-07,
+    "be": 1.0766695595521014e-05,
+    "tg": 1.0071934752886591e-07,
+    "sd": 1.220026479131775e-05,
+    "gu": 1.4093170364049001e-07,
+    "am": 8.56593089793023e-07,
+    "yi": 1.3824710549670272e-05,
+    "lo": 8.001128662726842e-06,
+    "uz": 4.0063390827072e-08,
+    "fo": 2.388695975241717e-05,
+    "ht": 0.0004040172789245844,
+    "ps": 3.2836567243066384e-06,
+    "tk": 1.9719890076430602e-07,
+    "nn": 0.07120601832866669,
+    "mt": 1.1708239071595017e-06,
+    "sa": 0.0002910027396865189,
+    "lb": 6.671153300885635e-07,
+    "my": 2.7926684197154827e-05,
+    "bo": 7.516364803450415e-06,
+    "tl": 7.243630534503609e-05,
+    "mg": 5.61767421913828e-07,
+    "as": 1.0660472753443173e-06,
+    "tt": 2.5071027920375855e-08,
+    "haw": 0.014466380700469017,
+    "ln": 2.9727802029810846e-05,
+    "ha": 3.40729144454599e-07,
+    "ba": 2.0666269051616837e-07,
+    "jw": 0.006833434104919434,
+    "su": 3.46094878977965e-07
+  }
+}
\ No newline at end of file
diff --git a/tests/expected/medium_auto/empty.mp3.words.json b/tests/expected/medium_auto/empty.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..894bb497261294d3fb3b7b5a7efa0b4c19e4c765
--- /dev/null
+++ b/tests/expected/medium_auto/empty.mp3.words.json
@@ -0,0 +1,147 @@
+{
+  "text": " Thanks for watching!",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.0,
+      "end": 2.52,
+      "text": " Thanks for watching!",
+      "tokens": [
+        50364,
+        2561,
+        337,
+        1976,
+        0,
+        50518
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.8084396634783063,
+      "compression_ratio": 0.7142857142857143,
+      "no_speech_prob": 0.43768733739852905,
+      "confidence": 0.369,
+      "words": [
+        {
+          "text": "Thanks",
+          "start": 0.0,
+          "end": 1.5,
+          "confidence": 0.056
+        },
+        {
+          "text": "for",
+          "start": 1.5,
+          "end": 2.46,
+          "confidence": 0.948
+        },
+        {
+          "text": "watching!",
+          "start": 2.46,
+          "end": 2.52,
+          "confidence": 0.948
+        }
+      ]
+    }
+  ],
+  "language": "en",
+  "language_probs": {
+    "en": 0.47364965081214905,
+    "zh": 0.014989392831921577,
+    "de": 0.0077763949520885944,
+    "es": 0.009985089302062988,
+    "ru": 0.07263652980327606,
+    "ko": 0.0810319036245346,
+    "fr": 0.008023244328796864,
+    "ja": 0.028444871306419373,
+    "pt": 0.011857587844133377,
+    "tr": 0.008675196208059788,
+    "pl": 0.005020818207412958,
+    "ca": 8.504862489644438e-05,
+    "nl": 0.0031914261635392904,
+    "ar": 0.005778925959020853,
+    "sv": 0.0022986982949078083,
+    "it": 0.0030932363588362932,
+    "id": 0.0014841509982943535,
+    "hi": 0.00324168405495584,
+    "fi": 0.0010042268550023437,
+    "vi": 0.0018761425744742155,
+    "he": 0.0002348267735214904,
+    "uk": 0.0007462779758498073,
+    "el": 0.0014161868020892143,
+    "ms": 0.0035050958395004272,
+    "cs": 0.000914358941372484,
+    "ro": 0.0007121034432202578,
+    "da": 0.0001516155753051862,
+    "hu": 0.0007820926839485765,
+    "ta": 0.0012694615870714188,
+    "no": 0.00027454033261165023,
+    "th": 0.0022279745899140835,
+    "ur": 0.0007462779758498073,
+    "hr": 6.833848601672798e-05,
+    "bg": 0.00011624769831541926,
+    "lt": 1.3456648048304487e-05,
+    "la": 0.010796455666422844,
+    "mi": 0.00033115886617451906,
+    "ml": 0.0007347080390900373,
+    "cy": 0.004942977800965309,
+    "sk": 6.941466563148424e-05,
+    "te": 0.000399453827412799,
+    "fa": 0.00016393551777582616,
+    "lv": 4.6504928832291625e-06,
+    "bn": 0.0001109243166865781,
+    "sr": 1.0057395911644562e-06,
+    "az": 9.596834615877015e-07,
+    "sl": 6.222290539881214e-05,
+    "kn": 1.6324765965691768e-06,
+    "et": 5.028381565352902e-06,
+    "mk": 1.6939416980221722e-07,
+    "br": 0.0001916600449476391,
+    "eu": 3.621807309173164e-06,
+    "is": 2.0842062440351583e-05,
+    "hy": 3.916107743862085e-06,
+    "ne": 8.161869118339382e-06,
+    "mn": 6.03085063630715e-05,
+    "bs": 8.161869118339382e-06,
+    "kk": 1.1758287428165204e-06,
+    "sq": 1.332388478658686e-06,
+    "sw": 5.0784856284735724e-05,
+    "gl": 5.406019772635773e-05,
+    "mr": 1.5097939467523247e-06,
+    "pa": 2.096141315632849e-06,
+    "si": 0.0002205993514508009,
+    "km": 0.0006383254658430815,
+    "sn": 0.00035251679946668446,
+    "yo": 3.657895649666898e-05,
+    "so": 7.75543043118887e-08,
+    "af": 1.1155952961416915e-05,
+    "oc": 7.910754902695771e-06,
+    "ka": 3.421856717977789e-07,
+    "be": 5.43697706234525e-06,
+    "tg": 4.3165474750139765e-08,
+    "sd": 2.1626799480145564e-06,
+    "gu": 1.4489052091448684e-07,
+    "am": 4.533224000624614e-07,
+    "yi": 2.338414788027876e-06,
+    "lo": 1.0000130714615807e-05,
+    "uz": 9.556565316870547e-09,
+    "fo": 7.66736593504902e-06,
+    "ht": 9.845093700278085e-06,
+    "ps": 4.79811478726333e-06,
+    "tk": 8.191367584231557e-08,
+    "nn": 0.21349063515663147,
+    "mt": 4.1925463278857933e-07,
+    "sa": 6.833848601672798e-05,
+    "lb": 4.0550212077050674e-08,
+    "my": 7.202823780971812e-06,
+    "bo": 8.290399819088634e-06,
+    "tl": 0.0013097586343064904,
+    "mg": 1.6418248094396404e-07,
+    "as": 3.36880560780628e-07,
+    "tt": 1.651226533283534e-08,
+    "haw": 0.0035050958395004272,
+    "ln": 3.0673325568386645e-07,
+    "ha": 1.2490343692661554e-07,
+    "ba": 7.877560648239523e-08,
+    "jw": 0.004942977800965309,
+    "su": 3.36880560780628e-07
+  }
+}
\ No newline at end of file
diff --git a/tests/expected/medium_auto/gaenswein15.mp3.words.json b/tests/expected/medium_auto/gaenswein15.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..e23e145f910be90eba7dd5a5f8e8a2fa74e40841
--- /dev/null
+++ b/tests/expected/medium_auto/gaenswein15.mp3.words.json
@@ -0,0 +1,417 @@
+{
+  "text": " Die Wiederzulassung des Messbuchs von 1962 als Missale für die außerordentliche Form des römischen Rethus ist dann nicht so weitergegangen, wie sich Papst Benediktas gewünscht hatte. Das hat er als Emeritor so gemacht.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.84,
+      "end": 8.56,
+      "text": " Die Wiederzulassung des Messbuchs von 1962 als Missale für die außerordentliche Form des römischen Rethus",
+      "tokens": [
+        50364,
+        3229,
+        45742,
+        89,
+        425,
+        40828,
+        730,
+        9847,
+        65,
+        37503,
+        2957,
+        39498,
+        3907,
+        5275,
+        1220,
+        2959,
+        978,
+        39428,
+        765,
+        7698,
+        68,
+        10126,
+        730,
+        367,
+        32374,
+        6282,
+        497,
+        3293,
+        301,
+        50814
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.28166988079364486,
+      "compression_ratio": 1.247191011235955,
+      "no_speech_prob": 0.2541781961917877,
+      "confidence": 0.869,
+      "words": [
+        {
+          "text": "Die",
+          "start": 0.84,
+          "end": 1.12,
+          "confidence": 0.872
+        },
+        {
+          "text": "Wiederzulassung",
+          "start": 1.12,
+          "end": 1.92,
+          "confidence": 0.976
+        },
+        {
+          "text": "des",
+          "start": 1.92,
+          "end": 2.16,
+          "confidence": 0.986
+        },
+        {
+          "text": "Messbuchs",
+          "start": 2.16,
+          "end": 2.74,
+          "confidence": 0.947
+        },
+        {
+          "text": "von",
+          "start": 2.74,
+          "end": 3.28,
+          "confidence": 0.971
+        },
+        {
+          "text": "1962",
+          "start": 3.28,
+          "end": 4.9,
+          "confidence": 0.981
+        },
+        {
+          "text": "als",
+          "start": 4.9,
+          "end": 5.26,
+          "confidence": 0.925
+        },
+        {
+          "text": "Missale",
+          "start": 5.26,
+          "end": 5.76,
+          "confidence": 0.905
+        },
+        {
+          "text": "für",
+          "start": 5.76,
+          "end": 5.96,
+          "confidence": 0.955
+        },
+        {
+          "text": "die",
+          "start": 5.96,
+          "end": 6.12,
+          "confidence": 0.99
+        },
+        {
+          "text": "außerordentliche",
+          "start": 6.12,
+          "end": 7.06,
+          "confidence": 0.943
+        },
+        {
+          "text": "Form",
+          "start": 7.06,
+          "end": 7.32,
+          "confidence": 0.834
+        },
+        {
+          "text": "des",
+          "start": 7.32,
+          "end": 7.64,
+          "confidence": 0.863
+        },
+        {
+          "text": "römischen",
+          "start": 7.64,
+          "end": 8.04,
+          "confidence": 0.676
+        },
+        {
+          "text": "Rethus",
+          "start": 8.04,
+          "end": 8.56,
+          "confidence": 0.629
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 9.44,
+      "end": 12.74,
+      "text": " ist dann nicht so weitergegangen, wie sich Papst Benediktas gewünscht hatte.",
+      "tokens": [
+        50814,
+        1418,
+        3594,
+        1979,
+        370,
+        8988,
+        432,
+        47152,
+        11,
+        3355,
+        3041,
+        15919,
+        372,
+        39753,
+        9874,
+        296,
+        6906,
+        3412,
+        82,
+        4701,
+        13299,
+        13,
+        51014
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.28166988079364486,
+      "compression_ratio": 1.247191011235955,
+      "no_speech_prob": 0.2541781961917877,
+      "confidence": 0.889,
+      "words": [
+        {
+          "text": "ist",
+          "start": 9.44,
+          "end": 9.66,
+          "confidence": 0.975
+        },
+        {
+          "text": "dann",
+          "start": 9.66,
+          "end": 9.82,
+          "confidence": 0.688
+        },
+        {
+          "text": "nicht",
+          "start": 9.82,
+          "end": 10.0,
+          "confidence": 0.996
+        },
+        {
+          "text": "so",
+          "start": 10.0,
+          "end": 10.16,
+          "confidence": 0.992
+        },
+        {
+          "text": "weitergegangen,",
+          "start": 10.16,
+          "end": 10.84,
+          "confidence": 0.811
+        },
+        {
+          "text": "wie",
+          "start": 10.9,
+          "end": 11.06,
+          "confidence": 0.988
+        },
+        {
+          "text": "sich",
+          "start": 11.06,
+          "end": 11.26,
+          "confidence": 0.964
+        },
+        {
+          "text": "Papst",
+          "start": 11.26,
+          "end": 11.56,
+          "confidence": 0.884
+        },
+        {
+          "text": "Benediktas",
+          "start": 11.56,
+          "end": 12.08,
+          "confidence": 0.764
+        },
+        {
+          "text": "gewünscht",
+          "start": 12.08,
+          "end": 12.56,
+          "confidence": 0.992
+        },
+        {
+          "text": "hatte.",
+          "start": 12.56,
+          "end": 12.74,
+          "confidence": 0.952
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 14.0,
+      "end": 15.48,
+      "text": " Das hat er als Emeritor so gemacht.",
+      "tokens": [
+        51014,
+        2846,
+        2385,
+        1189,
+        3907,
+        18477,
+        3029,
+        370,
+        12293,
+        13,
+        51114
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.28166988079364486,
+      "compression_ratio": 1.247191011235955,
+      "no_speech_prob": 0.2541781961917877,
+      "confidence": 0.442,
+      "words": [
+        {
+          "text": "Das",
+          "start": 14.0,
+          "end": 14.2,
+          "confidence": 0.968
+        },
+        {
+          "text": "hat",
+          "start": 14.2,
+          "end": 14.36,
+          "confidence": 0.845
+        },
+        {
+          "text": "er",
+          "start": 14.36,
+          "end": 14.5,
+          "confidence": 0.99
+        },
+        {
+          "text": "als",
+          "start": 14.5,
+          "end": 14.7,
+          "confidence": 0.977
+        },
+        {
+          "text": "Emeritor",
+          "start": 14.7,
+          "end": 15.24,
+          "confidence": 0.429
+        },
+        {
+          "text": "so",
+          "start": 15.24,
+          "end": 15.42,
+          "confidence": 0.111
+        },
+        {
+          "text": "gemacht.",
+          "start": 15.42,
+          "end": 15.48,
+          "confidence": 0.09
+        }
+      ]
+    }
+  ],
+  "language": "de",
+  "language_probs": {
+    "en": 0.006050508003681898,
+    "zh": 0.00035218181437812746,
+    "de": 0.9862326383590698,
+    "es": 0.0004315021797083318,
+    "ru": 0.0005806496483273804,
+    "ko": 0.0005627849022857845,
+    "fr": 0.0008188472711481154,
+    "ja": 0.0003577278694137931,
+    "pt": 0.0006683236570097506,
+    "tr": 0.0003577278694137931,
+    "pl": 0.0007455689483322203,
+    "ca": 1.2701659670710796e-06,
+    "nl": 0.0009877183474600315,
+    "ar": 0.00017434264009352773,
+    "sv": 5.3171497711446136e-05,
+    "it": 0.0005897935479879379,
+    "id": 1.8958882719743997e-05,
+    "hi": 5.2347153541632e-05,
+    "fi": 1.1145352800667752e-05,
+    "vi": 6.120002217357978e-05,
+    "he": 6.655193374172086e-06,
+    "uk": 7.903237928985618e-06,
+    "el": 4.013595389551483e-05,
+    "ms": 1.7810220015235245e-05,
+    "cs": 9.990628313971683e-06,
+    "ro": 1.673115730227437e-05,
+    "da": 4.945720320392866e-06,
+    "hu": 4.477489346754737e-05,
+    "ta": 1.7634508822084172e-06,
+    "no": 2.9532243388530333e-06,
+    "th": 4.076800178154372e-05,
+    "ur": 2.6321804398321547e-05,
+    "hr": 2.3131441651003115e-07,
+    "bg": 2.424154104119225e-07,
+    "lt": 1.8586635519568517e-07,
+    "la": 0.00021697291231248528,
+    "mi": 3.5070404464931926e-06,
+    "ml": 3.618366235969006e-06,
+    "cy": 4.013595389551483e-05,
+    "sk": 3.582667602586298e-07,
+    "te": 3.934790697712742e-07,
+    "fa": 3.0949524898460368e-06,
+    "lv": 4.3462691223794536e-08,
+    "bn": 5.131934699420526e-07,
+    "sr": 5.482659659605815e-09,
+    "az": 2.2903229535131686e-08,
+    "sl": 1.0206069873675006e-06,
+    "kn": 8.761265490875303e-09,
+    "et": 6.891269066500172e-08,
+    "mk": 1.5344205905876152e-09,
+    "br": 2.817986569425557e-06,
+    "eu": 2.207217590921573e-07,
+    "is": 1.3812415033953584e-07,
+    "hy": 1.4250868218823598e-07,
+    "ne": 1.2576346364312485e-07,
+    "mn": 3.1616932005817944e-07,
+    "bs": 4.7734424413192755e-08,
+    "kk": 7.320311024017201e-09,
+    "sq": 1.18820384642504e-08,
+    "sw": 2.621135593017243e-07,
+    "gl": 2.0941495222359663e-06,
+    "mr": 2.053031877835565e-08,
+    "pa": 3.776103696395694e-08,
+    "si": 6.487373411800945e-07,
+    "km": 2.396627314737998e-05,
+    "sn": 3.618366235969006e-06,
+    "yo": 2.2772820784666692e-07,
+    "so": 3.266969750281845e-10,
+    "af": 1.0264515282187858e-07,
+    "oc": 4.600236138685432e-07,
+    "ka": 1.333127719327365e-09,
+    "be": 2.7469266683510796e-07,
+    "tg": 2.060452086727338e-10,
+    "sd": 1.8547597235851754e-08,
+    "gu": 1.046383979463883e-09,
+    "am": 1.924594483782016e-09,
+    "yi": 2.704339294723468e-07,
+    "lo": 4.449337609457871e-08,
+    "uz": 1.6299518679208091e-10,
+    "fo": 7.870076501603762e-08,
+    "ht": 1.338745079237924e-07,
+    "ps": 6.945317920781235e-08,
+    "tk": 9.453291482941495e-10,
+    "nn": 0.00032066518906503916,
+    "mt": 1.4191070540903183e-09,
+    "sa": 3.2945599741651677e-06,
+    "lb": 7.837053783710246e-10,
+    "my": 1.2381367753278028e-07,
+    "bo": 6.784429729123076e-08,
+    "tl": 2.999730895680841e-06,
+    "mg": 1.046383979463883e-09,
+    "as": 1.685231287851252e-09,
+    "tt": 3.110817506368768e-11,
+    "haw": 7.195980288088322e-06,
+    "ln": 3.738849230217056e-09,
+    "ha": 3.8194747364883597e-10,
+    "ba": 9.306730386349216e-10,
+    "jw": 2.9826507670804858e-05,
+    "su": 2.2105424435370225e-10
+  }
+}
\ No newline at end of file
diff --git a/tests/expected/medium_auto/gloria.mp3.words.json b/tests/expected/medium_auto/gloria.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..666a4b26ecb2754eb9f31b9eaab69a53d7f7150a
--- /dev/null
+++ b/tests/expected/medium_auto/gloria.mp3.words.json
@@ -0,0 +1,639 @@
+{
+  "text": " Hello. How are you? Love. How are you? I'm okay. I will be. I said she could stay with us tomorrow, she feels better. Of course she can. This won't be for long. Well, you can stay as long as you want, my love. I really miss you.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 1.4,
+      "end": 1.74,
+      "text": " Hello.",
+      "tokens": [
+        50364,
+        2425,
+        13,
+        50464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23879062428193934,
+      "compression_ratio": 1.4615384615384615,
+      "no_speech_prob": 0.05016394704580307,
+      "confidence": 0.285,
+      "words": [
+        {
+          "text": "Hello.",
+          "start": 1.4,
+          "end": 1.74,
+          "confidence": 0.285
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 2.32,
+      "end": 3.5,
+      "text": " How are you?",
+      "tokens": [
+        50464,
+        1012,
+        366,
+        291,
+        30,
+        50564
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23879062428193934,
+      "compression_ratio": 1.4615384615384615,
+      "no_speech_prob": 0.05016394704580307,
+      "confidence": 0.786,
+      "words": [
+        {
+          "text": "How",
+          "start": 2.32,
+          "end": 2.82,
+          "confidence": 0.551
+        },
+        {
+          "text": "are",
+          "start": 2.82,
+          "end": 3.24,
+          "confidence": 0.989
+        },
+        {
+          "text": "you?",
+          "start": 3.24,
+          "end": 3.5,
+          "confidence": 0.893
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 3.5,
+      "end": 4.26,
+      "text": " Love.",
+      "tokens": [
+        50564,
+        5956,
+        13,
+        50664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23879062428193934,
+      "compression_ratio": 1.4615384615384615,
+      "no_speech_prob": 0.05016394704580307,
+      "confidence": 0.244,
+      "words": [
+        {
+          "text": "Love.",
+          "start": 3.5,
+          "end": 4.26,
+          "confidence": 0.244
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 5.5,
+      "end": 6.38,
+      "text": " How are you?",
+      "tokens": [
+        50664,
+        1012,
+        366,
+        291,
+        30,
+        50764
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23879062428193934,
+      "compression_ratio": 1.4615384615384615,
+      "no_speech_prob": 0.05016394704580307,
+      "confidence": 0.926,
+      "words": [
+        {
+          "text": "How",
+          "start": 5.5,
+          "end": 5.68,
+          "confidence": 0.851
+        },
+        {
+          "text": "are",
+          "start": 5.68,
+          "end": 6.08,
+          "confidence": 0.998
+        },
+        {
+          "text": "you?",
+          "start": 6.08,
+          "end": 6.38,
+          "confidence": 0.935
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 7.5,
+      "end": 9.18,
+      "text": " I'm okay. I will be.",
+      "tokens": [
+        50764,
+        286,
+        478,
+        1392,
+        13,
+        286,
+        486,
+        312,
+        13,
+        50864
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23879062428193934,
+      "compression_ratio": 1.4615384615384615,
+      "no_speech_prob": 0.05016394704580307,
+      "confidence": 0.77,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 7.5,
+          "end": 7.52,
+          "confidence": 0.767
+        },
+        {
+          "text": "okay.",
+          "start": 7.52,
+          "end": 8.22,
+          "confidence": 0.488
+        },
+        {
+          "text": "I",
+          "start": 8.42,
+          "end": 8.64,
+          "confidence": 0.767
+        },
+        {
+          "text": "will",
+          "start": 8.64,
+          "end": 8.94,
+          "confidence": 0.949
+        },
+        {
+          "text": "be.",
+          "start": 8.94,
+          "end": 9.18,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 0,
+      "start": 9.5,
+      "end": 11.52,
+      "text": " I said she could stay with us tomorrow, she feels better.",
+      "tokens": [
+        50864,
+        286,
+        848,
+        750,
+        727,
+        1754,
+        365,
+        505,
+        4153,
+        11,
+        750,
+        3417,
+        1101,
+        13,
+        50964
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23879062428193934,
+      "compression_ratio": 1.4615384615384615,
+      "no_speech_prob": 0.05016394704580307,
+      "confidence": 0.786,
+      "words": [
+        {
+          "text": "I",
+          "start": 9.5,
+          "end": 9.52,
+          "confidence": 0.883
+        },
+        {
+          "text": "said",
+          "start": 9.52,
+          "end": 9.64,
+          "confidence": 0.856
+        },
+        {
+          "text": "she",
+          "start": 9.64,
+          "end": 9.78,
+          "confidence": 0.928
+        },
+        {
+          "text": "could",
+          "start": 9.78,
+          "end": 9.96,
+          "confidence": 0.909
+        },
+        {
+          "text": "stay",
+          "start": 9.96,
+          "end": 10.16,
+          "confidence": 0.994
+        },
+        {
+          "text": "with",
+          "start": 10.16,
+          "end": 10.28,
+          "confidence": 0.977
+        },
+        {
+          "text": "us",
+          "start": 10.28,
+          "end": 10.46,
+          "confidence": 0.993
+        },
+        {
+          "text": "tomorrow,",
+          "start": 10.46,
+          "end": 10.66,
+          "confidence": 0.514
+        },
+        {
+          "text": "she",
+          "start": 10.72,
+          "end": 10.86,
+          "confidence": 0.279
+        },
+        {
+          "text": "feels",
+          "start": 10.86,
+          "end": 11.16,
+          "confidence": 0.809
+        },
+        {
+          "text": "better.",
+          "start": 11.16,
+          "end": 11.52,
+          "confidence": 0.992
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 0,
+      "start": 12.06,
+      "end": 13.36,
+      "text": " Of course she can.",
+      "tokens": [
+        50964,
+        2720,
+        1164,
+        750,
+        393,
+        13,
+        51064
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23879062428193934,
+      "compression_ratio": 1.4615384615384615,
+      "no_speech_prob": 0.05016394704580307,
+      "confidence": 0.928,
+      "words": [
+        {
+          "text": "Of",
+          "start": 12.06,
+          "end": 12.34,
+          "confidence": 0.788
+        },
+        {
+          "text": "course",
+          "start": 12.34,
+          "end": 12.56,
+          "confidence": 0.989
+        },
+        {
+          "text": "she",
+          "start": 12.56,
+          "end": 12.88,
+          "confidence": 0.958
+        },
+        {
+          "text": "can.",
+          "start": 12.88,
+          "end": 13.36,
+          "confidence": 0.993
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 0,
+      "start": 13.5,
+      "end": 15.26,
+      "text": " This won't be for long.",
+      "tokens": [
+        51064,
+        639,
+        1582,
+        380,
+        312,
+        337,
+        938,
+        13,
+        51164
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23879062428193934,
+      "compression_ratio": 1.4615384615384615,
+      "no_speech_prob": 0.05016394704580307,
+      "confidence": 0.892,
+      "words": [
+        {
+          "text": "This",
+          "start": 13.5,
+          "end": 14.28,
+          "confidence": 0.543
+        },
+        {
+          "text": "won't",
+          "start": 14.28,
+          "end": 14.6,
+          "confidence": 0.975
+        },
+        {
+          "text": "be",
+          "start": 14.6,
+          "end": 14.8,
+          "confidence": 0.996
+        },
+        {
+          "text": "for",
+          "start": 14.8,
+          "end": 14.96,
+          "confidence": 0.984
+        },
+        {
+          "text": "long.",
+          "start": 14.96,
+          "end": 15.26,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 0,
+      "start": 15.5,
+      "end": 17.62,
+      "text": " Well, you can stay as long as you want, my love.",
+      "tokens": [
+        51164,
+        1042,
+        11,
+        291,
+        393,
+        1754,
+        382,
+        938,
+        382,
+        291,
+        528,
+        11,
+        452,
+        959,
+        13,
+        51264
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23879062428193934,
+      "compression_ratio": 1.4615384615384615,
+      "no_speech_prob": 0.05016394704580307,
+      "confidence": 0.927,
+      "words": [
+        {
+          "text": "Well,",
+          "start": 15.5,
+          "end": 15.56,
+          "confidence": 0.675
+        },
+        {
+          "text": "you",
+          "start": 15.68,
+          "end": 15.7,
+          "confidence": 0.744
+        },
+        {
+          "text": "can",
+          "start": 15.7,
+          "end": 15.94,
+          "confidence": 0.982
+        },
+        {
+          "text": "stay",
+          "start": 15.94,
+          "end": 16.14,
+          "confidence": 0.985
+        },
+        {
+          "text": "as",
+          "start": 16.14,
+          "end": 16.28,
+          "confidence": 0.972
+        },
+        {
+          "text": "long",
+          "start": 16.28,
+          "end": 16.4,
+          "confidence": 0.994
+        },
+        {
+          "text": "as",
+          "start": 16.4,
+          "end": 16.48,
+          "confidence": 0.996
+        },
+        {
+          "text": "you",
+          "start": 16.48,
+          "end": 16.62,
+          "confidence": 0.995
+        },
+        {
+          "text": "want,",
+          "start": 16.62,
+          "end": 16.8,
+          "confidence": 0.995
+        },
+        {
+          "text": "my",
+          "start": 16.88,
+          "end": 17.22,
+          "confidence": 0.95
+        },
+        {
+          "text": "love.",
+          "start": 17.22,
+          "end": 17.62,
+          "confidence": 0.993
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 0,
+      "start": 17.76,
+      "end": 19.26,
+      "text": " I really miss you.",
+      "tokens": [
+        51264,
+        286,
+        534,
+        1713,
+        291,
+        13,
+        51364
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23879062428193934,
+      "compression_ratio": 1.4615384615384615,
+      "no_speech_prob": 0.05016394704580307,
+      "confidence": 0.792,
+      "words": [
+        {
+          "text": "I",
+          "start": 17.76,
+          "end": 17.98,
+          "confidence": 0.587
+        },
+        {
+          "text": "really",
+          "start": 17.98,
+          "end": 18.36,
+          "confidence": 0.944
+        },
+        {
+          "text": "miss",
+          "start": 18.36,
+          "end": 18.78,
+          "confidence": 0.905
+        },
+        {
+          "text": "you.",
+          "start": 18.78,
+          "end": 19.26,
+          "confidence": 0.787
+        }
+      ]
+    }
+  ],
+  "language": "en",
+  "language_probs": {
+    "en": 0.7642066478729248,
+    "zh": 0.002470605308189988,
+    "de": 0.00040966656524688005,
+    "es": 0.0006444960017688572,
+    "ru": 0.0002904970897361636,
+    "ko": 0.0003848461201414466,
+    "fr": 0.0005512665957212448,
+    "ja": 0.00021587910305242985,
+    "pt": 0.0011135890381410718,
+    "tr": 0.0011135890381410718,
+    "pl": 0.0003396255197003484,
+    "ca": 8.587077900301665e-05,
+    "nl": 0.0008538184338249266,
+    "ar": 0.0006860623834654689,
+    "sv": 0.00031410224619321525,
+    "it": 0.00036152946995571256,
+    "id": 1.690895987849217e-05,
+    "hi": 3.751416443265043e-05,
+    "fi": 2.0396098989294842e-05,
+    "vi": 0.00011555175296962261,
+    "he": 7.386976903944742e-06,
+    "uk": 2.3475764464819804e-05,
+    "el": 0.00016552023589611053,
+    "ms": 0.00035592447966337204,
+    "cs": 1.0917243344010785e-05,
+    "ro": 6.029074484104058e-06,
+    "da": 3.993362042820081e-05,
+    "hu": 1.6134639736264944e-05,
+    "ta": 6.518983809655765e-06,
+    "no": 2.7020438210456632e-05,
+    "th": 9.730433521326631e-05,
+    "ur": 4.317853745305911e-05,
+    "hr": 7.314098411370651e-07,
+    "bg": 1.324411982750462e-06,
+    "lt": 3.9149543340499804e-07,
+    "la": 0.0018942790338769555,
+    "mi": 0.00033436008379794657,
+    "ml": 1.02558014987153e-05,
+    "cy": 0.21894888579845428,
+    "sk": 1.3742783266934566e-07,
+    "te": 3.772898935494595e-06,
+    "fa": 2.3475764464819804e-05,
+    "lv": 3.195292492819135e-07,
+    "bn": 2.1835862753505353e-06,
+    "sr": 2.107523933148059e-08,
+    "az": 2.7330784746482095e-07,
+    "sl": 1.4690757780044805e-05,
+    "kn": 2.7061142660045334e-08,
+    "et": 1.1939934552174236e-07,
+    "mk": 1.615894618112179e-08,
+    "br": 1.7720436517265625e-05,
+    "eu": 1.0476960596861318e-06,
+    "is": 1.690895987849217e-05,
+    "hy": 4.8241702188533964e-08,
+    "ne": 3.096983789419028e-07,
+    "mn": 1.244169880010304e-06,
+    "bs": 2.5528709102218272e-06,
+    "kk": 3.114718438723685e-08,
+    "sq": 5.520970489669708e-07,
+    "sw": 3.2779512366687413e-06,
+    "gl": 2.2753489247406833e-05,
+    "mr": 7.019126258001052e-08,
+    "pa": 4.299735962831619e-07,
+    "si": 1.324411982750462e-06,
+    "km": 7.008568354649469e-05,
+    "sn": 9.78615389612969e-06,
+    "yo": 8.772251931077335e-06,
+    "so": 4.851795409877013e-09,
+    "af": 9.050712833413854e-06,
+    "oc": 2.474327402524068e-06,
+    "ka": 3.6055483043639924e-09,
+    "be": 1.115266741180676e-06,
+    "tg": 6.181347877998178e-09,
+    "sd": 6.003777031082791e-08,
+    "gu": 4.8898485260906455e-09,
+    "am": 2.278776634057067e-08,
+    "yi": 7.200703180387791e-07,
+    "lo": 5.186471412343963e-07,
+    "uz": 6.935280127962073e-10,
+    "fo": 1.5727781601526658e-06,
+    "ht": 2.7603114176599775e-06,
+    "ps": 1.597545633558184e-06,
+    "tk": 4.417610277585027e-09,
+    "nn": 0.0033245631493628025,
+    "mt": 3.4013709182545426e-07,
+    "sa": 3.544309947756119e-06,
+    "lb": 8.188955291643651e-09,
+    "my": 1.6227033938776003e-06,
+    "bo": 2.2529004581883783e-06,
+    "tl": 5.9018060710513964e-05,
+    "mg": 1.6934430746573526e-08,
+    "as": 3.6414750326230205e-08,
+    "tt": 4.248373652870896e-09,
+    "haw": 8.999180136015639e-05,
+    "ln": 5.216171672373093e-08,
+    "ha": 2.0748498030798146e-08,
+    "ba": 6.038157085441753e-09,
+    "jw": 7.460582128260285e-05,
+    "su": 2.351112904364072e-08
+  }
+}
\ No newline at end of file
diff --git a/tests/expected/medium_auto/laugh1.mp3.words.json b/tests/expected/medium_auto/laugh1.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..e30d1c3b3056b4e837f39521078bdd7051707de7
--- /dev/null
+++ b/tests/expected/medium_auto/laugh1.mp3.words.json
@@ -0,0 +1,133 @@
+{
+  "text": " hahahaha",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.32,
+      "end": 1.58,
+      "text": " hahahaha",
+      "tokens": [
+        50364,
+        17206,
+        15380,
+        50464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -1.2670220375061034,
+      "compression_ratio": 0.6666666666666666,
+      "no_speech_prob": 0.5899588465690613,
+      "confidence": 0.135,
+      "words": [
+        {
+          "text": "hahahaha",
+          "start": 0.32,
+          "end": 1.58,
+          "confidence": 0.135
+        }
+      ]
+    }
+  ],
+  "language": "en",
+  "language_probs": {
+    "en": 0.45703765749931335,
+    "zh": 0.024991001933813095,
+    "de": 0.04668933525681496,
+    "es": 0.07231386005878448,
+    "ru": 0.03362906724214554,
+    "ko": 0.012179641053080559,
+    "fr": 0.03751593455672264,
+    "ja": 0.01074849534779787,
+    "pt": 0.059950292110443115,
+    "tr": 0.016135403886437416,
+    "pl": 0.02240178734064102,
+    "ca": 0.0015244607347995043,
+    "nl": 0.008636659011244774,
+    "ar": 0.03014490194618702,
+    "sv": 0.016647595912218094,
+    "it": 0.011441714130342007,
+    "id": 0.0012837247923016548,
+    "hi": 0.009786616079509258,
+    "fi": 0.0038324943743646145,
+    "vi": 0.004695670213550329,
+    "he": 0.0012249386636540294,
+    "uk": 0.0059358831495046616,
+    "el": 0.0043427846394479275,
+    "ms": 0.006318714469671249,
+    "cs": 0.009940733201801777,
+    "ro": 0.01108968909829855,
+    "da": 0.0026755118742585182,
+    "hu": 0.0022180776577442884,
+    "ta": 0.00039767936686985195,
+    "no": 0.0018972221296280622,
+    "th": 0.0018678084015846252,
+    "ur": 0.006418219767510891,
+    "hr": 0.0008551450446248055,
+    "bg": 0.0015244607347995043,
+    "lt": 0.00019381343736313283,
+    "la": 0.006418219767510891,
+    "mi": 0.002717645140364766,
+    "ml": 0.0003620911738835275,
+    "cy": 0.011441714130342007,
+    "sk": 0.0009539831662550569,
+    "te": 0.001754643744789064,
+    "fa": 0.0038324943743646145,
+    "lv": 0.0001683880400378257,
+    "bn": 0.0016227801097556949,
+    "sr": 6.491936801467091e-05,
+    "az": 2.314771518285852e-05,
+    "sl": 0.0014320984482765198,
+    "kn": 2.664285602804739e-05,
+    "et": 0.00013320590369403362,
+    "mk": 4.7496025217697024e-05,
+    "br": 0.0002819968794938177,
+    "eu": 0.0001908086269395426,
+    "is": 0.0002776249311864376,
+    "hy": 0.0001849380787461996,
+    "ne": 0.00011940499098272994,
+    "mn": 0.00012128534581279382,
+    "bs": 0.00033487958717159927,
+    "kk": 5.216418139752932e-05,
+    "sq": 0.00022659085516352206,
+    "sw": 0.002183689270168543,
+    "gl": 0.0008033344056457281,
+    "mr": 4.977541175321676e-05,
+    "pa": 0.00011043157428503036,
+    "si": 0.0010642451234161854,
+    "km": 0.001047745579853654,
+    "sn": 0.0018972221296280622,
+    "yo": 0.0003049113438464701,
+    "so": 1.163940214610193e-05,
+    "af": 9.899021097226068e-05,
+    "oc": 9.013162343762815e-05,
+    "ka": 3.114865467068739e-05,
+    "be": 0.00017646915512159467,
+    "tg": 5.412824521044968e-06,
+    "sd": 6.194649904500693e-05,
+    "gu": 1.3396869690041058e-05,
+    "am": 1.9190129023627378e-05,
+    "yi": 7.589843880850822e-05,
+    "lo": 0.0001533190516056493,
+    "uz": 3.150641703086876e-07,
+    "fo": 5.729114491259679e-05,
+    "ht": 9.013162343762815e-05,
+    "ps": 0.00047969285515137017,
+    "tk": 2.2564011032955023e-06,
+    "nn": 0.012965160422027111,
+    "mt": 1.6672673154971562e-05,
+    "sa": 0.00034550981945358217,
+    "lb": 1.2856585271947552e-06,
+    "my": 0.0001533190516056493,
+    "bo": 0.0001657774264458567,
+    "tl": 0.002116504358127713,
+    "mg": 5.584645805356558e-06,
+    "as": 1.831134795793332e-05,
+    "tt": 1.5267572734956047e-06,
+    "haw": 0.0009539831662550569,
+    "ln": 1.0934206329693552e-05,
+    "ha": 5.49806418348453e-06,
+    "ba": 2.2919341517990688e-06,
+    "jw": 0.003127990523353219,
+    "su": 4.8520246309635695e-06
+  }
+}
\ No newline at end of file
diff --git a/tests/expected/medium_auto/laugh2.mp3.words.json b/tests/expected/medium_auto/laugh2.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..cc5244c74d4ffa3d0eec81aaee4bf9803b9da83e
--- /dev/null
+++ b/tests/expected/medium_auto/laugh2.mp3.words.json
@@ -0,0 +1,133 @@
+{
+  "text": " Hehehe",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.22,
+      "end": 0.64,
+      "text": " Hehehe",
+      "tokens": [
+        50364,
+        634,
+        23500,
+        50464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -1.0079832077026367,
+      "compression_ratio": 0.5,
+      "no_speech_prob": 0.3699853718280792,
+      "confidence": 0.334,
+      "words": [
+        {
+          "text": "Hehehe",
+          "start": 0.22,
+          "end": 0.64,
+          "confidence": 0.334
+        }
+      ]
+    }
+  ],
+  "language": "en",
+  "language_probs": {
+    "en": 0.6829636693000793,
+    "zh": 0.020623717457056046,
+    "de": 0.017097661271691322,
+    "es": 0.016832586377859116,
+    "ru": 0.02336973138153553,
+    "ko": 0.09388463199138641,
+    "fr": 0.014624404720962048,
+    "ja": 0.041015155613422394,
+    "pt": 0.01657162234187126,
+    "tr": 0.002581360749900341,
+    "pl": 0.0035283018369227648,
+    "ca": 0.00028962065698578954,
+    "nl": 0.0075870417058467865,
+    "ar": 0.003366729011759162,
+    "sv": 0.0032631459180265665,
+    "it": 0.0035838645417243242,
+    "id": 0.004898561630398035,
+    "hi": 0.004061050247400999,
+    "fi": 0.003065441967919469,
+    "vi": 0.002663301769644022,
+    "he": 0.0002516267995815724,
+    "uk": 0.0007872705464251339,
+    "el": 0.0005410826415754855,
+    "ms": 0.0037558579351752996,
+    "cs": 0.0009952031541615725,
+    "ro": 0.0006733882473781705,
+    "da": 0.00031808606581762433,
+    "hu": 0.0006131269037723541,
+    "ta": 0.00101087533403188,
+    "no": 0.0004020984342787415,
+    "th": 0.005214491859078407,
+    "ur": 0.0004020984342787415,
+    "hr": 0.00012073184188921005,
+    "bg": 8.8329310528934e-05,
+    "lt": 2.2684840587317012e-05,
+    "la": 0.0005163046298548579,
+    "mi": 0.0007872705464251339,
+    "ml": 0.0007057047332637012,
+    "cy": 0.001640812843106687,
+    "sk": 6.362121348502114e-05,
+    "te": 0.00036043874570168555,
+    "fa": 5.441810571937822e-05,
+    "lv": 1.4646435374743305e-05,
+    "bn": 5.7927773013943806e-05,
+    "sr": 1.9514486666594166e-06,
+    "az": 7.178978194133379e-07,
+    "sl": 0.00010654547804733738,
+    "kn": 2.1432470020954497e-06,
+    "et": 1.7123416910180822e-05,
+    "mk": 7.641982051609375e-07,
+    "br": 0.00010654547804733738,
+    "eu": 1.272504323424073e-05,
+    "is": 3.24945394822862e-05,
+    "hy": 8.345286914845929e-06,
+    "ne": 2.0334560758783482e-05,
+    "mn": 2.304207555425819e-05,
+    "bs": 1.088430690288078e-05,
+    "kk": 3.5336167911736993e-06,
+    "sq": 2.390964937148965e-06,
+    "sw": 0.0001265258906641975,
+    "gl": 8.8329310528934e-05,
+    "mr": 5.825949301652145e-06,
+    "pa": 2.751983856796869e-06,
+    "si": 0.0001456304162275046,
+    "km": 0.0007750650402158499,
+    "sn": 0.00042139552533626556,
+    "yo": 2.304207555425819e-05,
+    "so": 1.9935302475460048e-07,
+    "af": 1.1229812116653193e-05,
+    "oc": 9.309840606874786e-06,
+    "ka": 5.011734742765839e-07,
+    "be": 1.5111363609321415e-05,
+    "tg": 5.7563557476214555e-08,
+    "sd": 2.795321279336349e-06,
+    "gu": 5.951582124907873e-07,
+    "am": 1.1119018381577916e-06,
+    "yi": 4.262356014805846e-06,
+    "lo": 2.3773511202307418e-05,
+    "uz": 1.9585014499057252e-08,
+    "fo": 3.820750862360001e-06,
+    "ht": 7.138101864256896e-06,
+    "ps": 9.023407073982526e-06,
+    "tk": 1.7051567624548625e-07,
+    "nn": 0.007706519681960344,
+    "mt": 4.563236188914743e-07,
+    "sa": 3.798996112891473e-05,
+    "lb": 8.64131379785249e-08,
+    "my": 2.5306770112365484e-05,
+    "bo": 1.4419363651541062e-05,
+    "tl": 0.002663301769644022,
+    "mg": 4.286763726213394e-07,
+    "as": 7.406862891912169e-07,
+    "tt": 4.698200939401431e-08,
+    "haw": 0.0005326939281076193,
+    "ln": 4.6350965021701995e-07,
+    "ha": 3.087639868226688e-07,
+    "ba": 2.0249235888059047e-07,
+    "jw": 0.0017195570981130004,
+    "su": 6.045305553925573e-07
+  }
+}
\ No newline at end of file
diff --git a/tests/expected/medium_auto/punctuations.mp3.words.json b/tests/expected/medium_auto/punctuations.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..cf3491850620837ca929b3d250fdddf36252879e
--- /dev/null
+++ b/tests/expected/medium_auto/punctuations.mp3.words.json
@@ -0,0 +1,169 @@
+{
+  "text": " Dis-moi, est-ce que l'avion vole ?",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.38,
+      "end": 2.76,
+      "text": " Dis-moi, est-ce que l'avion vole ?",
+      "tokens": [
+        50364,
+        4208,
+        12,
+        29292,
+        11,
+        871,
+        12,
+        384,
+        631,
+        287,
+        6,
+        706,
+        313,
+        49877,
+        2506,
+        50496
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.26327380012063417,
+      "compression_ratio": 0.8095238095238095,
+      "no_speech_prob": 0.03882359713315964,
+      "confidence": 0.928,
+      "words": [
+        {
+          "text": "Dis-moi,",
+          "start": 0.38,
+          "end": 1.1,
+          "confidence": 0.809
+        },
+        {
+          "text": "est-ce",
+          "start": 1.28,
+          "end": 1.5,
+          "confidence": 0.968
+        },
+        {
+          "text": "que",
+          "start": 1.5,
+          "end": 1.66,
+          "confidence": 0.978
+        },
+        {
+          "text": "l'avion",
+          "start": 1.66,
+          "end": 2.04,
+          "confidence": 0.993
+        },
+        {
+          "text": "vole ?",
+          "start": 2.04,
+          "end": 2.76,
+          "confidence": 0.898
+        }
+      ]
+    }
+  ],
+  "language": "fr",
+  "language_probs": {
+    "en": 0.003270540852099657,
+    "zh": 0.00047116613131947815,
+    "de": 0.001078509958460927,
+    "es": 0.0011845114640891552,
+    "ru": 0.00093702576123178,
+    "ko": 0.0007529213326051831,
+    "fr": 0.9805174469947815,
+    "ja": 0.001148067880421877,
+    "pt": 0.0008141020080074668,
+    "tr": 0.00018451130017638206,
+    "pl": 0.000586375710554421,
+    "ca": 1.4227982319425792e-05,
+    "nl": 0.001078509958460927,
+    "ar": 0.00047116613131947815,
+    "sv": 9.133971616392955e-05,
+    "it": 0.0027540717273950577,
+    "id": 5.540033816942014e-05,
+    "hi": 4.88906262035016e-05,
+    "fi": 4.966054257238284e-05,
+    "vi": 5.8059056755155325e-05,
+    "he": 0.00010513137385714799,
+    "uk": 1.743249231367372e-05,
+    "el": 0.00029027703567408025,
+    "ms": 0.00015296523633878678,
+    "cs": 7.691574865020812e-05,
+    "ro": 0.00010846859368029982,
+    "da": 4.14057922171196e-06,
+    "hu": 7.0032590883784e-05,
+    "ta": 3.7700406210205983e-06,
+    "no": 5.234182481217431e-06,
+    "th": 4.966054257238284e-05,
+    "ur": 9.627135113987606e-06,
+    "hr": 9.330939064966515e-06,
+    "bg": 1.0409415153844748e-05,
+    "lt": 3.3987944902946765e-07,
+    "la": 0.0007412483682855964,
+    "mi": 1.7985856175073422e-05,
+    "ml": 7.195247917479719e-07,
+    "cy": 0.00010846859368029982,
+    "sk": 3.029312438229681e-06,
+    "te": 1.0633887086441973e-06,
+    "fa": 1.1795412319770548e-05,
+    "lv": 2.6886678483606374e-07,
+    "bn": 6.654516369053454e-07,
+    "sr": 7.124260292812323e-08,
+    "az": 1.4848232865460886e-07,
+    "sl": 1.3365954146138392e-05,
+    "kn": 2.600472903679929e-08,
+    "et": 6.865753903184668e-07,
+    "mk": 1.4848232865460886e-07,
+    "br": 0.0006049892399460077,
+    "eu": 5.839152890985133e-06,
+    "is": 3.094637577305548e-07,
+    "hy": 5.10219479110674e-07,
+    "ne": 1.3103519336254976e-07,
+    "mn": 8.679125471644511e-07,
+    "bs": 1.8956951635118457e-06,
+    "kk": 9.005908907511184e-08,
+    "sq": 8.59349853499225e-08,
+    "sw": 6.3136294556898065e-06,
+    "gl": 2.742515607678797e-05,
+    "mr": 1.330987089431801e-07,
+    "pa": 5.635753907995422e-08,
+    "si": 2.1819321318616858e-06,
+    "km": 0.00010846859368029982,
+    "sn": 5.7158933486789465e-05,
+    "yo": 4.5475362639990635e-06,
+    "so": 6.225109316915223e-09,
+    "af": 3.452317969276919e-07,
+    "oc": 9.423914889339358e-05,
+    "ka": 3.8432503401963913e-08,
+    "be": 4.917059413855895e-06,
+    "tg": 6.944611108394838e-09,
+    "sd": 2.5655444346739387e-07,
+    "gu": 3.01660172397078e-08,
+    "am": 6.141496555756021e-08,
+    "yi": 5.347054070625745e-07,
+    "lo": 9.238881375495112e-07,
+    "uz": 3.49196982440958e-09,
+    "fo": 1.936574705041494e-07,
+    "ht": 8.629708645457868e-06,
+    "ps": 6.059006523173593e-07,
+    "tk": 2.6414245013484106e-08,
+    "nn": 0.0012221119832247496,
+    "mt": 3.6672549441618685e-08,
+    "sa": 8.495916517858859e-06,
+    "lb": 2.2770503704805378e-08,
+    "my": 1.323408582720731e-06,
+    "bo": 5.264155902295897e-07,
+    "tl": 2.6169269403908402e-05,
+    "mg": 6.692623344406456e-08,
+    "as": 1.6659257084938872e-08,
+    "tt": 3.0576710052798717e-09,
+    "haw": 5.4541436838917434e-05,
+    "ln": 2.049735257969587e-06,
+    "ha": 2.041134550267998e-08,
+    "ba": 3.088138456064371e-08,
+    "jw": 0.0003727230941876769,
+    "su": 1.4028500139318112e-08
+  }
+}
\ No newline at end of file
diff --git a/tests/expected/medium_auto/radio_short.mp3.words.json b/tests/expected/medium_auto/radio_short.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..18b4b928cb799372f99eeaa6990b0375bcbcb839
--- /dev/null
+++ b/tests/expected/medium_auto/radio_short.mp3.words.json
@@ -0,0 +1,1632 @@
+{
+  "text": "3212122222222211111111111111111111111111111111111111111111111",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.04,
+      "end": 0.7,
+      "text": "3",
+      "tokens": [
+        50364,
+        18,
+        50464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.284898887981068,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8409799933433533,
+      "confidence": 0.029,
+      "words": [
+        {
+          "text": "3",
+          "start": 0.04,
+          "end": 0.7,
+          "confidence": 0.029
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 1.96,
+      "end": 3.02,
+      "text": "2",
+      "tokens": [
+        50464,
+        17,
+        50564
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.284898887981068,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8409799933433533,
+      "confidence": 0.691,
+      "words": [
+        {
+          "text": "2",
+          "start": 1.96,
+          "end": 3.02,
+          "confidence": 0.691
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 3.72,
+      "end": 4.92,
+      "text": "1",
+      "tokens": [
+        50564,
+        16,
+        50664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.284898887981068,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8409799933433533,
+      "confidence": 0.949,
+      "words": [
+        {
+          "text": "1",
+          "start": 3.72,
+          "end": 4.92,
+          "confidence": 0.949
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 5.5,
+      "end": 7.08,
+      "text": "2",
+      "tokens": [
+        50664,
+        17,
+        50764
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.284898887981068,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8409799933433533,
+      "confidence": 0.278,
+      "words": [
+        {
+          "text": "2",
+          "start": 5.5,
+          "end": 7.08,
+          "confidence": 0.278
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 8.46,
+      "end": 9.34,
+      "text": "1",
+      "tokens": [
+        50764,
+        16,
+        50864
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.284898887981068,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8409799933433533,
+      "confidence": 0.702,
+      "words": [
+        {
+          "text": "1",
+          "start": 8.46,
+          "end": 9.34,
+          "confidence": 0.702
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 0,
+      "start": 9.78,
+      "end": 11.34,
+      "text": "2",
+      "tokens": [
+        50864,
+        17,
+        50964
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.284898887981068,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8409799933433533,
+      "confidence": 0.919,
+      "words": [
+        {
+          "text": "2",
+          "start": 9.78,
+          "end": 11.34,
+          "confidence": 0.919
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 0,
+      "start": 11.8,
+      "end": 13.4,
+      "text": "2",
+      "tokens": [
+        50964,
+        17,
+        51064
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.284898887981068,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8409799933433533,
+      "confidence": 0.657,
+      "words": [
+        {
+          "text": "2",
+          "start": 11.8,
+          "end": 13.4,
+          "confidence": 0.657
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 0,
+      "start": 13.68,
+      "end": 15.54,
+      "text": "2",
+      "tokens": [
+        51064,
+        17,
+        51164
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.284898887981068,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8409799933433533,
+      "confidence": 0.773,
+      "words": [
+        {
+          "text": "2",
+          "start": 13.68,
+          "end": 15.54,
+          "confidence": 0.773
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 0,
+      "start": 15.54,
+      "end": 17.2,
+      "text": "2",
+      "tokens": [
+        51164,
+        17,
+        51264
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.284898887981068,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8409799933433533,
+      "confidence": 0.905,
+      "words": [
+        {
+          "text": "2",
+          "start": 15.54,
+          "end": 17.2,
+          "confidence": 0.905
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 0,
+      "start": 17.5,
+      "end": 19.24,
+      "text": "2",
+      "tokens": [
+        51264,
+        17,
+        51364
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.284898887981068,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8409799933433533,
+      "confidence": 0.809,
+      "words": [
+        {
+          "text": "2",
+          "start": 17.5,
+          "end": 19.24,
+          "confidence": 0.809
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 0,
+      "start": 19.64,
+      "end": 20.8,
+      "text": "2",
+      "tokens": [
+        51364,
+        17,
+        51464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.284898887981068,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8409799933433533,
+      "confidence": 0.626,
+      "words": [
+        {
+          "text": "2",
+          "start": 19.64,
+          "end": 20.8,
+          "confidence": 0.626
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 0,
+      "start": 22.06,
+      "end": 22.9,
+      "text": "2",
+      "tokens": [
+        51464,
+        17,
+        51564
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.284898887981068,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8409799933433533,
+      "confidence": 0.834,
+      "words": [
+        {
+          "text": "2",
+          "start": 22.06,
+          "end": 22.9,
+          "confidence": 0.834
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 0,
+      "start": 23.56,
+      "end": 25.08,
+      "text": "2",
+      "tokens": [
+        51564,
+        17,
+        51664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.284898887981068,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8409799933433533,
+      "confidence": 0.974,
+      "words": [
+        {
+          "text": "2",
+          "start": 23.56,
+          "end": 25.08,
+          "confidence": 0.974
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 0,
+      "start": 26.48,
+      "end": 27.08,
+      "text": "2",
+      "tokens": [
+        51664,
+        17,
+        51764
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.284898887981068,
+      "compression_ratio": 1.0,
+      "no_speech_prob": 0.8409799933433533,
+      "confidence": 0.971,
+      "words": [
+        {
+          "text": "2",
+          "start": 26.48,
+          "end": 27.08,
+          "confidence": 0.971
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 2800,
+      "start": 28.12,
+      "end": 29.62,
+      "text": "1",
+      "tokens": [
+        50364,
+        16,
+        50464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.11499140479347923,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.18292438983917236,
+      "confidence": 0.316,
+      "words": [
+        {
+          "text": "1",
+          "start": 28.12,
+          "end": 29.62,
+          "confidence": 0.316
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 2800,
+      "start": 30.84,
+      "end": 31.14,
+      "text": "1",
+      "tokens": [
+        50464,
+        16,
+        50564
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.11499140479347923,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.18292438983917236,
+      "confidence": 0.545,
+      "words": [
+        {
+          "text": "1",
+          "start": 30.84,
+          "end": 31.14,
+          "confidence": 0.545
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 2800,
+      "start": 32.06,
+      "end": 33.18,
+      "text": "1",
+      "tokens": [
+        50564,
+        16,
+        50664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.11499140479347923,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.18292438983917236,
+      "confidence": 0.913,
+      "words": [
+        {
+          "text": "1",
+          "start": 32.06,
+          "end": 33.18,
+          "confidence": 0.913
+        }
+      ]
+    },
+    {
+      "id": 17,
+      "seek": 2800,
+      "start": 33.5,
+      "end": 35.1,
+      "text": "1",
+      "tokens": [
+        50664,
+        16,
+        50764
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.11499140479347923,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.18292438983917236,
+      "confidence": 0.887,
+      "words": [
+        {
+          "text": "1",
+          "start": 33.5,
+          "end": 35.1,
+          "confidence": 0.887
+        }
+      ]
+    },
+    {
+      "id": 18,
+      "seek": 2800,
+      "start": 36.18,
+      "end": 36.64,
+      "text": "1",
+      "tokens": [
+        50764,
+        16,
+        50864
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.11499140479347923,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.18292438983917236,
+      "confidence": 0.957,
+      "words": [
+        {
+          "text": "1",
+          "start": 36.18,
+          "end": 36.64,
+          "confidence": 0.957
+        }
+      ]
+    },
+    {
+      "id": 19,
+      "seek": 2800,
+      "start": 37.5,
+      "end": 38.46,
+      "text": "1",
+      "tokens": [
+        50864,
+        16,
+        50964
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.11499140479347923,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.18292438983917236,
+      "confidence": 0.958,
+      "words": [
+        {
+          "text": "1",
+          "start": 37.5,
+          "end": 38.46,
+          "confidence": 0.958
+        }
+      ]
+    },
+    {
+      "id": 20,
+      "seek": 2800,
+      "start": 39.5,
+      "end": 41.14,
+      "text": "1",
+      "tokens": [
+        50964,
+        16,
+        51064
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.11499140479347923,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.18292438983917236,
+      "confidence": 0.966,
+      "words": [
+        {
+          "text": "1",
+          "start": 39.5,
+          "end": 41.14,
+          "confidence": 0.966
+        }
+      ]
+    },
+    {
+      "id": 21,
+      "seek": 2800,
+      "start": 41.5,
+      "end": 43.38,
+      "text": "1",
+      "tokens": [
+        51064,
+        16,
+        51164
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.11499140479347923,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.18292438983917236,
+      "confidence": 0.973,
+      "words": [
+        {
+          "text": "1",
+          "start": 41.5,
+          "end": 43.38,
+          "confidence": 0.973
+        }
+      ]
+    },
+    {
+      "id": 22,
+      "seek": 2800,
+      "start": 43.88,
+      "end": 44.68,
+      "text": "1",
+      "tokens": [
+        51164,
+        16,
+        51264
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.11499140479347923,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.18292438983917236,
+      "confidence": 0.946,
+      "words": [
+        {
+          "text": "1",
+          "start": 43.88,
+          "end": 44.68,
+          "confidence": 0.946
+        }
+      ]
+    },
+    {
+      "id": 23,
+      "seek": 2800,
+      "start": 45.5,
+      "end": 47.16,
+      "text": "1",
+      "tokens": [
+        51264,
+        16,
+        51364
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.11499140479347923,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.18292438983917236,
+      "confidence": 0.96,
+      "words": [
+        {
+          "text": "1",
+          "start": 45.5,
+          "end": 47.16,
+          "confidence": 0.96
+        }
+      ]
+    },
+    {
+      "id": 24,
+      "seek": 2800,
+      "start": 47.94,
+      "end": 48.8,
+      "text": "1",
+      "tokens": [
+        51364,
+        16,
+        51464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.11499140479347923,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.18292438983917236,
+      "confidence": 0.965,
+      "words": [
+        {
+          "text": "1",
+          "start": 47.94,
+          "end": 48.8,
+          "confidence": 0.965
+        }
+      ]
+    },
+    {
+      "id": 25,
+      "seek": 2800,
+      "start": 50.22,
+      "end": 50.96,
+      "text": "1",
+      "tokens": [
+        51464,
+        16,
+        51564
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.11499140479347923,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.18292438983917236,
+      "confidence": 0.967,
+      "words": [
+        {
+          "text": "1",
+          "start": 50.22,
+          "end": 50.96,
+          "confidence": 0.967
+        }
+      ]
+    },
+    {
+      "id": 26,
+      "seek": 2800,
+      "start": 52.22,
+      "end": 52.84,
+      "text": "1",
+      "tokens": [
+        51564,
+        16,
+        51664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.11499140479347923,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.18292438983917236,
+      "confidence": 0.963,
+      "words": [
+        {
+          "text": "1",
+          "start": 52.22,
+          "end": 52.84,
+          "confidence": 0.963
+        }
+      ]
+    },
+    {
+      "id": 27,
+      "seek": 2800,
+      "start": 53.5,
+      "end": 54.78,
+      "text": "1",
+      "tokens": [
+        51664,
+        16,
+        51764
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.11499140479347923,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.18292438983917236,
+      "confidence": 0.945,
+      "words": [
+        {
+          "text": "1",
+          "start": 53.5,
+          "end": 54.78,
+          "confidence": 0.945
+        }
+      ]
+    },
+    {
+      "id": 28,
+      "seek": 5600,
+      "start": 56.56,
+      "end": 57.24,
+      "text": "1",
+      "tokens": [
+        50364,
+        16,
+        50464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1206196438182484,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1875864416360855,
+      "confidence": 0.425,
+      "words": [
+        {
+          "text": "1",
+          "start": 56.56,
+          "end": 57.24,
+          "confidence": 0.425
+        }
+      ]
+    },
+    {
+      "id": 29,
+      "seek": 5600,
+      "start": 57.64,
+      "end": 58.86,
+      "text": "1",
+      "tokens": [
+        50464,
+        16,
+        50564
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1206196438182484,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1875864416360855,
+      "confidence": 0.789,
+      "words": [
+        {
+          "text": "1",
+          "start": 57.64,
+          "end": 58.86,
+          "confidence": 0.789
+        }
+      ]
+    },
+    {
+      "id": 30,
+      "seek": 5600,
+      "start": 60.08,
+      "end": 60.92,
+      "text": "1",
+      "tokens": [
+        50564,
+        16,
+        50664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1206196438182484,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1875864416360855,
+      "confidence": 0.953,
+      "words": [
+        {
+          "text": "1",
+          "start": 60.08,
+          "end": 60.92,
+          "confidence": 0.953
+        }
+      ]
+    },
+    {
+      "id": 31,
+      "seek": 5600,
+      "start": 61.5,
+      "end": 62.62,
+      "text": "1",
+      "tokens": [
+        50664,
+        16,
+        50764
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1206196438182484,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1875864416360855,
+      "confidence": 0.949,
+      "words": [
+        {
+          "text": "1",
+          "start": 61.5,
+          "end": 62.62,
+          "confidence": 0.949
+        }
+      ]
+    },
+    {
+      "id": 32,
+      "seek": 5600,
+      "start": 64.36,
+      "end": 65.06,
+      "text": "1",
+      "tokens": [
+        50764,
+        16,
+        50864
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1206196438182484,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1875864416360855,
+      "confidence": 0.954,
+      "words": [
+        {
+          "text": "1",
+          "start": 64.36,
+          "end": 65.06,
+          "confidence": 0.954
+        }
+      ]
+    },
+    {
+      "id": 33,
+      "seek": 5600,
+      "start": 65.5,
+      "end": 66.92,
+      "text": "1",
+      "tokens": [
+        50864,
+        16,
+        50964
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1206196438182484,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1875864416360855,
+      "confidence": 0.952,
+      "words": [
+        {
+          "text": "1",
+          "start": 65.5,
+          "end": 66.92,
+          "confidence": 0.952
+        }
+      ]
+    },
+    {
+      "id": 34,
+      "seek": 5600,
+      "start": 67.96,
+      "end": 69.06,
+      "text": "1",
+      "tokens": [
+        50964,
+        16,
+        51064
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1206196438182484,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1875864416360855,
+      "confidence": 0.965,
+      "words": [
+        {
+          "text": "1",
+          "start": 67.96,
+          "end": 69.06,
+          "confidence": 0.965
+        }
+      ]
+    },
+    {
+      "id": 35,
+      "seek": 5600,
+      "start": 70.38,
+      "end": 71.69,
+      "text": "1",
+      "tokens": [
+        51064,
+        16,
+        51164
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1206196438182484,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1875864416360855,
+      "confidence": 0.956,
+      "words": [
+        {
+          "text": "1",
+          "start": 70.38,
+          "end": 71.69,
+          "confidence": 0.956
+        }
+      ]
+    },
+    {
+      "id": 36,
+      "seek": 5600,
+      "start": 71.69,
+      "end": 73.56,
+      "text": "1",
+      "tokens": [
+        51164,
+        16,
+        51264
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1206196438182484,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1875864416360855,
+      "confidence": 0.957,
+      "words": [
+        {
+          "text": "1",
+          "start": 71.69,
+          "end": 73.56,
+          "confidence": 0.957
+        }
+      ]
+    },
+    {
+      "id": 37,
+      "seek": 5600,
+      "start": 73.56,
+      "end": 75.34,
+      "text": "1",
+      "tokens": [
+        51264,
+        16,
+        51364
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1206196438182484,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1875864416360855,
+      "confidence": 0.955,
+      "words": [
+        {
+          "text": "1",
+          "start": 73.56,
+          "end": 75.34,
+          "confidence": 0.955
+        }
+      ]
+    },
+    {
+      "id": 38,
+      "seek": 5600,
+      "start": 75.5,
+      "end": 76.42,
+      "text": "1",
+      "tokens": [
+        51364,
+        16,
+        51464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1206196438182484,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1875864416360855,
+      "confidence": 0.939,
+      "words": [
+        {
+          "text": "1",
+          "start": 75.5,
+          "end": 76.42,
+          "confidence": 0.939
+        }
+      ]
+    },
+    {
+      "id": 39,
+      "seek": 5600,
+      "start": 78.14,
+      "end": 78.78,
+      "text": "1",
+      "tokens": [
+        51464,
+        16,
+        51564
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1206196438182484,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1875864416360855,
+      "confidence": 0.936,
+      "words": [
+        {
+          "text": "1",
+          "start": 78.14,
+          "end": 78.78,
+          "confidence": 0.936
+        }
+      ]
+    },
+    {
+      "id": 40,
+      "seek": 5600,
+      "start": 80.08,
+      "end": 80.86,
+      "text": "1",
+      "tokens": [
+        51564,
+        16,
+        51664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1206196438182484,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1875864416360855,
+      "confidence": 0.922,
+      "words": [
+        {
+          "text": "1",
+          "start": 80.08,
+          "end": 80.86,
+          "confidence": 0.922
+        }
+      ]
+    },
+    {
+      "id": 41,
+      "seek": 5600,
+      "start": 81.5,
+      "end": 82.84,
+      "text": "1",
+      "tokens": [
+        51664,
+        16,
+        51764
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1206196438182484,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1875864416360855,
+      "confidence": 0.896,
+      "words": [
+        {
+          "text": "1",
+          "start": 81.5,
+          "end": 82.84,
+          "confidence": 0.896
+        }
+      ]
+    },
+    {
+      "id": 42,
+      "seek": 8400,
+      "start": 84.82,
+      "end": 85.6,
+      "text": "1",
+      "tokens": [
+        50364,
+        16,
+        50464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10664921457117255,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1820167452096939,
+      "confidence": 0.793,
+      "words": [
+        {
+          "text": "1",
+          "start": 84.82,
+          "end": 85.6,
+          "confidence": 0.793
+        }
+      ]
+    },
+    {
+      "id": 43,
+      "seek": 8400,
+      "start": 85.6,
+      "end": 86.8,
+      "text": "1",
+      "tokens": [
+        50464,
+        16,
+        50564
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10664921457117255,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1820167452096939,
+      "confidence": 0.88,
+      "words": [
+        {
+          "text": "1",
+          "start": 85.6,
+          "end": 86.8,
+          "confidence": 0.88
+        }
+      ]
+    },
+    {
+      "id": 44,
+      "seek": 8400,
+      "start": 87.76,
+      "end": 88.72,
+      "text": "1",
+      "tokens": [
+        50564,
+        16,
+        50664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10664921457117255,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1820167452096939,
+      "confidence": 0.954,
+      "words": [
+        {
+          "text": "1",
+          "start": 87.76,
+          "end": 88.72,
+          "confidence": 0.954
+        }
+      ]
+    },
+    {
+      "id": 45,
+      "seek": 8400,
+      "start": 89.5,
+      "end": 90.52,
+      "text": "1",
+      "tokens": [
+        50664,
+        16,
+        50764
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10664921457117255,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1820167452096939,
+      "confidence": 0.951,
+      "words": [
+        {
+          "text": "1",
+          "start": 89.5,
+          "end": 90.52,
+          "confidence": 0.951
+        }
+      ]
+    },
+    {
+      "id": 46,
+      "seek": 8400,
+      "start": 91.5,
+      "end": 93.02,
+      "text": "1",
+      "tokens": [
+        50764,
+        16,
+        50864
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10664921457117255,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1820167452096939,
+      "confidence": 0.91,
+      "words": [
+        {
+          "text": "1",
+          "start": 91.5,
+          "end": 93.02,
+          "confidence": 0.91
+        }
+      ]
+    },
+    {
+      "id": 47,
+      "seek": 8400,
+      "start": 93.68,
+      "end": 95.36,
+      "text": "1",
+      "tokens": [
+        50864,
+        16,
+        50964
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10664921457117255,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1820167452096939,
+      "confidence": 0.944,
+      "words": [
+        {
+          "text": "1",
+          "start": 93.68,
+          "end": 95.36,
+          "confidence": 0.944
+        }
+      ]
+    },
+    {
+      "id": 48,
+      "seek": 8400,
+      "start": 95.86,
+      "end": 97.84,
+      "text": "1",
+      "tokens": [
+        50964,
+        16,
+        51064
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10664921457117255,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1820167452096939,
+      "confidence": 0.967,
+      "words": [
+        {
+          "text": "1",
+          "start": 95.86,
+          "end": 97.84,
+          "confidence": 0.967
+        }
+      ]
+    },
+    {
+      "id": 49,
+      "seek": 8400,
+      "start": 97.84,
+      "end": 98.98,
+      "text": "1",
+      "tokens": [
+        51064,
+        16,
+        51164
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10664921457117255,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1820167452096939,
+      "confidence": 0.976,
+      "words": [
+        {
+          "text": "1",
+          "start": 97.84,
+          "end": 98.98,
+          "confidence": 0.976
+        }
+      ]
+    },
+    {
+      "id": 50,
+      "seek": 8400,
+      "start": 99.5,
+      "end": 101.1,
+      "text": "1",
+      "tokens": [
+        51164,
+        16,
+        51264
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10664921457117255,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1820167452096939,
+      "confidence": 0.981,
+      "words": [
+        {
+          "text": "1",
+          "start": 99.5,
+          "end": 101.1,
+          "confidence": 0.981
+        }
+      ]
+    },
+    {
+      "id": 51,
+      "seek": 8400,
+      "start": 101.5,
+      "end": 103.48,
+      "text": "1",
+      "tokens": [
+        51264,
+        16,
+        51364
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10664921457117255,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1820167452096939,
+      "confidence": 0.985,
+      "words": [
+        {
+          "text": "1",
+          "start": 101.5,
+          "end": 103.48,
+          "confidence": 0.985
+        }
+      ]
+    },
+    {
+      "id": 52,
+      "seek": 8400,
+      "start": 103.5,
+      "end": 105.44,
+      "text": "1",
+      "tokens": [
+        51364,
+        16,
+        51464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10664921457117255,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1820167452096939,
+      "confidence": 0.987,
+      "words": [
+        {
+          "text": "1",
+          "start": 103.5,
+          "end": 105.44,
+          "confidence": 0.987
+        }
+      ]
+    },
+    {
+      "id": 53,
+      "seek": 8400,
+      "start": 105.58,
+      "end": 107.08,
+      "text": "1",
+      "tokens": [
+        51464,
+        16,
+        51564
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10664921457117255,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1820167452096939,
+      "confidence": 0.956,
+      "words": [
+        {
+          "text": "1",
+          "start": 105.58,
+          "end": 107.08,
+          "confidence": 0.956
+        }
+      ]
+    },
+    {
+      "id": 54,
+      "seek": 8400,
+      "start": 108.32,
+      "end": 108.98,
+      "text": "1",
+      "tokens": [
+        51564,
+        16,
+        51664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10664921457117255,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1820167452096939,
+      "confidence": 0.946,
+      "words": [
+        {
+          "text": "1",
+          "start": 108.32,
+          "end": 108.98,
+          "confidence": 0.946
+        }
+      ]
+    },
+    {
+      "id": 55,
+      "seek": 8400,
+      "start": 109.5,
+      "end": 110.4,
+      "text": "1",
+      "tokens": [
+        51664,
+        16,
+        51764
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10664921457117255,
+      "compression_ratio": 1.2727272727272727,
+      "no_speech_prob": 0.1820167452096939,
+      "confidence": 0.888,
+      "words": [
+        {
+          "text": "1",
+          "start": 109.5,
+          "end": 110.4,
+          "confidence": 0.888
+        }
+      ]
+    },
+    {
+      "id": 56,
+      "seek": 11200,
+      "start": 112.66,
+      "end": 113.32,
+      "text": "1",
+      "tokens": [
+        50364,
+        16,
+        50464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12969079613685608,
+      "compression_ratio": 0.45454545454545453,
+      "no_speech_prob": 0.27970418334007263,
+      "confidence": 0.917,
+      "words": [
+        {
+          "text": "1",
+          "start": 112.66,
+          "end": 113.32,
+          "confidence": 0.917
+        }
+      ]
+    },
+    {
+      "id": 57,
+      "seek": 11200,
+      "start": 113.98,
+      "end": 114.82,
+      "text": "1",
+      "tokens": [
+        50464,
+        16,
+        50564
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12969079613685608,
+      "compression_ratio": 0.45454545454545453,
+      "no_speech_prob": 0.27970418334007263,
+      "confidence": 0.888,
+      "words": [
+        {
+          "text": "1",
+          "start": 113.98,
+          "end": 114.82,
+          "confidence": 0.888
+        }
+      ]
+    },
+    {
+      "id": 58,
+      "seek": 11200,
+      "start": 116.1,
+      "end": 117.3,
+      "text": "1",
+      "tokens": [
+        50564,
+        16,
+        50664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12969079613685608,
+      "compression_ratio": 0.45454545454545453,
+      "no_speech_prob": 0.27970418334007263,
+      "confidence": 0.979,
+      "words": [
+        {
+          "text": "1",
+          "start": 116.1,
+          "end": 117.3,
+          "confidence": 0.979
+        }
+      ]
+    },
+    {
+      "id": 59,
+      "seek": 11200,
+      "start": 117.5,
+      "end": 118.68,
+      "text": "1",
+      "tokens": [
+        50664,
+        16,
+        50764
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12969079613685608,
+      "compression_ratio": 0.45454545454545453,
+      "no_speech_prob": 0.27970418334007263,
+      "confidence": 0.981,
+      "words": [
+        {
+          "text": "1",
+          "start": 117.5,
+          "end": 118.68,
+          "confidence": 0.981
+        }
+      ]
+    },
+    {
+      "id": 60,
+      "seek": 11200,
+      "start": 119.5,
+      "end": 120.86,
+      "text": "1",
+      "tokens": [
+        50764,
+        16,
+        50864
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12969079613685608,
+      "compression_ratio": 0.45454545454545453,
+      "no_speech_prob": 0.27970418334007263,
+      "confidence": 0.973,
+      "words": [
+        {
+          "text": "1",
+          "start": 119.5,
+          "end": 120.86,
+          "confidence": 0.973
+        }
+      ]
+    }
+  ],
+  "language": "zh",
+  "language_probs": {
+    "en": 0.3608749508857727,
+    "zh": 0.40258511900901794,
+    "de": 0.017688356339931488,
+    "es": 0.013351871632039547,
+    "ru": 0.024557847529649734,
+    "ko": 0.03202947601675987,
+    "fr": 0.010237235575914383,
+    "ja": 0.024944579228758812,
+    "pt": 0.014436815865337849,
+    "tr": 0.011968540027737617,
+    "pl": 0.0067137423902750015,
+    "ca": 0.0001964998955372721,
+    "nl": 0.0022488220129162073,
+    "ar": 0.006306977476924658,
+    "sv": 0.0012813402572646737,
+    "it": 0.005653538275510073,
+    "id": 0.0013428329257294536,
+    "hi": 0.001451948657631874,
+    "fi": 0.0006052622338756919,
+    "vi": 0.004614283796399832,
+    "he": 0.0003614185843616724,
+    "uk": 0.0006442983285523951,
+    "el": 0.0013015182921662927,
+    "ms": 0.0029792049899697304,
+    "cs": 0.0003728912561200559,
+    "ro": 0.000982437515631318,
+    "da": 0.00043595407623797655,
+    "hu": 0.0023202074225991964,
+    "ta": 0.00022616998467128724,
+    "no": 0.00028590564033947885,
+    "th": 0.0027553143445402384,
+    "ur": 0.0006244753021746874,
+    "hr": 5.992907608742826e-05,
+    "bg": 4.594921847456135e-05,
+    "lt": 1.0744692190201022e-05,
+    "la": 0.0025482492055743933,
+    "mi": 0.0003502989129628986,
+    "ml": 0.00017614134412724525,
+    "cy": 0.0029792049899697304,
+    "sk": 1.9762512238230556e-05,
+    "te": 0.00020273745758458972,
+    "fa": 0.0007300855941139162,
+    "lv": 2.2876768071000697e-06,
+    "bn": 0.00011372540757292882,
+    "sr": 2.552088062657276e-06,
+    "az": 2.1490734525286825e-06,
+    "sl": 3.2077721698442474e-05,
+    "kn": 6.868851301078394e-07,
+    "et": 2.0188676899124403e-06,
+    "mk": 3.244615527364658e-07,
+    "br": 0.0006752188201062381,
+    "eu": 2.4594843125669286e-05,
+    "is": 1.8857521354220808e-05,
+    "hy": 6.415948973881314e-06,
+    "ne": 2.3838139895815402e-05,
+    "mn": 1.9456123482086696e-05,
+    "bs": 2.0389841665746644e-05,
+    "kk": 2.0188676899124403e-06,
+    "sq": 1.8671472616915707e-06,
+    "sw": 1.1085765436291695e-05,
+    "gl": 0.00017341053171548992,
+    "mr": 1.6737000123612233e-06,
+    "pa": 4.996745246899081e-06,
+    "si": 0.00014376237231772393,
+    "km": 0.00041599024552851915,
+    "sn": 0.00018459455168340355,
+    "yo": 3.9302449295064434e-05,
+    "so": 1.7097923432629614e-07,
+    "af": 1.8097013025908382e-06,
+    "oc": 1.4458562873187475e-05,
+    "ka": 3.1943122280608804e-07,
+    "be": 3.8093239709269255e-05,
+    "tg": 6.14426696188275e-08,
+    "sd": 5.8417867876414675e-06,
+    "gu": 2.4111935204018664e-07,
+    "am": 1.9833936448776512e-07,
+    "yi": 1.025265646603657e-05,
+    "lo": 1.4458562873187475e-05,
+    "uz": 1.0760877522386636e-08,
+    "fo": 1.2175330084573943e-05,
+    "ht": 8.499750947521534e-06,
+    "ps": 1.198656900669448e-05,
+    "tk": 7.411401270474016e-08,
+    "nn": 0.02100544236600399,
+    "mt": 1.9374485304979316e-07,
+    "sa": 0.00014376237231772393,
+    "lb": 2.2253061615629122e-08,
+    "my": 0.00010517879854887724,
+    "bo": 2.1368370653362945e-05,
+    "tl": 0.0008144693565554917,
+    "mg": 1.0616341228342208e-07,
+    "as": 1.2055209026584635e-06,
+    "tt": 1.0594044752565424e-08,
+    "haw": 0.004989230073988438,
+    "ln": 2.689880886919127e-07,
+    "ha": 5.296689664646692e-08,
+    "ba": 7.239716381945982e-08,
+    "jw": 0.007373603526502848,
+    "su": 1.3954918642866687e-07
+  }
+}
\ No newline at end of file
diff --git a/tests/expected/medium_auto/smartphone.mp3.words.json b/tests/expected/medium_auto/smartphone.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..45164d8b8e4c657445fbb0687e46114bd1acb1b5
--- /dev/null
+++ b/tests/expected/medium_auto/smartphone.mp3.words.json
@@ -0,0 +1,5000 @@
+{
+  "text": " C'est évident ce que dit Nicolas, mais je ne me l'étais jamais formulé comme ça. Ce qui fait la force du smartphone, c'est pas seulement l'accumulation des fonctions, mais la manière dont elles interagissent entre elles. Ce qui dit d'ailleurs sur la photo, c'est hyper convaincant. Alors évidemment, il faudrait ajouter les interfaces. L'écran tactile a été beaucoup très souvent mentionné. Mais bon, il faut dire qu'il profite aussi de 20 ans pendant lesquels les ordinateurs nous ont appris à cliquer sur des icônes. Sauf que le smartphone ajoute le toucher, ce qui rend le contact plus direct, plus sensible. Et puis évidemment, il faudrait parler aussi des applications qui permettent de contourner le côté touffu de la navigation web pour aller directement au but. Bref, tout ça, ce sont les conditions qui permettent de créer cet objet dont Nicolas dit qu'il est vraisemblablement inédit dans l'histoire de l'humanité. Mais ça, ça soulève une autre interrogation. Est-ce que le fait que cet objet soit inédit induit que notre rapport à lui est aussi un rapport inédit ? Je veux dire, est-ce que le rapport qu'on a au smartphone est comparable à celui qu'on entretenait à d'autres objets techniques comme la voiture ou le téléphone ? Il n'y a pas d'équivalent en fait. Et donc cette espèce de nouveauté dans la relation à l'objet, c'est fascinant et terrifiant. Parce qu'on a l'impression, comme le disent les utilisateurs et les services, d'être dépendant de cet objet, d'induire en fait une espèce de relation, de médiation avec le monde qui rend de l'ampleur et qui amène aussi à des formes de rejet. Donc à objet inédit, rapport inédit. Et ce rapport, si j'en crois à Nicolas, serait caractérisé par un mélange de dépendance et de rejet. Bon, en vrai, il faudrait remonter très très finement toute l'histoire des objets techniques et de leur insertion dans nos vies pour déterminer si ce rapport est totalement inédit. Mais j'ai l'impression comme ça que Nicolas ne se trompe pas vraiment. Pour autant que je sache, il y a eu plein de discussions autour de la voiture ou même du téléphone. Mais la dépendance n'était pas du même ordre. Donc le rejet non plus n'était pas du même ordre. On peut adorer sa bagnole, en avoir besoin pour plein de choses. Le soir, quand on va se coucher, on la laisse. On ne l'a pas dans la main quand on est au lit, on ne l'emmène pas au chiottes. On pouvait être énervé par son môme qui occupait la ligne de téléphone pendant une heure chaque soir pour discuter avec un copain. Mais ça ne ressemblait pas à ce qu'on peut ressentir à voir ce même môme aujourd'hui, continuellement avec son smartphone dans la main, comme si c'était une sorte de pacemaker externe, comme si le lâcher allait entraîner sa mort immédiate. Bon, je dis ça pour le môme, mais c'est évidemment valable pour nous aussi. Donc, rapport inédit, d'accord. Mais pourquoi a-t-on l'impression qu'on n'en sortira jamais ? Est-ce qu'il faut en remettre la faute sur les gens qui ont créé cet outil merveilleux et diabolique, et diabolique parce que merveilleux ? Les économistes parlent de dépendance du sentier. C'est l'idée qu'on met sur un sentier qui a été établi, soit volontairement en marchant dessus, soit en définissant des bornes, en définissant une signalétique.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.4,
+      "end": 3.66,
+      "text": " C'est évident ce que dit Nicolas, mais je ne me l'étais jamais formulé comme ça.",
+      "tokens": [
+        50364,
+        383,
+        6,
+        377,
+        20090,
+        1078,
+        1769,
+        631,
+        6176,
+        38268,
+        11,
+        2420,
+        1506,
+        408,
+        385,
+        287,
+        6,
+        22824,
+        14540,
+        49990,
+        526,
+        5173,
+        2788,
+        13,
+        50539
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2362650940749819,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.15368737280368805,
+      "confidence": 0.935,
+      "words": [
+        {
+          "text": "C'est",
+          "start": 0.4,
+          "end": 0.64,
+          "confidence": 0.961
+        },
+        {
+          "text": "évident",
+          "start": 0.64,
+          "end": 0.9,
+          "confidence": 0.984
+        },
+        {
+          "text": "ce",
+          "start": 0.9,
+          "end": 1.0,
+          "confidence": 0.663
+        },
+        {
+          "text": "que",
+          "start": 1.0,
+          "end": 1.08,
+          "confidence": 0.989
+        },
+        {
+          "text": "dit",
+          "start": 1.08,
+          "end": 1.2,
+          "confidence": 0.994
+        },
+        {
+          "text": "Nicolas,",
+          "start": 1.2,
+          "end": 1.48,
+          "confidence": 0.91
+        },
+        {
+          "text": "mais",
+          "start": 1.7,
+          "end": 2.04,
+          "confidence": 0.979
+        },
+        {
+          "text": "je",
+          "start": 2.04,
+          "end": 2.26,
+          "confidence": 0.981
+        },
+        {
+          "text": "ne",
+          "start": 2.26,
+          "end": 2.34,
+          "confidence": 0.837
+        },
+        {
+          "text": "me",
+          "start": 2.34,
+          "end": 2.36,
+          "confidence": 0.821
+        },
+        {
+          "text": "l'étais",
+          "start": 2.36,
+          "end": 2.58,
+          "confidence": 0.971
+        },
+        {
+          "text": "jamais",
+          "start": 2.58,
+          "end": 2.88,
+          "confidence": 0.989
+        },
+        {
+          "text": "formulé",
+          "start": 2.88,
+          "end": 3.26,
+          "confidence": 0.908
+        },
+        {
+          "text": "comme",
+          "start": 3.26,
+          "end": 3.44,
+          "confidence": 0.993
+        },
+        {
+          "text": "ça.",
+          "start": 3.44,
+          "end": 3.66,
+          "confidence": 0.975
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 4.16,
+      "end": 7.94,
+      "text": " Ce qui fait la force du smartphone, c'est pas seulement l'accumulation des fonctions,",
+      "tokens": [
+        50549,
+        8257,
+        1956,
+        3887,
+        635,
+        3464,
+        1581,
+        13307,
+        11,
+        269,
+        6,
+        377,
+        1736,
+        27772,
+        287,
+        6,
+        8476,
+        449,
+        2776,
+        730,
+        17290,
+        3916,
+        11,
+        50756
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2362650940749819,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.15368737280368805,
+      "confidence": 0.93,
+      "words": [
+        {
+          "text": "Ce",
+          "start": 4.16,
+          "end": 4.28,
+          "confidence": 0.952
+        },
+        {
+          "text": "qui",
+          "start": 4.28,
+          "end": 4.36,
+          "confidence": 0.958
+        },
+        {
+          "text": "fait",
+          "start": 4.36,
+          "end": 4.5,
+          "confidence": 0.567
+        },
+        {
+          "text": "la",
+          "start": 4.5,
+          "end": 4.76,
+          "confidence": 0.972
+        },
+        {
+          "text": "force",
+          "start": 4.76,
+          "end": 5.02,
+          "confidence": 0.999
+        },
+        {
+          "text": "du",
+          "start": 5.02,
+          "end": 5.22,
+          "confidence": 0.996
+        },
+        {
+          "text": "smartphone,",
+          "start": 5.22,
+          "end": 5.7,
+          "confidence": 0.912
+        },
+        {
+          "text": "c'est",
+          "start": 6.04,
+          "end": 6.16,
+          "confidence": 0.879
+        },
+        {
+          "text": "pas",
+          "start": 6.16,
+          "end": 6.26,
+          "confidence": 0.991
+        },
+        {
+          "text": "seulement",
+          "start": 6.26,
+          "end": 6.54,
+          "confidence": 0.999
+        },
+        {
+          "text": "l'accumulation",
+          "start": 6.54,
+          "end": 7.4,
+          "confidence": 0.958
+        },
+        {
+          "text": "des",
+          "start": 7.4,
+          "end": 7.58,
+          "confidence": 0.983
+        },
+        {
+          "text": "fonctions,",
+          "start": 7.58,
+          "end": 7.94,
+          "confidence": 0.987
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 8.32,
+      "end": 10.88,
+      "text": " mais la manière dont elles interagissent entre elles.",
+      "tokens": [
+        50756,
+        2420,
+        635,
+        22267,
+        9400,
+        23576,
+        728,
+        559,
+        25450,
+        3962,
+        23576,
+        13,
+        50906
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2362650940749819,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.15368737280368805,
+      "confidence": 0.977,
+      "words": [
+        {
+          "text": "mais",
+          "start": 8.32,
+          "end": 8.48,
+          "confidence": 0.992
+        },
+        {
+          "text": "la",
+          "start": 8.48,
+          "end": 8.7,
+          "confidence": 0.995
+        },
+        {
+          "text": "manière",
+          "start": 8.7,
+          "end": 8.94,
+          "confidence": 0.999
+        },
+        {
+          "text": "dont",
+          "start": 8.94,
+          "end": 9.08,
+          "confidence": 0.978
+        },
+        {
+          "text": "elles",
+          "start": 9.08,
+          "end": 9.48,
+          "confidence": 0.967
+        },
+        {
+          "text": "interagissent",
+          "start": 9.48,
+          "end": 10.38,
+          "confidence": 0.964
+        },
+        {
+          "text": "entre",
+          "start": 10.38,
+          "end": 10.7,
+          "confidence": 0.955
+        },
+        {
+          "text": "elles.",
+          "start": 10.7,
+          "end": 10.88,
+          "confidence": 0.989
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 10.96,
+      "end": 13.0,
+      "text": " Ce qui dit d'ailleurs sur la photo, c'est hyper convaincant.",
+      "tokens": [
+        50906,
+        8257,
+        1956,
+        6176,
+        274,
+        6,
+        19400,
+        1022,
+        635,
+        5052,
+        11,
+        269,
+        6,
+        377,
+        9848,
+        3754,
+        491,
+        66,
+        394,
+        13,
+        51006
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2362650940749819,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.15368737280368805,
+      "confidence": 0.906,
+      "words": [
+        {
+          "text": "Ce",
+          "start": 10.96,
+          "end": 11.16,
+          "confidence": 0.608
+        },
+        {
+          "text": "qui",
+          "start": 11.16,
+          "end": 11.26,
+          "confidence": 0.769
+        },
+        {
+          "text": "dit",
+          "start": 11.26,
+          "end": 11.38,
+          "confidence": 0.983
+        },
+        {
+          "text": "d'ailleurs",
+          "start": 11.38,
+          "end": 11.58,
+          "confidence": 0.985
+        },
+        {
+          "text": "sur",
+          "start": 11.58,
+          "end": 11.72,
+          "confidence": 0.48
+        },
+        {
+          "text": "la",
+          "start": 11.72,
+          "end": 11.82,
+          "confidence": 0.984
+        },
+        {
+          "text": "photo,",
+          "start": 11.82,
+          "end": 12.0,
+          "confidence": 0.994
+        },
+        {
+          "text": "c'est",
+          "start": 12.14,
+          "end": 12.2,
+          "confidence": 0.997
+        },
+        {
+          "text": "hyper",
+          "start": 12.2,
+          "end": 12.48,
+          "confidence": 0.993
+        },
+        {
+          "text": "convaincant.",
+          "start": 12.48,
+          "end": 13.0,
+          "confidence": 0.982
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 13.38,
+      "end": 16.04,
+      "text": " Alors évidemment, il faudrait ajouter les interfaces.",
+      "tokens": [
+        51006,
+        9946,
+        24724,
+        11,
+        1930,
+        38694,
+        8645,
+        17680,
+        23985,
+        1512,
+        28416,
+        13,
+        51166
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2362650940749819,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.15368737280368805,
+      "confidence": 0.912,
+      "words": [
+        {
+          "text": "Alors",
+          "start": 13.38,
+          "end": 13.58,
+          "confidence": 0.584
+        },
+        {
+          "text": "évidemment,",
+          "start": 13.58,
+          "end": 13.86,
+          "confidence": 0.832
+        },
+        {
+          "text": "il",
+          "start": 14.26,
+          "end": 14.42,
+          "confidence": 0.953
+        },
+        {
+          "text": "faudrait",
+          "start": 14.42,
+          "end": 14.76,
+          "confidence": 0.996
+        },
+        {
+          "text": "ajouter",
+          "start": 14.76,
+          "end": 15.2,
+          "confidence": 0.992
+        },
+        {
+          "text": "les",
+          "start": 15.2,
+          "end": 15.6,
+          "confidence": 0.985
+        },
+        {
+          "text": "interfaces.",
+          "start": 15.6,
+          "end": 16.04,
+          "confidence": 0.984
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 0,
+      "start": 16.22,
+      "end": 19.36,
+      "text": " L'écran tactile a été beaucoup très souvent mentionné.",
+      "tokens": [
+        51166,
+        441,
+        6,
+        9062,
+        4257,
+        47319,
+        257,
+        8862,
+        8796,
+        5732,
+        20847,
+        2152,
+        15055,
+        13,
+        51331
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2362650940749819,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.15368737280368805,
+      "confidence": 0.923,
+      "words": [
+        {
+          "text": "L'écran",
+          "start": 16.22,
+          "end": 16.78,
+          "confidence": 0.996
+        },
+        {
+          "text": "tactile",
+          "start": 16.78,
+          "end": 17.1,
+          "confidence": 0.986
+        },
+        {
+          "text": "a",
+          "start": 17.1,
+          "end": 17.3,
+          "confidence": 0.98
+        },
+        {
+          "text": "été",
+          "start": 17.3,
+          "end": 17.84,
+          "confidence": 0.974
+        },
+        {
+          "text": "beaucoup",
+          "start": 17.84,
+          "end": 18.28,
+          "confidence": 0.976
+        },
+        {
+          "text": "très",
+          "start": 18.28,
+          "end": 18.62,
+          "confidence": 0.447
+        },
+        {
+          "text": "souvent",
+          "start": 18.62,
+          "end": 18.9,
+          "confidence": 0.996
+        },
+        {
+          "text": "mentionné.",
+          "start": 18.9,
+          "end": 19.36,
+          "confidence": 0.978
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 0,
+      "start": 20.02,
+      "end": 25.44,
+      "text": " Mais bon, il faut dire qu'il profite aussi de 20 ans pendant lesquels les ordinateurs nous ont appris à cliquer sur des icônes.",
+      "tokens": [
+        51331,
+        6313,
+        4428,
+        11,
+        1930,
+        8487,
+        1264,
+        421,
+        6,
+        388,
+        1740,
+        642,
+        6212,
+        368,
+        945,
+        1567,
+        17338,
+        1512,
+        358,
+        1625,
+        1512,
+        4792,
+        13923,
+        2156,
+        4666,
+        6592,
+        724,
+        5714,
+        1531,
+        596,
+        23909,
+        1022,
+        730,
+        4376,
+        2851,
+        4081,
+        13,
+        51631
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2362650940749819,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.15368737280368805,
+      "confidence": 0.92,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 20.02,
+          "end": 20.26,
+          "confidence": 0.943
+        },
+        {
+          "text": "bon,",
+          "start": 20.26,
+          "end": 20.5,
+          "confidence": 0.666
+        },
+        {
+          "text": "il",
+          "start": 20.52,
+          "end": 20.62,
+          "confidence": 0.99
+        },
+        {
+          "text": "faut",
+          "start": 20.62,
+          "end": 20.7,
+          "confidence": 0.99
+        },
+        {
+          "text": "dire",
+          "start": 20.7,
+          "end": 20.82,
+          "confidence": 0.995
+        },
+        {
+          "text": "qu'il",
+          "start": 20.82,
+          "end": 21.04,
+          "confidence": 0.88
+        },
+        {
+          "text": "profite",
+          "start": 21.04,
+          "end": 21.3,
+          "confidence": 0.995
+        },
+        {
+          "text": "aussi",
+          "start": 21.3,
+          "end": 21.7,
+          "confidence": 0.972
+        },
+        {
+          "text": "de",
+          "start": 21.7,
+          "end": 21.94,
+          "confidence": 0.97
+        },
+        {
+          "text": "20",
+          "start": 21.94,
+          "end": 22.16,
+          "confidence": 0.812
+        },
+        {
+          "text": "ans",
+          "start": 22.16,
+          "end": 22.3,
+          "confidence": 0.997
+        },
+        {
+          "text": "pendant",
+          "start": 22.3,
+          "end": 22.54,
+          "confidence": 0.723
+        },
+        {
+          "text": "lesquels",
+          "start": 22.54,
+          "end": 22.92,
+          "confidence": 0.98
+        },
+        {
+          "text": "les",
+          "start": 22.92,
+          "end": 23.14,
+          "confidence": 0.71
+        },
+        {
+          "text": "ordinateurs",
+          "start": 23.14,
+          "end": 23.58,
+          "confidence": 0.966
+        },
+        {
+          "text": "nous",
+          "start": 23.58,
+          "end": 23.74,
+          "confidence": 0.602
+        },
+        {
+          "text": "ont",
+          "start": 23.74,
+          "end": 23.88,
+          "confidence": 0.974
+        },
+        {
+          "text": "appris",
+          "start": 23.88,
+          "end": 24.12,
+          "confidence": 0.991
+        },
+        {
+          "text": "à",
+          "start": 24.12,
+          "end": 24.26,
+          "confidence": 0.828
+        },
+        {
+          "text": "cliquer",
+          "start": 24.26,
+          "end": 24.54,
+          "confidence": 0.989
+        },
+        {
+          "text": "sur",
+          "start": 24.54,
+          "end": 24.72,
+          "confidence": 0.984
+        },
+        {
+          "text": "des",
+          "start": 24.72,
+          "end": 24.92,
+          "confidence": 0.971
+        },
+        {
+          "text": "icônes.",
+          "start": 24.92,
+          "end": 25.44,
+          "confidence": 0.992
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 2534,
+      "start": 25.54,
+      "end": 30.64,
+      "text": " Sauf que le smartphone ajoute le toucher, ce qui rend le contact plus direct, plus sensible.",
+      "tokens": [
+        50364,
+        318,
+        9507,
+        631,
+        476,
+        13307,
+        17680,
+        14040,
+        476,
+        2557,
+        260,
+        11,
+        1769,
+        1956,
+        6125,
+        476,
+        3385,
+        1804,
+        2047,
+        11,
+        1804,
+        25380,
+        13,
+        50639
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10785348191220537,
+      "compression_ratio": 1.6254416961130742,
+      "no_speech_prob": 0.18929888308048248,
+      "confidence": 0.968,
+      "words": [
+        {
+          "text": "Sauf",
+          "start": 25.54,
+          "end": 25.82,
+          "confidence": 0.974
+        },
+        {
+          "text": "que",
+          "start": 25.82,
+          "end": 26.3,
+          "confidence": 0.996
+        },
+        {
+          "text": "le",
+          "start": 26.3,
+          "end": 26.66,
+          "confidence": 0.671
+        },
+        {
+          "text": "smartphone",
+          "start": 26.66,
+          "end": 27.08,
+          "confidence": 0.995
+        },
+        {
+          "text": "ajoute",
+          "start": 27.08,
+          "end": 27.48,
+          "confidence": 0.99
+        },
+        {
+          "text": "le",
+          "start": 27.48,
+          "end": 27.66,
+          "confidence": 0.989
+        },
+        {
+          "text": "toucher,",
+          "start": 27.66,
+          "end": 28.06,
+          "confidence": 0.987
+        },
+        {
+          "text": "ce",
+          "start": 28.14,
+          "end": 28.16,
+          "confidence": 0.952
+        },
+        {
+          "text": "qui",
+          "start": 28.16,
+          "end": 28.3,
+          "confidence": 1.0
+        },
+        {
+          "text": "rend",
+          "start": 28.3,
+          "end": 28.54,
+          "confidence": 0.994
+        },
+        {
+          "text": "le",
+          "start": 28.54,
+          "end": 28.8,
+          "confidence": 0.992
+        },
+        {
+          "text": "contact",
+          "start": 28.8,
+          "end": 29.16,
+          "confidence": 0.999
+        },
+        {
+          "text": "plus",
+          "start": 29.16,
+          "end": 29.58,
+          "confidence": 0.983
+        },
+        {
+          "text": "direct,",
+          "start": 29.58,
+          "end": 30.0,
+          "confidence": 0.991
+        },
+        {
+          "text": "plus",
+          "start": 30.1,
+          "end": 30.24,
+          "confidence": 0.99
+        },
+        {
+          "text": "sensible.",
+          "start": 30.24,
+          "end": 30.64,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 2534,
+      "start": 31.04,
+      "end": 37.82,
+      "text": " Et puis évidemment, il faudrait parler aussi des applications qui permettent de contourner le côté touffu de la navigation web pour aller directement au but.",
+      "tokens": [
+        50639,
+        3790,
+        9093,
+        24724,
+        11,
+        1930,
+        38694,
+        8645,
+        16421,
+        6212,
+        730,
+        5821,
+        1956,
+        21540,
+        317,
+        368,
+        21234,
+        1193,
+        476,
+        18437,
+        10095,
+        602,
+        84,
+        368,
+        635,
+        17346,
+        3670,
+        2016,
+        8722,
+        37297,
+        1609,
+        457,
+        13,
+        50989
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10785348191220537,
+      "compression_ratio": 1.6254416961130742,
+      "no_speech_prob": 0.18929888308048248,
+      "confidence": 0.893,
+      "words": [
+        {
+          "text": "Et",
+          "start": 31.04,
+          "end": 31.24,
+          "confidence": 0.964
+        },
+        {
+          "text": "puis",
+          "start": 31.24,
+          "end": 31.34,
+          "confidence": 0.967
+        },
+        {
+          "text": "évidemment,",
+          "start": 31.34,
+          "end": 31.62,
+          "confidence": 0.87
+        },
+        {
+          "text": "il",
+          "start": 31.66,
+          "end": 31.72,
+          "confidence": 0.99
+        },
+        {
+          "text": "faudrait",
+          "start": 31.72,
+          "end": 31.94,
+          "confidence": 0.996
+        },
+        {
+          "text": "parler",
+          "start": 31.94,
+          "end": 32.16,
+          "confidence": 0.864
+        },
+        {
+          "text": "aussi",
+          "start": 32.16,
+          "end": 32.34,
+          "confidence": 0.971
+        },
+        {
+          "text": "des",
+          "start": 32.34,
+          "end": 32.48,
+          "confidence": 0.993
+        },
+        {
+          "text": "applications",
+          "start": 32.48,
+          "end": 32.92,
+          "confidence": 0.993
+        },
+        {
+          "text": "qui",
+          "start": 32.92,
+          "end": 33.22,
+          "confidence": 0.564
+        },
+        {
+          "text": "permettent",
+          "start": 33.22,
+          "end": 33.76,
+          "confidence": 0.99
+        },
+        {
+          "text": "de",
+          "start": 33.76,
+          "end": 33.98,
+          "confidence": 0.871
+        },
+        {
+          "text": "contourner",
+          "start": 33.98,
+          "end": 34.42,
+          "confidence": 0.953
+        },
+        {
+          "text": "le",
+          "start": 34.42,
+          "end": 34.54,
+          "confidence": 0.75
+        },
+        {
+          "text": "côté",
+          "start": 34.54,
+          "end": 34.78,
+          "confidence": 0.985
+        },
+        {
+          "text": "touffu",
+          "start": 34.78,
+          "end": 35.32,
+          "confidence": 0.726
+        },
+        {
+          "text": "de",
+          "start": 35.32,
+          "end": 35.7,
+          "confidence": 0.882
+        },
+        {
+          "text": "la",
+          "start": 35.7,
+          "end": 35.82,
+          "confidence": 0.991
+        },
+        {
+          "text": "navigation",
+          "start": 35.82,
+          "end": 36.3,
+          "confidence": 0.992
+        },
+        {
+          "text": "web",
+          "start": 36.3,
+          "end": 36.58,
+          "confidence": 0.847
+        },
+        {
+          "text": "pour",
+          "start": 36.58,
+          "end": 36.76,
+          "confidence": 0.59
+        },
+        {
+          "text": "aller",
+          "start": 36.76,
+          "end": 37.16,
+          "confidence": 0.981
+        },
+        {
+          "text": "directement",
+          "start": 37.16,
+          "end": 37.54,
+          "confidence": 0.997
+        },
+        {
+          "text": "au",
+          "start": 37.54,
+          "end": 37.7,
+          "confidence": 0.969
+        },
+        {
+          "text": "but.",
+          "start": 37.7,
+          "end": 37.82,
+          "confidence": 0.995
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 2534,
+      "start": 37.9,
+      "end": 46.6,
+      "text": " Bref, tout ça, ce sont les conditions qui permettent de créer cet objet dont Nicolas dit qu'il est vraisemblablement inédit dans l'histoire de l'humanité.",
+      "tokens": [
+        50989,
+        49957,
+        11,
+        3486,
+        2788,
+        11,
+        1769,
+        4900,
+        1512,
+        4487,
+        1956,
+        21540,
+        317,
+        368,
+        32062,
+        8603,
+        14964,
+        9400,
+        38268,
+        6176,
+        421,
+        6,
+        388,
+        871,
+        6070,
+        271,
+        443,
+        5199,
+        712,
+        518,
+        294,
+        7811,
+        270,
+        2680,
+        287,
+        6,
+        29093,
+        368,
+        287,
+        6,
+        18796,
+        5066,
+        13,
+        51439
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10785348191220537,
+      "compression_ratio": 1.6254416961130742,
+      "no_speech_prob": 0.18929888308048248,
+      "confidence": 0.973,
+      "words": [
+        {
+          "text": "Bref,",
+          "start": 37.9,
+          "end": 38.24,
+          "confidence": 0.984
+        },
+        {
+          "text": "tout",
+          "start": 38.88,
+          "end": 39.02,
+          "confidence": 0.701
+        },
+        {
+          "text": "ça,",
+          "start": 39.02,
+          "end": 39.4,
+          "confidence": 0.995
+        },
+        {
+          "text": "ce",
+          "start": 39.4,
+          "end": 39.72,
+          "confidence": 0.989
+        },
+        {
+          "text": "sont",
+          "start": 39.72,
+          "end": 39.92,
+          "confidence": 0.999
+        },
+        {
+          "text": "les",
+          "start": 39.92,
+          "end": 40.22,
+          "confidence": 0.992
+        },
+        {
+          "text": "conditions",
+          "start": 40.22,
+          "end": 40.7,
+          "confidence": 0.995
+        },
+        {
+          "text": "qui",
+          "start": 40.7,
+          "end": 41.02,
+          "confidence": 0.997
+        },
+        {
+          "text": "permettent",
+          "start": 41.02,
+          "end": 41.44,
+          "confidence": 0.996
+        },
+        {
+          "text": "de",
+          "start": 41.44,
+          "end": 41.74,
+          "confidence": 0.997
+        },
+        {
+          "text": "créer",
+          "start": 41.74,
+          "end": 42.1,
+          "confidence": 0.999
+        },
+        {
+          "text": "cet",
+          "start": 42.1,
+          "end": 42.38,
+          "confidence": 0.997
+        },
+        {
+          "text": "objet",
+          "start": 42.38,
+          "end": 42.64,
+          "confidence": 0.994
+        },
+        {
+          "text": "dont",
+          "start": 42.64,
+          "end": 42.84,
+          "confidence": 0.789
+        },
+        {
+          "text": "Nicolas",
+          "start": 42.84,
+          "end": 43.24,
+          "confidence": 0.988
+        },
+        {
+          "text": "dit",
+          "start": 43.24,
+          "end": 43.52,
+          "confidence": 0.986
+        },
+        {
+          "text": "qu'il",
+          "start": 43.52,
+          "end": 43.74,
+          "confidence": 0.982
+        },
+        {
+          "text": "est",
+          "start": 43.74,
+          "end": 43.94,
+          "confidence": 0.99
+        },
+        {
+          "text": "vraisemblablement",
+          "start": 43.94,
+          "end": 44.86,
+          "confidence": 0.99
+        },
+        {
+          "text": "inédit",
+          "start": 44.86,
+          "end": 45.44,
+          "confidence": 0.98
+        },
+        {
+          "text": "dans",
+          "start": 45.44,
+          "end": 45.72,
+          "confidence": 0.967
+        },
+        {
+          "text": "l'histoire",
+          "start": 45.72,
+          "end": 46.02,
+          "confidence": 0.958
+        },
+        {
+          "text": "de",
+          "start": 46.02,
+          "end": 46.14,
+          "confidence": 0.999
+        },
+        {
+          "text": "l'humanité.",
+          "start": 46.14,
+          "end": 46.6,
+          "confidence": 0.992
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 2534,
+      "start": 47.02,
+      "end": 48.78,
+      "text": " Mais ça, ça soulève une autre interrogation.",
+      "tokens": [
+        51439,
+        6313,
+        2788,
+        11,
+        2788,
+        5133,
+        31397,
+        2251,
+        15081,
+        24871,
+        399,
+        13,
+        51539
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10785348191220537,
+      "compression_ratio": 1.6254416961130742,
+      "no_speech_prob": 0.18929888308048248,
+      "confidence": 0.969,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 47.02,
+          "end": 47.28,
+          "confidence": 0.84
+        },
+        {
+          "text": "ça,",
+          "start": 47.28,
+          "end": 47.48,
+          "confidence": 0.942
+        },
+        {
+          "text": "ça",
+          "start": 47.62,
+          "end": 47.64,
+          "confidence": 0.976
+        },
+        {
+          "text": "soulève",
+          "start": 47.64,
+          "end": 47.86,
+          "confidence": 0.993
+        },
+        {
+          "text": "une",
+          "start": 47.86,
+          "end": 48.02,
+          "confidence": 0.998
+        },
+        {
+          "text": "autre",
+          "start": 48.02,
+          "end": 48.2,
+          "confidence": 0.999
+        },
+        {
+          "text": "interrogation.",
+          "start": 48.2,
+          "end": 48.78,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 4884,
+      "start": 49.36,
+      "end": 55.5,
+      "text": " Est-ce que le fait que cet objet soit inédit induit que notre rapport à lui est aussi un rapport inédit ?",
+      "tokens": [
+        50389,
+        4410,
+        12,
+        384,
+        631,
+        476,
+        3887,
+        631,
+        8603,
+        14964,
+        12703,
+        294,
+        7811,
+        270,
+        13716,
+        270,
+        631,
+        10349,
+        18018,
+        1531,
+        8783,
+        871,
+        6212,
+        517,
+        18018,
+        294,
+        7811,
+        270,
+        2506,
+        50689
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.08241327932058287,
+      "compression_ratio": 1.5960784313725491,
+      "no_speech_prob": 0.09794807434082031,
+      "confidence": 0.986,
+      "words": [
+        {
+          "text": "Est-ce",
+          "start": 49.36,
+          "end": 49.64,
+          "confidence": 0.978
+        },
+        {
+          "text": "que",
+          "start": 49.64,
+          "end": 49.76,
+          "confidence": 0.991
+        },
+        {
+          "text": "le",
+          "start": 49.76,
+          "end": 49.82,
+          "confidence": 0.993
+        },
+        {
+          "text": "fait",
+          "start": 49.82,
+          "end": 50.0,
+          "confidence": 0.999
+        },
+        {
+          "text": "que",
+          "start": 50.0,
+          "end": 50.14,
+          "confidence": 0.991
+        },
+        {
+          "text": "cet",
+          "start": 50.14,
+          "end": 50.32,
+          "confidence": 0.99
+        },
+        {
+          "text": "objet",
+          "start": 50.32,
+          "end": 50.66,
+          "confidence": 0.997
+        },
+        {
+          "text": "soit",
+          "start": 50.66,
+          "end": 51.12,
+          "confidence": 0.995
+        },
+        {
+          "text": "inédit",
+          "start": 51.12,
+          "end": 51.78,
+          "confidence": 0.995
+        },
+        {
+          "text": "induit",
+          "start": 51.78,
+          "end": 52.32,
+          "confidence": 0.955
+        },
+        {
+          "text": "que",
+          "start": 52.32,
+          "end": 52.42,
+          "confidence": 0.984
+        },
+        {
+          "text": "notre",
+          "start": 52.42,
+          "end": 52.78,
+          "confidence": 0.995
+        },
+        {
+          "text": "rapport",
+          "start": 52.78,
+          "end": 53.28,
+          "confidence": 0.997
+        },
+        {
+          "text": "à",
+          "start": 53.28,
+          "end": 53.46,
+          "confidence": 0.978
+        },
+        {
+          "text": "lui",
+          "start": 53.46,
+          "end": 53.68,
+          "confidence": 0.999
+        },
+        {
+          "text": "est",
+          "start": 53.68,
+          "end": 54.14,
+          "confidence": 0.907
+        },
+        {
+          "text": "aussi",
+          "start": 54.14,
+          "end": 54.52,
+          "confidence": 0.996
+        },
+        {
+          "text": "un",
+          "start": 54.52,
+          "end": 54.72,
+          "confidence": 0.994
+        },
+        {
+          "text": "rapport",
+          "start": 54.72,
+          "end": 55.0,
+          "confidence": 0.997
+        },
+        {
+          "text": "inédit ?",
+          "start": 55.0,
+          "end": 55.5,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 4884,
+      "start": 55.76,
+      "end": 63.4,
+      "text": " Je veux dire, est-ce que le rapport qu'on a au smartphone est comparable à celui qu'on entretenait à d'autres objets techniques comme la voiture ou le téléphone ?",
+      "tokens": [
+        50689,
+        2588,
+        16389,
+        1264,
+        11,
+        871,
+        12,
+        384,
+        631,
+        476,
+        18018,
+        421,
+        6,
+        266,
+        257,
+        1609,
+        13307,
+        871,
+        25323,
+        1531,
+        22829,
+        421,
+        6,
+        266,
+        3962,
+        1147,
+        1001,
+        1531,
+        274,
+        6,
+        16752,
+        1111,
+        25349,
+        7512,
+        5173,
+        635,
+        38859,
+        2820,
+        476,
+        47159,
+        2506,
+        51089
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.08241327932058287,
+      "compression_ratio": 1.5960784313725491,
+      "no_speech_prob": 0.09794807434082031,
+      "confidence": 0.96,
+      "words": [
+        {
+          "text": "Je",
+          "start": 55.76,
+          "end": 55.9,
+          "confidence": 0.904
+        },
+        {
+          "text": "veux",
+          "start": 55.9,
+          "end": 56.0,
+          "confidence": 0.989
+        },
+        {
+          "text": "dire,",
+          "start": 56.0,
+          "end": 56.12,
+          "confidence": 0.997
+        },
+        {
+          "text": "est-ce",
+          "start": 56.22,
+          "end": 56.38,
+          "confidence": 0.99
+        },
+        {
+          "text": "que",
+          "start": 56.38,
+          "end": 56.5,
+          "confidence": 0.991
+        },
+        {
+          "text": "le",
+          "start": 56.5,
+          "end": 56.66,
+          "confidence": 0.996
+        },
+        {
+          "text": "rapport",
+          "start": 56.66,
+          "end": 56.86,
+          "confidence": 0.998
+        },
+        {
+          "text": "qu'on",
+          "start": 56.86,
+          "end": 57.08,
+          "confidence": 0.985
+        },
+        {
+          "text": "a",
+          "start": 57.08,
+          "end": 57.16,
+          "confidence": 0.99
+        },
+        {
+          "text": "au",
+          "start": 57.16,
+          "end": 57.28,
+          "confidence": 0.966
+        },
+        {
+          "text": "smartphone",
+          "start": 57.28,
+          "end": 57.6,
+          "confidence": 0.995
+        },
+        {
+          "text": "est",
+          "start": 57.6,
+          "end": 57.86,
+          "confidence": 0.91
+        },
+        {
+          "text": "comparable",
+          "start": 57.86,
+          "end": 58.3,
+          "confidence": 0.996
+        },
+        {
+          "text": "à",
+          "start": 58.3,
+          "end": 58.5,
+          "confidence": 0.946
+        },
+        {
+          "text": "celui",
+          "start": 58.5,
+          "end": 58.66,
+          "confidence": 0.998
+        },
+        {
+          "text": "qu'on",
+          "start": 58.66,
+          "end": 58.96,
+          "confidence": 0.989
+        },
+        {
+          "text": "entretenait",
+          "start": 58.96,
+          "end": 59.36,
+          "confidence": 0.926
+        },
+        {
+          "text": "à",
+          "start": 59.36,
+          "end": 59.48,
+          "confidence": 0.951
+        },
+        {
+          "text": "d'autres",
+          "start": 59.48,
+          "end": 59.7,
+          "confidence": 0.997
+        },
+        {
+          "text": "objets",
+          "start": 59.7,
+          "end": 59.98,
+          "confidence": 0.99
+        },
+        {
+          "text": "techniques",
+          "start": 59.98,
+          "end": 60.44,
+          "confidence": 0.984
+        },
+        {
+          "text": "comme",
+          "start": 60.44,
+          "end": 60.96,
+          "confidence": 0.496
+        },
+        {
+          "text": "la",
+          "start": 60.96,
+          "end": 61.52,
+          "confidence": 0.987
+        },
+        {
+          "text": "voiture",
+          "start": 61.52,
+          "end": 62.08,
+          "confidence": 1.0
+        },
+        {
+          "text": "ou",
+          "start": 62.08,
+          "end": 62.52,
+          "confidence": 0.95
+        },
+        {
+          "text": "le",
+          "start": 62.52,
+          "end": 62.74,
+          "confidence": 0.998
+        },
+        {
+          "text": "téléphone ?",
+          "start": 62.74,
+          "end": 63.4,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 4884,
+      "start": 65.36,
+      "end": 66.62,
+      "text": " Il n'y a pas d'équivalent en fait.",
+      "tokens": [
+        51189,
+        4416,
+        297,
+        6,
+        88,
+        257,
+        1736,
+        274,
+        6,
+        20183,
+        3576,
+        317,
+        465,
+        3887,
+        13,
+        51239
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.08241327932058287,
+      "compression_ratio": 1.5960784313725491,
+      "no_speech_prob": 0.09794807434082031,
+      "confidence": 0.94,
+      "words": [
+        {
+          "text": "Il",
+          "start": 65.36,
+          "end": 65.5,
+          "confidence": 0.849
+        },
+        {
+          "text": "n'y",
+          "start": 65.5,
+          "end": 65.54,
+          "confidence": 0.979
+        },
+        {
+          "text": "a",
+          "start": 65.54,
+          "end": 65.56,
+          "confidence": 0.993
+        },
+        {
+          "text": "pas",
+          "start": 65.56,
+          "end": 65.66,
+          "confidence": 0.999
+        },
+        {
+          "text": "d'équivalent",
+          "start": 65.66,
+          "end": 66.3,
+          "confidence": 0.995
+        },
+        {
+          "text": "en",
+          "start": 66.3,
+          "end": 66.44,
+          "confidence": 0.582
+        },
+        {
+          "text": "fait.",
+          "start": 66.44,
+          "end": 66.62,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 4884,
+      "start": 66.88,
+      "end": 71.24,
+      "text": " Et donc cette espèce de nouveauté dans la relation à l'objet, c'est fascinant et terrifiant.",
+      "tokens": [
+        51239,
+        3790,
+        5926,
+        5550,
+        7089,
+        30236,
+        368,
+        11456,
+        1375,
+        526,
+        2680,
+        635,
+        9721,
+        1531,
+        287,
+        6,
+        996,
+        7108,
+        11,
+        269,
+        6,
+        377,
+        7184,
+        259,
+        394,
+        1030,
+        7245,
+        351,
+        5798,
+        13,
+        51489
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.08241327932058287,
+      "compression_ratio": 1.5960784313725491,
+      "no_speech_prob": 0.09794807434082031,
+      "confidence": 0.957,
+      "words": [
+        {
+          "text": "Et",
+          "start": 66.88,
+          "end": 67.02,
+          "confidence": 0.654
+        },
+        {
+          "text": "donc",
+          "start": 67.02,
+          "end": 67.12,
+          "confidence": 0.901
+        },
+        {
+          "text": "cette",
+          "start": 67.12,
+          "end": 67.3,
+          "confidence": 0.713
+        },
+        {
+          "text": "espèce",
+          "start": 67.3,
+          "end": 67.54,
+          "confidence": 0.996
+        },
+        {
+          "text": "de",
+          "start": 67.54,
+          "end": 67.76,
+          "confidence": 0.999
+        },
+        {
+          "text": "nouveauté",
+          "start": 67.76,
+          "end": 68.48,
+          "confidence": 0.98
+        },
+        {
+          "text": "dans",
+          "start": 68.48,
+          "end": 68.84,
+          "confidence": 0.982
+        },
+        {
+          "text": "la",
+          "start": 68.84,
+          "end": 68.96,
+          "confidence": 0.995
+        },
+        {
+          "text": "relation",
+          "start": 68.96,
+          "end": 69.24,
+          "confidence": 0.998
+        },
+        {
+          "text": "à",
+          "start": 69.24,
+          "end": 69.38,
+          "confidence": 0.997
+        },
+        {
+          "text": "l'objet,",
+          "start": 69.38,
+          "end": 70.0,
+          "confidence": 0.998
+        },
+        {
+          "text": "c'est",
+          "start": 70.28,
+          "end": 70.38,
+          "confidence": 0.977
+        },
+        {
+          "text": "fascinant",
+          "start": 70.38,
+          "end": 70.68,
+          "confidence": 0.98
+        },
+        {
+          "text": "et",
+          "start": 70.68,
+          "end": 70.76,
+          "confidence": 0.973
+        },
+        {
+          "text": "terrifiant.",
+          "start": 70.76,
+          "end": 71.24,
+          "confidence": 0.977
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 7134,
+      "start": 71.62,
+      "end": 76.42,
+      "text": " Parce qu'on a l'impression, comme le disent les utilisateurs et les services, d'être dépendant de cet objet,",
+      "tokens": [
+        50389,
+        20429,
+        421,
+        6,
+        266,
+        257,
+        287,
+        6,
+        36107,
+        11,
+        5173,
+        476,
+        37313,
+        1512,
+        33643,
+        25929,
+        1030,
+        1512,
+        3328,
+        11,
+        274,
+        6,
+        9498,
+        45768,
+        394,
+        368,
+        8603,
+        14964,
+        11,
+        50639
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.11220460018869173,
+      "compression_ratio": 1.5975609756097562,
+      "no_speech_prob": 0.015181643888354301,
+      "confidence": 0.862,
+      "words": [
+        {
+          "text": "Parce",
+          "start": 71.62,
+          "end": 71.9,
+          "confidence": 0.843
+        },
+        {
+          "text": "qu'on",
+          "start": 71.9,
+          "end": 72.4,
+          "confidence": 0.968
+        },
+        {
+          "text": "a",
+          "start": 72.4,
+          "end": 72.54,
+          "confidence": 0.979
+        },
+        {
+          "text": "l'impression,",
+          "start": 72.54,
+          "end": 72.9,
+          "confidence": 0.997
+        },
+        {
+          "text": "comme",
+          "start": 73.66,
+          "end": 73.9,
+          "confidence": 0.982
+        },
+        {
+          "text": "le",
+          "start": 73.9,
+          "end": 74.02,
+          "confidence": 0.984
+        },
+        {
+          "text": "disent",
+          "start": 74.02,
+          "end": 74.22,
+          "confidence": 0.997
+        },
+        {
+          "text": "les",
+          "start": 74.22,
+          "end": 74.52,
+          "confidence": 0.996
+        },
+        {
+          "text": "utilisateurs",
+          "start": 74.52,
+          "end": 74.84,
+          "confidence": 0.998
+        },
+        {
+          "text": "et",
+          "start": 74.84,
+          "end": 74.94,
+          "confidence": 0.845
+        },
+        {
+          "text": "les",
+          "start": 74.94,
+          "end": 75.02,
+          "confidence": 0.783
+        },
+        {
+          "text": "services,",
+          "start": 75.02,
+          "end": 75.18,
+          "confidence": 0.129
+        },
+        {
+          "text": "d'être",
+          "start": 75.22,
+          "end": 75.5,
+          "confidence": 0.935
+        },
+        {
+          "text": "dépendant",
+          "start": 75.5,
+          "end": 75.98,
+          "confidence": 0.709
+        },
+        {
+          "text": "de",
+          "start": 75.98,
+          "end": 76.08,
+          "confidence": 0.977
+        },
+        {
+          "text": "cet",
+          "start": 76.08,
+          "end": 76.26,
+          "confidence": 0.998
+        },
+        {
+          "text": "objet,",
+          "start": 76.26,
+          "end": 76.42,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 7134,
+      "start": 76.42,
+      "end": 83.3,
+      "text": " d'induire en fait une espèce de relation, de médiation avec le monde qui rend de l'ampleur et qui amène aussi à des formes de rejet.",
+      "tokens": [
+        50639,
+        274,
+        6,
+        471,
+        43612,
+        465,
+        3887,
+        2251,
+        7089,
+        30236,
+        368,
+        9721,
+        11,
+        368,
+        42436,
+        399,
+        4163,
+        476,
+        10431,
+        1956,
+        6125,
+        368,
+        287,
+        6,
+        335,
+        781,
+        374,
+        1030,
+        1956,
+        669,
+        18832,
+        6212,
+        1531,
+        730,
+        1254,
+        279,
+        368,
+        319,
+        7108,
+        13,
+        50989
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.11220460018869173,
+      "compression_ratio": 1.5975609756097562,
+      "no_speech_prob": 0.015181643888354301,
+      "confidence": 0.923,
+      "words": [
+        {
+          "text": "d'induire",
+          "start": 76.42,
+          "end": 77.1,
+          "confidence": 0.964
+        },
+        {
+          "text": "en",
+          "start": 77.1,
+          "end": 77.18,
+          "confidence": 0.72
+        },
+        {
+          "text": "fait",
+          "start": 77.18,
+          "end": 77.34,
+          "confidence": 0.997
+        },
+        {
+          "text": "une",
+          "start": 77.34,
+          "end": 77.5,
+          "confidence": 0.979
+        },
+        {
+          "text": "espèce",
+          "start": 77.5,
+          "end": 77.88,
+          "confidence": 0.997
+        },
+        {
+          "text": "de",
+          "start": 77.88,
+          "end": 78.28,
+          "confidence": 0.997
+        },
+        {
+          "text": "relation,",
+          "start": 78.28,
+          "end": 78.54,
+          "confidence": 0.422
+        },
+        {
+          "text": "de",
+          "start": 78.66,
+          "end": 78.96,
+          "confidence": 0.992
+        },
+        {
+          "text": "médiation",
+          "start": 78.96,
+          "end": 79.52,
+          "confidence": 0.997
+        },
+        {
+          "text": "avec",
+          "start": 79.52,
+          "end": 79.76,
+          "confidence": 0.954
+        },
+        {
+          "text": "le",
+          "start": 79.76,
+          "end": 80.02,
+          "confidence": 0.998
+        },
+        {
+          "text": "monde",
+          "start": 80.02,
+          "end": 80.3,
+          "confidence": 0.996
+        },
+        {
+          "text": "qui",
+          "start": 80.3,
+          "end": 81.24,
+          "confidence": 0.661
+        },
+        {
+          "text": "rend",
+          "start": 81.24,
+          "end": 81.66,
+          "confidence": 0.968
+        },
+        {
+          "text": "de",
+          "start": 81.66,
+          "end": 81.74,
+          "confidence": 0.688
+        },
+        {
+          "text": "l'ampleur",
+          "start": 81.74,
+          "end": 82.02,
+          "confidence": 0.995
+        },
+        {
+          "text": "et",
+          "start": 82.02,
+          "end": 82.1,
+          "confidence": 0.952
+        },
+        {
+          "text": "qui",
+          "start": 82.1,
+          "end": 82.2,
+          "confidence": 0.987
+        },
+        {
+          "text": "amène",
+          "start": 82.2,
+          "end": 82.38,
+          "confidence": 0.971
+        },
+        {
+          "text": "aussi",
+          "start": 82.38,
+          "end": 82.54,
+          "confidence": 0.946
+        },
+        {
+          "text": "à",
+          "start": 82.54,
+          "end": 82.62,
+          "confidence": 0.959
+        },
+        {
+          "text": "des",
+          "start": 82.62,
+          "end": 82.7,
+          "confidence": 0.992
+        },
+        {
+          "text": "formes",
+          "start": 82.7,
+          "end": 82.88,
+          "confidence": 0.995
+        },
+        {
+          "text": "de",
+          "start": 82.88,
+          "end": 83.04,
+          "confidence": 0.998
+        },
+        {
+          "text": "rejet.",
+          "start": 83.04,
+          "end": 83.3,
+          "confidence": 0.802
+        }
+      ]
+    },
+    {
+      "id": 17,
+      "seek": 7134,
+      "start": 83.92,
+      "end": 87.7,
+      "text": " Donc à objet inédit, rapport inédit.",
+      "tokens": [
+        50989,
+        7477,
+        1531,
+        14964,
+        294,
+        7811,
+        270,
+        11,
+        18018,
+        294,
+        7811,
+        270,
+        13,
+        51189
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.11220460018869173,
+      "compression_ratio": 1.5975609756097562,
+      "no_speech_prob": 0.015181643888354301,
+      "confidence": 0.901,
+      "words": [
+        {
+          "text": "Donc",
+          "start": 83.92,
+          "end": 84.46,
+          "confidence": 0.984
+        },
+        {
+          "text": "à",
+          "start": 84.46,
+          "end": 84.98,
+          "confidence": 0.483
+        },
+        {
+          "text": "objet",
+          "start": 84.98,
+          "end": 85.46,
+          "confidence": 0.77
+        },
+        {
+          "text": "inédit,",
+          "start": 85.46,
+          "end": 86.2,
+          "confidence": 0.994
+        },
+        {
+          "text": "rapport",
+          "start": 86.54,
+          "end": 86.9,
+          "confidence": 0.986
+        },
+        {
+          "text": "inédit.",
+          "start": 86.9,
+          "end": 87.7,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 18,
+      "seek": 7134,
+      "start": 88.02,
+      "end": 94.92,
+      "text": " Et ce rapport, si j'en crois à Nicolas, serait caractérisé par un mélange de dépendance et de rejet.",
+      "tokens": [
+        51189,
+        3790,
+        1769,
+        18018,
+        11,
+        1511,
+        361,
+        6,
+        268,
+        21724,
+        1531,
+        38268,
+        11,
+        23139,
+        1032,
+        578,
+        4198,
+        22118,
+        971,
+        517,
+        41953,
+        933,
+        368,
+        45768,
+        719,
+        1030,
+        368,
+        319,
+        7108,
+        13,
+        51539
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.11220460018869173,
+      "compression_ratio": 1.5975609756097562,
+      "no_speech_prob": 0.015181643888354301,
+      "confidence": 0.975,
+      "words": [
+        {
+          "text": "Et",
+          "start": 88.02,
+          "end": 88.62,
+          "confidence": 0.989
+        },
+        {
+          "text": "ce",
+          "start": 88.62,
+          "end": 88.9,
+          "confidence": 0.985
+        },
+        {
+          "text": "rapport,",
+          "start": 88.9,
+          "end": 89.32,
+          "confidence": 0.998
+        },
+        {
+          "text": "si",
+          "start": 89.38,
+          "end": 89.56,
+          "confidence": 0.999
+        },
+        {
+          "text": "j'en",
+          "start": 89.56,
+          "end": 89.78,
+          "confidence": 0.997
+        },
+        {
+          "text": "crois",
+          "start": 89.78,
+          "end": 89.88,
+          "confidence": 0.988
+        },
+        {
+          "text": "à",
+          "start": 89.88,
+          "end": 90.06,
+          "confidence": 0.724
+        },
+        {
+          "text": "Nicolas,",
+          "start": 90.06,
+          "end": 90.24,
+          "confidence": 0.997
+        },
+        {
+          "text": "serait",
+          "start": 90.7,
+          "end": 91.0,
+          "confidence": 0.904
+        },
+        {
+          "text": "caractérisé",
+          "start": 91.0,
+          "end": 91.8,
+          "confidence": 0.994
+        },
+        {
+          "text": "par",
+          "start": 91.8,
+          "end": 92.22,
+          "confidence": 0.995
+        },
+        {
+          "text": "un",
+          "start": 92.22,
+          "end": 92.52,
+          "confidence": 0.996
+        },
+        {
+          "text": "mélange",
+          "start": 92.52,
+          "end": 93.04,
+          "confidence": 0.999
+        },
+        {
+          "text": "de",
+          "start": 93.04,
+          "end": 93.46,
+          "confidence": 0.998
+        },
+        {
+          "text": "dépendance",
+          "start": 93.46,
+          "end": 94.12,
+          "confidence": 0.938
+        },
+        {
+          "text": "et",
+          "start": 94.12,
+          "end": 94.54,
+          "confidence": 0.998
+        },
+        {
+          "text": "de",
+          "start": 94.54,
+          "end": 94.72,
+          "confidence": 0.999
+        },
+        {
+          "text": "rejet.",
+          "start": 94.72,
+          "end": 94.92,
+          "confidence": 0.988
+        }
+      ]
+    },
+    {
+      "id": 19,
+      "seek": 9484,
+      "start": 95.74,
+      "end": 102.82,
+      "text": " Bon, en vrai, il faudrait remonter très très finement toute l'histoire des objets techniques et de leur insertion dans nos vies",
+      "tokens": [
+        50389,
+        7368,
+        11,
+        465,
+        17815,
+        11,
+        1930,
+        38694,
+        8645,
+        890,
+        41806,
+        5732,
+        5732,
+        962,
+        1712,
+        14953,
+        287,
+        6,
+        29093,
+        730,
+        1111,
+        25349,
+        7512,
+        1030,
+        368,
+        9580,
+        8969,
+        313,
+        2680,
+        3269,
+        371,
+        530,
+        50739
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.0781538827078683,
+      "compression_ratio": 1.6719745222929936,
+      "no_speech_prob": 0.017434891313314438,
+      "confidence": 0.932,
+      "words": [
+        {
+          "text": "Bon,",
+          "start": 95.74,
+          "end": 96.0,
+          "confidence": 0.751
+        },
+        {
+          "text": "en",
+          "start": 96.34,
+          "end": 96.54,
+          "confidence": 0.992
+        },
+        {
+          "text": "vrai,",
+          "start": 96.54,
+          "end": 96.86,
+          "confidence": 0.991
+        },
+        {
+          "text": "il",
+          "start": 97.06,
+          "end": 97.18,
+          "confidence": 0.992
+        },
+        {
+          "text": "faudrait",
+          "start": 97.18,
+          "end": 97.58,
+          "confidence": 0.996
+        },
+        {
+          "text": "remonter",
+          "start": 97.58,
+          "end": 98.06,
+          "confidence": 0.995
+        },
+        {
+          "text": "très",
+          "start": 98.06,
+          "end": 98.58,
+          "confidence": 0.995
+        },
+        {
+          "text": "très",
+          "start": 98.58,
+          "end": 98.84,
+          "confidence": 0.757
+        },
+        {
+          "text": "finement",
+          "start": 98.84,
+          "end": 99.38,
+          "confidence": 0.823
+        },
+        {
+          "text": "toute",
+          "start": 99.38,
+          "end": 99.7,
+          "confidence": 0.937
+        },
+        {
+          "text": "l'histoire",
+          "start": 99.7,
+          "end": 100.08,
+          "confidence": 0.996
+        },
+        {
+          "text": "des",
+          "start": 100.08,
+          "end": 100.26,
+          "confidence": 0.991
+        },
+        {
+          "text": "objets",
+          "start": 100.26,
+          "end": 100.52,
+          "confidence": 0.998
+        },
+        {
+          "text": "techniques",
+          "start": 100.52,
+          "end": 100.94,
+          "confidence": 0.982
+        },
+        {
+          "text": "et",
+          "start": 100.94,
+          "end": 101.54,
+          "confidence": 0.512
+        },
+        {
+          "text": "de",
+          "start": 101.54,
+          "end": 101.7,
+          "confidence": 0.984
+        },
+        {
+          "text": "leur",
+          "start": 101.7,
+          "end": 101.84,
+          "confidence": 0.818
+        },
+        {
+          "text": "insertion",
+          "start": 101.84,
+          "end": 102.34,
+          "confidence": 0.994
+        },
+        {
+          "text": "dans",
+          "start": 102.34,
+          "end": 102.5,
+          "confidence": 0.969
+        },
+        {
+          "text": "nos",
+          "start": 102.5,
+          "end": 102.66,
+          "confidence": 0.998
+        },
+        {
+          "text": "vies",
+          "start": 102.66,
+          "end": 102.82,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 20,
+      "seek": 9484,
+      "start": 102.86,
+      "end": 105.72,
+      "text": " pour déterminer si ce rapport est totalement inédit.",
+      "tokens": [
+        50739,
+        2016,
+        2795,
+        29725,
+        260,
+        1511,
+        1769,
+        18018,
+        871,
+        45203,
+        294,
+        7811,
+        270,
+        13,
+        50889
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.0781538827078683,
+      "compression_ratio": 1.6719745222929936,
+      "no_speech_prob": 0.017434891313314438,
+      "confidence": 0.995,
+      "words": [
+        {
+          "text": "pour",
+          "start": 102.86,
+          "end": 103.1,
+          "confidence": 0.989
+        },
+        {
+          "text": "déterminer",
+          "start": 103.1,
+          "end": 103.64,
+          "confidence": 0.995
+        },
+        {
+          "text": "si",
+          "start": 103.64,
+          "end": 103.76,
+          "confidence": 0.986
+        },
+        {
+          "text": "ce",
+          "start": 103.76,
+          "end": 103.94,
+          "confidence": 0.991
+        },
+        {
+          "text": "rapport",
+          "start": 103.94,
+          "end": 104.26,
+          "confidence": 0.998
+        },
+        {
+          "text": "est",
+          "start": 104.26,
+          "end": 104.84,
+          "confidence": 0.997
+        },
+        {
+          "text": "totalement",
+          "start": 104.84,
+          "end": 105.3,
+          "confidence": 0.998
+        },
+        {
+          "text": "inédit.",
+          "start": 105.3,
+          "end": 105.72,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 21,
+      "seek": 9484,
+      "start": 106.14,
+      "end": 109.32,
+      "text": " Mais j'ai l'impression comme ça que Nicolas ne se trompe pas vraiment.",
+      "tokens": [
+        50889,
+        6313,
+        361,
+        6,
+        1301,
+        287,
+        6,
+        36107,
+        5173,
+        2788,
+        631,
+        38268,
+        408,
+        369,
+        504,
+        298,
+        494,
+        1736,
+        8322,
+        13,
+        51089
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.0781538827078683,
+      "compression_ratio": 1.6719745222929936,
+      "no_speech_prob": 0.017434891313314438,
+      "confidence": 0.932,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 106.14,
+          "end": 106.4,
+          "confidence": 0.975
+        },
+        {
+          "text": "j'ai",
+          "start": 106.4,
+          "end": 106.92,
+          "confidence": 0.956
+        },
+        {
+          "text": "l'impression",
+          "start": 106.92,
+          "end": 107.38,
+          "confidence": 0.999
+        },
+        {
+          "text": "comme",
+          "start": 107.38,
+          "end": 107.58,
+          "confidence": 0.513
+        },
+        {
+          "text": "ça",
+          "start": 107.58,
+          "end": 107.82,
+          "confidence": 0.969
+        },
+        {
+          "text": "que",
+          "start": 107.82,
+          "end": 108.14,
+          "confidence": 0.973
+        },
+        {
+          "text": "Nicolas",
+          "start": 108.14,
+          "end": 108.48,
+          "confidence": 0.983
+        },
+        {
+          "text": "ne",
+          "start": 108.48,
+          "end": 108.6,
+          "confidence": 0.72
+        },
+        {
+          "text": "se",
+          "start": 108.6,
+          "end": 108.72,
+          "confidence": 0.992
+        },
+        {
+          "text": "trompe",
+          "start": 108.72,
+          "end": 108.88,
+          "confidence": 0.993
+        },
+        {
+          "text": "pas",
+          "start": 108.88,
+          "end": 109.08,
+          "confidence": 0.999
+        },
+        {
+          "text": "vraiment.",
+          "start": 109.08,
+          "end": 109.32,
+          "confidence": 0.989
+        }
+      ]
+    },
+    {
+      "id": 22,
+      "seek": 9484,
+      "start": 109.94,
+      "end": 115.06,
+      "text": " Pour autant que je sache, il y a eu plein de discussions autour de la voiture ou même du téléphone.",
+      "tokens": [
+        51089,
+        8732,
+        34081,
+        631,
+        1506,
+        262,
+        6000,
+        11,
+        1930,
+        288,
+        257,
+        2228,
+        21088,
+        368,
+        11088,
+        30249,
+        368,
+        635,
+        38859,
+        2820,
+        5698,
+        1581,
+        47159,
+        13,
+        51389
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.0781538827078683,
+      "compression_ratio": 1.6719745222929936,
+      "no_speech_prob": 0.017434891313314438,
+      "confidence": 0.964,
+      "words": [
+        {
+          "text": "Pour",
+          "start": 109.94,
+          "end": 110.1,
+          "confidence": 0.995
+        },
+        {
+          "text": "autant",
+          "start": 110.1,
+          "end": 110.24,
+          "confidence": 1.0
+        },
+        {
+          "text": "que",
+          "start": 110.24,
+          "end": 110.38,
+          "confidence": 0.984
+        },
+        {
+          "text": "je",
+          "start": 110.38,
+          "end": 110.52,
+          "confidence": 0.998
+        },
+        {
+          "text": "sache,",
+          "start": 110.52,
+          "end": 110.84,
+          "confidence": 0.952
+        },
+        {
+          "text": "il",
+          "start": 111.08,
+          "end": 111.16,
+          "confidence": 0.994
+        },
+        {
+          "text": "y",
+          "start": 111.16,
+          "end": 111.3,
+          "confidence": 0.995
+        },
+        {
+          "text": "a",
+          "start": 111.3,
+          "end": 111.32,
+          "confidence": 0.993
+        },
+        {
+          "text": "eu",
+          "start": 111.32,
+          "end": 111.62,
+          "confidence": 0.998
+        },
+        {
+          "text": "plein",
+          "start": 111.62,
+          "end": 111.9,
+          "confidence": 0.966
+        },
+        {
+          "text": "de",
+          "start": 111.9,
+          "end": 112.14,
+          "confidence": 0.997
+        },
+        {
+          "text": "discussions",
+          "start": 112.14,
+          "end": 112.66,
+          "confidence": 0.83
+        },
+        {
+          "text": "autour",
+          "start": 112.66,
+          "end": 113.02,
+          "confidence": 0.995
+        },
+        {
+          "text": "de",
+          "start": 113.02,
+          "end": 113.38,
+          "confidence": 0.996
+        },
+        {
+          "text": "la",
+          "start": 113.38,
+          "end": 113.52,
+          "confidence": 0.998
+        },
+        {
+          "text": "voiture",
+          "start": 113.52,
+          "end": 113.88,
+          "confidence": 1.0
+        },
+        {
+          "text": "ou",
+          "start": 113.88,
+          "end": 114.06,
+          "confidence": 0.69
+        },
+        {
+          "text": "même",
+          "start": 114.06,
+          "end": 114.34,
+          "confidence": 0.995
+        },
+        {
+          "text": "du",
+          "start": 114.34,
+          "end": 114.64,
+          "confidence": 0.992
+        },
+        {
+          "text": "téléphone.",
+          "start": 114.64,
+          "end": 115.06,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 23,
+      "seek": 9484,
+      "start": 115.48,
+      "end": 117.7,
+      "text": " Mais la dépendance n'était pas du même ordre.",
+      "tokens": [
+        51389,
+        6313,
+        635,
+        45768,
+        719,
+        297,
+        6,
+        9743,
+        1736,
+        1581,
+        5698,
+        4792,
+        265,
+        13,
+        51489
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.0781538827078683,
+      "compression_ratio": 1.6719745222929936,
+      "no_speech_prob": 0.017434891313314438,
+      "confidence": 0.992,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 115.48,
+          "end": 115.78,
+          "confidence": 0.993
+        },
+        {
+          "text": "la",
+          "start": 115.78,
+          "end": 116.04,
+          "confidence": 0.943
+        },
+        {
+          "text": "dépendance",
+          "start": 116.04,
+          "end": 116.42,
+          "confidence": 0.996
+        },
+        {
+          "text": "n'était",
+          "start": 116.42,
+          "end": 116.7,
+          "confidence": 0.994
+        },
+        {
+          "text": "pas",
+          "start": 116.7,
+          "end": 117.0,
+          "confidence": 0.998
+        },
+        {
+          "text": "du",
+          "start": 117.0,
+          "end": 117.2,
+          "confidence": 0.996
+        },
+        {
+          "text": "même",
+          "start": 117.2,
+          "end": 117.44,
+          "confidence": 0.998
+        },
+        {
+          "text": "ordre.",
+          "start": 117.44,
+          "end": 117.7,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 24,
+      "seek": 9484,
+      "start": 117.72,
+      "end": 119.78,
+      "text": " Donc le rejet non plus n'était pas du même ordre.",
+      "tokens": [
+        51489,
+        7477,
+        476,
+        319,
+        7108,
+        2107,
+        1804,
+        297,
+        6,
+        9743,
+        1736,
+        1581,
+        5698,
+        4792,
+        265,
+        13,
+        51589
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.0781538827078683,
+      "compression_ratio": 1.6719745222929936,
+      "no_speech_prob": 0.017434891313314438,
+      "confidence": 0.979,
+      "words": [
+        {
+          "text": "Donc",
+          "start": 117.72,
+          "end": 118.02,
+          "confidence": 0.959
+        },
+        {
+          "text": "le",
+          "start": 118.02,
+          "end": 118.4,
+          "confidence": 0.819
+        },
+        {
+          "text": "rejet",
+          "start": 118.4,
+          "end": 118.64,
+          "confidence": 0.999
+        },
+        {
+          "text": "non",
+          "start": 118.64,
+          "end": 118.82,
+          "confidence": 0.982
+        },
+        {
+          "text": "plus",
+          "start": 118.82,
+          "end": 118.94,
+          "confidence": 0.994
+        },
+        {
+          "text": "n'était",
+          "start": 118.94,
+          "end": 119.18,
+          "confidence": 0.991
+        },
+        {
+          "text": "pas",
+          "start": 119.18,
+          "end": 119.3,
+          "confidence": 0.998
+        },
+        {
+          "text": "du",
+          "start": 119.3,
+          "end": 119.42,
+          "confidence": 0.995
+        },
+        {
+          "text": "même",
+          "start": 119.42,
+          "end": 119.58,
+          "confidence": 0.999
+        },
+        {
+          "text": "ordre.",
+          "start": 119.58,
+          "end": 119.78,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 25,
+      "seek": 9484,
+      "start": 120.04,
+      "end": 123.1,
+      "text": " On peut adorer sa bagnole, en avoir besoin pour plein de choses.",
+      "tokens": [
+        51589,
+        1282,
+        5977,
+        614,
+        17618,
+        601,
+        3411,
+        1771,
+        306,
+        11,
+        465,
+        10853,
+        19207,
+        2016,
+        21088,
+        368,
+        14488,
+        13,
+        51789
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.0781538827078683,
+      "compression_ratio": 1.6719745222929936,
+      "no_speech_prob": 0.017434891313314438,
+      "confidence": 0.971,
+      "words": [
+        {
+          "text": "On",
+          "start": 120.04,
+          "end": 120.16,
+          "confidence": 0.757
+        },
+        {
+          "text": "peut",
+          "start": 120.16,
+          "end": 120.36,
+          "confidence": 0.997
+        },
+        {
+          "text": "adorer",
+          "start": 120.36,
+          "end": 120.68,
+          "confidence": 0.991
+        },
+        {
+          "text": "sa",
+          "start": 120.68,
+          "end": 120.88,
+          "confidence": 0.98
+        },
+        {
+          "text": "bagnole,",
+          "start": 120.88,
+          "end": 121.34,
+          "confidence": 0.985
+        },
+        {
+          "text": "en",
+          "start": 121.42,
+          "end": 121.56,
+          "confidence": 0.971
+        },
+        {
+          "text": "avoir",
+          "start": 121.56,
+          "end": 121.8,
+          "confidence": 0.997
+        },
+        {
+          "text": "besoin",
+          "start": 121.8,
+          "end": 122.12,
+          "confidence": 0.999
+        },
+        {
+          "text": "pour",
+          "start": 122.12,
+          "end": 122.46,
+          "confidence": 0.989
+        },
+        {
+          "text": "plein",
+          "start": 122.46,
+          "end": 122.7,
+          "confidence": 0.987
+        },
+        {
+          "text": "de",
+          "start": 122.7,
+          "end": 122.78,
+          "confidence": 0.997
+        },
+        {
+          "text": "choses.",
+          "start": 122.78,
+          "end": 123.1,
+          "confidence": 0.99
+        }
+      ]
+    },
+    {
+      "id": 26,
+      "seek": 12334,
+      "start": 123.38,
+      "end": 126.44,
+      "text": " Le soir, quand on va se coucher, on la laisse.",
+      "tokens": [
+        50389,
+        1456,
+        27105,
+        11,
+        6932,
+        322,
+        2773,
+        369,
+        1384,
+        6759,
+        11,
+        322,
+        635,
+        30969,
+        13,
+        50539
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.08272041363662548,
+      "compression_ratio": 1.6818181818181819,
+      "no_speech_prob": 0.01115426979959011,
+      "confidence": 0.94,
+      "words": [
+        {
+          "text": "Le",
+          "start": 123.38,
+          "end": 123.96,
+          "confidence": 0.645
+        },
+        {
+          "text": "soir,",
+          "start": 123.96,
+          "end": 124.54,
+          "confidence": 0.998
+        },
+        {
+          "text": "quand",
+          "start": 124.74,
+          "end": 124.94,
+          "confidence": 0.982
+        },
+        {
+          "text": "on",
+          "start": 124.94,
+          "end": 125.06,
+          "confidence": 0.996
+        },
+        {
+          "text": "va",
+          "start": 125.06,
+          "end": 125.16,
+          "confidence": 0.99
+        },
+        {
+          "text": "se",
+          "start": 125.16,
+          "end": 125.26,
+          "confidence": 0.989
+        },
+        {
+          "text": "coucher,",
+          "start": 125.26,
+          "end": 125.7,
+          "confidence": 0.989
+        },
+        {
+          "text": "on",
+          "start": 125.94,
+          "end": 126.04,
+          "confidence": 0.992
+        },
+        {
+          "text": "la",
+          "start": 126.04,
+          "end": 126.18,
+          "confidence": 0.852
+        },
+        {
+          "text": "laisse.",
+          "start": 126.18,
+          "end": 126.44,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 27,
+      "seek": 12334,
+      "start": 127.0,
+      "end": 130.3,
+      "text": " On ne l'a pas dans la main quand on est au lit, on ne l'emmène pas au chiottes.",
+      "tokens": [
+        50539,
+        1282,
+        408,
+        287,
+        6,
+        64,
+        1736,
+        2680,
+        635,
+        2135,
+        6932,
+        322,
+        871,
+        1609,
+        7997,
+        11,
+        322,
+        408,
+        287,
+        6,
+        443,
+        76,
+        18832,
+        1736,
+        1609,
+        13228,
+        1521,
+        279,
+        13,
+        50739
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.08272041363662548,
+      "compression_ratio": 1.6818181818181819,
+      "no_speech_prob": 0.01115426979959011,
+      "confidence": 0.918,
+      "words": [
+        {
+          "text": "On",
+          "start": 127.0,
+          "end": 127.34,
+          "confidence": 0.967
+        },
+        {
+          "text": "ne",
+          "start": 127.34,
+          "end": 127.46,
+          "confidence": 0.801
+        },
+        {
+          "text": "l'a",
+          "start": 127.46,
+          "end": 127.56,
+          "confidence": 0.929
+        },
+        {
+          "text": "pas",
+          "start": 127.56,
+          "end": 127.68,
+          "confidence": 0.999
+        },
+        {
+          "text": "dans",
+          "start": 127.68,
+          "end": 127.86,
+          "confidence": 0.992
+        },
+        {
+          "text": "la",
+          "start": 127.86,
+          "end": 128.08,
+          "confidence": 0.996
+        },
+        {
+          "text": "main",
+          "start": 128.08,
+          "end": 128.26,
+          "confidence": 0.999
+        },
+        {
+          "text": "quand",
+          "start": 128.26,
+          "end": 128.48,
+          "confidence": 0.936
+        },
+        {
+          "text": "on",
+          "start": 128.48,
+          "end": 128.6,
+          "confidence": 0.993
+        },
+        {
+          "text": "est",
+          "start": 128.6,
+          "end": 128.74,
+          "confidence": 0.992
+        },
+        {
+          "text": "au",
+          "start": 128.74,
+          "end": 128.94,
+          "confidence": 0.976
+        },
+        {
+          "text": "lit,",
+          "start": 128.94,
+          "end": 129.1,
+          "confidence": 0.999
+        },
+        {
+          "text": "on",
+          "start": 129.16,
+          "end": 129.28,
+          "confidence": 0.43
+        },
+        {
+          "text": "ne",
+          "start": 129.28,
+          "end": 129.3,
+          "confidence": 0.949
+        },
+        {
+          "text": "l'emmène",
+          "start": 129.3,
+          "end": 129.58,
+          "confidence": 0.993
+        },
+        {
+          "text": "pas",
+          "start": 129.58,
+          "end": 129.7,
+          "confidence": 0.997
+        },
+        {
+          "text": "au",
+          "start": 129.7,
+          "end": 129.88,
+          "confidence": 0.72
+        },
+        {
+          "text": "chiottes.",
+          "start": 129.88,
+          "end": 130.3,
+          "confidence": 0.886
+        }
+      ]
+    },
+    {
+      "id": 28,
+      "seek": 12334,
+      "start": 130.84,
+      "end": 136.88,
+      "text": " On pouvait être énervé par son môme qui occupait la ligne de téléphone pendant une heure chaque soir pour discuter avec un copain.",
+      "tokens": [
+        50739,
+        1282,
+        45913,
+        7418,
+        45045,
+        15797,
+        971,
+        1872,
+        275,
+        2851,
+        1398,
+        1956,
+        8073,
+        1001,
+        635,
+        34207,
+        368,
+        47159,
+        17338,
+        2251,
+        30027,
+        18920,
+        27105,
+        2016,
+        2983,
+        20314,
+        4163,
+        517,
+        2971,
+        491,
+        13,
+        51039
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.08272041363662548,
+      "compression_ratio": 1.6818181818181819,
+      "no_speech_prob": 0.01115426979959011,
+      "confidence": 0.925,
+      "words": [
+        {
+          "text": "On",
+          "start": 130.84,
+          "end": 131.06,
+          "confidence": 0.996
+        },
+        {
+          "text": "pouvait",
+          "start": 131.06,
+          "end": 131.26,
+          "confidence": 0.989
+        },
+        {
+          "text": "être",
+          "start": 131.26,
+          "end": 131.58,
+          "confidence": 0.995
+        },
+        {
+          "text": "énervé",
+          "start": 131.58,
+          "end": 132.22,
+          "confidence": 0.896
+        },
+        {
+          "text": "par",
+          "start": 132.22,
+          "end": 132.46,
+          "confidence": 0.992
+        },
+        {
+          "text": "son",
+          "start": 132.46,
+          "end": 132.72,
+          "confidence": 0.998
+        },
+        {
+          "text": "môme",
+          "start": 132.72,
+          "end": 133.08,
+          "confidence": 0.758
+        },
+        {
+          "text": "qui",
+          "start": 133.08,
+          "end": 133.34,
+          "confidence": 0.916
+        },
+        {
+          "text": "occupait",
+          "start": 133.34,
+          "end": 133.74,
+          "confidence": 0.992
+        },
+        {
+          "text": "la",
+          "start": 133.74,
+          "end": 133.86,
+          "confidence": 0.986
+        },
+        {
+          "text": "ligne",
+          "start": 133.86,
+          "end": 134.06,
+          "confidence": 0.999
+        },
+        {
+          "text": "de",
+          "start": 134.06,
+          "end": 134.22,
+          "confidence": 0.995
+        },
+        {
+          "text": "téléphone",
+          "start": 134.22,
+          "end": 134.6,
+          "confidence": 0.992
+        },
+        {
+          "text": "pendant",
+          "start": 134.6,
+          "end": 134.92,
+          "confidence": 0.709
+        },
+        {
+          "text": "une",
+          "start": 134.92,
+          "end": 135.16,
+          "confidence": 0.78
+        },
+        {
+          "text": "heure",
+          "start": 135.16,
+          "end": 135.34,
+          "confidence": 0.995
+        },
+        {
+          "text": "chaque",
+          "start": 135.34,
+          "end": 135.58,
+          "confidence": 0.982
+        },
+        {
+          "text": "soir",
+          "start": 135.58,
+          "end": 135.8,
+          "confidence": 0.995
+        },
+        {
+          "text": "pour",
+          "start": 135.8,
+          "end": 135.98,
+          "confidence": 0.66
+        },
+        {
+          "text": "discuter",
+          "start": 135.98,
+          "end": 136.3,
+          "confidence": 0.997
+        },
+        {
+          "text": "avec",
+          "start": 136.3,
+          "end": 136.5,
+          "confidence": 0.995
+        },
+        {
+          "text": "un",
+          "start": 136.5,
+          "end": 136.66,
+          "confidence": 0.997
+        },
+        {
+          "text": "copain.",
+          "start": 136.66,
+          "end": 136.88,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 29,
+      "seek": 12334,
+      "start": 137.26,
+      "end": 141.86,
+      "text": " Mais ça ne ressemblait pas à ce qu'on peut ressentir à voir ce même môme aujourd'hui,",
+      "tokens": [
+        51039,
+        6313,
+        2788,
+        408,
+        725,
+        15750,
+        35235,
+        1736,
+        1531,
+        1769,
+        421,
+        6,
+        266,
+        5977,
+        24689,
+        317,
+        347,
+        1531,
+        10695,
+        1769,
+        5698,
+        275,
+        2851,
+        1398,
+        14023,
+        6,
+        10556,
+        11,
+        51289
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.08272041363662548,
+      "compression_ratio": 1.6818181818181819,
+      "no_speech_prob": 0.01115426979959011,
+      "confidence": 0.956,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 137.26,
+          "end": 137.5,
+          "confidence": 0.989
+        },
+        {
+          "text": "ça",
+          "start": 137.5,
+          "end": 137.68,
+          "confidence": 0.928
+        },
+        {
+          "text": "ne",
+          "start": 137.68,
+          "end": 137.88,
+          "confidence": 0.999
+        },
+        {
+          "text": "ressemblait",
+          "start": 137.88,
+          "end": 138.42,
+          "confidence": 0.993
+        },
+        {
+          "text": "pas",
+          "start": 138.42,
+          "end": 138.78,
+          "confidence": 0.994
+        },
+        {
+          "text": "à",
+          "start": 138.78,
+          "end": 138.9,
+          "confidence": 0.989
+        },
+        {
+          "text": "ce",
+          "start": 138.9,
+          "end": 138.98,
+          "confidence": 0.998
+        },
+        {
+          "text": "qu'on",
+          "start": 138.98,
+          "end": 139.12,
+          "confidence": 0.976
+        },
+        {
+          "text": "peut",
+          "start": 139.12,
+          "end": 139.48,
+          "confidence": 0.979
+        },
+        {
+          "text": "ressentir",
+          "start": 139.48,
+          "end": 140.1,
+          "confidence": 0.996
+        },
+        {
+          "text": "à",
+          "start": 140.1,
+          "end": 140.32,
+          "confidence": 0.575
+        },
+        {
+          "text": "voir",
+          "start": 140.32,
+          "end": 140.46,
+          "confidence": 0.728
+        },
+        {
+          "text": "ce",
+          "start": 140.46,
+          "end": 140.7,
+          "confidence": 0.985
+        },
+        {
+          "text": "même",
+          "start": 140.7,
+          "end": 140.94,
+          "confidence": 0.982
+        },
+        {
+          "text": "môme",
+          "start": 140.94,
+          "end": 141.28,
+          "confidence": 0.997
+        },
+        {
+          "text": "aujourd'hui,",
+          "start": 141.28,
+          "end": 141.86,
+          "confidence": 0.994
+        }
+      ]
+    },
+    {
+      "id": 30,
+      "seek": 12334,
+      "start": 142.16,
+      "end": 144.22,
+      "text": " continuellement avec son smartphone dans la main,",
+      "tokens": [
+        51289,
+        2354,
+        285,
+        1712,
+        4163,
+        1872,
+        13307,
+        2680,
+        635,
+        2135,
+        11,
+        51414
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.08272041363662548,
+      "compression_ratio": 1.6818181818181819,
+      "no_speech_prob": 0.01115426979959011,
+      "confidence": 0.961,
+      "words": [
+        {
+          "text": "continuellement",
+          "start": 142.16,
+          "end": 142.94,
+          "confidence": 0.963
+        },
+        {
+          "text": "avec",
+          "start": 142.94,
+          "end": 143.2,
+          "confidence": 0.844
+        },
+        {
+          "text": "son",
+          "start": 143.2,
+          "end": 143.42,
+          "confidence": 0.994
+        },
+        {
+          "text": "smartphone",
+          "start": 143.42,
+          "end": 143.76,
+          "confidence": 0.972
+        },
+        {
+          "text": "dans",
+          "start": 143.76,
+          "end": 143.92,
+          "confidence": 0.963
+        },
+        {
+          "text": "la",
+          "start": 143.92,
+          "end": 144.02,
+          "confidence": 0.997
+        },
+        {
+          "text": "main,",
+          "start": 144.02,
+          "end": 144.22,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 31,
+      "seek": 12334,
+      "start": 144.34,
+      "end": 148.8,
+      "text": " comme si c'était une sorte de pacemaker externe, comme si le lâcher allait entraîner sa mort immédiate.",
+      "tokens": [
+        51414,
+        5173,
+        1511,
+        269,
+        6,
+        9743,
+        2251,
+        25559,
+        368,
+        15165,
+        49523,
+        454,
+        391,
+        716,
+        11,
+        5173,
+        1511,
+        476,
+        48835,
+        6759,
+        439,
+        1001,
+        22284,
+        7517,
+        1193,
+        601,
+        6599,
+        3397,
+        526,
+        4504,
+        473,
+        13,
+        51639
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.08272041363662548,
+      "compression_ratio": 1.6818181818181819,
+      "no_speech_prob": 0.01115426979959011,
+      "confidence": 0.973,
+      "words": [
+        {
+          "text": "comme",
+          "start": 144.34,
+          "end": 144.56,
+          "confidence": 0.985
+        },
+        {
+          "text": "si",
+          "start": 144.56,
+          "end": 144.66,
+          "confidence": 0.971
+        },
+        {
+          "text": "c'était",
+          "start": 144.66,
+          "end": 144.86,
+          "confidence": 0.987
+        },
+        {
+          "text": "une",
+          "start": 144.86,
+          "end": 144.98,
+          "confidence": 0.983
+        },
+        {
+          "text": "sorte",
+          "start": 144.98,
+          "end": 145.14,
+          "confidence": 0.992
+        },
+        {
+          "text": "de",
+          "start": 145.14,
+          "end": 145.34,
+          "confidence": 0.989
+        },
+        {
+          "text": "pacemaker",
+          "start": 145.34,
+          "end": 145.82,
+          "confidence": 0.931
+        },
+        {
+          "text": "externe,",
+          "start": 145.82,
+          "end": 146.4,
+          "confidence": 0.99
+        },
+        {
+          "text": "comme",
+          "start": 146.44,
+          "end": 146.6,
+          "confidence": 0.721
+        },
+        {
+          "text": "si",
+          "start": 146.6,
+          "end": 146.74,
+          "confidence": 0.993
+        },
+        {
+          "text": "le",
+          "start": 146.74,
+          "end": 147.0,
+          "confidence": 0.996
+        },
+        {
+          "text": "lâcher",
+          "start": 147.0,
+          "end": 147.36,
+          "confidence": 0.968
+        },
+        {
+          "text": "allait",
+          "start": 147.36,
+          "end": 147.58,
+          "confidence": 0.991
+        },
+        {
+          "text": "entraîner",
+          "start": 147.58,
+          "end": 147.88,
+          "confidence": 0.982
+        },
+        {
+          "text": "sa",
+          "start": 147.88,
+          "end": 148.02,
+          "confidence": 0.999
+        },
+        {
+          "text": "mort",
+          "start": 148.02,
+          "end": 148.3,
+          "confidence": 0.998
+        },
+        {
+          "text": "immédiate.",
+          "start": 148.3,
+          "end": 148.8,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 32,
+      "seek": 12334,
+      "start": 148.94,
+      "end": 152.02,
+      "text": " Bon, je dis ça pour le môme, mais c'est évidemment valable pour nous aussi.",
+      "tokens": [
+        51639,
+        7368,
+        11,
+        1506,
+        717,
+        2788,
+        2016,
+        476,
+        275,
+        2851,
+        1398,
+        11,
+        2420,
+        269,
+        6,
+        377,
+        24724,
+        1323,
+        712,
+        2016,
+        4666,
+        6212,
+        13,
+        51839
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.08272041363662548,
+      "compression_ratio": 1.6818181818181819,
+      "no_speech_prob": 0.01115426979959011,
+      "confidence": 0.973,
+      "words": [
+        {
+          "text": "Bon,",
+          "start": 148.94,
+          "end": 149.24,
+          "confidence": 0.804
+        },
+        {
+          "text": "je",
+          "start": 149.26,
+          "end": 149.34,
+          "confidence": 0.933
+        },
+        {
+          "text": "dis",
+          "start": 149.34,
+          "end": 149.46,
+          "confidence": 0.982
+        },
+        {
+          "text": "ça",
+          "start": 149.46,
+          "end": 149.64,
+          "confidence": 0.992
+        },
+        {
+          "text": "pour",
+          "start": 149.64,
+          "end": 149.78,
+          "confidence": 0.997
+        },
+        {
+          "text": "le",
+          "start": 149.78,
+          "end": 149.9,
+          "confidence": 0.994
+        },
+        {
+          "text": "môme,",
+          "start": 149.9,
+          "end": 150.1,
+          "confidence": 0.999
+        },
+        {
+          "text": "mais",
+          "start": 150.32,
+          "end": 150.5,
+          "confidence": 0.904
+        },
+        {
+          "text": "c'est",
+          "start": 150.5,
+          "end": 150.84,
+          "confidence": 0.979
+        },
+        {
+          "text": "évidemment",
+          "start": 150.84,
+          "end": 151.18,
+          "confidence": 0.979
+        },
+        {
+          "text": "valable",
+          "start": 151.18,
+          "end": 151.48,
+          "confidence": 0.997
+        },
+        {
+          "text": "pour",
+          "start": 151.48,
+          "end": 151.64,
+          "confidence": 0.996
+        },
+        {
+          "text": "nous",
+          "start": 151.64,
+          "end": 151.78,
+          "confidence": 0.998
+        },
+        {
+          "text": "aussi.",
+          "start": 151.78,
+          "end": 152.02,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 33,
+      "seek": 15284,
+      "start": 153.14,
+      "end": 154.68,
+      "text": " Donc, rapport inédit, d'accord.",
+      "tokens": [
+        50389,
+        7477,
+        11,
+        18018,
+        294,
+        7811,
+        270,
+        11,
+        274,
+        6,
+        19947,
+        13,
+        50489
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12394786888444928,
+      "compression_ratio": 1.6703296703296704,
+      "no_speech_prob": 0.07031125575304031,
+      "confidence": 0.813,
+      "words": [
+        {
+          "text": "Donc,",
+          "start": 153.14,
+          "end": 153.24,
+          "confidence": 0.232
+        },
+        {
+          "text": "rapport",
+          "start": 153.26,
+          "end": 153.62,
+          "confidence": 0.855
+        },
+        {
+          "text": "inédit,",
+          "start": 153.62,
+          "end": 154.18,
+          "confidence": 0.992
+        },
+        {
+          "text": "d'accord.",
+          "start": 154.28,
+          "end": 154.68,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 34,
+      "seek": 15284,
+      "start": 155.64,
+      "end": 158.52,
+      "text": " Mais pourquoi a-t-on l'impression qu'on n'en sortira jamais ?",
+      "tokens": [
+        50489,
+        6313,
+        19934,
+        257,
+        12,
+        83,
+        12,
+        266,
+        287,
+        6,
+        36107,
+        421,
+        6,
+        266,
+        297,
+        6,
+        268,
+        1333,
+        4271,
+        14540,
+        2506,
+        50639
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12394786888444928,
+      "compression_ratio": 1.6703296703296704,
+      "no_speech_prob": 0.07031125575304031,
+      "confidence": 0.958,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 155.64,
+          "end": 155.88,
+          "confidence": 0.991
+        },
+        {
+          "text": "pourquoi",
+          "start": 155.88,
+          "end": 156.36,
+          "confidence": 0.992
+        },
+        {
+          "text": "a-t-on",
+          "start": 156.36,
+          "end": 156.7,
+          "confidence": 0.95
+        },
+        {
+          "text": "l'impression",
+          "start": 156.7,
+          "end": 157.06,
+          "confidence": 0.998
+        },
+        {
+          "text": "qu'on",
+          "start": 157.06,
+          "end": 157.28,
+          "confidence": 0.99
+        },
+        {
+          "text": "n'en",
+          "start": 157.28,
+          "end": 157.5,
+          "confidence": 0.859
+        },
+        {
+          "text": "sortira",
+          "start": 157.5,
+          "end": 157.86,
+          "confidence": 0.974
+        },
+        {
+          "text": "jamais ?",
+          "start": 157.86,
+          "end": 158.52,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 35,
+      "seek": 15284,
+      "start": 159.12,
+      "end": 165.36,
+      "text": " Est-ce qu'il faut en remettre la faute sur les gens qui ont créé cet outil merveilleux et diabolique, et diabolique parce que merveilleux ?",
+      "tokens": [
+        50639,
+        4410,
+        12,
+        384,
+        421,
+        6,
+        388,
+        8487,
+        465,
+        890,
+        40681,
+        635,
+        2050,
+        1169,
+        1022,
+        1512,
+        10668,
+        1956,
+        6592,
+        15609,
+        526,
+        8603,
+        484,
+        388,
+        3551,
+        303,
+        3409,
+        2449,
+        1030,
+        1026,
+        14923,
+        1925,
+        11,
+        1030,
+        1026,
+        14923,
+        1925,
+        6992,
+        631,
+        3551,
+        303,
+        3409,
+        2449,
+        2506,
+        50989
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12394786888444928,
+      "compression_ratio": 1.6703296703296704,
+      "no_speech_prob": 0.07031125575304031,
+      "confidence": 0.959,
+      "words": [
+        {
+          "text": "Est-ce",
+          "start": 159.12,
+          "end": 159.34,
+          "confidence": 0.987
+        },
+        {
+          "text": "qu'il",
+          "start": 159.34,
+          "end": 159.46,
+          "confidence": 0.993
+        },
+        {
+          "text": "faut",
+          "start": 159.46,
+          "end": 159.64,
+          "confidence": 0.998
+        },
+        {
+          "text": "en",
+          "start": 159.64,
+          "end": 159.88,
+          "confidence": 0.961
+        },
+        {
+          "text": "remettre",
+          "start": 159.88,
+          "end": 160.14,
+          "confidence": 0.999
+        },
+        {
+          "text": "la",
+          "start": 160.14,
+          "end": 160.46,
+          "confidence": 0.995
+        },
+        {
+          "text": "faute",
+          "start": 160.46,
+          "end": 160.64,
+          "confidence": 0.986
+        },
+        {
+          "text": "sur",
+          "start": 160.64,
+          "end": 161.06,
+          "confidence": 0.982
+        },
+        {
+          "text": "les",
+          "start": 161.06,
+          "end": 161.3,
+          "confidence": 0.991
+        },
+        {
+          "text": "gens",
+          "start": 161.3,
+          "end": 161.46,
+          "confidence": 0.998
+        },
+        {
+          "text": "qui",
+          "start": 161.46,
+          "end": 161.56,
+          "confidence": 0.724
+        },
+        {
+          "text": "ont",
+          "start": 161.56,
+          "end": 161.82,
+          "confidence": 0.996
+        },
+        {
+          "text": "créé",
+          "start": 161.82,
+          "end": 162.28,
+          "confidence": 0.985
+        },
+        {
+          "text": "cet",
+          "start": 162.28,
+          "end": 162.48,
+          "confidence": 0.816
+        },
+        {
+          "text": "outil",
+          "start": 162.48,
+          "end": 162.78,
+          "confidence": 0.993
+        },
+        {
+          "text": "merveilleux",
+          "start": 162.78,
+          "end": 163.36,
+          "confidence": 0.981
+        },
+        {
+          "text": "et",
+          "start": 163.36,
+          "end": 163.5,
+          "confidence": 0.983
+        },
+        {
+          "text": "diabolique,",
+          "start": 163.5,
+          "end": 163.84,
+          "confidence": 0.991
+        },
+        {
+          "text": "et",
+          "start": 163.86,
+          "end": 164.0,
+          "confidence": 0.555
+        },
+        {
+          "text": "diabolique",
+          "start": 164.0,
+          "end": 164.4,
+          "confidence": 0.949
+        },
+        {
+          "text": "parce",
+          "start": 164.4,
+          "end": 164.66,
+          "confidence": 0.927
+        },
+        {
+          "text": "que",
+          "start": 164.66,
+          "end": 164.86,
+          "confidence": 0.979
+        },
+        {
+          "text": "merveilleux ?",
+          "start": 164.86,
+          "end": 165.36,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 36,
+      "seek": 15284,
+      "start": 166.84,
+      "end": 168.82,
+      "text": " Les économistes parlent de dépendance du sentier.",
+      "tokens": [
+        51039,
+        6965,
+        31171,
+        22368,
+        13734,
+        317,
+        368,
+        45768,
+        719,
+        1581,
+        2279,
+        811,
+        13,
+        51139
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12394786888444928,
+      "compression_ratio": 1.6703296703296704,
+      "no_speech_prob": 0.07031125575304031,
+      "confidence": 0.986,
+      "words": [
+        {
+          "text": "Les",
+          "start": 166.84,
+          "end": 167.08,
+          "confidence": 0.945
+        },
+        {
+          "text": "économistes",
+          "start": 167.08,
+          "end": 167.46,
+          "confidence": 0.997
+        },
+        {
+          "text": "parlent",
+          "start": 167.46,
+          "end": 167.72,
+          "confidence": 0.993
+        },
+        {
+          "text": "de",
+          "start": 167.72,
+          "end": 167.88,
+          "confidence": 0.992
+        },
+        {
+          "text": "dépendance",
+          "start": 167.88,
+          "end": 168.34,
+          "confidence": 0.986
+        },
+        {
+          "text": "du",
+          "start": 168.34,
+          "end": 168.52,
+          "confidence": 0.996
+        },
+        {
+          "text": "sentier.",
+          "start": 168.52,
+          "end": 168.82,
+          "confidence": 0.983
+        }
+      ]
+    },
+    {
+      "id": 37,
+      "seek": 15284,
+      "start": 168.98,
+      "end": 177.38,
+      "text": " C'est l'idée qu'on met sur un sentier qui a été établi, soit volontairement en marchant dessus, soit en définissant des bornes, en définissant une signalétique.",
+      "tokens": [
+        51139,
+        383,
+        6,
+        377,
+        287,
+        6,
+        34281,
+        421,
+        6,
+        266,
+        1131,
+        1022,
+        517,
+        2279,
+        811,
+        1956,
+        257,
+        8862,
+        4823,
+        455,
+        2081,
+        11,
+        12703,
+        40005,
+        9020,
+        518,
+        465,
+        8368,
+        394,
+        30677,
+        11,
+        12703,
+        465,
+        40763,
+        29492,
+        730,
+        4232,
+        279,
+        11,
+        465,
+        40763,
+        29492,
+        2251,
+        6358,
+        42379,
+        13,
+        51589
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12394786888444928,
+      "compression_ratio": 1.6703296703296704,
+      "no_speech_prob": 0.07031125575304031,
+      "confidence": 0.907,
+      "words": [
+        {
+          "text": "C'est",
+          "start": 168.98,
+          "end": 169.2,
+          "confidence": 0.996
+        },
+        {
+          "text": "l'idée",
+          "start": 169.2,
+          "end": 169.38,
+          "confidence": 0.998
+        },
+        {
+          "text": "qu'on",
+          "start": 169.38,
+          "end": 169.74,
+          "confidence": 0.7
+        },
+        {
+          "text": "met",
+          "start": 169.74,
+          "end": 169.88,
+          "confidence": 0.648
+        },
+        {
+          "text": "sur",
+          "start": 169.88,
+          "end": 170.1,
+          "confidence": 0.995
+        },
+        {
+          "text": "un",
+          "start": 170.1,
+          "end": 170.52,
+          "confidence": 0.997
+        },
+        {
+          "text": "sentier",
+          "start": 170.52,
+          "end": 170.84,
+          "confidence": 0.991
+        },
+        {
+          "text": "qui",
+          "start": 170.84,
+          "end": 170.9,
+          "confidence": 0.955
+        },
+        {
+          "text": "a",
+          "start": 170.9,
+          "end": 171.0,
+          "confidence": 0.969
+        },
+        {
+          "text": "été",
+          "start": 171.0,
+          "end": 171.14,
+          "confidence": 0.994
+        },
+        {
+          "text": "établi,",
+          "start": 171.14,
+          "end": 171.5,
+          "confidence": 0.995
+        },
+        {
+          "text": "soit",
+          "start": 171.76,
+          "end": 172.1,
+          "confidence": 0.527
+        },
+        {
+          "text": "volontairement",
+          "start": 172.1,
+          "end": 172.7,
+          "confidence": 0.987
+        },
+        {
+          "text": "en",
+          "start": 172.7,
+          "end": 172.86,
+          "confidence": 0.927
+        },
+        {
+          "text": "marchant",
+          "start": 172.86,
+          "end": 173.1,
+          "confidence": 0.997
+        },
+        {
+          "text": "dessus,",
+          "start": 173.1,
+          "end": 173.48,
+          "confidence": 0.995
+        },
+        {
+          "text": "soit",
+          "start": 173.86,
+          "end": 174.28,
+          "confidence": 0.749
+        },
+        {
+          "text": "en",
+          "start": 174.28,
+          "end": 175.16,
+          "confidence": 0.967
+        },
+        {
+          "text": "définissant",
+          "start": 175.16,
+          "end": 175.54,
+          "confidence": 0.981
+        },
+        {
+          "text": "des",
+          "start": 175.54,
+          "end": 175.74,
+          "confidence": 0.99
+        },
+        {
+          "text": "bornes,",
+          "start": 175.74,
+          "end": 175.98,
+          "confidence": 0.977
+        },
+        {
+          "text": "en",
+          "start": 176.04,
+          "end": 176.14,
+          "confidence": 0.673
+        },
+        {
+          "text": "définissant",
+          "start": 176.14,
+          "end": 176.66,
+          "confidence": 0.996
+        },
+        {
+          "text": "une",
+          "start": 176.66,
+          "end": 176.94,
+          "confidence": 0.983
+        },
+        {
+          "text": "signalétique.",
+          "start": 176.94,
+          "end": 177.38,
+          "confidence": 0.686
+        }
+      ]
+    }
+  ],
+  "language": "fr",
+  "language_probs": {
+    "en": 0.001014346838928759,
+    "zh": 5.72255376027897e-05,
+    "de": 9.583473729435354e-05,
+    "es": 0.00010201553959632292,
+    "ru": 3.111298428848386e-05,
+    "ko": 5.633833643514663e-05,
+    "fr": 0.9971188306808472,
+    "ja": 0.00011926825391128659,
+    "pt": 0.00024857642711140215,
+    "tr": 3.111298428848386e-05,
+    "pl": 0.00016302037693094462,
+    "ca": 4.259047159393958e-08,
+    "nl": 1.5644591258023866e-05,
+    "ar": 9.288621367886662e-05,
+    "sv": 2.0521238184301183e-06,
+    "it": 0.0006971497205086052,
+    "id": 2.9227943741716444e-05,
+    "hi": 3.2284438020724338e-06,
+    "fi": 8.965064921540034e-07,
+    "vi": 5.546489046537317e-05,
+    "he": 5.610194193650386e-07,
+    "uk": 1.0875857014980284e-07,
+    "el": 4.624531811714405e-06,
+    "ms": 2.939531441370491e-06,
+    "cs": 1.2841862826462602e-06,
+    "ro": 3.4907800454675453e-06,
+    "da": 7.956947456477792e-08,
+    "hu": 5.322803644958185e-06,
+    "ta": 2.338676807767115e-07,
+    "no": 1.1047126236007898e-07,
+    "th": 6.222988304216415e-06,
+    "ur": 2.0003761846965062e-07,
+    "hr": 1.4044846174954273e-08,
+    "bg": 1.846160024854271e-08,
+    "lt": 2.347129157698191e-09,
+    "la": 5.8459563661017455e-06,
+    "mi": 1.850045805440459e-07,
+    "ml": 6.357183224281471e-07,
+    "cy": 2.3619797957508126e-06,
+    "sk": 3.265524739504144e-08,
+    "te": 2.7931511326073633e-08,
+    "fa": 1.1577289171782468e-07,
+    "lv": 2.3058872866688063e-10,
+    "bn": 5.300469752000936e-08,
+    "sr": 2.1831703111985235e-10,
+    "az": 5.115834977864608e-10,
+    "sl": 3.4222402689465525e-08,
+    "kn": 2.287942890699668e-10,
+    "et": 1.0830222274549328e-09,
+    "mk": 1.6351191234331708e-10,
+    "br": 5.406625859905034e-06,
+    "eu": 3.817784843818117e-08,
+    "is": 9.191490346616149e-10,
+    "hy": 2.2396462462381805e-09,
+    "ne": 5.289337856595466e-09,
+    "mn": 6.634315763420773e-09,
+    "bs": 3.415052907129734e-09,
+    "kk": 1.0393448601764277e-10,
+    "sq": 3.3289374035128105e-10,
+    "sw": 3.530873726731443e-08,
+    "gl": 1.509963283297111e-07,
+    "mr": 1.1710261649255926e-09,
+    "pa": 1.961099949099321e-09,
+    "si": 6.805937857734534e-08,
+    "km": 3.7744330256828107e-06,
+    "sn": 1.7379569783315674e-07,
+    "yo": 1.9047636357072406e-08,
+    "so": 1.3956540784176852e-11,
+    "af": 7.740010854462298e-10,
+    "oc": 2.734190331921127e-07,
+    "ka": 2.9087926511905948e-11,
+    "be": 2.279703537055866e-08,
+    "tg": 3.669336102324339e-12,
+    "sd": 1.1528712429154098e-09,
+    "gu": 1.3769081708137065e-10,
+    "am": 8.416871366545564e-11,
+    "yi": 9.784290044834165e-10,
+    "lo": 2.809145804860691e-09,
+    "uz": 5.235589739527313e-12,
+    "fo": 1.6905737920680508e-09,
+    "ht": 4.75131045618582e-08,
+    "ps": 2.007606081377844e-09,
+    "tk": 2.44944915045453e-11,
+    "nn": 1.7182223018608056e-05,
+    "mt": 3.048388971804705e-11,
+    "sa": 2.338676807767115e-07,
+    "lb": 6.963176563123952e-12,
+    "my": 3.0676766016313195e-08,
+    "bo": 1.2688460948595548e-08,
+    "tl": 3.4027550555038033e-07,
+    "mg": 3.001127818480498e-11,
+    "as": 2.7169991256847936e-10,
+    "tt": 5.143594426250397e-13,
+    "haw": 8.965064921540034e-07,
+    "ln": 1.041532304846271e-09,
+    "ha": 8.9408957668069e-12,
+    "ba": 2.775589653947197e-11,
+    "jw": 2.3991756279428955e-06,
+    "su": 2.425283281495827e-12
+  }
+}
\ No newline at end of file
diff --git a/tests/expected/medium_fr.cpu/radio_short.mp3.words.json b/tests/expected/medium_fr.cpu/radio_short.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..55a81cf3b19c05b84cbe3d2f0fc3db1d81a0f42e
--- /dev/null
+++ b/tests/expected/medium_fr.cpu/radio_short.mp3.words.json
@@ -0,0 +1,1977 @@
+{
+  "text": " Le plus important au poker ce ne sont pas les cartes, c'est ce que vous en faites. Winamax, la référence du poker en ligne. Bonsoir à toutes et tous, vous êtes sur BFM TV, nous sommes en direct, c'est bien sûr BFM story avec tout ce qui fait l'actualité. Durant 60 minutes ce sont des gros plans, des analyses, des réactions que nous vous proposons. Comment Eric Verth peut-il encore soutenir la réforme des retraites alors qu'il est englué dans sa propre affaire, l'affaire Verth-Bettancourt? Question posée par les leaders de la CFDT et la CGT. Réponse de Nicolas Sarkozy, Eric Verth portera le débat sur les retraites, on en parle dans BFM story avec le numéro de la CFDT. Et puis il y a une bataille qui a démarré, celle entre Marine Le Pen et Bruno Gognich, la bataille de la succession de Jean-Marie Le Pen à la tête du Front National. La tournée de campagne de Marine Le Pen commence aujourd'hui dans le Var, Marine Le Pen sera en direct dans BFM story. Restez avec nous Marine Le Pen dans moins de 3 minutes, à tout de suite. Musique L'actualité c'est aussi aujourd'hui un dernier adieu, dernier adieu à Laurent Fignon, c'était au cimetière du Père Lachaise à Paris. L'ancien double vainqueur du Tour de France, vaincu par le cancer à 50 ans, a été incinéré en petit comité aujourd'hui.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 3000,
+      "start": 30.86,
+      "end": 34.26,
+      "text": " Le plus important au poker ce ne sont pas les cartes, c'est ce que vous en faites.",
+      "tokens": [
+        1456,
+        1804,
+        1021,
+        1609,
+        36863,
+        1769,
+        408,
+        4900,
+        1736,
+        1512,
+        5467,
+        279,
+        11,
+        269,
+        6,
+        377,
+        1769,
+        631,
+        2630,
+        465,
+        29902,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1935427300283842,
+      "compression_ratio": 1.5084745762711864,
+      "no_speech_prob": 0.5593915581703186,
+      "confidence": 0.92,
+      "words": [
+        {
+          "text": "Le",
+          "start": 30.86,
+          "end": 31.02,
+          "confidence": 0.535
+        },
+        {
+          "text": "plus",
+          "start": 31.02,
+          "end": 31.12,
+          "confidence": 0.99
+        },
+        {
+          "text": "important",
+          "start": 31.12,
+          "end": 31.48,
+          "confidence": 0.993
+        },
+        {
+          "text": "au",
+          "start": 31.48,
+          "end": 31.64,
+          "confidence": 0.946
+        },
+        {
+          "text": "poker",
+          "start": 31.64,
+          "end": 31.84,
+          "confidence": 0.992
+        },
+        {
+          "text": "ce",
+          "start": 31.84,
+          "end": 32.02,
+          "confidence": 0.581
+        },
+        {
+          "text": "ne",
+          "start": 32.02,
+          "end": 32.06,
+          "confidence": 0.961
+        },
+        {
+          "text": "sont",
+          "start": 32.06,
+          "end": 32.16,
+          "confidence": 0.991
+        },
+        {
+          "text": "pas",
+          "start": 32.16,
+          "end": 32.28,
+          "confidence": 0.991
+        },
+        {
+          "text": "les",
+          "start": 32.28,
+          "end": 32.42,
+          "confidence": 0.969
+        },
+        {
+          "text": "cartes,",
+          "start": 32.42,
+          "end": 33.56,
+          "confidence": 0.996
+        },
+        {
+          "text": "c'est",
+          "start": 33.56,
+          "end": 33.62,
+          "confidence": 0.95
+        },
+        {
+          "text": "ce",
+          "start": 33.62,
+          "end": 33.66,
+          "confidence": 0.99
+        },
+        {
+          "text": "que",
+          "start": 33.66,
+          "end": 33.7,
+          "confidence": 0.991
+        },
+        {
+          "text": "vous",
+          "start": 33.7,
+          "end": 33.86,
+          "confidence": 0.991
+        },
+        {
+          "text": "en",
+          "start": 33.86,
+          "end": 34.04,
+          "confidence": 0.982
+        },
+        {
+          "text": "faites.",
+          "start": 34.04,
+          "end": 34.26,
+          "confidence": 0.894
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 3000,
+      "start": 36.18,
+      "end": 38.76,
+      "text": " Winamax, la référence du poker en ligne.",
+      "tokens": [
+        10427,
+        2404,
+        87,
+        11,
+        635,
+        30170,
+        41635,
+        1581,
+        36863,
+        465,
+        34207,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1935427300283842,
+      "compression_ratio": 1.5084745762711864,
+      "no_speech_prob": 0.5593915581703186,
+      "confidence": 0.967,
+      "words": [
+        {
+          "text": "Winamax,",
+          "start": 36.18,
+          "end": 37.28,
+          "confidence": 0.905
+        },
+        {
+          "text": "la",
+          "start": 37.28,
+          "end": 37.32,
+          "confidence": 0.988
+        },
+        {
+          "text": "référence",
+          "start": 37.32,
+          "end": 37.78,
+          "confidence": 0.998
+        },
+        {
+          "text": "du",
+          "start": 37.78,
+          "end": 37.96,
+          "confidence": 0.992
+        },
+        {
+          "text": "poker",
+          "start": 37.96,
+          "end": 38.22,
+          "confidence": 0.998
+        },
+        {
+          "text": "en",
+          "start": 38.22,
+          "end": 38.4,
+          "confidence": 0.993
+        },
+        {
+          "text": "ligne.",
+          "start": 38.4,
+          "end": 38.76,
+          "confidence": 0.993
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 3000,
+      "start": 44.94,
+      "end": 51.38,
+      "text": " Bonsoir à toutes et tous, vous êtes sur BFM TV, nous sommes en direct, c'est bien sûr BFM story avec tout ce qui fait l'actualité.",
+      "tokens": [
+        7368,
+        539,
+        347,
+        1531,
+        14437,
+        1030,
+        8317,
+        11,
+        2630,
+        18935,
+        1022,
+        363,
+        37,
+        44,
+        3558,
+        11,
+        4666,
+        25232,
+        465,
+        2047,
+        11,
+        269,
+        6,
+        377,
+        3610,
+        18143,
+        363,
+        37,
+        44,
+        1657,
+        4163,
+        3486,
+        1769,
+        1956,
+        3887,
+        287,
+        6,
+        578,
+        901,
+        5066,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1935427300283842,
+      "compression_ratio": 1.5084745762711864,
+      "no_speech_prob": 0.5593915581703186,
+      "confidence": 0.907,
+      "words": [
+        {
+          "text": "Bonsoir",
+          "start": 44.94,
+          "end": 45.4,
+          "confidence": 0.955
+        },
+        {
+          "text": "à",
+          "start": 45.4,
+          "end": 45.84,
+          "confidence": 0.54
+        },
+        {
+          "text": "toutes",
+          "start": 45.84,
+          "end": 46.06,
+          "confidence": 0.917
+        },
+        {
+          "text": "et",
+          "start": 46.06,
+          "end": 46.14,
+          "confidence": 0.988
+        },
+        {
+          "text": "tous,",
+          "start": 46.14,
+          "end": 46.7,
+          "confidence": 0.981
+        },
+        {
+          "text": "vous",
+          "start": 46.7,
+          "end": 46.74,
+          "confidence": 0.97
+        },
+        {
+          "text": "êtes",
+          "start": 46.74,
+          "end": 46.9,
+          "confidence": 0.995
+        },
+        {
+          "text": "sur",
+          "start": 46.9,
+          "end": 47.04,
+          "confidence": 0.989
+        },
+        {
+          "text": "BFM",
+          "start": 47.04,
+          "end": 47.56,
+          "confidence": 0.987
+        },
+        {
+          "text": "TV,",
+          "start": 47.56,
+          "end": 47.88,
+          "confidence": 0.853
+        },
+        {
+          "text": "nous",
+          "start": 47.88,
+          "end": 47.92,
+          "confidence": 0.829
+        },
+        {
+          "text": "sommes",
+          "start": 47.92,
+          "end": 48.14,
+          "confidence": 0.988
+        },
+        {
+          "text": "en",
+          "start": 48.14,
+          "end": 48.2,
+          "confidence": 0.986
+        },
+        {
+          "text": "direct,",
+          "start": 48.2,
+          "end": 48.74,
+          "confidence": 0.998
+        },
+        {
+          "text": "c'est",
+          "start": 48.74,
+          "end": 48.8,
+          "confidence": 0.939
+        },
+        {
+          "text": "bien",
+          "start": 48.8,
+          "end": 48.94,
+          "confidence": 0.971
+        },
+        {
+          "text": "sûr",
+          "start": 48.94,
+          "end": 49.2,
+          "confidence": 0.906
+        },
+        {
+          "text": "BFM",
+          "start": 49.2,
+          "end": 49.84,
+          "confidence": 0.95
+        },
+        {
+          "text": "story",
+          "start": 49.84,
+          "end": 50.04,
+          "confidence": 0.356
+        },
+        {
+          "text": "avec",
+          "start": 50.04,
+          "end": 50.24,
+          "confidence": 0.553
+        },
+        {
+          "text": "tout",
+          "start": 50.24,
+          "end": 50.42,
+          "confidence": 0.93
+        },
+        {
+          "text": "ce",
+          "start": 50.42,
+          "end": 50.46,
+          "confidence": 0.995
+        },
+        {
+          "text": "qui",
+          "start": 50.46,
+          "end": 50.56,
+          "confidence": 0.952
+        },
+        {
+          "text": "fait",
+          "start": 50.56,
+          "end": 50.72,
+          "confidence": 0.961
+        },
+        {
+          "text": "l'actualité.",
+          "start": 50.72,
+          "end": 51.38,
+          "confidence": 0.994
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 3000,
+      "start": 51.5,
+      "end": 56.11,
+      "text": " Durant 60 minutes ce sont des gros plans, des analyses, des réactions que nous vous proposons.",
+      "tokens": [
+        13710,
+        394,
+        4060,
+        2077,
+        1769,
+        4900,
+        730,
+        18638,
+        5482,
+        11,
+        730,
+        37560,
+        11,
+        730,
+        3960,
+        12299,
+        631,
+        4666,
+        2630,
+        7532,
+        892,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1935427300283842,
+      "compression_ratio": 1.5084745762711864,
+      "no_speech_prob": 0.5593915581703186,
+      "confidence": 0.947,
+      "words": [
+        {
+          "text": "Durant",
+          "start": 51.5,
+          "end": 52.3,
+          "confidence": 0.935
+        },
+        {
+          "text": "60",
+          "start": 52.3,
+          "end": 52.7,
+          "confidence": 0.922
+        },
+        {
+          "text": "minutes",
+          "start": 52.7,
+          "end": 53.08,
+          "confidence": 0.912
+        },
+        {
+          "text": "ce",
+          "start": 53.08,
+          "end": 53.26,
+          "confidence": 0.752
+        },
+        {
+          "text": "sont",
+          "start": 53.26,
+          "end": 53.58,
+          "confidence": 0.979
+        },
+        {
+          "text": "des",
+          "start": 53.58,
+          "end": 53.86,
+          "confidence": 0.99
+        },
+        {
+          "text": "gros",
+          "start": 53.86,
+          "end": 54.02,
+          "confidence": 0.969
+        },
+        {
+          "text": "plans,",
+          "start": 54.02,
+          "end": 54.32,
+          "confidence": 0.958
+        },
+        {
+          "text": "des",
+          "start": 54.32,
+          "end": 54.44,
+          "confidence": 0.986
+        },
+        {
+          "text": "analyses,",
+          "start": 54.44,
+          "end": 54.78,
+          "confidence": 0.913
+        },
+        {
+          "text": "des",
+          "start": 54.78,
+          "end": 54.86,
+          "confidence": 0.995
+        },
+        {
+          "text": "réactions",
+          "start": 54.86,
+          "end": 55.22,
+          "confidence": 0.996
+        },
+        {
+          "text": "que",
+          "start": 55.22,
+          "end": 55.4,
+          "confidence": 0.882
+        },
+        {
+          "text": "nous",
+          "start": 55.4,
+          "end": 55.54,
+          "confidence": 0.947
+        },
+        {
+          "text": "vous",
+          "start": 55.54,
+          "end": 55.64,
+          "confidence": 0.99
+        },
+        {
+          "text": "proposons.",
+          "start": 55.64,
+          "end": 56.11,
+          "confidence": 0.991
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 5600,
+      "start": 56.11,
+      "end": 63.98,
+      "text": " Comment Eric Verth peut-il encore soutenir la réforme des retraites alors qu'il est englué dans sa propre affaire, l'affaire Verth-Bettancourt?",
+      "tokens": [
+        16328,
+        9336,
+        4281,
+        392,
+        5977,
+        12,
+        388,
+        10122,
+        29350,
+        268,
+        347,
+        635,
+        3960,
+        44562,
+        730,
+        49356,
+        3324,
+        11246,
+        421,
+        6,
+        388,
+        871,
+        1741,
+        2781,
+        526,
+        2680,
+        601,
+        35221,
+        2096,
+        9020,
+        11,
+        287,
+        6,
+        2518,
+        9020,
+        4281,
+        392,
+        12,
+        33,
+        3093,
+        4463,
+        33403,
+        2506
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12757631117297757,
+      "compression_ratio": 1.5705329153605017,
+      "no_speech_prob": 6.333013880066574e-05,
+      "confidence": 0.858,
+      "words": [
+        {
+          "text": "Comment",
+          "start": 56.11,
+          "end": 56.94,
+          "confidence": 0.966
+        },
+        {
+          "text": "Eric",
+          "start": 56.94,
+          "end": 57.2,
+          "confidence": 0.888
+        },
+        {
+          "text": "Verth",
+          "start": 57.2,
+          "end": 57.36,
+          "confidence": 0.376
+        },
+        {
+          "text": "peut-il",
+          "start": 57.36,
+          "end": 57.8,
+          "confidence": 0.951
+        },
+        {
+          "text": "encore",
+          "start": 57.8,
+          "end": 58.36,
+          "confidence": 0.971
+        },
+        {
+          "text": "soutenir",
+          "start": 58.36,
+          "end": 58.62,
+          "confidence": 0.997
+        },
+        {
+          "text": "la",
+          "start": 58.62,
+          "end": 58.72,
+          "confidence": 0.98
+        },
+        {
+          "text": "réforme",
+          "start": 58.72,
+          "end": 59.18,
+          "confidence": 0.996
+        },
+        {
+          "text": "des",
+          "start": 59.18,
+          "end": 59.38,
+          "confidence": 0.994
+        },
+        {
+          "text": "retraites",
+          "start": 59.38,
+          "end": 59.78,
+          "confidence": 0.988
+        },
+        {
+          "text": "alors",
+          "start": 59.78,
+          "end": 59.94,
+          "confidence": 0.508
+        },
+        {
+          "text": "qu'il",
+          "start": 59.94,
+          "end": 60.72,
+          "confidence": 0.965
+        },
+        {
+          "text": "est",
+          "start": 60.72,
+          "end": 60.86,
+          "confidence": 0.975
+        },
+        {
+          "text": "englué",
+          "start": 60.86,
+          "end": 61.74,
+          "confidence": 0.945
+        },
+        {
+          "text": "dans",
+          "start": 61.74,
+          "end": 61.92,
+          "confidence": 0.97
+        },
+        {
+          "text": "sa",
+          "start": 61.92,
+          "end": 62.42,
+          "confidence": 0.871
+        },
+        {
+          "text": "propre",
+          "start": 62.42,
+          "end": 62.74,
+          "confidence": 0.992
+        },
+        {
+          "text": "affaire,",
+          "start": 62.74,
+          "end": 62.98,
+          "confidence": 0.993
+        },
+        {
+          "text": "l'affaire",
+          "start": 62.98,
+          "end": 63.24,
+          "confidence": 0.903
+        },
+        {
+          "text": "Verth-Bettancourt?",
+          "start": 63.24,
+          "end": 63.98,
+          "confidence": 0.714
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 5600,
+      "start": 64.0,
+      "end": 67.18,
+      "text": " Question posée par les leaders de la CFDT et la CGT.",
+      "tokens": [
+        14464,
+        1366,
+        3856,
+        971,
+        1512,
+        3523,
+        368,
+        635,
+        21792,
+        35,
+        51,
+        1030,
+        635,
+        38007,
+        51,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12757631117297757,
+      "compression_ratio": 1.5705329153605017,
+      "no_speech_prob": 6.333013880066574e-05,
+      "confidence": 0.896,
+      "words": [
+        {
+          "text": "Question",
+          "start": 64.0,
+          "end": 64.3,
+          "confidence": 0.639
+        },
+        {
+          "text": "posée",
+          "start": 64.3,
+          "end": 64.76,
+          "confidence": 0.977
+        },
+        {
+          "text": "par",
+          "start": 64.76,
+          "end": 64.94,
+          "confidence": 0.989
+        },
+        {
+          "text": "les",
+          "start": 64.94,
+          "end": 65.08,
+          "confidence": 0.966
+        },
+        {
+          "text": "leaders",
+          "start": 65.08,
+          "end": 65.66,
+          "confidence": 0.977
+        },
+        {
+          "text": "de",
+          "start": 65.66,
+          "end": 65.9,
+          "confidence": 0.988
+        },
+        {
+          "text": "la",
+          "start": 65.9,
+          "end": 66.1,
+          "confidence": 0.967
+        },
+        {
+          "text": "CFDT",
+          "start": 66.1,
+          "end": 66.54,
+          "confidence": 0.994
+        },
+        {
+          "text": "et",
+          "start": 66.54,
+          "end": 66.62,
+          "confidence": 0.586
+        },
+        {
+          "text": "la",
+          "start": 66.62,
+          "end": 66.66,
+          "confidence": 0.627
+        },
+        {
+          "text": "CGT.",
+          "start": 66.66,
+          "end": 67.18,
+          "confidence": 0.987
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 5600,
+      "start": 67.44,
+      "end": 76.42,
+      "text": " Réponse de Nicolas Sarkozy, Eric Verth portera le débat sur les retraites, on en parle dans BFM story avec le numéro de la CFDT.",
+      "tokens": [
+        41587,
+        3739,
+        368,
+        38268,
+        318,
+        809,
+        78,
+        1229,
+        11,
+        9336,
+        4281,
+        392,
+        1515,
+        23833,
+        476,
+        2795,
+        11980,
+        1022,
+        1512,
+        49356,
+        3324,
+        11,
+        322,
+        465,
+        18508,
+        2680,
+        363,
+        37,
+        44,
+        1657,
+        4163,
+        476,
+        49525,
+        368,
+        635,
+        21792,
+        35,
+        51,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12757631117297757,
+      "compression_ratio": 1.5705329153605017,
+      "no_speech_prob": 6.333013880066574e-05,
+      "confidence": 0.968,
+      "words": [
+        {
+          "text": "Réponse",
+          "start": 67.44,
+          "end": 67.94,
+          "confidence": 0.957
+        },
+        {
+          "text": "de",
+          "start": 67.94,
+          "end": 68.1,
+          "confidence": 0.966
+        },
+        {
+          "text": "Nicolas",
+          "start": 68.1,
+          "end": 68.36,
+          "confidence": 0.934
+        },
+        {
+          "text": "Sarkozy,",
+          "start": 68.36,
+          "end": 69.06,
+          "confidence": 0.988
+        },
+        {
+          "text": "Eric",
+          "start": 69.06,
+          "end": 69.24,
+          "confidence": 0.962
+        },
+        {
+          "text": "Verth",
+          "start": 69.24,
+          "end": 69.8,
+          "confidence": 0.988
+        },
+        {
+          "text": "portera",
+          "start": 69.8,
+          "end": 70.64,
+          "confidence": 0.966
+        },
+        {
+          "text": "le",
+          "start": 70.64,
+          "end": 71.0,
+          "confidence": 0.99
+        },
+        {
+          "text": "débat",
+          "start": 71.0,
+          "end": 71.4,
+          "confidence": 0.996
+        },
+        {
+          "text": "sur",
+          "start": 71.4,
+          "end": 71.66,
+          "confidence": 0.99
+        },
+        {
+          "text": "les",
+          "start": 71.66,
+          "end": 71.82,
+          "confidence": 0.997
+        },
+        {
+          "text": "retraites,",
+          "start": 71.82,
+          "end": 72.34,
+          "confidence": 0.996
+        },
+        {
+          "text": "on",
+          "start": 72.34,
+          "end": 72.46,
+          "confidence": 0.842
+        },
+        {
+          "text": "en",
+          "start": 72.46,
+          "end": 72.74,
+          "confidence": 0.948
+        },
+        {
+          "text": "parle",
+          "start": 72.74,
+          "end": 72.92,
+          "confidence": 0.996
+        },
+        {
+          "text": "dans",
+          "start": 72.92,
+          "end": 73.42,
+          "confidence": 0.983
+        },
+        {
+          "text": "BFM",
+          "start": 73.42,
+          "end": 74.6,
+          "confidence": 0.992
+        },
+        {
+          "text": "story",
+          "start": 74.6,
+          "end": 74.7,
+          "confidence": 0.756
+        },
+        {
+          "text": "avec",
+          "start": 74.7,
+          "end": 75.08,
+          "confidence": 0.837
+        },
+        {
+          "text": "le",
+          "start": 75.08,
+          "end": 75.26,
+          "confidence": 0.984
+        },
+        {
+          "text": "numéro",
+          "start": 75.26,
+          "end": 75.52,
+          "confidence": 0.997
+        },
+        {
+          "text": "de",
+          "start": 75.52,
+          "end": 75.76,
+          "confidence": 0.996
+        },
+        {
+          "text": "la",
+          "start": 75.76,
+          "end": 75.9,
+          "confidence": 0.99
+        },
+        {
+          "text": "CFDT.",
+          "start": 75.9,
+          "end": 76.42,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 5600,
+      "start": 76.5,
+      "end": 83.0,
+      "text": " Et puis il y a une bataille qui a démarré, celle entre Marine Le Pen et Bruno Gognich, la bataille de la succession de Jean-Marie Le Pen à la tête du Front National.",
+      "tokens": [
+        3790,
+        9093,
+        1930,
+        288,
+        257,
+        2251,
+        272,
+        3274,
+        3409,
+        1956,
+        257,
+        22761,
+        2284,
+        526,
+        11,
+        25722,
+        3962,
+        20415,
+        1456,
+        10571,
+        1030,
+        23046,
+        460,
+        2912,
+        480,
+        11,
+        635,
+        272,
+        3274,
+        3409,
+        368,
+        635,
+        36624,
+        368,
+        13854,
+        12,
+        16639,
+        414,
+        1456,
+        10571,
+        1531,
+        635,
+        24661,
+        1581,
+        17348,
+        4862,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12757631117297757,
+      "compression_ratio": 1.5705329153605017,
+      "no_speech_prob": 6.333013880066574e-05,
+      "confidence": 0.872,
+      "words": [
+        {
+          "text": "Et",
+          "start": 76.5,
+          "end": 76.96,
+          "confidence": 0.912
+        },
+        {
+          "text": "puis",
+          "start": 76.96,
+          "end": 77.08,
+          "confidence": 0.958
+        },
+        {
+          "text": "il",
+          "start": 77.08,
+          "end": 77.14,
+          "confidence": 0.794
+        },
+        {
+          "text": "y",
+          "start": 77.14,
+          "end": 77.18,
+          "confidence": 0.994
+        },
+        {
+          "text": "a",
+          "start": 77.18,
+          "end": 77.22,
+          "confidence": 0.986
+        },
+        {
+          "text": "une",
+          "start": 77.22,
+          "end": 77.3,
+          "confidence": 0.996
+        },
+        {
+          "text": "bataille",
+          "start": 77.3,
+          "end": 77.56,
+          "confidence": 0.996
+        },
+        {
+          "text": "qui",
+          "start": 77.56,
+          "end": 77.68,
+          "confidence": 0.997
+        },
+        {
+          "text": "a",
+          "start": 77.68,
+          "end": 77.72,
+          "confidence": 0.985
+        },
+        {
+          "text": "démarré,",
+          "start": 77.72,
+          "end": 78.16,
+          "confidence": 0.987
+        },
+        {
+          "text": "celle",
+          "start": 78.16,
+          "end": 78.38,
+          "confidence": 0.997
+        },
+        {
+          "text": "entre",
+          "start": 78.38,
+          "end": 78.64,
+          "confidence": 0.976
+        },
+        {
+          "text": "Marine",
+          "start": 78.64,
+          "end": 78.96,
+          "confidence": 0.987
+        },
+        {
+          "text": "Le",
+          "start": 78.96,
+          "end": 79.12,
+          "confidence": 0.986
+        },
+        {
+          "text": "Pen",
+          "start": 79.12,
+          "end": 79.16,
+          "confidence": 0.987
+        },
+        {
+          "text": "et",
+          "start": 79.16,
+          "end": 79.32,
+          "confidence": 0.997
+        },
+        {
+          "text": "Bruno",
+          "start": 79.32,
+          "end": 79.54,
+          "confidence": 0.986
+        },
+        {
+          "text": "Gognich,",
+          "start": 79.54,
+          "end": 80.2,
+          "confidence": 0.24
+        },
+        {
+          "text": "la",
+          "start": 80.2,
+          "end": 80.32,
+          "confidence": 0.676
+        },
+        {
+          "text": "bataille",
+          "start": 80.32,
+          "end": 80.54,
+          "confidence": 0.998
+        },
+        {
+          "text": "de",
+          "start": 80.54,
+          "end": 80.72,
+          "confidence": 0.975
+        },
+        {
+          "text": "la",
+          "start": 80.72,
+          "end": 80.92,
+          "confidence": 0.988
+        },
+        {
+          "text": "succession",
+          "start": 80.92,
+          "end": 81.18,
+          "confidence": 0.983
+        },
+        {
+          "text": "de",
+          "start": 81.18,
+          "end": 81.44,
+          "confidence": 0.984
+        },
+        {
+          "text": "Jean-Marie",
+          "start": 81.44,
+          "end": 81.7,
+          "confidence": 0.95
+        },
+        {
+          "text": "Le",
+          "start": 81.7,
+          "end": 81.94,
+          "confidence": 0.996
+        },
+        {
+          "text": "Pen",
+          "start": 81.94,
+          "end": 81.98,
+          "confidence": 0.999
+        },
+        {
+          "text": "à",
+          "start": 81.98,
+          "end": 82.12,
+          "confidence": 0.976
+        },
+        {
+          "text": "la",
+          "start": 82.12,
+          "end": 82.28,
+          "confidence": 0.995
+        },
+        {
+          "text": "tête",
+          "start": 82.28,
+          "end": 82.32,
+          "confidence": 0.926
+        },
+        {
+          "text": "du",
+          "start": 82.32,
+          "end": 82.48,
+          "confidence": 0.997
+        },
+        {
+          "text": "Front",
+          "start": 82.48,
+          "end": 82.64,
+          "confidence": 0.775
+        },
+        {
+          "text": "National.",
+          "start": 82.64,
+          "end": 83.0,
+          "confidence": 0.836
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 8300,
+      "start": 83.3,
+      "end": 88.82,
+      "text": " La tournée de campagne de Marine Le Pen commence aujourd'hui dans le Var, Marine Le Pen sera en direct dans BFM story.",
+      "tokens": [
+        2369,
+        3512,
+        77,
+        3856,
+        368,
+        2255,
+        13887,
+        368,
+        20415,
+        1456,
+        10571,
+        18137,
+        14023,
+        6,
+        10556,
+        2680,
+        476,
+        14662,
+        11,
+        20415,
+        1456,
+        10571,
+        15021,
+        465,
+        2047,
+        2680,
+        363,
+        37,
+        44,
+        1657,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10741670781915838,
+      "compression_ratio": 1.3591549295774648,
+      "no_speech_prob": 0.00011412434105295688,
+      "confidence": 0.958,
+      "words": [
+        {
+          "text": "La",
+          "start": 83.3,
+          "end": 83.56,
+          "confidence": 0.98
+        },
+        {
+          "text": "tournée",
+          "start": 83.56,
+          "end": 84.14,
+          "confidence": 0.995
+        },
+        {
+          "text": "de",
+          "start": 84.14,
+          "end": 84.36,
+          "confidence": 0.947
+        },
+        {
+          "text": "campagne",
+          "start": 84.36,
+          "end": 84.84,
+          "confidence": 0.984
+        },
+        {
+          "text": "de",
+          "start": 84.84,
+          "end": 84.9,
+          "confidence": 0.977
+        },
+        {
+          "text": "Marine",
+          "start": 84.9,
+          "end": 85.18,
+          "confidence": 0.997
+        },
+        {
+          "text": "Le",
+          "start": 85.18,
+          "end": 85.26,
+          "confidence": 0.998
+        },
+        {
+          "text": "Pen",
+          "start": 85.26,
+          "end": 85.44,
+          "confidence": 0.999
+        },
+        {
+          "text": "commence",
+          "start": 85.44,
+          "end": 85.78,
+          "confidence": 0.98
+        },
+        {
+          "text": "aujourd'hui",
+          "start": 85.78,
+          "end": 86.14,
+          "confidence": 0.991
+        },
+        {
+          "text": "dans",
+          "start": 86.14,
+          "end": 86.24,
+          "confidence": 0.984
+        },
+        {
+          "text": "le",
+          "start": 86.24,
+          "end": 86.38,
+          "confidence": 0.913
+        },
+        {
+          "text": "Var,",
+          "start": 86.38,
+          "end": 86.82,
+          "confidence": 0.523
+        },
+        {
+          "text": "Marine",
+          "start": 86.82,
+          "end": 86.96,
+          "confidence": 0.993
+        },
+        {
+          "text": "Le",
+          "start": 86.96,
+          "end": 87.04,
+          "confidence": 0.993
+        },
+        {
+          "text": "Pen",
+          "start": 87.04,
+          "end": 87.22,
+          "confidence": 0.999
+        },
+        {
+          "text": "sera",
+          "start": 87.22,
+          "end": 87.48,
+          "confidence": 0.991
+        },
+        {
+          "text": "en",
+          "start": 87.48,
+          "end": 87.68,
+          "confidence": 0.991
+        },
+        {
+          "text": "direct",
+          "start": 87.68,
+          "end": 87.98,
+          "confidence": 0.997
+        },
+        {
+          "text": "dans",
+          "start": 87.98,
+          "end": 88.3,
+          "confidence": 0.935
+        },
+        {
+          "text": "BFM",
+          "start": 88.3,
+          "end": 88.72,
+          "confidence": 0.997
+        },
+        {
+          "text": "story.",
+          "start": 88.72,
+          "end": 88.82,
+          "confidence": 0.827
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 8300,
+      "start": 89.0,
+      "end": 92.15,
+      "text": " Restez avec nous Marine Le Pen dans moins de 3 minutes, à tout de suite.",
+      "tokens": [
+        13094,
+        4371,
+        4163,
+        4666,
+        20415,
+        1456,
+        10571,
+        2680,
+        13099,
+        368,
+        805,
+        2077,
+        11,
+        1531,
+        3486,
+        368,
+        14205,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10741670781915838,
+      "compression_ratio": 1.3591549295774648,
+      "no_speech_prob": 0.00011412434105295688,
+      "confidence": 0.937,
+      "words": [
+        {
+          "text": "Restez",
+          "start": 89.0,
+          "end": 89.64,
+          "confidence": 0.966
+        },
+        {
+          "text": "avec",
+          "start": 89.64,
+          "end": 89.68,
+          "confidence": 0.997
+        },
+        {
+          "text": "nous",
+          "start": 89.68,
+          "end": 89.94,
+          "confidence": 0.968
+        },
+        {
+          "text": "Marine",
+          "start": 89.94,
+          "end": 90.18,
+          "confidence": 0.906
+        },
+        {
+          "text": "Le",
+          "start": 90.18,
+          "end": 90.4,
+          "confidence": 0.998
+        },
+        {
+          "text": "Pen",
+          "start": 90.4,
+          "end": 90.68,
+          "confidence": 0.999
+        },
+        {
+          "text": "dans",
+          "start": 90.68,
+          "end": 90.88,
+          "confidence": 0.836
+        },
+        {
+          "text": "moins",
+          "start": 90.88,
+          "end": 91.18,
+          "confidence": 0.993
+        },
+        {
+          "text": "de",
+          "start": 91.18,
+          "end": 91.28,
+          "confidence": 0.991
+        },
+        {
+          "text": "3",
+          "start": 91.28,
+          "end": 91.46,
+          "confidence": 0.609
+        },
+        {
+          "text": "minutes,",
+          "start": 91.46,
+          "end": 91.86,
+          "confidence": 0.986
+        },
+        {
+          "text": "à",
+          "start": 91.86,
+          "end": 91.9,
+          "confidence": 0.962
+        },
+        {
+          "text": "tout",
+          "start": 91.9,
+          "end": 92.04,
+          "confidence": 0.918
+        },
+        {
+          "text": "de",
+          "start": 92.04,
+          "end": 92.1,
+          "confidence": 0.999
+        },
+        {
+          "text": "suite.",
+          "start": 92.1,
+          "end": 92.15,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 9200,
+      "start": 92.15,
+      "end": 93.74,
+      "text": " Musique",
+      "tokens": [
+        3569,
+        1925
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.15070751414579503,
+      "compression_ratio": 1.4545454545454546,
+      "no_speech_prob": 8.21087378426455e-05,
+      "confidence": 0.328,
+      "words": [
+        {
+          "text": "Musique",
+          "start": 92.15,
+          "end": 93.74,
+          "confidence": 0.328
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 9200,
+      "start": 106.7,
+      "end": 113.5,
+      "text": " L'actualité c'est aussi aujourd'hui un dernier adieu, dernier adieu à Laurent Fignon, c'était au cimetière du Père Lachaise à Paris.",
+      "tokens": [
+        441,
+        6,
+        578,
+        901,
+        5066,
+        269,
+        6,
+        377,
+        6212,
+        14023,
+        6,
+        10556,
+        517,
+        29332,
+        614,
+        19347,
+        11,
+        29332,
+        614,
+        19347,
+        1531,
+        49357,
+        479,
+        41846,
+        11,
+        269,
+        6,
+        9743,
+        1609,
+        269,
+        26123,
+        10195,
+        1581,
+        430,
+        4212,
+        441,
+        27442,
+        908,
+        1531,
+        8380,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.15070751414579503,
+      "compression_ratio": 1.4545454545454546,
+      "no_speech_prob": 8.21087378426455e-05,
+      "confidence": 0.898,
+      "words": [
+        {
+          "text": "L'actualité",
+          "start": 106.7,
+          "end": 107.44,
+          "confidence": 0.868
+        },
+        {
+          "text": "c'est",
+          "start": 107.44,
+          "end": 107.66,
+          "confidence": 0.84
+        },
+        {
+          "text": "aussi",
+          "start": 107.66,
+          "end": 108.02,
+          "confidence": 0.804
+        },
+        {
+          "text": "aujourd'hui",
+          "start": 108.02,
+          "end": 108.38,
+          "confidence": 0.928
+        },
+        {
+          "text": "un",
+          "start": 108.38,
+          "end": 108.48,
+          "confidence": 0.887
+        },
+        {
+          "text": "dernier",
+          "start": 108.48,
+          "end": 108.8,
+          "confidence": 0.991
+        },
+        {
+          "text": "adieu,",
+          "start": 108.8,
+          "end": 109.2,
+          "confidence": 0.982
+        },
+        {
+          "text": "dernier",
+          "start": 109.2,
+          "end": 109.38,
+          "confidence": 0.501
+        },
+        {
+          "text": "adieu",
+          "start": 109.38,
+          "end": 109.96,
+          "confidence": 0.997
+        },
+        {
+          "text": "à",
+          "start": 109.96,
+          "end": 110.12,
+          "confidence": 0.978
+        },
+        {
+          "text": "Laurent",
+          "start": 110.12,
+          "end": 110.42,
+          "confidence": 0.94
+        },
+        {
+          "text": "Fignon,",
+          "start": 110.42,
+          "end": 111.12,
+          "confidence": 0.816
+        },
+        {
+          "text": "c'était",
+          "start": 111.12,
+          "end": 111.24,
+          "confidence": 0.972
+        },
+        {
+          "text": "au",
+          "start": 111.24,
+          "end": 111.46,
+          "confidence": 0.99
+        },
+        {
+          "text": "cimetière",
+          "start": 111.46,
+          "end": 111.94,
+          "confidence": 0.984
+        },
+        {
+          "text": "du",
+          "start": 111.94,
+          "end": 112.14,
+          "confidence": 0.963
+        },
+        {
+          "text": "Père",
+          "start": 112.14,
+          "end": 112.36,
+          "confidence": 0.892
+        },
+        {
+          "text": "Lachaise",
+          "start": 112.36,
+          "end": 112.88,
+          "confidence": 0.864
+        },
+        {
+          "text": "à",
+          "start": 112.88,
+          "end": 113.12,
+          "confidence": 0.795
+        },
+        {
+          "text": "Paris.",
+          "start": 113.12,
+          "end": 113.5,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 11400,
+      "start": 114.02,
+      "end": 120.46,
+      "text": " L'ancien double vainqueur du Tour de France, vaincu par le cancer à 50 ans, a été incinéré en petit comité aujourd'hui.",
+      "tokens": [
+        50364,
+        441,
+        6,
+        38840,
+        268,
+        3834,
+        22240,
+        1077,
+        374,
+        1581,
+        13077,
+        368,
+        6190,
+        11,
+        22240,
+        12032,
+        971,
+        476,
+        5592,
+        1531,
+        2625,
+        1567,
+        11,
+        257,
+        8862,
+        834,
+        259,
+        29071,
+        465,
+        9686,
+        395,
+        5066,
+        14023,
+        6,
+        10556,
+        13,
+        50764
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10655183541147333,
+      "compression_ratio": 1.1160714285714286,
+      "no_speech_prob": 0.0002510416379664093,
+      "confidence": 0.933,
+      "words": [
+        {
+          "text": "L'ancien",
+          "start": 114.02,
+          "end": 114.36,
+          "confidence": 0.735
+        },
+        {
+          "text": "double",
+          "start": 114.36,
+          "end": 114.64,
+          "confidence": 0.991
+        },
+        {
+          "text": "vainqueur",
+          "start": 114.64,
+          "end": 115.08,
+          "confidence": 0.996
+        },
+        {
+          "text": "du",
+          "start": 115.08,
+          "end": 115.18,
+          "confidence": 0.971
+        },
+        {
+          "text": "Tour",
+          "start": 115.18,
+          "end": 115.36,
+          "confidence": 0.828
+        },
+        {
+          "text": "de",
+          "start": 115.36,
+          "end": 115.5,
+          "confidence": 0.992
+        },
+        {
+          "text": "France,",
+          "start": 115.5,
+          "end": 116.32,
+          "confidence": 0.999
+        },
+        {
+          "text": "vaincu",
+          "start": 116.32,
+          "end": 116.48,
+          "confidence": 0.989
+        },
+        {
+          "text": "par",
+          "start": 116.48,
+          "end": 116.6,
+          "confidence": 0.997
+        },
+        {
+          "text": "le",
+          "start": 116.6,
+          "end": 116.74,
+          "confidence": 0.994
+        },
+        {
+          "text": "cancer",
+          "start": 116.74,
+          "end": 117.06,
+          "confidence": 0.966
+        },
+        {
+          "text": "à",
+          "start": 117.06,
+          "end": 117.24,
+          "confidence": 0.964
+        },
+        {
+          "text": "50",
+          "start": 117.24,
+          "end": 117.54,
+          "confidence": 0.977
+        },
+        {
+          "text": "ans,",
+          "start": 117.54,
+          "end": 118.34,
+          "confidence": 0.989
+        },
+        {
+          "text": "a",
+          "start": 118.34,
+          "end": 118.38,
+          "confidence": 0.989
+        },
+        {
+          "text": "été",
+          "start": 118.38,
+          "end": 118.56,
+          "confidence": 0.996
+        },
+        {
+          "text": "incinéré",
+          "start": 118.56,
+          "end": 119.24,
+          "confidence": 0.965
+        },
+        {
+          "text": "en",
+          "start": 119.24,
+          "end": 119.48,
+          "confidence": 0.913
+        },
+        {
+          "text": "petit",
+          "start": 119.48,
+          "end": 119.74,
+          "confidence": 0.883
+        },
+        {
+          "text": "comité",
+          "start": 119.74,
+          "end": 120.18,
+          "confidence": 0.978
+        },
+        {
+          "text": "aujourd'hui.",
+          "start": 120.18,
+          "end": 120.46,
+          "confidence": 0.929
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/medium_fr.cpu/smartphone.mp3.words.json b/tests/expected/medium_fr.cpu/smartphone.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..9faa961d5cf4a38b6ac04b76010aeaddb28cee89
--- /dev/null
+++ b/tests/expected/medium_fr.cpu/smartphone.mp3.words.json
@@ -0,0 +1,4802 @@
+{
+  "text": " C'est évident ce que dit Nicolas, mais je ne me l'étais jamais formulé comme ça. Ce qui fait la force du smartphone, c'est pas seulement l'accumulation des fonctions, mais la manière dont elles interagissent entre elles. Ce qui dit d'ailleurs sur la photo, c'est hyper convaincant. Alors évidemment, il faudrait ajouter les interfaces. L'écran tactile a été beaucoup très souvent mentionné. Mais bon, il faut dire qu'il profite aussi de 20 ans pendant lesquels les ordinateurs nous ont appris à cliquer sur des icônes. Sauf que le smartphone ajoute le toucher, ce qui rend le contact plus direct, plus sensible. Et puis évidemment, il faudrait parler aussi des applications qui permettent de contourner le côté touffu de la navigation web pour aller directement au but. Bref, tout ça, ce sont les conditions qui permettent de créer cet objet dont Nicolas dit qu'il est vraisemblablement inédit dans l'histoire de l'humanité. Mais ça, ça soulève une autre interrogation. Est-ce que le fait que cet objet soit inédit induit que notre rapport à lui est aussi un rapport inédit? Je veux dire, est-ce que le rapport qu'on a au smartphone est comparable à celui qu'on entretenait à d'autres objets techniques comme la voiture ou le téléphone? Il n'y a pas d'équivalent en fait. Et donc cette espèce de nouveauté dans la relation à l'objet, c'est fascinant et terrifiant. Parce qu'on a l'impression, comme le disent les utilisateurs et les services, d'être dépendants de cet objet, d'induire en fait une espèce de relation, de médiation avec le monde qui rend de l'ampleur et qui amène aussi à des formes de rejet. Donc, à objet inédit, rapport inédit. Et ce rapport, si j'en crois Nicolas, serait caractérisé par un mélange de dépendance et de rejet. Bon, en vrai, il faudrait remonter très très finement toute l'histoire des objets techniques et de leur insertion dans nos vies pour déterminer si ce rapport est totalement inédit. Mais j'ai l'impression comme ça que Nicolas ne se trompe pas vraiment. Pour autant que je sache, il y a eu plein de discussions autour de la voiture ou même du téléphone. Mais la dépendance n'était pas du même ordre. Donc le rejet non plus n'était pas du même ordre. On peut adorer sa bagnole, en avoir besoin pour plein de choses. Et bien, le soir, quand on va se coucher, on la laisse. On ne l'a pas dans la main quand on est au lit, on ne l'emmène pas au chiottes. On pouvait être énervé par son môme qui occupait la ligne de téléphone pendant une heure chaque soir pour discuter avec un copain. Mais ça ne ressemblait pas à ce qu'on peut ressentir à voir ce même môme aujourd'hui, continuellement avec son smartphone dans la main, comme si c'était une sorte de pacemaker externe, comme si le lâcher allait entraîner sa mort immédiate. Bon, je dis ça pour le môme, mais c'est évidemment valable pour nous aussi. Donc, rapport inédit. D'accord. Mais pourquoi a-t-on l'impression qu'on n'en sortira jamais? Est-ce qu'il faut en remettre la faute sur les gens qui ont créé cet outil merveilleux et diabolique, et diabolique parce que merveilleux? Les économistes parlent de dépendance du sentier. C'est l'idée qu'on est sur un sentier qui a été établi, soit volontairement en marchant dessus, soit en définissant des bornes, en définissant une signalétique.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.38,
+      "end": 3.62,
+      "text": " C'est évident ce que dit Nicolas, mais je ne me l'étais jamais formulé comme ça.",
+      "tokens": [
+        383,
+        6,
+        377,
+        20090,
+        1078,
+        1769,
+        631,
+        6176,
+        38268,
+        11,
+        2420,
+        1506,
+        408,
+        385,
+        287,
+        6,
+        22824,
+        14540,
+        49990,
+        526,
+        5173,
+        2788,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23666970461409614,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.1567964404821396,
+      "confidence": 0.935,
+      "words": [
+        {
+          "text": "C'est",
+          "start": 0.38,
+          "end": 0.58,
+          "confidence": 0.961
+        },
+        {
+          "text": "évident",
+          "start": 0.58,
+          "end": 0.88,
+          "confidence": 0.984
+        },
+        {
+          "text": "ce",
+          "start": 0.88,
+          "end": 1.02,
+          "confidence": 0.663
+        },
+        {
+          "text": "que",
+          "start": 1.02,
+          "end": 1.08,
+          "confidence": 0.989
+        },
+        {
+          "text": "dit",
+          "start": 1.08,
+          "end": 1.2,
+          "confidence": 0.994
+        },
+        {
+          "text": "Nicolas,",
+          "start": 1.2,
+          "end": 1.78,
+          "confidence": 0.91
+        },
+        {
+          "text": "mais",
+          "start": 1.78,
+          "end": 1.9,
+          "confidence": 0.979
+        },
+        {
+          "text": "je",
+          "start": 1.9,
+          "end": 2.24,
+          "confidence": 0.982
+        },
+        {
+          "text": "ne",
+          "start": 2.24,
+          "end": 2.34,
+          "confidence": 0.835
+        },
+        {
+          "text": "me",
+          "start": 2.34,
+          "end": 2.38,
+          "confidence": 0.82
+        },
+        {
+          "text": "l'étais",
+          "start": 2.38,
+          "end": 2.58,
+          "confidence": 0.971
+        },
+        {
+          "text": "jamais",
+          "start": 2.58,
+          "end": 2.84,
+          "confidence": 0.989
+        },
+        {
+          "text": "formulé",
+          "start": 2.84,
+          "end": 3.26,
+          "confidence": 0.909
+        },
+        {
+          "text": "comme",
+          "start": 3.26,
+          "end": 3.42,
+          "confidence": 0.993
+        },
+        {
+          "text": "ça.",
+          "start": 3.42,
+          "end": 3.62,
+          "confidence": 0.975
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 4.08,
+      "end": 7.92,
+      "text": " Ce qui fait la force du smartphone, c'est pas seulement l'accumulation des fonctions,",
+      "tokens": [
+        8257,
+        1956,
+        3887,
+        635,
+        3464,
+        1581,
+        13307,
+        11,
+        269,
+        6,
+        377,
+        1736,
+        27772,
+        287,
+        6,
+        8476,
+        449,
+        2776,
+        730,
+        17290,
+        3916,
+        11
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23666970461409614,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.1567964404821396,
+      "confidence": 0.93,
+      "words": [
+        {
+          "text": "Ce",
+          "start": 4.08,
+          "end": 4.26,
+          "confidence": 0.952
+        },
+        {
+          "text": "qui",
+          "start": 4.26,
+          "end": 4.34,
+          "confidence": 0.958
+        },
+        {
+          "text": "fait",
+          "start": 4.34,
+          "end": 4.48,
+          "confidence": 0.565
+        },
+        {
+          "text": "la",
+          "start": 4.48,
+          "end": 4.66,
+          "confidence": 0.971
+        },
+        {
+          "text": "force",
+          "start": 4.66,
+          "end": 5.0,
+          "confidence": 0.999
+        },
+        {
+          "text": "du",
+          "start": 5.0,
+          "end": 5.2,
+          "confidence": 0.996
+        },
+        {
+          "text": "smartphone,",
+          "start": 5.2,
+          "end": 5.88,
+          "confidence": 0.911
+        },
+        {
+          "text": "c'est",
+          "start": 5.88,
+          "end": 6.12,
+          "confidence": 0.88
+        },
+        {
+          "text": "pas",
+          "start": 6.12,
+          "end": 6.26,
+          "confidence": 0.992
+        },
+        {
+          "text": "seulement",
+          "start": 6.26,
+          "end": 6.52,
+          "confidence": 0.999
+        },
+        {
+          "text": "l'accumulation",
+          "start": 6.52,
+          "end": 7.38,
+          "confidence": 0.958
+        },
+        {
+          "text": "des",
+          "start": 7.38,
+          "end": 7.56,
+          "confidence": 0.983
+        },
+        {
+          "text": "fonctions,",
+          "start": 7.56,
+          "end": 7.92,
+          "confidence": 0.987
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 8.32,
+      "end": 10.88,
+      "text": " mais la manière dont elles interagissent entre elles.",
+      "tokens": [
+        2420,
+        635,
+        22267,
+        9400,
+        23576,
+        728,
+        559,
+        25450,
+        3962,
+        23576,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23666970461409614,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.1567964404821396,
+      "confidence": 0.977,
+      "words": [
+        {
+          "text": "mais",
+          "start": 8.32,
+          "end": 8.44,
+          "confidence": 0.992
+        },
+        {
+          "text": "la",
+          "start": 8.44,
+          "end": 8.6,
+          "confidence": 0.995
+        },
+        {
+          "text": "manière",
+          "start": 8.6,
+          "end": 8.9,
+          "confidence": 0.999
+        },
+        {
+          "text": "dont",
+          "start": 8.9,
+          "end": 9.1,
+          "confidence": 0.978
+        },
+        {
+          "text": "elles",
+          "start": 9.1,
+          "end": 9.48,
+          "confidence": 0.967
+        },
+        {
+          "text": "interagissent",
+          "start": 9.48,
+          "end": 10.32,
+          "confidence": 0.964
+        },
+        {
+          "text": "entre",
+          "start": 10.32,
+          "end": 10.58,
+          "confidence": 0.956
+        },
+        {
+          "text": "elles.",
+          "start": 10.58,
+          "end": 10.88,
+          "confidence": 0.99
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 10.96,
+      "end": 13.0,
+      "text": " Ce qui dit d'ailleurs sur la photo, c'est hyper convaincant.",
+      "tokens": [
+        8257,
+        1956,
+        6176,
+        274,
+        6,
+        19400,
+        1022,
+        635,
+        5052,
+        11,
+        269,
+        6,
+        377,
+        9848,
+        3754,
+        491,
+        66,
+        394,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23666970461409614,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.1567964404821396,
+      "confidence": 0.906,
+      "words": [
+        {
+          "text": "Ce",
+          "start": 10.96,
+          "end": 11.16,
+          "confidence": 0.607
+        },
+        {
+          "text": "qui",
+          "start": 11.16,
+          "end": 11.22,
+          "confidence": 0.765
+        },
+        {
+          "text": "dit",
+          "start": 11.22,
+          "end": 11.4,
+          "confidence": 0.983
+        },
+        {
+          "text": "d'ailleurs",
+          "start": 11.4,
+          "end": 11.56,
+          "confidence": 0.985
+        },
+        {
+          "text": "sur",
+          "start": 11.56,
+          "end": 11.72,
+          "confidence": 0.477
+        },
+        {
+          "text": "la",
+          "start": 11.72,
+          "end": 11.78,
+          "confidence": 0.984
+        },
+        {
+          "text": "photo,",
+          "start": 11.78,
+          "end": 12.12,
+          "confidence": 0.994
+        },
+        {
+          "text": "c'est",
+          "start": 12.12,
+          "end": 12.2,
+          "confidence": 0.997
+        },
+        {
+          "text": "hyper",
+          "start": 12.2,
+          "end": 12.42,
+          "confidence": 0.993
+        },
+        {
+          "text": "convaincant.",
+          "start": 12.42,
+          "end": 13.0,
+          "confidence": 0.982
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 13.34,
+      "end": 16.02,
+      "text": " Alors évidemment, il faudrait ajouter les interfaces.",
+      "tokens": [
+        9946,
+        24724,
+        11,
+        1930,
+        38694,
+        8645,
+        17680,
+        23985,
+        1512,
+        28416,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23666970461409614,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.1567964404821396,
+      "confidence": 0.913,
+      "words": [
+        {
+          "text": "Alors",
+          "start": 13.34,
+          "end": 13.62,
+          "confidence": 0.585
+        },
+        {
+          "text": "évidemment,",
+          "start": 13.62,
+          "end": 14.34,
+          "confidence": 0.832
+        },
+        {
+          "text": "il",
+          "start": 14.34,
+          "end": 14.38,
+          "confidence": 0.952
+        },
+        {
+          "text": "faudrait",
+          "start": 14.38,
+          "end": 14.74,
+          "confidence": 0.996
+        },
+        {
+          "text": "ajouter",
+          "start": 14.74,
+          "end": 15.16,
+          "confidence": 0.992
+        },
+        {
+          "text": "les",
+          "start": 15.16,
+          "end": 15.52,
+          "confidence": 0.985
+        },
+        {
+          "text": "interfaces.",
+          "start": 15.52,
+          "end": 16.02,
+          "confidence": 0.984
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 0,
+      "start": 16.22,
+      "end": 19.36,
+      "text": " L'écran tactile a été beaucoup très souvent mentionné.",
+      "tokens": [
+        441,
+        6,
+        9062,
+        4257,
+        47319,
+        257,
+        8862,
+        8796,
+        5732,
+        20847,
+        2152,
+        15055,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23666970461409614,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.1567964404821396,
+      "confidence": 0.923,
+      "words": [
+        {
+          "text": "L'écran",
+          "start": 16.22,
+          "end": 16.7,
+          "confidence": 0.996
+        },
+        {
+          "text": "tactile",
+          "start": 16.7,
+          "end": 17.06,
+          "confidence": 0.986
+        },
+        {
+          "text": "a",
+          "start": 17.06,
+          "end": 17.26,
+          "confidence": 0.98
+        },
+        {
+          "text": "été",
+          "start": 17.26,
+          "end": 17.88,
+          "confidence": 0.975
+        },
+        {
+          "text": "beaucoup",
+          "start": 17.88,
+          "end": 18.28,
+          "confidence": 0.976
+        },
+        {
+          "text": "très",
+          "start": 18.28,
+          "end": 18.62,
+          "confidence": 0.447
+        },
+        {
+          "text": "souvent",
+          "start": 18.62,
+          "end": 18.9,
+          "confidence": 0.996
+        },
+        {
+          "text": "mentionné.",
+          "start": 18.9,
+          "end": 19.36,
+          "confidence": 0.978
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 0,
+      "start": 19.84,
+      "end": 25.26,
+      "text": " Mais bon, il faut dire qu'il profite aussi de 20 ans pendant lesquels les ordinateurs nous ont appris à cliquer sur des icônes.",
+      "tokens": [
+        6313,
+        4428,
+        11,
+        1930,
+        8487,
+        1264,
+        421,
+        6,
+        388,
+        1740,
+        642,
+        6212,
+        368,
+        945,
+        1567,
+        17338,
+        1512,
+        358,
+        1625,
+        1512,
+        4792,
+        13923,
+        2156,
+        4666,
+        6592,
+        724,
+        5714,
+        1531,
+        596,
+        23909,
+        1022,
+        730,
+        4376,
+        2851,
+        4081,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23666970461409614,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.1567964404821396,
+      "confidence": 0.92,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 19.84,
+          "end": 20.22,
+          "confidence": 0.944
+        },
+        {
+          "text": "bon,",
+          "start": 20.22,
+          "end": 20.52,
+          "confidence": 0.667
+        },
+        {
+          "text": "il",
+          "start": 20.52,
+          "end": 20.6,
+          "confidence": 0.99
+        },
+        {
+          "text": "faut",
+          "start": 20.6,
+          "end": 20.7,
+          "confidence": 0.99
+        },
+        {
+          "text": "dire",
+          "start": 20.7,
+          "end": 20.84,
+          "confidence": 0.995
+        },
+        {
+          "text": "qu'il",
+          "start": 20.84,
+          "end": 20.96,
+          "confidence": 0.88
+        },
+        {
+          "text": "profite",
+          "start": 20.96,
+          "end": 21.26,
+          "confidence": 0.995
+        },
+        {
+          "text": "aussi",
+          "start": 21.26,
+          "end": 21.68,
+          "confidence": 0.972
+        },
+        {
+          "text": "de",
+          "start": 21.68,
+          "end": 21.9,
+          "confidence": 0.97
+        },
+        {
+          "text": "20",
+          "start": 21.9,
+          "end": 22.1,
+          "confidence": 0.812
+        },
+        {
+          "text": "ans",
+          "start": 22.1,
+          "end": 22.32,
+          "confidence": 0.997
+        },
+        {
+          "text": "pendant",
+          "start": 22.32,
+          "end": 22.48,
+          "confidence": 0.72
+        },
+        {
+          "text": "lesquels",
+          "start": 22.48,
+          "end": 22.92,
+          "confidence": 0.98
+        },
+        {
+          "text": "les",
+          "start": 22.92,
+          "end": 23.04,
+          "confidence": 0.709
+        },
+        {
+          "text": "ordinateurs",
+          "start": 23.04,
+          "end": 23.54,
+          "confidence": 0.965
+        },
+        {
+          "text": "nous",
+          "start": 23.54,
+          "end": 23.72,
+          "confidence": 0.602
+        },
+        {
+          "text": "ont",
+          "start": 23.72,
+          "end": 23.82,
+          "confidence": 0.974
+        },
+        {
+          "text": "appris",
+          "start": 23.82,
+          "end": 24.1,
+          "confidence": 0.991
+        },
+        {
+          "text": "à",
+          "start": 24.1,
+          "end": 24.24,
+          "confidence": 0.829
+        },
+        {
+          "text": "cliquer",
+          "start": 24.24,
+          "end": 24.5,
+          "confidence": 0.989
+        },
+        {
+          "text": "sur",
+          "start": 24.5,
+          "end": 24.66,
+          "confidence": 0.984
+        },
+        {
+          "text": "des",
+          "start": 24.66,
+          "end": 24.94,
+          "confidence": 0.971
+        },
+        {
+          "text": "icônes.",
+          "start": 24.94,
+          "end": 25.26,
+          "confidence": 0.992
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 2534,
+      "start": 25.42,
+      "end": 30.64,
+      "text": " Sauf que le smartphone ajoute le toucher, ce qui rend le contact plus direct, plus sensible.",
+      "tokens": [
+        318,
+        9507,
+        631,
+        476,
+        13307,
+        17680,
+        14040,
+        476,
+        2557,
+        260,
+        11,
+        1769,
+        1956,
+        6125,
+        476,
+        3385,
+        1804,
+        2047,
+        11,
+        1804,
+        25380,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07915337880452473,
+      "compression_ratio": 1.6254416961130742,
+      "no_speech_prob": 3.457161710684886e-06,
+      "confidence": 0.969,
+      "words": [
+        {
+          "text": "Sauf",
+          "start": 25.42,
+          "end": 25.76,
+          "confidence": 0.99
+        },
+        {
+          "text": "que",
+          "start": 25.76,
+          "end": 26.26,
+          "confidence": 0.996
+        },
+        {
+          "text": "le",
+          "start": 26.26,
+          "end": 26.66,
+          "confidence": 0.631
+        },
+        {
+          "text": "smartphone",
+          "start": 26.66,
+          "end": 27.06,
+          "confidence": 0.996
+        },
+        {
+          "text": "ajoute",
+          "start": 27.06,
+          "end": 27.44,
+          "confidence": 0.991
+        },
+        {
+          "text": "le",
+          "start": 27.44,
+          "end": 27.62,
+          "confidence": 0.992
+        },
+        {
+          "text": "toucher,",
+          "start": 27.62,
+          "end": 28.18,
+          "confidence": 0.988
+        },
+        {
+          "text": "ce",
+          "start": 28.18,
+          "end": 28.22,
+          "confidence": 0.99
+        },
+        {
+          "text": "qui",
+          "start": 28.22,
+          "end": 28.28,
+          "confidence": 1.0
+        },
+        {
+          "text": "rend",
+          "start": 28.28,
+          "end": 28.48,
+          "confidence": 0.994
+        },
+        {
+          "text": "le",
+          "start": 28.48,
+          "end": 28.68,
+          "confidence": 0.993
+        },
+        {
+          "text": "contact",
+          "start": 28.68,
+          "end": 29.1,
+          "confidence": 0.999
+        },
+        {
+          "text": "plus",
+          "start": 29.1,
+          "end": 29.46,
+          "confidence": 0.985
+        },
+        {
+          "text": "direct,",
+          "start": 29.46,
+          "end": 30.22,
+          "confidence": 0.995
+        },
+        {
+          "text": "plus",
+          "start": 30.22,
+          "end": 30.26,
+          "confidence": 0.994
+        },
+        {
+          "text": "sensible.",
+          "start": 30.26,
+          "end": 30.64,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 2534,
+      "start": 31.04,
+      "end": 37.82,
+      "text": " Et puis évidemment, il faudrait parler aussi des applications qui permettent de contourner le côté touffu de la navigation web pour aller directement au but.",
+      "tokens": [
+        3790,
+        9093,
+        24724,
+        11,
+        1930,
+        38694,
+        8645,
+        16421,
+        6212,
+        730,
+        5821,
+        1956,
+        21540,
+        317,
+        368,
+        21234,
+        1193,
+        476,
+        18437,
+        10095,
+        602,
+        84,
+        368,
+        635,
+        17346,
+        3670,
+        2016,
+        8722,
+        37297,
+        1609,
+        457,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07915337880452473,
+      "compression_ratio": 1.6254416961130742,
+      "no_speech_prob": 3.457161710684886e-06,
+      "confidence": 0.892,
+      "words": [
+        {
+          "text": "Et",
+          "start": 31.04,
+          "end": 31.22,
+          "confidence": 0.97
+        },
+        {
+          "text": "puis",
+          "start": 31.22,
+          "end": 31.36,
+          "confidence": 0.971
+        },
+        {
+          "text": "évidemment,",
+          "start": 31.36,
+          "end": 31.7,
+          "confidence": 0.875
+        },
+        {
+          "text": "il",
+          "start": 31.7,
+          "end": 31.74,
+          "confidence": 0.993
+        },
+        {
+          "text": "faudrait",
+          "start": 31.74,
+          "end": 31.94,
+          "confidence": 0.995
+        },
+        {
+          "text": "parler",
+          "start": 31.94,
+          "end": 32.12,
+          "confidence": 0.84
+        },
+        {
+          "text": "aussi",
+          "start": 32.12,
+          "end": 32.34,
+          "confidence": 0.977
+        },
+        {
+          "text": "des",
+          "start": 32.34,
+          "end": 32.48,
+          "confidence": 0.994
+        },
+        {
+          "text": "applications",
+          "start": 32.48,
+          "end": 32.9,
+          "confidence": 0.993
+        },
+        {
+          "text": "qui",
+          "start": 32.9,
+          "end": 33.18,
+          "confidence": 0.481
+        },
+        {
+          "text": "permettent",
+          "start": 33.18,
+          "end": 33.74,
+          "confidence": 0.992
+        },
+        {
+          "text": "de",
+          "start": 33.74,
+          "end": 33.96,
+          "confidence": 0.885
+        },
+        {
+          "text": "contourner",
+          "start": 33.96,
+          "end": 34.42,
+          "confidence": 0.958
+        },
+        {
+          "text": "le",
+          "start": 34.42,
+          "end": 34.52,
+          "confidence": 0.775
+        },
+        {
+          "text": "côté",
+          "start": 34.52,
+          "end": 34.8,
+          "confidence": 0.984
+        },
+        {
+          "text": "touffu",
+          "start": 34.8,
+          "end": 35.32,
+          "confidence": 0.741
+        },
+        {
+          "text": "de",
+          "start": 35.32,
+          "end": 35.72,
+          "confidence": 0.882
+        },
+        {
+          "text": "la",
+          "start": 35.72,
+          "end": 35.78,
+          "confidence": 0.992
+        },
+        {
+          "text": "navigation",
+          "start": 35.78,
+          "end": 36.24,
+          "confidence": 0.994
+        },
+        {
+          "text": "web",
+          "start": 36.24,
+          "end": 36.6,
+          "confidence": 0.854
+        },
+        {
+          "text": "pour",
+          "start": 36.6,
+          "end": 36.78,
+          "confidence": 0.585
+        },
+        {
+          "text": "aller",
+          "start": 36.78,
+          "end": 36.98,
+          "confidence": 0.987
+        },
+        {
+          "text": "directement",
+          "start": 36.98,
+          "end": 37.52,
+          "confidence": 0.997
+        },
+        {
+          "text": "au",
+          "start": 37.52,
+          "end": 37.68,
+          "confidence": 0.967
+        },
+        {
+          "text": "but.",
+          "start": 37.68,
+          "end": 37.82,
+          "confidence": 0.995
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 2534,
+      "start": 37.82,
+      "end": 46.54,
+      "text": " Bref, tout ça, ce sont les conditions qui permettent de créer cet objet dont Nicolas dit qu'il est vraisemblablement inédit dans l'histoire de l'humanité.",
+      "tokens": [
+        49957,
+        11,
+        3486,
+        2788,
+        11,
+        1769,
+        4900,
+        1512,
+        4487,
+        1956,
+        21540,
+        317,
+        368,
+        32062,
+        8603,
+        14964,
+        9400,
+        38268,
+        6176,
+        421,
+        6,
+        388,
+        871,
+        6070,
+        271,
+        443,
+        5199,
+        712,
+        518,
+        294,
+        7811,
+        270,
+        2680,
+        287,
+        6,
+        29093,
+        368,
+        287,
+        6,
+        18796,
+        5066,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07915337880452473,
+      "compression_ratio": 1.6254416961130742,
+      "no_speech_prob": 3.457161710684886e-06,
+      "confidence": 0.974,
+      "words": [
+        {
+          "text": "Bref,",
+          "start": 37.82,
+          "end": 38.76,
+          "confidence": 0.987
+        },
+        {
+          "text": "tout",
+          "start": 38.76,
+          "end": 38.98,
+          "confidence": 0.711
+        },
+        {
+          "text": "ça,",
+          "start": 38.98,
+          "end": 39.42,
+          "confidence": 0.995
+        },
+        {
+          "text": "ce",
+          "start": 39.42,
+          "end": 39.7,
+          "confidence": 0.993
+        },
+        {
+          "text": "sont",
+          "start": 39.7,
+          "end": 39.88,
+          "confidence": 0.999
+        },
+        {
+          "text": "les",
+          "start": 39.88,
+          "end": 40.16,
+          "confidence": 0.991
+        },
+        {
+          "text": "conditions",
+          "start": 40.16,
+          "end": 40.68,
+          "confidence": 0.995
+        },
+        {
+          "text": "qui",
+          "start": 40.68,
+          "end": 40.96,
+          "confidence": 0.997
+        },
+        {
+          "text": "permettent",
+          "start": 40.96,
+          "end": 41.46,
+          "confidence": 0.997
+        },
+        {
+          "text": "de",
+          "start": 41.46,
+          "end": 41.6,
+          "confidence": 0.998
+        },
+        {
+          "text": "créer",
+          "start": 41.6,
+          "end": 42.06,
+          "confidence": 0.998
+        },
+        {
+          "text": "cet",
+          "start": 42.06,
+          "end": 42.38,
+          "confidence": 0.998
+        },
+        {
+          "text": "objet",
+          "start": 42.38,
+          "end": 42.6,
+          "confidence": 0.994
+        },
+        {
+          "text": "dont",
+          "start": 42.6,
+          "end": 42.8,
+          "confidence": 0.779
+        },
+        {
+          "text": "Nicolas",
+          "start": 42.8,
+          "end": 43.26,
+          "confidence": 0.989
+        },
+        {
+          "text": "dit",
+          "start": 43.26,
+          "end": 43.5,
+          "confidence": 0.986
+        },
+        {
+          "text": "qu'il",
+          "start": 43.5,
+          "end": 43.7,
+          "confidence": 0.983
+        },
+        {
+          "text": "est",
+          "start": 43.7,
+          "end": 43.88,
+          "confidence": 0.991
+        },
+        {
+          "text": "vraisemblablement",
+          "start": 43.88,
+          "end": 44.98,
+          "confidence": 0.991
+        },
+        {
+          "text": "inédit",
+          "start": 44.98,
+          "end": 45.38,
+          "confidence": 0.98
+        },
+        {
+          "text": "dans",
+          "start": 45.38,
+          "end": 45.7,
+          "confidence": 0.969
+        },
+        {
+          "text": "l'histoire",
+          "start": 45.7,
+          "end": 45.98,
+          "confidence": 0.957
+        },
+        {
+          "text": "de",
+          "start": 45.98,
+          "end": 46.18,
+          "confidence": 0.999
+        },
+        {
+          "text": "l'humanité.",
+          "start": 46.18,
+          "end": 46.54,
+          "confidence": 0.992
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 2534,
+      "start": 46.54,
+      "end": 48.82,
+      "text": " Mais ça, ça soulève une autre interrogation.",
+      "tokens": [
+        6313,
+        2788,
+        11,
+        2788,
+        5133,
+        31397,
+        2251,
+        15081,
+        24871,
+        399,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07915337880452473,
+      "compression_ratio": 1.6254416961130742,
+      "no_speech_prob": 3.457161710684886e-06,
+      "confidence": 0.969,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 46.54,
+          "end": 47.24,
+          "confidence": 0.846
+        },
+        {
+          "text": "ça,",
+          "start": 47.24,
+          "end": 47.72,
+          "confidence": 0.935
+        },
+        {
+          "text": "ça",
+          "start": 47.72,
+          "end": 47.76,
+          "confidence": 0.977
+        },
+        {
+          "text": "soulève",
+          "start": 47.76,
+          "end": 47.84,
+          "confidence": 0.993
+        },
+        {
+          "text": "une",
+          "start": 47.84,
+          "end": 48.02,
+          "confidence": 0.998
+        },
+        {
+          "text": "autre",
+          "start": 48.02,
+          "end": 48.26,
+          "confidence": 0.999
+        },
+        {
+          "text": "interrogation.",
+          "start": 48.26,
+          "end": 48.82,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 4884,
+      "start": 49.22,
+      "end": 55.46,
+      "text": " Est-ce que le fait que cet objet soit inédit induit que notre rapport à lui est aussi un rapport inédit?",
+      "tokens": [
+        4410,
+        12,
+        384,
+        631,
+        476,
+        3887,
+        631,
+        8603,
+        14964,
+        12703,
+        294,
+        7811,
+        270,
+        13716,
+        270,
+        631,
+        10349,
+        18018,
+        1531,
+        8783,
+        871,
+        6212,
+        517,
+        18018,
+        294,
+        7811,
+        270,
+        2506
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10746372298689078,
+      "compression_ratio": 1.662379421221865,
+      "no_speech_prob": 1.3105129255563952e-05,
+      "confidence": 0.988,
+      "words": [
+        {
+          "text": "Est-ce",
+          "start": 49.22,
+          "end": 49.62,
+          "confidence": 0.982
+        },
+        {
+          "text": "que",
+          "start": 49.62,
+          "end": 49.72,
+          "confidence": 0.991
+        },
+        {
+          "text": "le",
+          "start": 49.72,
+          "end": 49.82,
+          "confidence": 0.993
+        },
+        {
+          "text": "fait",
+          "start": 49.82,
+          "end": 49.98,
+          "confidence": 0.999
+        },
+        {
+          "text": "que",
+          "start": 49.98,
+          "end": 50.14,
+          "confidence": 0.991
+        },
+        {
+          "text": "cet",
+          "start": 50.14,
+          "end": 50.32,
+          "confidence": 0.991
+        },
+        {
+          "text": "objet",
+          "start": 50.32,
+          "end": 50.66,
+          "confidence": 0.997
+        },
+        {
+          "text": "soit",
+          "start": 50.66,
+          "end": 51.12,
+          "confidence": 0.995
+        },
+        {
+          "text": "inédit",
+          "start": 51.12,
+          "end": 51.8,
+          "confidence": 0.996
+        },
+        {
+          "text": "induit",
+          "start": 51.8,
+          "end": 52.32,
+          "confidence": 0.977
+        },
+        {
+          "text": "que",
+          "start": 52.32,
+          "end": 52.42,
+          "confidence": 0.983
+        },
+        {
+          "text": "notre",
+          "start": 52.42,
+          "end": 52.72,
+          "confidence": 0.996
+        },
+        {
+          "text": "rapport",
+          "start": 52.72,
+          "end": 53.28,
+          "confidence": 0.997
+        },
+        {
+          "text": "à",
+          "start": 53.28,
+          "end": 53.44,
+          "confidence": 0.978
+        },
+        {
+          "text": "lui",
+          "start": 53.44,
+          "end": 53.66,
+          "confidence": 0.999
+        },
+        {
+          "text": "est",
+          "start": 53.66,
+          "end": 54.02,
+          "confidence": 0.916
+        },
+        {
+          "text": "aussi",
+          "start": 54.02,
+          "end": 54.54,
+          "confidence": 0.995
+        },
+        {
+          "text": "un",
+          "start": 54.54,
+          "end": 54.7,
+          "confidence": 0.995
+        },
+        {
+          "text": "rapport",
+          "start": 54.7,
+          "end": 55.0,
+          "confidence": 0.996
+        },
+        {
+          "text": "inédit?",
+          "start": 55.0,
+          "end": 55.46,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 4884,
+      "start": 55.46,
+      "end": 63.12,
+      "text": " Je veux dire, est-ce que le rapport qu'on a au smartphone est comparable à celui qu'on entretenait à d'autres objets techniques comme la voiture ou le téléphone?",
+      "tokens": [
+        2588,
+        16389,
+        1264,
+        11,
+        871,
+        12,
+        384,
+        631,
+        476,
+        18018,
+        421,
+        6,
+        266,
+        257,
+        1609,
+        13307,
+        871,
+        25323,
+        1531,
+        22829,
+        421,
+        6,
+        266,
+        3962,
+        1147,
+        1001,
+        1531,
+        274,
+        6,
+        16752,
+        1111,
+        25349,
+        7512,
+        5173,
+        635,
+        38859,
+        2820,
+        476,
+        47159,
+        2506
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10746372298689078,
+      "compression_ratio": 1.662379421221865,
+      "no_speech_prob": 1.3105129255563952e-05,
+      "confidence": 0.965,
+      "words": [
+        {
+          "text": "Je",
+          "start": 55.46,
+          "end": 55.9,
+          "confidence": 0.88
+        },
+        {
+          "text": "veux",
+          "start": 55.9,
+          "end": 56.0,
+          "confidence": 0.988
+        },
+        {
+          "text": "dire,",
+          "start": 56.0,
+          "end": 56.24,
+          "confidence": 0.997
+        },
+        {
+          "text": "est-ce",
+          "start": 56.24,
+          "end": 56.36,
+          "confidence": 0.99
+        },
+        {
+          "text": "que",
+          "start": 56.36,
+          "end": 56.42,
+          "confidence": 0.99
+        },
+        {
+          "text": "le",
+          "start": 56.42,
+          "end": 56.58,
+          "confidence": 0.995
+        },
+        {
+          "text": "rapport",
+          "start": 56.58,
+          "end": 56.88,
+          "confidence": 0.998
+        },
+        {
+          "text": "qu'on",
+          "start": 56.88,
+          "end": 57.04,
+          "confidence": 0.986
+        },
+        {
+          "text": "a",
+          "start": 57.04,
+          "end": 57.18,
+          "confidence": 0.989
+        },
+        {
+          "text": "au",
+          "start": 57.18,
+          "end": 57.28,
+          "confidence": 0.968
+        },
+        {
+          "text": "smartphone",
+          "start": 57.28,
+          "end": 57.6,
+          "confidence": 0.994
+        },
+        {
+          "text": "est",
+          "start": 57.6,
+          "end": 57.92,
+          "confidence": 0.95
+        },
+        {
+          "text": "comparable",
+          "start": 57.92,
+          "end": 58.24,
+          "confidence": 0.997
+        },
+        {
+          "text": "à",
+          "start": 58.24,
+          "end": 58.48,
+          "confidence": 0.949
+        },
+        {
+          "text": "celui",
+          "start": 58.48,
+          "end": 58.66,
+          "confidence": 0.998
+        },
+        {
+          "text": "qu'on",
+          "start": 58.66,
+          "end": 58.9,
+          "confidence": 0.989
+        },
+        {
+          "text": "entretenait",
+          "start": 58.9,
+          "end": 59.32,
+          "confidence": 0.929
+        },
+        {
+          "text": "à",
+          "start": 59.32,
+          "end": 59.46,
+          "confidence": 0.958
+        },
+        {
+          "text": "d'autres",
+          "start": 59.46,
+          "end": 59.7,
+          "confidence": 0.997
+        },
+        {
+          "text": "objets",
+          "start": 59.7,
+          "end": 59.96,
+          "confidence": 0.991
+        },
+        {
+          "text": "techniques",
+          "start": 59.96,
+          "end": 60.46,
+          "confidence": 0.983
+        },
+        {
+          "text": "comme",
+          "start": 60.46,
+          "end": 60.88,
+          "confidence": 0.587
+        },
+        {
+          "text": "la",
+          "start": 60.88,
+          "end": 61.5,
+          "confidence": 0.987
+        },
+        {
+          "text": "voiture",
+          "start": 61.5,
+          "end": 62.06,
+          "confidence": 1.0
+        },
+        {
+          "text": "ou",
+          "start": 62.06,
+          "end": 62.36,
+          "confidence": 0.945
+        },
+        {
+          "text": "le",
+          "start": 62.36,
+          "end": 62.68,
+          "confidence": 0.998
+        },
+        {
+          "text": "téléphone?",
+          "start": 62.68,
+          "end": 63.12,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 4884,
+      "start": 63.36,
+      "end": 66.66,
+      "text": " Il n'y a pas d'équivalent en fait.",
+      "tokens": [
+        4416,
+        297,
+        6,
+        88,
+        257,
+        1736,
+        274,
+        6,
+        20183,
+        3576,
+        317,
+        465,
+        3887,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10746372298689078,
+      "compression_ratio": 1.662379421221865,
+      "no_speech_prob": 1.3105129255563952e-05,
+      "confidence": 0.936,
+      "words": [
+        {
+          "text": "Il",
+          "start": 63.36,
+          "end": 65.42,
+          "confidence": 0.779
+        },
+        {
+          "text": "n'y",
+          "start": 65.42,
+          "end": 65.48,
+          "confidence": 0.978
+        },
+        {
+          "text": "a",
+          "start": 65.48,
+          "end": 65.54,
+          "confidence": 0.992
+        },
+        {
+          "text": "pas",
+          "start": 65.54,
+          "end": 65.66,
+          "confidence": 0.999
+        },
+        {
+          "text": "d'équivalent",
+          "start": 65.66,
+          "end": 66.22,
+          "confidence": 0.995
+        },
+        {
+          "text": "en",
+          "start": 66.22,
+          "end": 66.42,
+          "confidence": 0.601
+        },
+        {
+          "text": "fait.",
+          "start": 66.42,
+          "end": 66.66,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 4884,
+      "start": 66.88,
+      "end": 71.52,
+      "text": " Et donc cette espèce de nouveauté dans la relation à l'objet, c'est fascinant et terrifiant.",
+      "tokens": [
+        3790,
+        5926,
+        5550,
+        7089,
+        30236,
+        368,
+        11456,
+        1375,
+        526,
+        2680,
+        635,
+        9721,
+        1531,
+        287,
+        6,
+        996,
+        7108,
+        11,
+        269,
+        6,
+        377,
+        7184,
+        259,
+        394,
+        1030,
+        7245,
+        351,
+        5798,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10746372298689078,
+      "compression_ratio": 1.662379421221865,
+      "no_speech_prob": 1.3105129255563952e-05,
+      "confidence": 0.953,
+      "words": [
+        {
+          "text": "Et",
+          "start": 66.88,
+          "end": 66.98,
+          "confidence": 0.599
+        },
+        {
+          "text": "donc",
+          "start": 66.98,
+          "end": 67.08,
+          "confidence": 0.901
+        },
+        {
+          "text": "cette",
+          "start": 67.08,
+          "end": 67.28,
+          "confidence": 0.71
+        },
+        {
+          "text": "espèce",
+          "start": 67.28,
+          "end": 67.54,
+          "confidence": 0.995
+        },
+        {
+          "text": "de",
+          "start": 67.54,
+          "end": 67.68,
+          "confidence": 0.999
+        },
+        {
+          "text": "nouveauté",
+          "start": 67.68,
+          "end": 68.48,
+          "confidence": 0.979
+        },
+        {
+          "text": "dans",
+          "start": 68.48,
+          "end": 68.66,
+          "confidence": 0.98
+        },
+        {
+          "text": "la",
+          "start": 68.66,
+          "end": 68.94,
+          "confidence": 0.995
+        },
+        {
+          "text": "relation",
+          "start": 68.94,
+          "end": 69.22,
+          "confidence": 0.998
+        },
+        {
+          "text": "à",
+          "start": 69.22,
+          "end": 69.38,
+          "confidence": 0.997
+        },
+        {
+          "text": "l'objet,",
+          "start": 69.38,
+          "end": 70.24,
+          "confidence": 0.997
+        },
+        {
+          "text": "c'est",
+          "start": 70.24,
+          "end": 70.38,
+          "confidence": 0.98
+        },
+        {
+          "text": "fascinant",
+          "start": 70.38,
+          "end": 70.64,
+          "confidence": 0.978
+        },
+        {
+          "text": "et",
+          "start": 70.64,
+          "end": 70.76,
+          "confidence": 0.964
+        },
+        {
+          "text": "terrifiant.",
+          "start": 70.76,
+          "end": 71.52,
+          "confidence": 0.977
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 4884,
+      "start": 71.62,
+      "end": 76.48,
+      "text": " Parce qu'on a l'impression, comme le disent les utilisateurs et les services, d'être dépendants de cet objet,",
+      "tokens": [
+        20429,
+        421,
+        6,
+        266,
+        257,
+        287,
+        6,
+        36107,
+        11,
+        5173,
+        476,
+        37313,
+        1512,
+        33643,
+        25929,
+        1030,
+        1512,
+        3328,
+        11,
+        274,
+        6,
+        9498,
+        45768,
+        1719,
+        368,
+        8603,
+        14964,
+        11
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10746372298689078,
+      "compression_ratio": 1.662379421221865,
+      "no_speech_prob": 1.3105129255563952e-05,
+      "confidence": 0.813,
+      "words": [
+        {
+          "text": "Parce",
+          "start": 71.62,
+          "end": 71.86,
+          "confidence": 0.512
+        },
+        {
+          "text": "qu'on",
+          "start": 71.86,
+          "end": 72.12,
+          "confidence": 0.937
+        },
+        {
+          "text": "a",
+          "start": 72.12,
+          "end": 72.44,
+          "confidence": 0.982
+        },
+        {
+          "text": "l'impression,",
+          "start": 72.44,
+          "end": 73.56,
+          "confidence": 0.998
+        },
+        {
+          "text": "comme",
+          "start": 73.56,
+          "end": 73.84,
+          "confidence": 0.964
+        },
+        {
+          "text": "le",
+          "start": 73.84,
+          "end": 74.0,
+          "confidence": 0.984
+        },
+        {
+          "text": "disent",
+          "start": 74.0,
+          "end": 74.2,
+          "confidence": 0.998
+        },
+        {
+          "text": "les",
+          "start": 74.2,
+          "end": 74.4,
+          "confidence": 0.994
+        },
+        {
+          "text": "utilisateurs",
+          "start": 74.4,
+          "end": 74.84,
+          "confidence": 0.997
+        },
+        {
+          "text": "et",
+          "start": 74.84,
+          "end": 74.96,
+          "confidence": 0.329
+        },
+        {
+          "text": "les",
+          "start": 74.96,
+          "end": 75.0,
+          "confidence": 0.773
+        },
+        {
+          "text": "services,",
+          "start": 75.0,
+          "end": 75.22,
+          "confidence": 0.214
+        },
+        {
+          "text": "d'être",
+          "start": 75.22,
+          "end": 75.42,
+          "confidence": 0.766
+        },
+        {
+          "text": "dépendants",
+          "start": 75.42,
+          "end": 75.96,
+          "confidence": 0.789
+        },
+        {
+          "text": "de",
+          "start": 75.96,
+          "end": 76.08,
+          "confidence": 0.986
+        },
+        {
+          "text": "cet",
+          "start": 76.08,
+          "end": 76.26,
+          "confidence": 0.996
+        },
+        {
+          "text": "objet,",
+          "start": 76.26,
+          "end": 76.48,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 7684,
+      "start": 76.86,
+      "end": 83.26,
+      "text": " d'induire en fait une espèce de relation, de médiation avec le monde qui rend de l'ampleur et qui amène aussi à des formes de rejet.",
+      "tokens": [
+        274,
+        6,
+        471,
+        43612,
+        465,
+        3887,
+        2251,
+        7089,
+        30236,
+        368,
+        9721,
+        11,
+        368,
+        42436,
+        399,
+        4163,
+        476,
+        10431,
+        1956,
+        6125,
+        368,
+        287,
+        6,
+        335,
+        781,
+        374,
+        1030,
+        1956,
+        669,
+        18832,
+        6212,
+        1531,
+        730,
+        1254,
+        279,
+        368,
+        319,
+        7108,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06937986261704389,
+      "compression_ratio": 1.6787003610108304,
+      "no_speech_prob": 5.948771558905719e-06,
+      "confidence": 0.917,
+      "words": [
+        {
+          "text": "d'induire",
+          "start": 76.86,
+          "end": 77.08,
+          "confidence": 0.841
+        },
+        {
+          "text": "en",
+          "start": 77.08,
+          "end": 77.24,
+          "confidence": 0.618
+        },
+        {
+          "text": "fait",
+          "start": 77.24,
+          "end": 77.34,
+          "confidence": 0.994
+        },
+        {
+          "text": "une",
+          "start": 77.34,
+          "end": 77.52,
+          "confidence": 0.983
+        },
+        {
+          "text": "espèce",
+          "start": 77.52,
+          "end": 77.88,
+          "confidence": 0.996
+        },
+        {
+          "text": "de",
+          "start": 77.88,
+          "end": 78.48,
+          "confidence": 0.997
+        },
+        {
+          "text": "relation,",
+          "start": 78.48,
+          "end": 78.6,
+          "confidence": 0.596
+        },
+        {
+          "text": "de",
+          "start": 78.6,
+          "end": 78.94,
+          "confidence": 0.987
+        },
+        {
+          "text": "médiation",
+          "start": 78.94,
+          "end": 79.52,
+          "confidence": 0.997
+        },
+        {
+          "text": "avec",
+          "start": 79.52,
+          "end": 79.74,
+          "confidence": 0.967
+        },
+        {
+          "text": "le",
+          "start": 79.74,
+          "end": 79.92,
+          "confidence": 0.998
+        },
+        {
+          "text": "monde",
+          "start": 79.92,
+          "end": 80.64,
+          "confidence": 0.992
+        },
+        {
+          "text": "qui",
+          "start": 80.64,
+          "end": 81.1,
+          "confidence": 0.696
+        },
+        {
+          "text": "rend",
+          "start": 81.1,
+          "end": 81.64,
+          "confidence": 0.91
+        },
+        {
+          "text": "de",
+          "start": 81.64,
+          "end": 81.78,
+          "confidence": 0.712
+        },
+        {
+          "text": "l'ampleur",
+          "start": 81.78,
+          "end": 82.02,
+          "confidence": 0.987
+        },
+        {
+          "text": "et",
+          "start": 82.02,
+          "end": 82.12,
+          "confidence": 0.931
+        },
+        {
+          "text": "qui",
+          "start": 82.12,
+          "end": 82.24,
+          "confidence": 0.976
+        },
+        {
+          "text": "amène",
+          "start": 82.24,
+          "end": 82.36,
+          "confidence": 0.973
+        },
+        {
+          "text": "aussi",
+          "start": 82.36,
+          "end": 82.56,
+          "confidence": 0.938
+        },
+        {
+          "text": "à",
+          "start": 82.56,
+          "end": 82.62,
+          "confidence": 0.941
+        },
+        {
+          "text": "des",
+          "start": 82.62,
+          "end": 82.72,
+          "confidence": 0.992
+        },
+        {
+          "text": "formes",
+          "start": 82.72,
+          "end": 82.9,
+          "confidence": 0.993
+        },
+        {
+          "text": "de",
+          "start": 82.9,
+          "end": 83.02,
+          "confidence": 0.998
+        },
+        {
+          "text": "rejet.",
+          "start": 83.02,
+          "end": 83.26,
+          "confidence": 0.883
+        }
+      ]
+    },
+    {
+      "id": 17,
+      "seek": 7684,
+      "start": 83.94,
+      "end": 87.8,
+      "text": " Donc, à objet inédit, rapport inédit.",
+      "tokens": [
+        7477,
+        11,
+        1531,
+        14964,
+        294,
+        7811,
+        270,
+        11,
+        18018,
+        294,
+        7811,
+        270,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06937986261704389,
+      "compression_ratio": 1.6787003610108304,
+      "no_speech_prob": 5.948771558905719e-06,
+      "confidence": 0.962,
+      "words": [
+        {
+          "text": "Donc,",
+          "start": 83.94,
+          "end": 84.94,
+          "confidence": 0.971
+        },
+        {
+          "text": "à",
+          "start": 84.94,
+          "end": 84.98,
+          "confidence": 0.88
+        },
+        {
+          "text": "objet",
+          "start": 84.98,
+          "end": 85.36,
+          "confidence": 0.828
+        },
+        {
+          "text": "inédit,",
+          "start": 85.36,
+          "end": 86.56,
+          "confidence": 0.993
+        },
+        {
+          "text": "rapport",
+          "start": 86.56,
+          "end": 87.0,
+          "confidence": 0.981
+        },
+        {
+          "text": "inédit.",
+          "start": 87.0,
+          "end": 87.8,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 18,
+      "seek": 7684,
+      "start": 88.02,
+      "end": 95.14,
+      "text": " Et ce rapport, si j'en crois Nicolas, serait caractérisé par un mélange de dépendance et de rejet.",
+      "tokens": [
+        3790,
+        1769,
+        18018,
+        11,
+        1511,
+        361,
+        6,
+        268,
+        21724,
+        38268,
+        11,
+        23139,
+        1032,
+        578,
+        4198,
+        22118,
+        971,
+        517,
+        41953,
+        933,
+        368,
+        45768,
+        719,
+        1030,
+        368,
+        319,
+        7108,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06937986261704389,
+      "compression_ratio": 1.6787003610108304,
+      "no_speech_prob": 5.948771558905719e-06,
+      "confidence": 0.972,
+      "words": [
+        {
+          "text": "Et",
+          "start": 88.02,
+          "end": 88.48,
+          "confidence": 0.992
+        },
+        {
+          "text": "ce",
+          "start": 88.48,
+          "end": 88.86,
+          "confidence": 0.975
+        },
+        {
+          "text": "rapport,",
+          "start": 88.86,
+          "end": 89.28,
+          "confidence": 0.998
+        },
+        {
+          "text": "si",
+          "start": 89.28,
+          "end": 89.56,
+          "confidence": 0.999
+        },
+        {
+          "text": "j'en",
+          "start": 89.56,
+          "end": 89.84,
+          "confidence": 0.996
+        },
+        {
+          "text": "crois",
+          "start": 89.84,
+          "end": 89.88,
+          "confidence": 0.984
+        },
+        {
+          "text": "Nicolas,",
+          "start": 89.88,
+          "end": 90.54,
+          "confidence": 0.681
+        },
+        {
+          "text": "serait",
+          "start": 90.54,
+          "end": 90.94,
+          "confidence": 0.885
+        },
+        {
+          "text": "caractérisé",
+          "start": 90.94,
+          "end": 91.8,
+          "confidence": 0.993
+        },
+        {
+          "text": "par",
+          "start": 91.8,
+          "end": 92.12,
+          "confidence": 0.997
+        },
+        {
+          "text": "un",
+          "start": 92.12,
+          "end": 92.44,
+          "confidence": 0.997
+        },
+        {
+          "text": "mélange",
+          "start": 92.44,
+          "end": 92.98,
+          "confidence": 0.999
+        },
+        {
+          "text": "de",
+          "start": 92.98,
+          "end": 93.4,
+          "confidence": 0.998
+        },
+        {
+          "text": "dépendance",
+          "start": 93.4,
+          "end": 94.24,
+          "confidence": 0.953
+        },
+        {
+          "text": "et",
+          "start": 94.24,
+          "end": 94.54,
+          "confidence": 0.998
+        },
+        {
+          "text": "de",
+          "start": 94.54,
+          "end": 94.68,
+          "confidence": 0.999
+        },
+        {
+          "text": "rejet.",
+          "start": 94.68,
+          "end": 95.14,
+          "confidence": 0.993
+        }
+      ]
+    },
+    {
+      "id": 19,
+      "seek": 7684,
+      "start": 95.78,
+      "end": 102.86,
+      "text": " Bon, en vrai, il faudrait remonter très très finement toute l'histoire des objets techniques et de leur insertion dans nos vies",
+      "tokens": [
+        7368,
+        11,
+        465,
+        17815,
+        11,
+        1930,
+        38694,
+        8645,
+        890,
+        41806,
+        5732,
+        5732,
+        962,
+        1712,
+        14953,
+        287,
+        6,
+        29093,
+        730,
+        1111,
+        25349,
+        7512,
+        1030,
+        368,
+        9580,
+        8969,
+        313,
+        2680,
+        3269,
+        371,
+        530
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06937986261704389,
+      "compression_ratio": 1.6787003610108304,
+      "no_speech_prob": 5.948771558905719e-06,
+      "confidence": 0.941,
+      "words": [
+        {
+          "text": "Bon,",
+          "start": 95.78,
+          "end": 96.38,
+          "confidence": 0.792
+        },
+        {
+          "text": "en",
+          "start": 96.38,
+          "end": 96.52,
+          "confidence": 0.998
+        },
+        {
+          "text": "vrai,",
+          "start": 96.52,
+          "end": 97.14,
+          "confidence": 0.994
+        },
+        {
+          "text": "il",
+          "start": 97.14,
+          "end": 97.18,
+          "confidence": 0.998
+        },
+        {
+          "text": "faudrait",
+          "start": 97.18,
+          "end": 97.58,
+          "confidence": 0.997
+        },
+        {
+          "text": "remonter",
+          "start": 97.58,
+          "end": 98.08,
+          "confidence": 0.997
+        },
+        {
+          "text": "très",
+          "start": 98.08,
+          "end": 98.6,
+          "confidence": 0.997
+        },
+        {
+          "text": "très",
+          "start": 98.6,
+          "end": 98.7,
+          "confidence": 0.768
+        },
+        {
+          "text": "finement",
+          "start": 98.7,
+          "end": 99.32,
+          "confidence": 0.849
+        },
+        {
+          "text": "toute",
+          "start": 99.32,
+          "end": 99.7,
+          "confidence": 0.984
+        },
+        {
+          "text": "l'histoire",
+          "start": 99.7,
+          "end": 100.06,
+          "confidence": 0.997
+        },
+        {
+          "text": "des",
+          "start": 100.06,
+          "end": 100.24,
+          "confidence": 0.998
+        },
+        {
+          "text": "objets",
+          "start": 100.24,
+          "end": 100.48,
+          "confidence": 0.999
+        },
+        {
+          "text": "techniques",
+          "start": 100.48,
+          "end": 101.02,
+          "confidence": 0.984
+        },
+        {
+          "text": "et",
+          "start": 101.02,
+          "end": 101.48,
+          "confidence": 0.527
+        },
+        {
+          "text": "de",
+          "start": 101.48,
+          "end": 101.68,
+          "confidence": 0.994
+        },
+        {
+          "text": "leur",
+          "start": 101.68,
+          "end": 101.84,
+          "confidence": 0.833
+        },
+        {
+          "text": "insertion",
+          "start": 101.84,
+          "end": 102.32,
+          "confidence": 0.994
+        },
+        {
+          "text": "dans",
+          "start": 102.32,
+          "end": 102.48,
+          "confidence": 0.99
+        },
+        {
+          "text": "nos",
+          "start": 102.48,
+          "end": 102.66,
+          "confidence": 0.998
+        },
+        {
+          "text": "vies",
+          "start": 102.66,
+          "end": 102.86,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 20,
+      "seek": 7684,
+      "start": 102.9,
+      "end": 105.74,
+      "text": " pour déterminer si ce rapport est totalement inédit.",
+      "tokens": [
+        2016,
+        2795,
+        29725,
+        260,
+        1511,
+        1769,
+        18018,
+        871,
+        45203,
+        294,
+        7811,
+        270,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06937986261704389,
+      "compression_ratio": 1.6787003610108304,
+      "no_speech_prob": 5.948771558905719e-06,
+      "confidence": 0.981,
+      "words": [
+        {
+          "text": "pour",
+          "start": 102.9,
+          "end": 103.06,
+          "confidence": 0.822
+        },
+        {
+          "text": "déterminer",
+          "start": 103.06,
+          "end": 103.66,
+          "confidence": 0.997
+        },
+        {
+          "text": "si",
+          "start": 103.66,
+          "end": 103.76,
+          "confidence": 0.992
+        },
+        {
+          "text": "ce",
+          "start": 103.76,
+          "end": 103.94,
+          "confidence": 0.997
+        },
+        {
+          "text": "rapport",
+          "start": 103.94,
+          "end": 104.26,
+          "confidence": 0.997
+        },
+        {
+          "text": "est",
+          "start": 104.26,
+          "end": 104.74,
+          "confidence": 0.998
+        },
+        {
+          "text": "totalement",
+          "start": 104.74,
+          "end": 105.3,
+          "confidence": 0.999
+        },
+        {
+          "text": "inédit.",
+          "start": 105.3,
+          "end": 105.74,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 21,
+      "seek": 10584,
+      "start": 106.1,
+      "end": 109.34,
+      "text": " Mais j'ai l'impression comme ça que Nicolas ne se trompe pas vraiment.",
+      "tokens": [
+        6313,
+        361,
+        6,
+        1301,
+        287,
+        6,
+        36107,
+        5173,
+        2788,
+        631,
+        38268,
+        408,
+        369,
+        504,
+        298,
+        494,
+        1736,
+        8322,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07386374800172571,
+      "compression_ratio": 1.685512367491166,
+      "no_speech_prob": 5.46344235772267e-05,
+      "confidence": 0.94,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 106.1,
+          "end": 106.36,
+          "confidence": 0.947
+        },
+        {
+          "text": "j'ai",
+          "start": 106.36,
+          "end": 106.92,
+          "confidence": 0.941
+        },
+        {
+          "text": "l'impression",
+          "start": 106.92,
+          "end": 107.36,
+          "confidence": 0.996
+        },
+        {
+          "text": "comme",
+          "start": 107.36,
+          "end": 107.56,
+          "confidence": 0.641
+        },
+        {
+          "text": "ça",
+          "start": 107.56,
+          "end": 107.82,
+          "confidence": 0.978
+        },
+        {
+          "text": "que",
+          "start": 107.82,
+          "end": 107.96,
+          "confidence": 0.976
+        },
+        {
+          "text": "Nicolas",
+          "start": 107.96,
+          "end": 108.46,
+          "confidence": 0.985
+        },
+        {
+          "text": "ne",
+          "start": 108.46,
+          "end": 108.66,
+          "confidence": 0.726
+        },
+        {
+          "text": "se",
+          "start": 108.66,
+          "end": 108.7,
+          "confidence": 0.991
+        },
+        {
+          "text": "trompe",
+          "start": 108.7,
+          "end": 108.88,
+          "confidence": 0.995
+        },
+        {
+          "text": "pas",
+          "start": 108.88,
+          "end": 109.08,
+          "confidence": 0.999
+        },
+        {
+          "text": "vraiment.",
+          "start": 109.08,
+          "end": 109.34,
+          "confidence": 0.991
+        }
+      ]
+    },
+    {
+      "id": 22,
+      "seek": 10584,
+      "start": 109.88,
+      "end": 114.98,
+      "text": " Pour autant que je sache, il y a eu plein de discussions autour de la voiture ou même du téléphone.",
+      "tokens": [
+        8732,
+        34081,
+        631,
+        1506,
+        262,
+        6000,
+        11,
+        1930,
+        288,
+        257,
+        2228,
+        21088,
+        368,
+        11088,
+        30249,
+        368,
+        635,
+        38859,
+        2820,
+        5698,
+        1581,
+        47159,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07386374800172571,
+      "compression_ratio": 1.685512367491166,
+      "no_speech_prob": 5.46344235772267e-05,
+      "confidence": 0.969,
+      "words": [
+        {
+          "text": "Pour",
+          "start": 109.88,
+          "end": 110.08,
+          "confidence": 0.997
+        },
+        {
+          "text": "autant",
+          "start": 110.08,
+          "end": 110.24,
+          "confidence": 1.0
+        },
+        {
+          "text": "que",
+          "start": 110.24,
+          "end": 110.42,
+          "confidence": 0.988
+        },
+        {
+          "text": "je",
+          "start": 110.42,
+          "end": 110.52,
+          "confidence": 0.998
+        },
+        {
+          "text": "sache,",
+          "start": 110.52,
+          "end": 111.14,
+          "confidence": 0.963
+        },
+        {
+          "text": "il",
+          "start": 111.14,
+          "end": 111.18,
+          "confidence": 0.997
+        },
+        {
+          "text": "y",
+          "start": 111.18,
+          "end": 111.32,
+          "confidence": 0.992
+        },
+        {
+          "text": "a",
+          "start": 111.32,
+          "end": 111.36,
+          "confidence": 0.993
+        },
+        {
+          "text": "eu",
+          "start": 111.36,
+          "end": 111.68,
+          "confidence": 0.998
+        },
+        {
+          "text": "plein",
+          "start": 111.68,
+          "end": 111.88,
+          "confidence": 0.974
+        },
+        {
+          "text": "de",
+          "start": 111.88,
+          "end": 112.06,
+          "confidence": 0.997
+        },
+        {
+          "text": "discussions",
+          "start": 112.06,
+          "end": 112.6,
+          "confidence": 0.799
+        },
+        {
+          "text": "autour",
+          "start": 112.6,
+          "end": 112.94,
+          "confidence": 0.995
+        },
+        {
+          "text": "de",
+          "start": 112.94,
+          "end": 113.46,
+          "confidence": 0.997
+        },
+        {
+          "text": "la",
+          "start": 113.46,
+          "end": 113.52,
+          "confidence": 0.998
+        },
+        {
+          "text": "voiture",
+          "start": 113.52,
+          "end": 113.86,
+          "confidence": 1.0
+        },
+        {
+          "text": "ou",
+          "start": 113.86,
+          "end": 114.06,
+          "confidence": 0.765
+        },
+        {
+          "text": "même",
+          "start": 114.06,
+          "end": 114.44,
+          "confidence": 0.996
+        },
+        {
+          "text": "du",
+          "start": 114.44,
+          "end": 114.6,
+          "confidence": 0.995
+        },
+        {
+          "text": "téléphone.",
+          "start": 114.6,
+          "end": 114.98,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 23,
+      "seek": 10584,
+      "start": 115.34,
+      "end": 119.84,
+      "text": " Mais la dépendance n'était pas du même ordre. Donc le rejet non plus n'était pas du même ordre.",
+      "tokens": [
+        6313,
+        635,
+        45768,
+        719,
+        297,
+        6,
+        9743,
+        1736,
+        1581,
+        5698,
+        4792,
+        265,
+        13,
+        7477,
+        476,
+        319,
+        7108,
+        2107,
+        1804,
+        297,
+        6,
+        9743,
+        1736,
+        1581,
+        5698,
+        4792,
+        265,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07386374800172571,
+      "compression_ratio": 1.685512367491166,
+      "no_speech_prob": 5.46344235772267e-05,
+      "confidence": 0.972,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 115.34,
+          "end": 115.72,
+          "confidence": 0.994
+        },
+        {
+          "text": "la",
+          "start": 115.72,
+          "end": 116.02,
+          "confidence": 0.937
+        },
+        {
+          "text": "dépendance",
+          "start": 116.02,
+          "end": 116.4,
+          "confidence": 0.997
+        },
+        {
+          "text": "n'était",
+          "start": 116.4,
+          "end": 116.62,
+          "confidence": 0.994
+        },
+        {
+          "text": "pas",
+          "start": 116.62,
+          "end": 117.0,
+          "confidence": 0.998
+        },
+        {
+          "text": "du",
+          "start": 117.0,
+          "end": 117.16,
+          "confidence": 0.995
+        },
+        {
+          "text": "même",
+          "start": 117.16,
+          "end": 117.46,
+          "confidence": 0.999
+        },
+        {
+          "text": "ordre.",
+          "start": 117.46,
+          "end": 117.78,
+          "confidence": 0.999
+        },
+        {
+          "text": "Donc",
+          "start": 117.78,
+          "end": 117.98,
+          "confidence": 0.804
+        },
+        {
+          "text": "le",
+          "start": 117.98,
+          "end": 118.34,
+          "confidence": 0.715
+        },
+        {
+          "text": "rejet",
+          "start": 118.34,
+          "end": 118.62,
+          "confidence": 0.999
+        },
+        {
+          "text": "non",
+          "start": 118.62,
+          "end": 118.78,
+          "confidence": 0.975
+        },
+        {
+          "text": "plus",
+          "start": 118.78,
+          "end": 118.94,
+          "confidence": 0.996
+        },
+        {
+          "text": "n'était",
+          "start": 118.94,
+          "end": 119.12,
+          "confidence": 0.987
+        },
+        {
+          "text": "pas",
+          "start": 119.12,
+          "end": 119.3,
+          "confidence": 0.998
+        },
+        {
+          "text": "du",
+          "start": 119.3,
+          "end": 119.38,
+          "confidence": 0.995
+        },
+        {
+          "text": "même",
+          "start": 119.38,
+          "end": 119.56,
+          "confidence": 0.999
+        },
+        {
+          "text": "ordre.",
+          "start": 119.56,
+          "end": 119.84,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 24,
+      "seek": 10584,
+      "start": 119.98,
+      "end": 123.02,
+      "text": " On peut adorer sa bagnole, en avoir besoin pour plein de choses.",
+      "tokens": [
+        1282,
+        5977,
+        614,
+        17618,
+        601,
+        3411,
+        1771,
+        306,
+        11,
+        465,
+        10853,
+        19207,
+        2016,
+        21088,
+        368,
+        14488,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07386374800172571,
+      "compression_ratio": 1.685512367491166,
+      "no_speech_prob": 5.46344235772267e-05,
+      "confidence": 0.991,
+      "words": [
+        {
+          "text": "On",
+          "start": 119.98,
+          "end": 120.18,
+          "confidence": 0.996
+        },
+        {
+          "text": "peut",
+          "start": 120.18,
+          "end": 120.38,
+          "confidence": 0.997
+        },
+        {
+          "text": "adorer",
+          "start": 120.38,
+          "end": 120.66,
+          "confidence": 0.99
+        },
+        {
+          "text": "sa",
+          "start": 120.66,
+          "end": 120.88,
+          "confidence": 0.985
+        },
+        {
+          "text": "bagnole,",
+          "start": 120.88,
+          "end": 121.46,
+          "confidence": 0.984
+        },
+        {
+          "text": "en",
+          "start": 121.46,
+          "end": 121.56,
+          "confidence": 0.989
+        },
+        {
+          "text": "avoir",
+          "start": 121.56,
+          "end": 121.74,
+          "confidence": 0.998
+        },
+        {
+          "text": "besoin",
+          "start": 121.74,
+          "end": 122.1,
+          "confidence": 0.999
+        },
+        {
+          "text": "pour",
+          "start": 122.1,
+          "end": 122.34,
+          "confidence": 0.987
+        },
+        {
+          "text": "plein",
+          "start": 122.34,
+          "end": 122.68,
+          "confidence": 0.989
+        },
+        {
+          "text": "de",
+          "start": 122.68,
+          "end": 122.8,
+          "confidence": 0.998
+        },
+        {
+          "text": "choses.",
+          "start": 122.8,
+          "end": 123.02,
+          "confidence": 0.989
+        }
+      ]
+    },
+    {
+      "id": 25,
+      "seek": 10584,
+      "start": 123.28,
+      "end": 126.36,
+      "text": " Et bien, le soir, quand on va se coucher, on la laisse.",
+      "tokens": [
+        3790,
+        3610,
+        11,
+        476,
+        27105,
+        11,
+        6932,
+        322,
+        2773,
+        369,
+        1384,
+        6759,
+        11,
+        322,
+        635,
+        30969,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07386374800172571,
+      "compression_ratio": 1.685512367491166,
+      "no_speech_prob": 5.46344235772267e-05,
+      "confidence": 0.895,
+      "words": [
+        {
+          "text": "Et",
+          "start": 123.28,
+          "end": 123.46,
+          "confidence": 0.667
+        },
+        {
+          "text": "bien,",
+          "start": 123.46,
+          "end": 123.86,
+          "confidence": 0.469
+        },
+        {
+          "text": "le",
+          "start": 123.86,
+          "end": 123.98,
+          "confidence": 0.996
+        },
+        {
+          "text": "soir,",
+          "start": 123.98,
+          "end": 124.68,
+          "confidence": 0.999
+        },
+        {
+          "text": "quand",
+          "start": 124.68,
+          "end": 124.9,
+          "confidence": 0.997
+        },
+        {
+          "text": "on",
+          "start": 124.9,
+          "end": 125.02,
+          "confidence": 0.998
+        },
+        {
+          "text": "va",
+          "start": 125.02,
+          "end": 125.14,
+          "confidence": 0.996
+        },
+        {
+          "text": "se",
+          "start": 125.14,
+          "end": 125.38,
+          "confidence": 0.988
+        },
+        {
+          "text": "coucher,",
+          "start": 125.38,
+          "end": 125.8,
+          "confidence": 0.987
+        },
+        {
+          "text": "on",
+          "start": 125.8,
+          "end": 126.02,
+          "confidence": 0.995
+        },
+        {
+          "text": "la",
+          "start": 126.02,
+          "end": 126.22,
+          "confidence": 0.802
+        },
+        {
+          "text": "laisse.",
+          "start": 126.22,
+          "end": 126.36,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 26,
+      "seek": 10584,
+      "start": 126.98,
+      "end": 130.48,
+      "text": " On ne l'a pas dans la main quand on est au lit, on ne l'emmène pas au chiottes.",
+      "tokens": [
+        1282,
+        408,
+        287,
+        6,
+        64,
+        1736,
+        2680,
+        635,
+        2135,
+        6932,
+        322,
+        871,
+        1609,
+        7997,
+        11,
+        322,
+        408,
+        287,
+        6,
+        443,
+        76,
+        18832,
+        1736,
+        1609,
+        13228,
+        1521,
+        279,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07386374800172571,
+      "compression_ratio": 1.685512367491166,
+      "no_speech_prob": 5.46344235772267e-05,
+      "confidence": 0.914,
+      "words": [
+        {
+          "text": "On",
+          "start": 126.98,
+          "end": 127.32,
+          "confidence": 0.954
+        },
+        {
+          "text": "ne",
+          "start": 127.32,
+          "end": 127.36,
+          "confidence": 0.803
+        },
+        {
+          "text": "l'a",
+          "start": 127.36,
+          "end": 127.48,
+          "confidence": 0.974
+        },
+        {
+          "text": "pas",
+          "start": 127.48,
+          "end": 127.68,
+          "confidence": 0.999
+        },
+        {
+          "text": "dans",
+          "start": 127.68,
+          "end": 127.8,
+          "confidence": 0.996
+        },
+        {
+          "text": "la",
+          "start": 127.8,
+          "end": 128.06,
+          "confidence": 0.994
+        },
+        {
+          "text": "main",
+          "start": 128.06,
+          "end": 128.26,
+          "confidence": 0.999
+        },
+        {
+          "text": "quand",
+          "start": 128.26,
+          "end": 128.44,
+          "confidence": 0.935
+        },
+        {
+          "text": "on",
+          "start": 128.44,
+          "end": 128.62,
+          "confidence": 0.997
+        },
+        {
+          "text": "est",
+          "start": 128.62,
+          "end": 128.68,
+          "confidence": 0.993
+        },
+        {
+          "text": "au",
+          "start": 128.68,
+          "end": 129.04,
+          "confidence": 0.984
+        },
+        {
+          "text": "lit,",
+          "start": 129.04,
+          "end": 129.14,
+          "confidence": 0.999
+        },
+        {
+          "text": "on",
+          "start": 129.14,
+          "end": 129.26,
+          "confidence": 0.427
+        },
+        {
+          "text": "ne",
+          "start": 129.26,
+          "end": 129.3,
+          "confidence": 0.963
+        },
+        {
+          "text": "l'emmène",
+          "start": 129.3,
+          "end": 129.5,
+          "confidence": 0.992
+        },
+        {
+          "text": "pas",
+          "start": 129.5,
+          "end": 129.68,
+          "confidence": 0.997
+        },
+        {
+          "text": "au",
+          "start": 129.68,
+          "end": 129.86,
+          "confidence": 0.674
+        },
+        {
+          "text": "chiottes.",
+          "start": 129.86,
+          "end": 130.48,
+          "confidence": 0.828
+        }
+      ]
+    },
+    {
+      "id": 27,
+      "seek": 13084,
+      "start": 130.86,
+      "end": 136.9,
+      "text": " On pouvait être énervé par son môme qui occupait la ligne de téléphone pendant une heure chaque soir pour discuter avec un copain.",
+      "tokens": [
+        1282,
+        45913,
+        7418,
+        45045,
+        15797,
+        971,
+        1872,
+        275,
+        2851,
+        1398,
+        1956,
+        8073,
+        1001,
+        635,
+        34207,
+        368,
+        47159,
+        17338,
+        2251,
+        30027,
+        18920,
+        27105,
+        2016,
+        2983,
+        20314,
+        4163,
+        517,
+        2971,
+        491,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06199159333200166,
+      "compression_ratio": 1.6127167630057804,
+      "no_speech_prob": 1.6126719856401905e-05,
+      "confidence": 0.955,
+      "words": [
+        {
+          "text": "On",
+          "start": 130.86,
+          "end": 131.04,
+          "confidence": 0.983
+        },
+        {
+          "text": "pouvait",
+          "start": 131.04,
+          "end": 131.28,
+          "confidence": 0.989
+        },
+        {
+          "text": "être",
+          "start": 131.28,
+          "end": 131.48,
+          "confidence": 0.996
+        },
+        {
+          "text": "énervé",
+          "start": 131.48,
+          "end": 132.22,
+          "confidence": 0.906
+        },
+        {
+          "text": "par",
+          "start": 132.22,
+          "end": 132.44,
+          "confidence": 0.991
+        },
+        {
+          "text": "son",
+          "start": 132.44,
+          "end": 132.7,
+          "confidence": 0.998
+        },
+        {
+          "text": "môme",
+          "start": 132.7,
+          "end": 133.1,
+          "confidence": 0.832
+        },
+        {
+          "text": "qui",
+          "start": 133.1,
+          "end": 133.34,
+          "confidence": 0.919
+        },
+        {
+          "text": "occupait",
+          "start": 133.34,
+          "end": 133.76,
+          "confidence": 0.991
+        },
+        {
+          "text": "la",
+          "start": 133.76,
+          "end": 133.8,
+          "confidence": 0.992
+        },
+        {
+          "text": "ligne",
+          "start": 133.8,
+          "end": 134.08,
+          "confidence": 0.999
+        },
+        {
+          "text": "de",
+          "start": 134.08,
+          "end": 134.14,
+          "confidence": 0.997
+        },
+        {
+          "text": "téléphone",
+          "start": 134.14,
+          "end": 134.6,
+          "confidence": 0.985
+        },
+        {
+          "text": "pendant",
+          "start": 134.6,
+          "end": 134.82,
+          "confidence": 0.981
+        },
+        {
+          "text": "une",
+          "start": 134.82,
+          "end": 135.2,
+          "confidence": 0.87
+        },
+        {
+          "text": "heure",
+          "start": 135.2,
+          "end": 135.36,
+          "confidence": 0.998
+        },
+        {
+          "text": "chaque",
+          "start": 135.36,
+          "end": 135.54,
+          "confidence": 0.991
+        },
+        {
+          "text": "soir",
+          "start": 135.54,
+          "end": 135.8,
+          "confidence": 0.996
+        },
+        {
+          "text": "pour",
+          "start": 135.8,
+          "end": 135.96,
+          "confidence": 0.79
+        },
+        {
+          "text": "discuter",
+          "start": 135.96,
+          "end": 136.28,
+          "confidence": 0.997
+        },
+        {
+          "text": "avec",
+          "start": 136.28,
+          "end": 136.48,
+          "confidence": 0.996
+        },
+        {
+          "text": "un",
+          "start": 136.48,
+          "end": 136.6,
+          "confidence": 0.999
+        },
+        {
+          "text": "copain.",
+          "start": 136.6,
+          "end": 136.9,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 28,
+      "seek": 13084,
+      "start": 137.28,
+      "end": 141.88,
+      "text": " Mais ça ne ressemblait pas à ce qu'on peut ressentir à voir ce même môme aujourd'hui,",
+      "tokens": [
+        6313,
+        2788,
+        408,
+        725,
+        15750,
+        35235,
+        1736,
+        1531,
+        1769,
+        421,
+        6,
+        266,
+        5977,
+        24689,
+        317,
+        347,
+        1531,
+        10695,
+        1769,
+        5698,
+        275,
+        2851,
+        1398,
+        14023,
+        6,
+        10556,
+        11
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06199159333200166,
+      "compression_ratio": 1.6127167630057804,
+      "no_speech_prob": 1.6126719856401905e-05,
+      "confidence": 0.959,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 137.28,
+          "end": 137.46,
+          "confidence": 0.993
+        },
+        {
+          "text": "ça",
+          "start": 137.46,
+          "end": 137.68,
+          "confidence": 0.938
+        },
+        {
+          "text": "ne",
+          "start": 137.68,
+          "end": 137.94,
+          "confidence": 0.998
+        },
+        {
+          "text": "ressemblait",
+          "start": 137.94,
+          "end": 138.4,
+          "confidence": 0.991
+        },
+        {
+          "text": "pas",
+          "start": 138.4,
+          "end": 138.76,
+          "confidence": 0.995
+        },
+        {
+          "text": "à",
+          "start": 138.76,
+          "end": 138.94,
+          "confidence": 0.988
+        },
+        {
+          "text": "ce",
+          "start": 138.94,
+          "end": 138.98,
+          "confidence": 0.998
+        },
+        {
+          "text": "qu'on",
+          "start": 138.98,
+          "end": 139.1,
+          "confidence": 0.986
+        },
+        {
+          "text": "peut",
+          "start": 139.1,
+          "end": 139.48,
+          "confidence": 0.988
+        },
+        {
+          "text": "ressentir",
+          "start": 139.48,
+          "end": 140.12,
+          "confidence": 0.997
+        },
+        {
+          "text": "à",
+          "start": 140.12,
+          "end": 140.32,
+          "confidence": 0.498
+        },
+        {
+          "text": "voir",
+          "start": 140.32,
+          "end": 140.46,
+          "confidence": 0.855
+        },
+        {
+          "text": "ce",
+          "start": 140.46,
+          "end": 140.68,
+          "confidence": 0.989
+        },
+        {
+          "text": "même",
+          "start": 140.68,
+          "end": 140.94,
+          "confidence": 0.984
+        },
+        {
+          "text": "môme",
+          "start": 140.94,
+          "end": 141.34,
+          "confidence": 0.998
+        },
+        {
+          "text": "aujourd'hui,",
+          "start": 141.34,
+          "end": 141.88,
+          "confidence": 0.988
+        }
+      ]
+    },
+    {
+      "id": 29,
+      "seek": 13084,
+      "start": 142.14,
+      "end": 146.3,
+      "text": " continuellement avec son smartphone dans la main, comme si c'était une sorte de pacemaker externe,",
+      "tokens": [
+        2354,
+        285,
+        1712,
+        4163,
+        1872,
+        13307,
+        2680,
+        635,
+        2135,
+        11,
+        5173,
+        1511,
+        269,
+        6,
+        9743,
+        2251,
+        25559,
+        368,
+        15165,
+        49523,
+        454,
+        391,
+        716,
+        11
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06199159333200166,
+      "compression_ratio": 1.6127167630057804,
+      "no_speech_prob": 1.6126719856401905e-05,
+      "confidence": 0.963,
+      "words": [
+        {
+          "text": "continuellement",
+          "start": 142.14,
+          "end": 142.94,
+          "confidence": 0.971
+        },
+        {
+          "text": "avec",
+          "start": 142.94,
+          "end": 143.18,
+          "confidence": 0.805
+        },
+        {
+          "text": "son",
+          "start": 143.18,
+          "end": 143.38,
+          "confidence": 0.995
+        },
+        {
+          "text": "smartphone",
+          "start": 143.38,
+          "end": 143.76,
+          "confidence": 0.978
+        },
+        {
+          "text": "dans",
+          "start": 143.76,
+          "end": 143.94,
+          "confidence": 0.979
+        },
+        {
+          "text": "la",
+          "start": 143.94,
+          "end": 144.0,
+          "confidence": 0.996
+        },
+        {
+          "text": "main,",
+          "start": 144.0,
+          "end": 144.36,
+          "confidence": 0.998
+        },
+        {
+          "text": "comme",
+          "start": 144.36,
+          "end": 144.52,
+          "confidence": 0.835
+        },
+        {
+          "text": "si",
+          "start": 144.52,
+          "end": 144.64,
+          "confidence": 0.975
+        },
+        {
+          "text": "c'était",
+          "start": 144.64,
+          "end": 144.82,
+          "confidence": 0.991
+        },
+        {
+          "text": "une",
+          "start": 144.82,
+          "end": 145.06,
+          "confidence": 0.989
+        },
+        {
+          "text": "sorte",
+          "start": 145.06,
+          "end": 145.22,
+          "confidence": 0.997
+        },
+        {
+          "text": "de",
+          "start": 145.22,
+          "end": 145.3,
+          "confidence": 0.982
+        },
+        {
+          "text": "pacemaker",
+          "start": 145.3,
+          "end": 145.82,
+          "confidence": 0.917
+        },
+        {
+          "text": "externe,",
+          "start": 145.82,
+          "end": 146.3,
+          "confidence": 0.992
+        }
+      ]
+    },
+    {
+      "id": 30,
+      "seek": 13084,
+      "start": 146.34,
+      "end": 148.84,
+      "text": " comme si le lâcher allait entraîner sa mort immédiate.",
+      "tokens": [
+        5173,
+        1511,
+        476,
+        48835,
+        6759,
+        439,
+        1001,
+        22284,
+        7517,
+        1193,
+        601,
+        6599,
+        3397,
+        526,
+        4504,
+        473,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06199159333200166,
+      "compression_ratio": 1.6127167630057804,
+      "no_speech_prob": 1.6126719856401905e-05,
+      "confidence": 0.989,
+      "words": [
+        {
+          "text": "comme",
+          "start": 146.34,
+          "end": 146.58,
+          "confidence": 0.996
+        },
+        {
+          "text": "si",
+          "start": 146.58,
+          "end": 146.76,
+          "confidence": 0.994
+        },
+        {
+          "text": "le",
+          "start": 146.76,
+          "end": 146.84,
+          "confidence": 0.997
+        },
+        {
+          "text": "lâcher",
+          "start": 146.84,
+          "end": 147.36,
+          "confidence": 0.969
+        },
+        {
+          "text": "allait",
+          "start": 147.36,
+          "end": 147.56,
+          "confidence": 0.993
+        },
+        {
+          "text": "entraîner",
+          "start": 147.56,
+          "end": 147.86,
+          "confidence": 0.978
+        },
+        {
+          "text": "sa",
+          "start": 147.86,
+          "end": 148.0,
+          "confidence": 0.999
+        },
+        {
+          "text": "mort",
+          "start": 148.0,
+          "end": 148.22,
+          "confidence": 0.998
+        },
+        {
+          "text": "immédiate.",
+          "start": 148.22,
+          "end": 148.84,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 31,
+      "seek": 13084,
+      "start": 149.04,
+      "end": 151.96,
+      "text": " Bon, je dis ça pour le môme, mais c'est évidemment valable pour nous aussi.",
+      "tokens": [
+        7368,
+        11,
+        1506,
+        717,
+        2788,
+        2016,
+        476,
+        275,
+        2851,
+        1398,
+        11,
+        2420,
+        269,
+        6,
+        377,
+        24724,
+        1323,
+        712,
+        2016,
+        4666,
+        6212,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06199159333200166,
+      "compression_ratio": 1.6127167630057804,
+      "no_speech_prob": 1.6126719856401905e-05,
+      "confidence": 0.974,
+      "words": [
+        {
+          "text": "Bon,",
+          "start": 149.04,
+          "end": 149.28,
+          "confidence": 0.918
+        },
+        {
+          "text": "je",
+          "start": 149.28,
+          "end": 149.32,
+          "confidence": 0.934
+        },
+        {
+          "text": "dis",
+          "start": 149.32,
+          "end": 149.46,
+          "confidence": 0.988
+        },
+        {
+          "text": "ça",
+          "start": 149.46,
+          "end": 149.64,
+          "confidence": 0.994
+        },
+        {
+          "text": "pour",
+          "start": 149.64,
+          "end": 149.74,
+          "confidence": 0.997
+        },
+        {
+          "text": "le",
+          "start": 149.74,
+          "end": 149.88,
+          "confidence": 0.995
+        },
+        {
+          "text": "môme,",
+          "start": 149.88,
+          "end": 150.32,
+          "confidence": 0.998
+        },
+        {
+          "text": "mais",
+          "start": 150.32,
+          "end": 150.52,
+          "confidence": 0.791
+        },
+        {
+          "text": "c'est",
+          "start": 150.52,
+          "end": 150.82,
+          "confidence": 0.981
+        },
+        {
+          "text": "évidemment",
+          "start": 150.82,
+          "end": 151.14,
+          "confidence": 0.98
+        },
+        {
+          "text": "valable",
+          "start": 151.14,
+          "end": 151.48,
+          "confidence": 0.998
+        },
+        {
+          "text": "pour",
+          "start": 151.48,
+          "end": 151.62,
+          "confidence": 0.997
+        },
+        {
+          "text": "nous",
+          "start": 151.62,
+          "end": 151.76,
+          "confidence": 0.999
+        },
+        {
+          "text": "aussi.",
+          "start": 151.76,
+          "end": 151.96,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 32,
+      "seek": 13084,
+      "start": 152.34,
+      "end": 158.22,
+      "text": " Donc, rapport inédit. D'accord. Mais pourquoi a-t-on l'impression qu'on n'en sortira jamais?",
+      "tokens": [
+        7477,
+        11,
+        18018,
+        294,
+        7811,
+        270,
+        13,
+        413,
+        6,
+        19947,
+        13,
+        6313,
+        19934,
+        257,
+        12,
+        83,
+        12,
+        266,
+        287,
+        6,
+        36107,
+        421,
+        6,
+        266,
+        297,
+        6,
+        268,
+        1333,
+        4271,
+        14540,
+        2506
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06199159333200166,
+      "compression_ratio": 1.6127167630057804,
+      "no_speech_prob": 1.6126719856401905e-05,
+      "confidence": 0.948,
+      "words": [
+        {
+          "text": "Donc,",
+          "start": 152.34,
+          "end": 153.46,
+          "confidence": 0.991
+        },
+        {
+          "text": "rapport",
+          "start": 153.46,
+          "end": 153.66,
+          "confidence": 0.976
+        },
+        {
+          "text": "inédit.",
+          "start": 153.66,
+          "end": 154.24,
+          "confidence": 0.996
+        },
+        {
+          "text": "D'accord.",
+          "start": 154.24,
+          "end": 155.48,
+          "confidence": 0.978
+        },
+        {
+          "text": "Mais",
+          "start": 155.48,
+          "end": 155.82,
+          "confidence": 0.557
+        },
+        {
+          "text": "pourquoi",
+          "start": 155.82,
+          "end": 156.32,
+          "confidence": 0.994
+        },
+        {
+          "text": "a-t-on",
+          "start": 156.32,
+          "end": 156.68,
+          "confidence": 0.94
+        },
+        {
+          "text": "l'impression",
+          "start": 156.68,
+          "end": 157.06,
+          "confidence": 0.999
+        },
+        {
+          "text": "qu'on",
+          "start": 157.06,
+          "end": 157.26,
+          "confidence": 0.995
+        },
+        {
+          "text": "n'en",
+          "start": 157.26,
+          "end": 157.44,
+          "confidence": 0.878
+        },
+        {
+          "text": "sortira",
+          "start": 157.44,
+          "end": 157.9,
+          "confidence": 0.989
+        },
+        {
+          "text": "jamais?",
+          "start": 157.9,
+          "end": 158.22,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 33,
+      "seek": 15884,
+      "start": 158.86,
+      "end": 165.32,
+      "text": " Est-ce qu'il faut en remettre la faute sur les gens qui ont créé cet outil merveilleux et diabolique, et diabolique parce que merveilleux?",
+      "tokens": [
+        4410,
+        12,
+        384,
+        421,
+        6,
+        388,
+        8487,
+        465,
+        890,
+        40681,
+        635,
+        2050,
+        1169,
+        1022,
+        1512,
+        10668,
+        1956,
+        6592,
+        15609,
+        526,
+        8603,
+        484,
+        388,
+        3551,
+        303,
+        3409,
+        2449,
+        1030,
+        1026,
+        14923,
+        1925,
+        11,
+        1030,
+        1026,
+        14923,
+        1925,
+        6992,
+        631,
+        3551,
+        303,
+        3409,
+        2449,
+        2506
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.079788723507443,
+      "compression_ratio": 1.6517857142857142,
+      "no_speech_prob": 5.4980162531137466e-05,
+      "confidence": 0.962,
+      "words": [
+        {
+          "text": "Est-ce",
+          "start": 158.86,
+          "end": 159.34,
+          "confidence": 0.981
+        },
+        {
+          "text": "qu'il",
+          "start": 159.34,
+          "end": 159.46,
+          "confidence": 0.997
+        },
+        {
+          "text": "faut",
+          "start": 159.46,
+          "end": 159.62,
+          "confidence": 0.999
+        },
+        {
+          "text": "en",
+          "start": 159.62,
+          "end": 159.78,
+          "confidence": 0.97
+        },
+        {
+          "text": "remettre",
+          "start": 159.78,
+          "end": 160.12,
+          "confidence": 0.999
+        },
+        {
+          "text": "la",
+          "start": 160.12,
+          "end": 160.34,
+          "confidence": 0.998
+        },
+        {
+          "text": "faute",
+          "start": 160.34,
+          "end": 160.66,
+          "confidence": 0.986
+        },
+        {
+          "text": "sur",
+          "start": 160.66,
+          "end": 160.94,
+          "confidence": 0.995
+        },
+        {
+          "text": "les",
+          "start": 160.94,
+          "end": 161.28,
+          "confidence": 0.995
+        },
+        {
+          "text": "gens",
+          "start": 161.28,
+          "end": 161.44,
+          "confidence": 1.0
+        },
+        {
+          "text": "qui",
+          "start": 161.44,
+          "end": 161.58,
+          "confidence": 0.984
+        },
+        {
+          "text": "ont",
+          "start": 161.58,
+          "end": 161.72,
+          "confidence": 0.998
+        },
+        {
+          "text": "créé",
+          "start": 161.72,
+          "end": 162.3,
+          "confidence": 0.99
+        },
+        {
+          "text": "cet",
+          "start": 162.3,
+          "end": 162.46,
+          "confidence": 0.852
+        },
+        {
+          "text": "outil",
+          "start": 162.46,
+          "end": 162.78,
+          "confidence": 0.99
+        },
+        {
+          "text": "merveilleux",
+          "start": 162.78,
+          "end": 163.34,
+          "confidence": 0.994
+        },
+        {
+          "text": "et",
+          "start": 163.34,
+          "end": 163.5,
+          "confidence": 0.954
+        },
+        {
+          "text": "diabolique,",
+          "start": 163.5,
+          "end": 163.86,
+          "confidence": 0.992
+        },
+        {
+          "text": "et",
+          "start": 163.86,
+          "end": 163.92,
+          "confidence": 0.54
+        },
+        {
+          "text": "diabolique",
+          "start": 163.92,
+          "end": 164.4,
+          "confidence": 0.951
+        },
+        {
+          "text": "parce",
+          "start": 164.4,
+          "end": 164.66,
+          "confidence": 0.703
+        },
+        {
+          "text": "que",
+          "start": 164.66,
+          "end": 164.84,
+          "confidence": 0.99
+        },
+        {
+          "text": "merveilleux?",
+          "start": 164.84,
+          "end": 165.32,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 34,
+      "seek": 15884,
+      "start": 166.34,
+      "end": 168.82,
+      "text": " Les économistes parlent de dépendance du sentier.",
+      "tokens": [
+        6965,
+        31171,
+        22368,
+        13734,
+        317,
+        368,
+        45768,
+        719,
+        1581,
+        2279,
+        811,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.079788723507443,
+      "compression_ratio": 1.6517857142857142,
+      "no_speech_prob": 5.4980162531137466e-05,
+      "confidence": 0.984,
+      "words": [
+        {
+          "text": "Les",
+          "start": 166.34,
+          "end": 167.04,
+          "confidence": 0.926
+        },
+        {
+          "text": "économistes",
+          "start": 167.04,
+          "end": 167.48,
+          "confidence": 0.998
+        },
+        {
+          "text": "parlent",
+          "start": 167.48,
+          "end": 167.68,
+          "confidence": 0.995
+        },
+        {
+          "text": "de",
+          "start": 167.68,
+          "end": 167.82,
+          "confidence": 0.995
+        },
+        {
+          "text": "dépendance",
+          "start": 167.82,
+          "end": 168.36,
+          "confidence": 0.985
+        },
+        {
+          "text": "du",
+          "start": 168.36,
+          "end": 168.5,
+          "confidence": 0.997
+        },
+        {
+          "text": "sentier.",
+          "start": 168.5,
+          "end": 168.82,
+          "confidence": 0.978
+        }
+      ]
+    },
+    {
+      "id": 35,
+      "seek": 16884,
+      "start": 168.86,
+      "end": 177.42,
+      "text": " C'est l'idée qu'on est sur un sentier qui a été établi, soit volontairement en marchant dessus, soit en définissant des bornes, en définissant une signalétique.",
+      "tokens": [
+        50364,
+        383,
+        6,
+        377,
+        287,
+        6,
+        34281,
+        421,
+        6,
+        266,
+        871,
+        1022,
+        517,
+        2279,
+        811,
+        1956,
+        257,
+        8862,
+        4823,
+        455,
+        2081,
+        11,
+        12703,
+        40005,
+        9020,
+        518,
+        465,
+        8368,
+        394,
+        30677,
+        11,
+        12703,
+        465,
+        40763,
+        29492,
+        730,
+        4232,
+        279,
+        11,
+        465,
+        40763,
+        29492,
+        2251,
+        6358,
+        42379,
+        13,
+        51414
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10415018598238628,
+      "compression_ratio": 1.3916666666666666,
+      "no_speech_prob": 3.958350498578511e-05,
+      "confidence": 0.93,
+      "words": [
+        {
+          "text": "C'est",
+          "start": 168.86,
+          "end": 169.1,
+          "confidence": 0.952
+        },
+        {
+          "text": "l'idée",
+          "start": 169.1,
+          "end": 169.34,
+          "confidence": 0.992
+        },
+        {
+          "text": "qu'on",
+          "start": 169.34,
+          "end": 169.7,
+          "confidence": 0.825
+        },
+        {
+          "text": "est",
+          "start": 169.7,
+          "end": 169.88,
+          "confidence": 0.631
+        },
+        {
+          "text": "sur",
+          "start": 169.88,
+          "end": 170.0,
+          "confidence": 0.993
+        },
+        {
+          "text": "un",
+          "start": 170.0,
+          "end": 170.54,
+          "confidence": 0.998
+        },
+        {
+          "text": "sentier",
+          "start": 170.54,
+          "end": 170.78,
+          "confidence": 0.99
+        },
+        {
+          "text": "qui",
+          "start": 170.78,
+          "end": 170.84,
+          "confidence": 0.961
+        },
+        {
+          "text": "a",
+          "start": 170.84,
+          "end": 170.94,
+          "confidence": 0.98
+        },
+        {
+          "text": "été",
+          "start": 170.94,
+          "end": 171.12,
+          "confidence": 0.996
+        },
+        {
+          "text": "établi,",
+          "start": 171.12,
+          "end": 171.9,
+          "confidence": 0.995
+        },
+        {
+          "text": "soit",
+          "start": 171.9,
+          "end": 172.12,
+          "confidence": 0.989
+        },
+        {
+          "text": "volontairement",
+          "start": 172.12,
+          "end": 172.72,
+          "confidence": 0.965
+        },
+        {
+          "text": "en",
+          "start": 172.72,
+          "end": 172.8,
+          "confidence": 0.941
+        },
+        {
+          "text": "marchant",
+          "start": 172.8,
+          "end": 173.06,
+          "confidence": 0.997
+        },
+        {
+          "text": "dessus,",
+          "start": 173.06,
+          "end": 174.24,
+          "confidence": 0.972
+        },
+        {
+          "text": "soit",
+          "start": 174.24,
+          "end": 174.92,
+          "confidence": 0.996
+        },
+        {
+          "text": "en",
+          "start": 174.92,
+          "end": 175.36,
+          "confidence": 0.991
+        },
+        {
+          "text": "définissant",
+          "start": 175.36,
+          "end": 175.5,
+          "confidence": 0.983
+        },
+        {
+          "text": "des",
+          "start": 175.5,
+          "end": 175.76,
+          "confidence": 0.984
+        },
+        {
+          "text": "bornes,",
+          "start": 175.76,
+          "end": 176.04,
+          "confidence": 0.975
+        },
+        {
+          "text": "en",
+          "start": 176.04,
+          "end": 176.08,
+          "confidence": 0.68
+        },
+        {
+          "text": "définissant",
+          "start": 176.08,
+          "end": 176.58,
+          "confidence": 0.997
+        },
+        {
+          "text": "une",
+          "start": 176.58,
+          "end": 176.82,
+          "confidence": 0.944
+        },
+        {
+          "text": "signalétique.",
+          "start": 176.82,
+          "end": 177.42,
+          "confidence": 0.642
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/medium_fr/bonjour.wav.words.json b/tests/expected/medium_fr/bonjour.wav.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..1539b7c83897fb3c4c929768b3ef7782d28c3f37
--- /dev/null
+++ b/tests/expected/medium_fr/bonjour.wav.words.json
@@ -0,0 +1,32 @@
+{
+  "text": " Bonjour !",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.14,
+      "end": 0.94,
+      "text": " Bonjour !",
+      "tokens": [
+        50364,
+        25431,
+        2298,
+        50402
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7046648502349854,
+      "compression_ratio": 0.5294117647058824,
+      "no_speech_prob": 0.08610370755195618,
+      "confidence": 0.964,
+      "words": [
+        {
+          "text": "Bonjour !",
+          "start": 0.14,
+          "end": 0.94,
+          "confidence": 0.964
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/medium_fr/bonjour_vous_allez_bien.mp3.words.json b/tests/expected/medium_fr/bonjour_vous_allez_bien.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..08b0c5b49b0b16bb75f05209f83a47dced01f458
--- /dev/null
+++ b/tests/expected/medium_fr/bonjour_vous_allez_bien.mp3.words.json
@@ -0,0 +1,134 @@
+{
+  "text": " Bonjour ! Est-ce que vous allez bien ? Bonjour ! Est-ce que vous allez bien ?",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.42,
+      "end": 3.46,
+      "text": " Bonjour ! Est-ce que vous allez bien ?",
+      "tokens": [
+        50364,
+        25431,
+        2298,
+        4410,
+        12,
+        384,
+        631,
+        2630,
+        18146,
+        3610,
+        2506,
+        50564
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3616434610806979,
+      "compression_ratio": 0.8260869565217391,
+      "no_speech_prob": 0.07169149070978165,
+      "confidence": 0.936,
+      "words": [
+        {
+          "text": "Bonjour !",
+          "start": 0.42,
+          "end": 1.92,
+          "confidence": 0.874
+        },
+        {
+          "text": "Est-ce",
+          "start": 1.92,
+          "end": 2.16,
+          "confidence": 0.885
+        },
+        {
+          "text": "que",
+          "start": 2.16,
+          "end": 2.24,
+          "confidence": 0.988
+        },
+        {
+          "text": "vous",
+          "start": 2.24,
+          "end": 2.38,
+          "confidence": 0.996
+        },
+        {
+          "text": "allez",
+          "start": 2.38,
+          "end": 2.58,
+          "confidence": 0.99
+        },
+        {
+          "text": "bien ?",
+          "start": 2.58,
+          "end": 3.46,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 3000,
+      "start": 32.94,
+      "end": 35.86,
+      "text": " Bonjour ! Est-ce que vous allez bien ?",
+      "tokens": [
+        50364,
+        25431,
+        2298,
+        4410,
+        12,
+        384,
+        631,
+        2630,
+        18146,
+        3610,
+        2506,
+        50664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.30651259422302246,
+      "compression_ratio": 0.8260869565217391,
+      "no_speech_prob": 0.40451279282569885,
+      "confidence": 0.933,
+      "words": [
+        {
+          "text": "Bonjour !",
+          "start": 32.94,
+          "end": 34.44,
+          "confidence": 0.741
+        },
+        {
+          "text": "Est-ce",
+          "start": 34.44,
+          "end": 34.7,
+          "confidence": 0.921
+        },
+        {
+          "text": "que",
+          "start": 34.7,
+          "end": 34.76,
+          "confidence": 0.996
+        },
+        {
+          "text": "vous",
+          "start": 34.76,
+          "end": 34.9,
+          "confidence": 0.998
+        },
+        {
+          "text": "allez",
+          "start": 34.9,
+          "end": 35.1,
+          "confidence": 0.997
+        },
+        {
+          "text": "bien ?",
+          "start": 35.1,
+          "end": 35.86,
+          "confidence": 0.999
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/medium_fr/empty.mp3.words.json b/tests/expected/medium_fr/empty.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..47a1595fd330caa6c2c345a710e711d889a3f382
--- /dev/null
+++ b/tests/expected/medium_fr/empty.mp3.words.json
@@ -0,0 +1,31 @@
+{
+  "text": " ...",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.08,
+      "end": 1.58,
+      "text": " ...",
+      "tokens": [
+        50364,
+        1097,
+        50518
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.8880113959312439,
+      "compression_ratio": 0.2727272727272727,
+      "no_speech_prob": 0.43768733739852905,
+      "confidence": 0.128,
+      "words": [
+        {
+          "text": "...",
+          "start": 0.08,
+          "end": 1.58,
+          "confidence": 0.128
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/medium_fr/gaenswein15.mp3.words.json b/tests/expected/medium_fr/gaenswein15.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..95a2283ba53201569be582ec5261ce28bb185973
--- /dev/null
+++ b/tests/expected/medium_fr/gaenswein15.mp3.words.json
@@ -0,0 +1,31 @@
+{
+  "text": " ...",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.0,
+      "end": 8.46,
+      "text": " ...",
+      "tokens": [
+        50364,
+        1097,
+        51122
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -1.0786787271499634,
+      "compression_ratio": 0.2727272727272727,
+      "no_speech_prob": 0.2541781961917877,
+      "confidence": 0.133,
+      "words": [
+        {
+          "text": "...",
+          "start": 0.0,
+          "end": 8.46,
+          "confidence": 0.133
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/medium_fr/gloria.mp3.words.json b/tests/expected/medium_fr/gloria.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..492ca53823a9f27db55911658859392f74a909f8
--- /dev/null
+++ b/tests/expected/medium_fr/gloria.mp3.words.json
@@ -0,0 +1,31 @@
+{
+  "text": " ...",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 20.18,
+      "end": 20.2,
+      "text": " ...",
+      "tokens": [
+        50364,
+        1097,
+        51392
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -1.4416182041168213,
+      "compression_ratio": 0.2727272727272727,
+      "no_speech_prob": 0.05016394704580307,
+      "confidence": 0.158,
+      "words": [
+        {
+          "text": "...",
+          "start": 20.18,
+          "end": 20.2,
+          "confidence": 0.158
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/medium_fr/laugh1.mp3.words.json b/tests/expected/medium_fr/laugh1.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..982601e67e3c8090e3078fea82fcd7caff43daef
--- /dev/null
+++ b/tests/expected/medium_fr/laugh1.mp3.words.json
@@ -0,0 +1,32 @@
+{
+  "text": " Rires",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.0,
+      "end": 1.7,
+      "text": " Rires",
+      "tokens": [
+        50364,
+        497,
+        3145,
+        50576
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -1.057028102874756,
+      "compression_ratio": 0.38461538461538464,
+      "no_speech_prob": 0.5899588465690613,
+      "confidence": 0.254,
+      "words": [
+        {
+          "text": "Rires",
+          "start": 0.0,
+          "end": 1.7,
+          "confidence": 0.254
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/medium_fr/laugh2.mp3.words.json b/tests/expected/medium_fr/laugh2.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..fcbde787e9d6c24115a59dccde034b48cdaa5a0c
--- /dev/null
+++ b/tests/expected/medium_fr/laugh2.mp3.words.json
@@ -0,0 +1,32 @@
+{
+  "text": " Hehehe",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.22,
+      "end": 0.64,
+      "text": " Hehehe",
+      "tokens": [
+        50364,
+        634,
+        23500,
+        50398
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -1.2401897430419921,
+      "compression_ratio": 0.5,
+      "no_speech_prob": 0.3699853718280792,
+      "confidence": 0.173,
+      "words": [
+        {
+          "text": "Hehehe",
+          "start": 0.22,
+          "end": 0.64,
+          "confidence": 0.173
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/medium_fr/punctuations.mp3.words.json b/tests/expected/medium_fr/punctuations.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..ea6d774cf345132b175fedfe5a717c4cd27cc3aa
--- /dev/null
+++ b/tests/expected/medium_fr/punctuations.mp3.words.json
@@ -0,0 +1,68 @@
+{
+  "text": " Dis-moi, est-ce que l'avion vole ?",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.38,
+      "end": 2.76,
+      "text": " Dis-moi, est-ce que l'avion vole ?",
+      "tokens": [
+        50364,
+        4208,
+        12,
+        29292,
+        11,
+        871,
+        12,
+        384,
+        631,
+        287,
+        6,
+        706,
+        313,
+        49877,
+        2506,
+        50496
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.26327380012063417,
+      "compression_ratio": 0.8095238095238095,
+      "no_speech_prob": 0.03882359713315964,
+      "confidence": 0.928,
+      "words": [
+        {
+          "text": "Dis-moi,",
+          "start": 0.38,
+          "end": 1.1,
+          "confidence": 0.809
+        },
+        {
+          "text": "est-ce",
+          "start": 1.28,
+          "end": 1.5,
+          "confidence": 0.968
+        },
+        {
+          "text": "que",
+          "start": 1.5,
+          "end": 1.66,
+          "confidence": 0.978
+        },
+        {
+          "text": "l'avion",
+          "start": 1.66,
+          "end": 2.04,
+          "confidence": 0.993
+        },
+        {
+          "text": "vole ?",
+          "start": 2.04,
+          "end": 2.76,
+          "confidence": 0.898
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/medium_fr/radio_short.mp3.words.json b/tests/expected/medium_fr/radio_short.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..44dd933b03beec4ddff2fb3dcdf5e15abf6dec1e
--- /dev/null
+++ b/tests/expected/medium_fr/radio_short.mp3.words.json
@@ -0,0 +1,1642 @@
+{
+  "text": " Le plus important au poker ce ne sont pas les cartes, c'est ce que vous en faites. Winamax, la référence du poker en ligne. Bonsoir à toutes et tous, vous êtes sur BFM TV, nous sommes en direct, c'est bien sûr BFM story avec tout ce qui fait l'actualité. Durant 60 minutes ce sont des gros plans, des analyses, des réactions que nous vous proposons. Comment Eric Verth peut-il encore soutenir la réforme des retraites alors qu'il est englué dans sa propre affaire, l'affaire Verth-Bettancourt ? Question posée par les leaders de la CFDT et la CGT. Réponse de Nicolas Sarkozy, Eric Verth portera le débat sur les retraites, on en parle dans BFM story avec le numéro de la CFDT. Et puis il y a une bataille qui a démarré, celle entre Marine Le Pen et Bruno Gognich, la bataille de la succession de Jean-Marie Le Pen à la tête du Front National. La tournée de campagne de Marine Le Pen commence aujourd'hui dans le Var, Marine Le Pen sera en direct dans BFM story. Restez avec nous Marine Le Pen dans moins de 3 minutes, à tout de suite. ...",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 3000,
+      "start": 30.88,
+      "end": 34.26,
+      "text": " Le plus important au poker ce ne sont pas les cartes, c'est ce que vous en faites.",
+      "tokens": [
+        50364,
+        1456,
+        1804,
+        1021,
+        1609,
+        36863,
+        1769,
+        408,
+        4900,
+        1736,
+        1512,
+        5467,
+        279,
+        11,
+        269,
+        6,
+        377,
+        1769,
+        631,
+        2630,
+        465,
+        29902,
+        13,
+        50664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.19321525431124964,
+      "compression_ratio": 1.5084745762711864,
+      "no_speech_prob": 0.5535648465156555,
+      "confidence": 0.92,
+      "words": [
+        {
+          "text": "Le",
+          "start": 30.88,
+          "end": 31.02,
+          "confidence": 0.534
+        },
+        {
+          "text": "plus",
+          "start": 31.02,
+          "end": 31.18,
+          "confidence": 0.99
+        },
+        {
+          "text": "important",
+          "start": 31.18,
+          "end": 31.5,
+          "confidence": 0.993
+        },
+        {
+          "text": "au",
+          "start": 31.5,
+          "end": 31.62,
+          "confidence": 0.946
+        },
+        {
+          "text": "poker",
+          "start": 31.62,
+          "end": 31.84,
+          "confidence": 0.992
+        },
+        {
+          "text": "ce",
+          "start": 31.84,
+          "end": 32.0,
+          "confidence": 0.583
+        },
+        {
+          "text": "ne",
+          "start": 32.0,
+          "end": 32.06,
+          "confidence": 0.961
+        },
+        {
+          "text": "sont",
+          "start": 32.06,
+          "end": 32.16,
+          "confidence": 0.991
+        },
+        {
+          "text": "pas",
+          "start": 32.16,
+          "end": 32.3,
+          "confidence": 0.991
+        },
+        {
+          "text": "les",
+          "start": 32.3,
+          "end": 32.46,
+          "confidence": 0.969
+        },
+        {
+          "text": "cartes,",
+          "start": 32.46,
+          "end": 33.26,
+          "confidence": 0.996
+        },
+        {
+          "text": "c'est",
+          "start": 33.48,
+          "end": 33.62,
+          "confidence": 0.95
+        },
+        {
+          "text": "ce",
+          "start": 33.62,
+          "end": 33.66,
+          "confidence": 0.99
+        },
+        {
+          "text": "que",
+          "start": 33.66,
+          "end": 33.76,
+          "confidence": 0.991
+        },
+        {
+          "text": "vous",
+          "start": 33.76,
+          "end": 33.9,
+          "confidence": 0.991
+        },
+        {
+          "text": "en",
+          "start": 33.9,
+          "end": 34.06,
+          "confidence": 0.982
+        },
+        {
+          "text": "faites.",
+          "start": 34.06,
+          "end": 34.26,
+          "confidence": 0.893
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 3000,
+      "start": 36.26,
+      "end": 38.74,
+      "text": " Winamax, la référence du poker en ligne.",
+      "tokens": [
+        50664,
+        10427,
+        2404,
+        87,
+        11,
+        635,
+        30170,
+        41635,
+        1581,
+        36863,
+        465,
+        34207,
+        13,
+        50814
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.19321525431124964,
+      "compression_ratio": 1.5084745762711864,
+      "no_speech_prob": 0.5535648465156555,
+      "confidence": 0.967,
+      "words": [
+        {
+          "text": "Winamax,",
+          "start": 36.26,
+          "end": 37.04,
+          "confidence": 0.905
+        },
+        {
+          "text": "la",
+          "start": 37.26,
+          "end": 37.36,
+          "confidence": 0.988
+        },
+        {
+          "text": "référence",
+          "start": 37.36,
+          "end": 37.78,
+          "confidence": 0.998
+        },
+        {
+          "text": "du",
+          "start": 37.78,
+          "end": 37.96,
+          "confidence": 0.992
+        },
+        {
+          "text": "poker",
+          "start": 37.96,
+          "end": 38.22,
+          "confidence": 0.998
+        },
+        {
+          "text": "en",
+          "start": 38.22,
+          "end": 38.44,
+          "confidence": 0.993
+        },
+        {
+          "text": "ligne.",
+          "start": 38.44,
+          "end": 38.74,
+          "confidence": 0.993
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 3000,
+      "start": 44.9,
+      "end": 51.38,
+      "text": " Bonsoir à toutes et tous, vous êtes sur BFM TV, nous sommes en direct, c'est bien sûr BFM story avec tout ce qui fait l'actualité.",
+      "tokens": [
+        51114,
+        7368,
+        539,
+        347,
+        1531,
+        14437,
+        1030,
+        8317,
+        11,
+        2630,
+        18935,
+        1022,
+        363,
+        37,
+        44,
+        3558,
+        11,
+        4666,
+        25232,
+        465,
+        2047,
+        11,
+        269,
+        6,
+        377,
+        3610,
+        18143,
+        363,
+        37,
+        44,
+        1657,
+        4163,
+        3486,
+        1769,
+        1956,
+        3887,
+        287,
+        6,
+        578,
+        901,
+        5066,
+        13,
+        51414
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.19321525431124964,
+      "compression_ratio": 1.5084745762711864,
+      "no_speech_prob": 0.5535648465156555,
+      "confidence": 0.907,
+      "words": [
+        {
+          "text": "Bonsoir",
+          "start": 44.9,
+          "end": 45.42,
+          "confidence": 0.955
+        },
+        {
+          "text": "à",
+          "start": 45.42,
+          "end": 45.84,
+          "confidence": 0.542
+        },
+        {
+          "text": "toutes",
+          "start": 45.84,
+          "end": 46.06,
+          "confidence": 0.916
+        },
+        {
+          "text": "et",
+          "start": 46.06,
+          "end": 46.26,
+          "confidence": 0.988
+        },
+        {
+          "text": "tous,",
+          "start": 46.26,
+          "end": 46.5,
+          "confidence": 0.981
+        },
+        {
+          "text": "vous",
+          "start": 46.6,
+          "end": 46.74,
+          "confidence": 0.97
+        },
+        {
+          "text": "êtes",
+          "start": 46.74,
+          "end": 46.88,
+          "confidence": 0.995
+        },
+        {
+          "text": "sur",
+          "start": 46.88,
+          "end": 47.1,
+          "confidence": 0.989
+        },
+        {
+          "text": "BFM",
+          "start": 47.1,
+          "end": 47.52,
+          "confidence": 0.987
+        },
+        {
+          "text": "TV,",
+          "start": 47.52,
+          "end": 47.72,
+          "confidence": 0.853
+        },
+        {
+          "text": "nous",
+          "start": 47.84,
+          "end": 47.92,
+          "confidence": 0.83
+        },
+        {
+          "text": "sommes",
+          "start": 47.92,
+          "end": 48.14,
+          "confidence": 0.988
+        },
+        {
+          "text": "en",
+          "start": 48.14,
+          "end": 48.28,
+          "confidence": 0.987
+        },
+        {
+          "text": "direct,",
+          "start": 48.28,
+          "end": 48.52,
+          "confidence": 0.998
+        },
+        {
+          "text": "c'est",
+          "start": 48.7,
+          "end": 48.76,
+          "confidence": 0.939
+        },
+        {
+          "text": "bien",
+          "start": 48.76,
+          "end": 48.98,
+          "confidence": 0.971
+        },
+        {
+          "text": "sûr",
+          "start": 48.98,
+          "end": 49.22,
+          "confidence": 0.906
+        },
+        {
+          "text": "BFM",
+          "start": 49.22,
+          "end": 49.82,
+          "confidence": 0.949
+        },
+        {
+          "text": "story",
+          "start": 49.82,
+          "end": 50.04,
+          "confidence": 0.356
+        },
+        {
+          "text": "avec",
+          "start": 50.04,
+          "end": 50.26,
+          "confidence": 0.551
+        },
+        {
+          "text": "tout",
+          "start": 50.26,
+          "end": 50.42,
+          "confidence": 0.931
+        },
+        {
+          "text": "ce",
+          "start": 50.42,
+          "end": 50.52,
+          "confidence": 0.995
+        },
+        {
+          "text": "qui",
+          "start": 50.52,
+          "end": 50.58,
+          "confidence": 0.952
+        },
+        {
+          "text": "fait",
+          "start": 50.58,
+          "end": 50.72,
+          "confidence": 0.961
+        },
+        {
+          "text": "l'actualité.",
+          "start": 50.72,
+          "end": 51.38,
+          "confidence": 0.994
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 3000,
+      "start": 51.96,
+      "end": 56.22,
+      "text": " Durant 60 minutes ce sont des gros plans, des analyses, des réactions que nous vous proposons.",
+      "tokens": [
+        51414,
+        13710,
+        394,
+        4060,
+        2077,
+        1769,
+        4900,
+        730,
+        18638,
+        5482,
+        11,
+        730,
+        37560,
+        11,
+        730,
+        3960,
+        12299,
+        631,
+        4666,
+        2630,
+        7532,
+        892,
+        13,
+        51664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.19321525431124964,
+      "compression_ratio": 1.5084745762711864,
+      "no_speech_prob": 0.5535648465156555,
+      "confidence": 0.947,
+      "words": [
+        {
+          "text": "Durant",
+          "start": 51.96,
+          "end": 52.32,
+          "confidence": 0.935
+        },
+        {
+          "text": "60",
+          "start": 52.32,
+          "end": 52.76,
+          "confidence": 0.922
+        },
+        {
+          "text": "minutes",
+          "start": 52.76,
+          "end": 53.08,
+          "confidence": 0.912
+        },
+        {
+          "text": "ce",
+          "start": 53.08,
+          "end": 53.28,
+          "confidence": 0.748
+        },
+        {
+          "text": "sont",
+          "start": 53.28,
+          "end": 53.62,
+          "confidence": 0.979
+        },
+        {
+          "text": "des",
+          "start": 53.62,
+          "end": 53.84,
+          "confidence": 0.99
+        },
+        {
+          "text": "gros",
+          "start": 53.84,
+          "end": 54.06,
+          "confidence": 0.969
+        },
+        {
+          "text": "plans,",
+          "start": 54.06,
+          "end": 54.2,
+          "confidence": 0.958
+        },
+        {
+          "text": "des",
+          "start": 54.32,
+          "end": 54.44,
+          "confidence": 0.986
+        },
+        {
+          "text": "analyses,",
+          "start": 54.44,
+          "end": 54.68,
+          "confidence": 0.914
+        },
+        {
+          "text": "des",
+          "start": 54.78,
+          "end": 54.86,
+          "confidence": 0.995
+        },
+        {
+          "text": "réactions",
+          "start": 54.86,
+          "end": 55.22,
+          "confidence": 0.996
+        },
+        {
+          "text": "que",
+          "start": 55.22,
+          "end": 55.4,
+          "confidence": 0.881
+        },
+        {
+          "text": "nous",
+          "start": 55.4,
+          "end": 55.52,
+          "confidence": 0.947
+        },
+        {
+          "text": "vous",
+          "start": 55.52,
+          "end": 55.78,
+          "confidence": 0.99
+        },
+        {
+          "text": "proposons.",
+          "start": 55.78,
+          "end": 56.22,
+          "confidence": 0.991
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 5600,
+      "start": 56.66,
+      "end": 64.23,
+      "text": " Comment Eric Verth peut-il encore soutenir la réforme des retraites alors qu'il est englué dans sa propre affaire, l'affaire Verth-Bettancourt ?",
+      "tokens": [
+        50364,
+        16328,
+        9336,
+        4281,
+        392,
+        5977,
+        12,
+        388,
+        10122,
+        29350,
+        268,
+        347,
+        635,
+        3960,
+        44562,
+        730,
+        49356,
+        3324,
+        11246,
+        421,
+        6,
+        388,
+        871,
+        1741,
+        2781,
+        526,
+        2680,
+        601,
+        35221,
+        2096,
+        9020,
+        11,
+        287,
+        6,
+        2518,
+        9020,
+        4281,
+        392,
+        12,
+        33,
+        3093,
+        4463,
+        33403,
+        2506,
+        50764
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.13355242821478075,
+      "compression_ratio": 1.573667711598746,
+      "no_speech_prob": 0.4252333343029022,
+      "confidence": 0.854,
+      "words": [
+        {
+          "text": "Comment",
+          "start": 56.66,
+          "end": 56.96,
+          "confidence": 0.944
+        },
+        {
+          "text": "Eric",
+          "start": 56.96,
+          "end": 57.2,
+          "confidence": 0.877
+        },
+        {
+          "text": "Verth",
+          "start": 57.2,
+          "end": 57.36,
+          "confidence": 0.369
+        },
+        {
+          "text": "peut-il",
+          "start": 57.36,
+          "end": 57.8,
+          "confidence": 0.947
+        },
+        {
+          "text": "encore",
+          "start": 57.8,
+          "end": 58.22,
+          "confidence": 0.954
+        },
+        {
+          "text": "soutenir",
+          "start": 58.22,
+          "end": 58.62,
+          "confidence": 0.997
+        },
+        {
+          "text": "la",
+          "start": 58.62,
+          "end": 58.76,
+          "confidence": 0.977
+        },
+        {
+          "text": "réforme",
+          "start": 58.76,
+          "end": 59.2,
+          "confidence": 0.996
+        },
+        {
+          "text": "des",
+          "start": 59.2,
+          "end": 59.42,
+          "confidence": 0.992
+        },
+        {
+          "text": "retraites",
+          "start": 59.42,
+          "end": 59.76,
+          "confidence": 0.99
+        },
+        {
+          "text": "alors",
+          "start": 59.76,
+          "end": 59.98,
+          "confidence": 0.492
+        },
+        {
+          "text": "qu'il",
+          "start": 59.98,
+          "end": 60.74,
+          "confidence": 0.959
+        },
+        {
+          "text": "est",
+          "start": 60.74,
+          "end": 60.9,
+          "confidence": 0.973
+        },
+        {
+          "text": "englué",
+          "start": 60.9,
+          "end": 61.7,
+          "confidence": 0.945
+        },
+        {
+          "text": "dans",
+          "start": 61.7,
+          "end": 61.96,
+          "confidence": 0.961
+        },
+        {
+          "text": "sa",
+          "start": 61.96,
+          "end": 62.44,
+          "confidence": 0.848
+        },
+        {
+          "text": "propre",
+          "start": 62.44,
+          "end": 62.68,
+          "confidence": 0.992
+        },
+        {
+          "text": "affaire,",
+          "start": 62.68,
+          "end": 62.94,
+          "confidence": 0.993
+        },
+        {
+          "text": "l'affaire",
+          "start": 63.02,
+          "end": 63.3,
+          "confidence": 0.909
+        },
+        {
+          "text": "Verth-Bettancourt ?",
+          "start": 63.3,
+          "end": 64.23,
+          "confidence": 0.711
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 5600,
+      "start": 64.23,
+      "end": 67.18,
+      "text": " Question posée par les leaders de la CFDT et la CGT.",
+      "tokens": [
+        50764,
+        14464,
+        1366,
+        3856,
+        971,
+        1512,
+        3523,
+        368,
+        635,
+        21792,
+        35,
+        51,
+        1030,
+        635,
+        38007,
+        51,
+        13,
+        50914
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.13355242821478075,
+      "compression_ratio": 1.573667711598746,
+      "no_speech_prob": 0.4252333343029022,
+      "confidence": 0.895,
+      "words": [
+        {
+          "text": "Question",
+          "start": 64.23,
+          "end": 64.34,
+          "confidence": 0.63
+        },
+        {
+          "text": "posée",
+          "start": 64.34,
+          "end": 64.74,
+          "confidence": 0.977
+        },
+        {
+          "text": "par",
+          "start": 64.74,
+          "end": 64.96,
+          "confidence": 0.988
+        },
+        {
+          "text": "les",
+          "start": 64.96,
+          "end": 65.12,
+          "confidence": 0.965
+        },
+        {
+          "text": "leaders",
+          "start": 65.12,
+          "end": 65.66,
+          "confidence": 0.977
+        },
+        {
+          "text": "de",
+          "start": 65.66,
+          "end": 65.92,
+          "confidence": 0.986
+        },
+        {
+          "text": "la",
+          "start": 65.92,
+          "end": 66.1,
+          "confidence": 0.967
+        },
+        {
+          "text": "CFDT",
+          "start": 66.1,
+          "end": 66.52,
+          "confidence": 0.994
+        },
+        {
+          "text": "et",
+          "start": 66.52,
+          "end": 66.6,
+          "confidence": 0.606
+        },
+        {
+          "text": "la",
+          "start": 66.6,
+          "end": 66.74,
+          "confidence": 0.609
+        },
+        {
+          "text": "CGT.",
+          "start": 66.74,
+          "end": 67.18,
+          "confidence": 0.987
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 5600,
+      "start": 67.5,
+      "end": 76.38,
+      "text": " Réponse de Nicolas Sarkozy, Eric Verth portera le débat sur les retraites, on en parle dans BFM story avec le numéro de la CFDT.",
+      "tokens": [
+        50914,
+        41587,
+        3739,
+        368,
+        38268,
+        318,
+        809,
+        78,
+        1229,
+        11,
+        9336,
+        4281,
+        392,
+        1515,
+        23833,
+        476,
+        2795,
+        11980,
+        1022,
+        1512,
+        49356,
+        3324,
+        11,
+        322,
+        465,
+        18508,
+        2680,
+        363,
+        37,
+        44,
+        1657,
+        4163,
+        476,
+        49525,
+        368,
+        635,
+        21792,
+        35,
+        51,
+        13,
+        51364
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.13355242821478075,
+      "compression_ratio": 1.573667711598746,
+      "no_speech_prob": 0.4252333343029022,
+      "confidence": 0.968,
+      "words": [
+        {
+          "text": "Réponse",
+          "start": 67.5,
+          "end": 67.96,
+          "confidence": 0.947
+        },
+        {
+          "text": "de",
+          "start": 67.96,
+          "end": 68.14,
+          "confidence": 0.962
+        },
+        {
+          "text": "Nicolas",
+          "start": 68.14,
+          "end": 68.38,
+          "confidence": 0.931
+        },
+        {
+          "text": "Sarkozy,",
+          "start": 68.38,
+          "end": 68.88,
+          "confidence": 0.987
+        },
+        {
+          "text": "Eric",
+          "start": 68.98,
+          "end": 69.24,
+          "confidence": 0.962
+        },
+        {
+          "text": "Verth",
+          "start": 69.24,
+          "end": 69.84,
+          "confidence": 0.986
+        },
+        {
+          "text": "portera",
+          "start": 69.84,
+          "end": 70.44,
+          "confidence": 0.966
+        },
+        {
+          "text": "le",
+          "start": 70.44,
+          "end": 71.06,
+          "confidence": 0.989
+        },
+        {
+          "text": "débat",
+          "start": 71.06,
+          "end": 71.46,
+          "confidence": 0.996
+        },
+        {
+          "text": "sur",
+          "start": 71.46,
+          "end": 71.7,
+          "confidence": 0.988
+        },
+        {
+          "text": "les",
+          "start": 71.7,
+          "end": 71.88,
+          "confidence": 0.997
+        },
+        {
+          "text": "retraites,",
+          "start": 71.88,
+          "end": 72.26,
+          "confidence": 0.997
+        },
+        {
+          "text": "on",
+          "start": 72.36,
+          "end": 72.5,
+          "confidence": 0.865
+        },
+        {
+          "text": "en",
+          "start": 72.5,
+          "end": 72.68,
+          "confidence": 0.951
+        },
+        {
+          "text": "parle",
+          "start": 72.68,
+          "end": 73.1,
+          "confidence": 0.996
+        },
+        {
+          "text": "dans",
+          "start": 73.1,
+          "end": 73.56,
+          "confidence": 0.981
+        },
+        {
+          "text": "BFM",
+          "start": 73.56,
+          "end": 74.46,
+          "confidence": 0.991
+        },
+        {
+          "text": "story",
+          "start": 74.46,
+          "end": 74.76,
+          "confidence": 0.761
+        },
+        {
+          "text": "avec",
+          "start": 74.76,
+          "end": 75.12,
+          "confidence": 0.845
+        },
+        {
+          "text": "le",
+          "start": 75.12,
+          "end": 75.32,
+          "confidence": 0.982
+        },
+        {
+          "text": "numéro",
+          "start": 75.32,
+          "end": 75.54,
+          "confidence": 0.997
+        },
+        {
+          "text": "de",
+          "start": 75.54,
+          "end": 75.76,
+          "confidence": 0.996
+        },
+        {
+          "text": "la",
+          "start": 75.76,
+          "end": 75.9,
+          "confidence": 0.987
+        },
+        {
+          "text": "CFDT.",
+          "start": 75.9,
+          "end": 76.38,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 5600,
+      "start": 76.8,
+      "end": 83.04,
+      "text": " Et puis il y a une bataille qui a démarré, celle entre Marine Le Pen et Bruno Gognich, la bataille de la succession de Jean-Marie Le Pen à la tête du Front National.",
+      "tokens": [
+        51364,
+        3790,
+        9093,
+        1930,
+        288,
+        257,
+        2251,
+        272,
+        3274,
+        3409,
+        1956,
+        257,
+        22761,
+        2284,
+        526,
+        11,
+        25722,
+        3962,
+        20415,
+        1456,
+        10571,
+        1030,
+        23046,
+        460,
+        2912,
+        480,
+        11,
+        635,
+        272,
+        3274,
+        3409,
+        368,
+        635,
+        36624,
+        368,
+        13854,
+        12,
+        16639,
+        414,
+        1456,
+        10571,
+        1531,
+        635,
+        24661,
+        1581,
+        17348,
+        4862,
+        13,
+        51714
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.13355242821478075,
+      "compression_ratio": 1.573667711598746,
+      "no_speech_prob": 0.4252333343029022,
+      "confidence": 0.871,
+      "words": [
+        {
+          "text": "Et",
+          "start": 76.8,
+          "end": 76.96,
+          "confidence": 0.883
+        },
+        {
+          "text": "puis",
+          "start": 76.96,
+          "end": 77.06,
+          "confidence": 0.952
+        },
+        {
+          "text": "il",
+          "start": 77.06,
+          "end": 77.18,
+          "confidence": 0.792
+        },
+        {
+          "text": "y",
+          "start": 77.18,
+          "end": 77.2,
+          "confidence": 0.995
+        },
+        {
+          "text": "a",
+          "start": 77.2,
+          "end": 77.22,
+          "confidence": 0.986
+        },
+        {
+          "text": "une",
+          "start": 77.22,
+          "end": 77.28,
+          "confidence": 0.995
+        },
+        {
+          "text": "bataille",
+          "start": 77.28,
+          "end": 77.56,
+          "confidence": 0.996
+        },
+        {
+          "text": "qui",
+          "start": 77.56,
+          "end": 77.72,
+          "confidence": 0.997
+        },
+        {
+          "text": "a",
+          "start": 77.72,
+          "end": 77.76,
+          "confidence": 0.985
+        },
+        {
+          "text": "démarré,",
+          "start": 77.76,
+          "end": 78.16,
+          "confidence": 0.988
+        },
+        {
+          "text": "celle",
+          "start": 78.24,
+          "end": 78.4,
+          "confidence": 0.997
+        },
+        {
+          "text": "entre",
+          "start": 78.4,
+          "end": 78.64,
+          "confidence": 0.975
+        },
+        {
+          "text": "Marine",
+          "start": 78.64,
+          "end": 78.94,
+          "confidence": 0.987
+        },
+        {
+          "text": "Le",
+          "start": 78.94,
+          "end": 79.12,
+          "confidence": 0.986
+        },
+        {
+          "text": "Pen",
+          "start": 79.12,
+          "end": 79.18,
+          "confidence": 0.986
+        },
+        {
+          "text": "et",
+          "start": 79.18,
+          "end": 79.34,
+          "confidence": 0.997
+        },
+        {
+          "text": "Bruno",
+          "start": 79.34,
+          "end": 79.54,
+          "confidence": 0.986
+        },
+        {
+          "text": "Gognich,",
+          "start": 79.54,
+          "end": 80.02,
+          "confidence": 0.239
+        },
+        {
+          "text": "la",
+          "start": 80.2,
+          "end": 80.32,
+          "confidence": 0.71
+        },
+        {
+          "text": "bataille",
+          "start": 80.32,
+          "end": 80.58,
+          "confidence": 0.998
+        },
+        {
+          "text": "de",
+          "start": 80.58,
+          "end": 80.72,
+          "confidence": 0.976
+        },
+        {
+          "text": "la",
+          "start": 80.72,
+          "end": 80.84,
+          "confidence": 0.987
+        },
+        {
+          "text": "succession",
+          "start": 80.84,
+          "end": 81.22,
+          "confidence": 0.982
+        },
+        {
+          "text": "de",
+          "start": 81.22,
+          "end": 81.44,
+          "confidence": 0.985
+        },
+        {
+          "text": "Jean-Marie",
+          "start": 81.44,
+          "end": 81.72,
+          "confidence": 0.95
+        },
+        {
+          "text": "Le",
+          "start": 81.72,
+          "end": 81.9,
+          "confidence": 0.996
+        },
+        {
+          "text": "Pen",
+          "start": 81.9,
+          "end": 82.0,
+          "confidence": 0.999
+        },
+        {
+          "text": "à",
+          "start": 82.0,
+          "end": 82.16,
+          "confidence": 0.977
+        },
+        {
+          "text": "la",
+          "start": 82.16,
+          "end": 82.22,
+          "confidence": 0.995
+        },
+        {
+          "text": "tête",
+          "start": 82.22,
+          "end": 82.32,
+          "confidence": 0.926
+        },
+        {
+          "text": "du",
+          "start": 82.32,
+          "end": 82.46,
+          "confidence": 0.997
+        },
+        {
+          "text": "Front",
+          "start": 82.46,
+          "end": 82.66,
+          "confidence": 0.777
+        },
+        {
+          "text": "National.",
+          "start": 82.66,
+          "end": 83.04,
+          "confidence": 0.822
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 8300,
+      "start": 83.34,
+      "end": 88.88,
+      "text": " La tournée de campagne de Marine Le Pen commence aujourd'hui dans le Var, Marine Le Pen sera en direct dans BFM story.",
+      "tokens": [
+        50364,
+        2369,
+        3512,
+        77,
+        3856,
+        368,
+        2255,
+        13887,
+        368,
+        20415,
+        1456,
+        10571,
+        18137,
+        14023,
+        6,
+        10556,
+        2680,
+        476,
+        14662,
+        11,
+        20415,
+        1456,
+        10571,
+        15021,
+        465,
+        2047,
+        2680,
+        363,
+        37,
+        44,
+        1657,
+        13,
+        50664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1127048058943315,
+      "compression_ratio": 1.3591549295774648,
+      "no_speech_prob": 0.4064846634864807,
+      "confidence": 0.954,
+      "words": [
+        {
+          "text": "La",
+          "start": 83.34,
+          "end": 83.68,
+          "confidence": 0.921
+        },
+        {
+          "text": "tournée",
+          "start": 83.68,
+          "end": 84.16,
+          "confidence": 0.994
+        },
+        {
+          "text": "de",
+          "start": 84.16,
+          "end": 84.48,
+          "confidence": 0.936
+        },
+        {
+          "text": "campagne",
+          "start": 84.48,
+          "end": 84.8,
+          "confidence": 0.981
+        },
+        {
+          "text": "de",
+          "start": 84.8,
+          "end": 84.98,
+          "confidence": 0.971
+        },
+        {
+          "text": "Marine",
+          "start": 84.98,
+          "end": 85.14,
+          "confidence": 0.997
+        },
+        {
+          "text": "Le",
+          "start": 85.14,
+          "end": 85.32,
+          "confidence": 0.997
+        },
+        {
+          "text": "Pen",
+          "start": 85.32,
+          "end": 85.44,
+          "confidence": 0.999
+        },
+        {
+          "text": "commence",
+          "start": 85.44,
+          "end": 85.8,
+          "confidence": 0.971
+        },
+        {
+          "text": "aujourd'hui",
+          "start": 85.8,
+          "end": 86.14,
+          "confidence": 0.988
+        },
+        {
+          "text": "dans",
+          "start": 86.14,
+          "end": 86.28,
+          "confidence": 0.979
+        },
+        {
+          "text": "le",
+          "start": 86.28,
+          "end": 86.46,
+          "confidence": 0.923
+        },
+        {
+          "text": "Var,",
+          "start": 86.46,
+          "end": 86.64,
+          "confidence": 0.533
+        },
+        {
+          "text": "Marine",
+          "start": 86.74,
+          "end": 86.96,
+          "confidence": 0.992
+        },
+        {
+          "text": "Le",
+          "start": 86.96,
+          "end": 87.12,
+          "confidence": 0.992
+        },
+        {
+          "text": "Pen",
+          "start": 87.12,
+          "end": 87.22,
+          "confidence": 0.999
+        },
+        {
+          "text": "sera",
+          "start": 87.22,
+          "end": 87.48,
+          "confidence": 0.989
+        },
+        {
+          "text": "en",
+          "start": 87.48,
+          "end": 87.76,
+          "confidence": 0.989
+        },
+        {
+          "text": "direct",
+          "start": 87.76,
+          "end": 88.04,
+          "confidence": 0.997
+        },
+        {
+          "text": "dans",
+          "start": 88.04,
+          "end": 88.34,
+          "confidence": 0.925
+        },
+        {
+          "text": "BFM",
+          "start": 88.34,
+          "end": 88.68,
+          "confidence": 0.996
+        },
+        {
+          "text": "story.",
+          "start": 88.68,
+          "end": 88.88,
+          "confidence": 0.831
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 8300,
+      "start": 89.02,
+      "end": 92.28,
+      "text": " Restez avec nous Marine Le Pen dans moins de 3 minutes, à tout de suite.",
+      "tokens": [
+        50664,
+        13094,
+        4371,
+        4163,
+        4666,
+        20415,
+        1456,
+        10571,
+        2680,
+        13099,
+        368,
+        805,
+        2077,
+        11,
+        1531,
+        3486,
+        368,
+        14205,
+        13,
+        50814
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1127048058943315,
+      "compression_ratio": 1.3591549295774648,
+      "no_speech_prob": 0.4064846634864807,
+      "confidence": 0.936,
+      "words": [
+        {
+          "text": "Restez",
+          "start": 89.02,
+          "end": 89.4,
+          "confidence": 0.967
+        },
+        {
+          "text": "avec",
+          "start": 89.4,
+          "end": 89.7,
+          "confidence": 0.997
+        },
+        {
+          "text": "nous",
+          "start": 89.7,
+          "end": 89.94,
+          "confidence": 0.956
+        },
+        {
+          "text": "Marine",
+          "start": 89.94,
+          "end": 90.24,
+          "confidence": 0.912
+        },
+        {
+          "text": "Le",
+          "start": 90.24,
+          "end": 90.52,
+          "confidence": 0.997
+        },
+        {
+          "text": "Pen",
+          "start": 90.52,
+          "end": 90.68,
+          "confidence": 0.999
+        },
+        {
+          "text": "dans",
+          "start": 90.68,
+          "end": 90.98,
+          "confidence": 0.843
+        },
+        {
+          "text": "moins",
+          "start": 90.98,
+          "end": 91.2,
+          "confidence": 0.992
+        },
+        {
+          "text": "de",
+          "start": 91.2,
+          "end": 91.34,
+          "confidence": 0.991
+        },
+        {
+          "text": "3",
+          "start": 91.34,
+          "end": 91.52,
+          "confidence": 0.595
+        },
+        {
+          "text": "minutes,",
+          "start": 91.52,
+          "end": 91.8,
+          "confidence": 0.985
+        },
+        {
+          "text": "à",
+          "start": 91.82,
+          "end": 91.98,
+          "confidence": 0.962
+        },
+        {
+          "text": "tout",
+          "start": 91.98,
+          "end": 92.1,
+          "confidence": 0.917
+        },
+        {
+          "text": "de",
+          "start": 92.1,
+          "end": 92.14,
+          "confidence": 0.999
+        },
+        {
+          "text": "suite.",
+          "start": 92.14,
+          "end": 92.28,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 9200,
+      "start": 92.28,
+      "end": 93.08,
+      "text": " ...",
+      "tokens": [
+        50364,
+        1097,
+        51064
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6883202791213989,
+      "compression_ratio": 0.2727272727272727,
+      "no_speech_prob": 0.8045242428779602,
+      "confidence": 0.153,
+      "words": [
+        {
+          "text": "...",
+          "start": 92.28,
+          "end": 93.08,
+          "confidence": 0.153
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/medium_fr/smartphone.mp3.words.json b/tests/expected/medium_fr/smartphone.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..a51a598ad65798c6c7f09c9ee8eac752e218e74e
--- /dev/null
+++ b/tests/expected/medium_fr/smartphone.mp3.words.json
@@ -0,0 +1,4899 @@
+{
+  "text": " C'est évident ce que dit Nicolas, mais je ne me l'étais jamais formulé comme ça. Ce qui fait la force du smartphone, c'est pas seulement l'accumulation des fonctions, mais la manière dont elles interagissent entre elles. Ce qui dit d'ailleurs sur la photo, c'est hyper convaincant. Alors évidemment, il faudrait ajouter les interfaces. L'écran tactile a été beaucoup très souvent mentionné. Mais bon, il faut dire qu'il profite aussi de 20 ans pendant lesquels les ordinateurs nous ont appris à cliquer sur des icônes. Sauf que le smartphone ajoute le toucher, ce qui rend le contact plus direct, plus sensible. Et puis évidemment, il faudrait parler aussi des applications qui permettent de contourner le côté touffu de la navigation web pour aller directement au but. Bref, tout ça, ce sont les conditions qui permettent de créer cet objet dont Nicolas dit qu'il est vraisemblablement inédit dans l'histoire de l'humanité. Mais ça, ça soulève une autre interrogation. Est-ce que le fait que cet objet soit inédit induit que notre rapport à lui est aussi un rapport inédit ? Je veux dire, est-ce que le rapport qu'on a au smartphone est comparable à celui qu'on entretenait à d'autres objets techniques comme la voiture ou le téléphone ? Il n'y a pas d'équivalent en fait. Et donc cette espèce de nouveauté dans la relation à l'objet, c'est fascinant et terrifiant. Parce qu'on a l'impression, comme le disent les utilisateurs et les services, d'être dépendant de cet objet, d'induire en fait une espèce de relation, de médiation avec le monde qui rend de l'ampleur et qui amène aussi à des formes de rejet. Donc à objet inédit, rapport inédit. Et ce rapport, si j'en crois à Nicolas, serait caractérisé par un mélange de dépendance et de rejet. Bon, en vrai, il faudrait remonter très très finement toute l'histoire des objets techniques et de leur insertion dans nos vies pour déterminer si ce rapport est totalement inédit. Mais j'ai l'impression comme ça que Nicolas ne se trompe pas vraiment. Pour autant que je sache, il y a eu plein de discussions autour de la voiture ou même du téléphone. Mais la dépendance n'était pas du même ordre. Donc le rejet non plus n'était pas du même ordre. On peut adorer sa bagnole, en avoir besoin pour plein de choses. Le soir, quand on va se coucher, on la laisse. On ne l'a pas dans la main quand on est au lit, on ne l'emmène pas au chiottes. On pouvait être énervé par son môme qui occupait la ligne de téléphone pendant une heure chaque soir pour discuter avec un copain. Mais ça ne ressemblait pas à ce qu'on peut ressentir à voir ce même môme aujourd'hui, continuellement avec son smartphone dans la main, comme si c'était une sorte de pacemaker externe, comme si le lâcher allait entraîner sa mort immédiate. Bon, je dis ça pour le môme, mais c'est évidemment valable pour nous aussi. Donc, rapport inédit, d'accord. Mais pourquoi a-t-on l'impression qu'on n'en sortira jamais ? Est-ce qu'il faut en remettre la faute sur les gens qui ont créé cet outil merveilleux et diabolique, et diabolique parce que merveilleux ? Les économistes parlent de dépendance du sentier. C'est l'idée qu'on met sur un sentier qui a été établi, soit volontairement en marchant dessus, soit en définissant des bornes, en définissant une signalétique.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.4,
+      "end": 3.66,
+      "text": " C'est évident ce que dit Nicolas, mais je ne me l'étais jamais formulé comme ça.",
+      "tokens": [
+        50364,
+        383,
+        6,
+        377,
+        20090,
+        1078,
+        1769,
+        631,
+        6176,
+        38268,
+        11,
+        2420,
+        1506,
+        408,
+        385,
+        287,
+        6,
+        22824,
+        14540,
+        49990,
+        526,
+        5173,
+        2788,
+        13,
+        50539
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2362650940749819,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.15368737280368805,
+      "confidence": 0.935,
+      "words": [
+        {
+          "text": "C'est",
+          "start": 0.4,
+          "end": 0.64,
+          "confidence": 0.961
+        },
+        {
+          "text": "évident",
+          "start": 0.64,
+          "end": 0.9,
+          "confidence": 0.984
+        },
+        {
+          "text": "ce",
+          "start": 0.9,
+          "end": 1.0,
+          "confidence": 0.663
+        },
+        {
+          "text": "que",
+          "start": 1.0,
+          "end": 1.08,
+          "confidence": 0.989
+        },
+        {
+          "text": "dit",
+          "start": 1.08,
+          "end": 1.2,
+          "confidence": 0.994
+        },
+        {
+          "text": "Nicolas,",
+          "start": 1.2,
+          "end": 1.48,
+          "confidence": 0.91
+        },
+        {
+          "text": "mais",
+          "start": 1.7,
+          "end": 2.04,
+          "confidence": 0.979
+        },
+        {
+          "text": "je",
+          "start": 2.04,
+          "end": 2.26,
+          "confidence": 0.981
+        },
+        {
+          "text": "ne",
+          "start": 2.26,
+          "end": 2.34,
+          "confidence": 0.837
+        },
+        {
+          "text": "me",
+          "start": 2.34,
+          "end": 2.36,
+          "confidence": 0.821
+        },
+        {
+          "text": "l'étais",
+          "start": 2.36,
+          "end": 2.58,
+          "confidence": 0.971
+        },
+        {
+          "text": "jamais",
+          "start": 2.58,
+          "end": 2.88,
+          "confidence": 0.989
+        },
+        {
+          "text": "formulé",
+          "start": 2.88,
+          "end": 3.26,
+          "confidence": 0.908
+        },
+        {
+          "text": "comme",
+          "start": 3.26,
+          "end": 3.44,
+          "confidence": 0.993
+        },
+        {
+          "text": "ça.",
+          "start": 3.44,
+          "end": 3.66,
+          "confidence": 0.975
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 4.16,
+      "end": 7.94,
+      "text": " Ce qui fait la force du smartphone, c'est pas seulement l'accumulation des fonctions,",
+      "tokens": [
+        50549,
+        8257,
+        1956,
+        3887,
+        635,
+        3464,
+        1581,
+        13307,
+        11,
+        269,
+        6,
+        377,
+        1736,
+        27772,
+        287,
+        6,
+        8476,
+        449,
+        2776,
+        730,
+        17290,
+        3916,
+        11,
+        50756
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2362650940749819,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.15368737280368805,
+      "confidence": 0.93,
+      "words": [
+        {
+          "text": "Ce",
+          "start": 4.16,
+          "end": 4.28,
+          "confidence": 0.952
+        },
+        {
+          "text": "qui",
+          "start": 4.28,
+          "end": 4.36,
+          "confidence": 0.958
+        },
+        {
+          "text": "fait",
+          "start": 4.36,
+          "end": 4.5,
+          "confidence": 0.567
+        },
+        {
+          "text": "la",
+          "start": 4.5,
+          "end": 4.76,
+          "confidence": 0.972
+        },
+        {
+          "text": "force",
+          "start": 4.76,
+          "end": 5.02,
+          "confidence": 0.999
+        },
+        {
+          "text": "du",
+          "start": 5.02,
+          "end": 5.22,
+          "confidence": 0.996
+        },
+        {
+          "text": "smartphone,",
+          "start": 5.22,
+          "end": 5.7,
+          "confidence": 0.912
+        },
+        {
+          "text": "c'est",
+          "start": 6.04,
+          "end": 6.16,
+          "confidence": 0.879
+        },
+        {
+          "text": "pas",
+          "start": 6.16,
+          "end": 6.26,
+          "confidence": 0.991
+        },
+        {
+          "text": "seulement",
+          "start": 6.26,
+          "end": 6.54,
+          "confidence": 0.999
+        },
+        {
+          "text": "l'accumulation",
+          "start": 6.54,
+          "end": 7.4,
+          "confidence": 0.958
+        },
+        {
+          "text": "des",
+          "start": 7.4,
+          "end": 7.58,
+          "confidence": 0.983
+        },
+        {
+          "text": "fonctions,",
+          "start": 7.58,
+          "end": 7.94,
+          "confidence": 0.987
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 8.32,
+      "end": 10.88,
+      "text": " mais la manière dont elles interagissent entre elles.",
+      "tokens": [
+        50756,
+        2420,
+        635,
+        22267,
+        9400,
+        23576,
+        728,
+        559,
+        25450,
+        3962,
+        23576,
+        13,
+        50906
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2362650940749819,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.15368737280368805,
+      "confidence": 0.977,
+      "words": [
+        {
+          "text": "mais",
+          "start": 8.32,
+          "end": 8.48,
+          "confidence": 0.992
+        },
+        {
+          "text": "la",
+          "start": 8.48,
+          "end": 8.7,
+          "confidence": 0.995
+        },
+        {
+          "text": "manière",
+          "start": 8.7,
+          "end": 8.94,
+          "confidence": 0.999
+        },
+        {
+          "text": "dont",
+          "start": 8.94,
+          "end": 9.08,
+          "confidence": 0.978
+        },
+        {
+          "text": "elles",
+          "start": 9.08,
+          "end": 9.48,
+          "confidence": 0.967
+        },
+        {
+          "text": "interagissent",
+          "start": 9.48,
+          "end": 10.38,
+          "confidence": 0.964
+        },
+        {
+          "text": "entre",
+          "start": 10.38,
+          "end": 10.7,
+          "confidence": 0.955
+        },
+        {
+          "text": "elles.",
+          "start": 10.7,
+          "end": 10.88,
+          "confidence": 0.989
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 10.96,
+      "end": 13.0,
+      "text": " Ce qui dit d'ailleurs sur la photo, c'est hyper convaincant.",
+      "tokens": [
+        50906,
+        8257,
+        1956,
+        6176,
+        274,
+        6,
+        19400,
+        1022,
+        635,
+        5052,
+        11,
+        269,
+        6,
+        377,
+        9848,
+        3754,
+        491,
+        66,
+        394,
+        13,
+        51006
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2362650940749819,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.15368737280368805,
+      "confidence": 0.906,
+      "words": [
+        {
+          "text": "Ce",
+          "start": 10.96,
+          "end": 11.16,
+          "confidence": 0.608
+        },
+        {
+          "text": "qui",
+          "start": 11.16,
+          "end": 11.26,
+          "confidence": 0.769
+        },
+        {
+          "text": "dit",
+          "start": 11.26,
+          "end": 11.38,
+          "confidence": 0.983
+        },
+        {
+          "text": "d'ailleurs",
+          "start": 11.38,
+          "end": 11.58,
+          "confidence": 0.985
+        },
+        {
+          "text": "sur",
+          "start": 11.58,
+          "end": 11.72,
+          "confidence": 0.48
+        },
+        {
+          "text": "la",
+          "start": 11.72,
+          "end": 11.82,
+          "confidence": 0.984
+        },
+        {
+          "text": "photo,",
+          "start": 11.82,
+          "end": 12.0,
+          "confidence": 0.994
+        },
+        {
+          "text": "c'est",
+          "start": 12.14,
+          "end": 12.2,
+          "confidence": 0.997
+        },
+        {
+          "text": "hyper",
+          "start": 12.2,
+          "end": 12.48,
+          "confidence": 0.993
+        },
+        {
+          "text": "convaincant.",
+          "start": 12.48,
+          "end": 13.0,
+          "confidence": 0.982
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 13.38,
+      "end": 16.04,
+      "text": " Alors évidemment, il faudrait ajouter les interfaces.",
+      "tokens": [
+        51006,
+        9946,
+        24724,
+        11,
+        1930,
+        38694,
+        8645,
+        17680,
+        23985,
+        1512,
+        28416,
+        13,
+        51166
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2362650940749819,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.15368737280368805,
+      "confidence": 0.912,
+      "words": [
+        {
+          "text": "Alors",
+          "start": 13.38,
+          "end": 13.58,
+          "confidence": 0.584
+        },
+        {
+          "text": "évidemment,",
+          "start": 13.58,
+          "end": 13.86,
+          "confidence": 0.832
+        },
+        {
+          "text": "il",
+          "start": 14.26,
+          "end": 14.42,
+          "confidence": 0.953
+        },
+        {
+          "text": "faudrait",
+          "start": 14.42,
+          "end": 14.76,
+          "confidence": 0.996
+        },
+        {
+          "text": "ajouter",
+          "start": 14.76,
+          "end": 15.2,
+          "confidence": 0.992
+        },
+        {
+          "text": "les",
+          "start": 15.2,
+          "end": 15.6,
+          "confidence": 0.985
+        },
+        {
+          "text": "interfaces.",
+          "start": 15.6,
+          "end": 16.04,
+          "confidence": 0.984
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 0,
+      "start": 16.22,
+      "end": 19.36,
+      "text": " L'écran tactile a été beaucoup très souvent mentionné.",
+      "tokens": [
+        51166,
+        441,
+        6,
+        9062,
+        4257,
+        47319,
+        257,
+        8862,
+        8796,
+        5732,
+        20847,
+        2152,
+        15055,
+        13,
+        51331
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2362650940749819,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.15368737280368805,
+      "confidence": 0.923,
+      "words": [
+        {
+          "text": "L'écran",
+          "start": 16.22,
+          "end": 16.78,
+          "confidence": 0.996
+        },
+        {
+          "text": "tactile",
+          "start": 16.78,
+          "end": 17.1,
+          "confidence": 0.986
+        },
+        {
+          "text": "a",
+          "start": 17.1,
+          "end": 17.3,
+          "confidence": 0.98
+        },
+        {
+          "text": "été",
+          "start": 17.3,
+          "end": 17.84,
+          "confidence": 0.974
+        },
+        {
+          "text": "beaucoup",
+          "start": 17.84,
+          "end": 18.28,
+          "confidence": 0.976
+        },
+        {
+          "text": "très",
+          "start": 18.28,
+          "end": 18.62,
+          "confidence": 0.447
+        },
+        {
+          "text": "souvent",
+          "start": 18.62,
+          "end": 18.9,
+          "confidence": 0.996
+        },
+        {
+          "text": "mentionné.",
+          "start": 18.9,
+          "end": 19.36,
+          "confidence": 0.978
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 0,
+      "start": 20.02,
+      "end": 25.44,
+      "text": " Mais bon, il faut dire qu'il profite aussi de 20 ans pendant lesquels les ordinateurs nous ont appris à cliquer sur des icônes.",
+      "tokens": [
+        51331,
+        6313,
+        4428,
+        11,
+        1930,
+        8487,
+        1264,
+        421,
+        6,
+        388,
+        1740,
+        642,
+        6212,
+        368,
+        945,
+        1567,
+        17338,
+        1512,
+        358,
+        1625,
+        1512,
+        4792,
+        13923,
+        2156,
+        4666,
+        6592,
+        724,
+        5714,
+        1531,
+        596,
+        23909,
+        1022,
+        730,
+        4376,
+        2851,
+        4081,
+        13,
+        51631
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2362650940749819,
+      "compression_ratio": 1.6238532110091743,
+      "no_speech_prob": 0.15368737280368805,
+      "confidence": 0.92,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 20.02,
+          "end": 20.26,
+          "confidence": 0.943
+        },
+        {
+          "text": "bon,",
+          "start": 20.26,
+          "end": 20.5,
+          "confidence": 0.666
+        },
+        {
+          "text": "il",
+          "start": 20.52,
+          "end": 20.62,
+          "confidence": 0.99
+        },
+        {
+          "text": "faut",
+          "start": 20.62,
+          "end": 20.7,
+          "confidence": 0.99
+        },
+        {
+          "text": "dire",
+          "start": 20.7,
+          "end": 20.82,
+          "confidence": 0.995
+        },
+        {
+          "text": "qu'il",
+          "start": 20.82,
+          "end": 21.04,
+          "confidence": 0.88
+        },
+        {
+          "text": "profite",
+          "start": 21.04,
+          "end": 21.3,
+          "confidence": 0.995
+        },
+        {
+          "text": "aussi",
+          "start": 21.3,
+          "end": 21.7,
+          "confidence": 0.972
+        },
+        {
+          "text": "de",
+          "start": 21.7,
+          "end": 21.94,
+          "confidence": 0.97
+        },
+        {
+          "text": "20",
+          "start": 21.94,
+          "end": 22.16,
+          "confidence": 0.812
+        },
+        {
+          "text": "ans",
+          "start": 22.16,
+          "end": 22.3,
+          "confidence": 0.997
+        },
+        {
+          "text": "pendant",
+          "start": 22.3,
+          "end": 22.54,
+          "confidence": 0.723
+        },
+        {
+          "text": "lesquels",
+          "start": 22.54,
+          "end": 22.92,
+          "confidence": 0.98
+        },
+        {
+          "text": "les",
+          "start": 22.92,
+          "end": 23.14,
+          "confidence": 0.71
+        },
+        {
+          "text": "ordinateurs",
+          "start": 23.14,
+          "end": 23.58,
+          "confidence": 0.966
+        },
+        {
+          "text": "nous",
+          "start": 23.58,
+          "end": 23.74,
+          "confidence": 0.602
+        },
+        {
+          "text": "ont",
+          "start": 23.74,
+          "end": 23.88,
+          "confidence": 0.974
+        },
+        {
+          "text": "appris",
+          "start": 23.88,
+          "end": 24.12,
+          "confidence": 0.991
+        },
+        {
+          "text": "à",
+          "start": 24.12,
+          "end": 24.26,
+          "confidence": 0.828
+        },
+        {
+          "text": "cliquer",
+          "start": 24.26,
+          "end": 24.54,
+          "confidence": 0.989
+        },
+        {
+          "text": "sur",
+          "start": 24.54,
+          "end": 24.72,
+          "confidence": 0.984
+        },
+        {
+          "text": "des",
+          "start": 24.72,
+          "end": 24.92,
+          "confidence": 0.971
+        },
+        {
+          "text": "icônes.",
+          "start": 24.92,
+          "end": 25.44,
+          "confidence": 0.992
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 2534,
+      "start": 25.54,
+      "end": 30.64,
+      "text": " Sauf que le smartphone ajoute le toucher, ce qui rend le contact plus direct, plus sensible.",
+      "tokens": [
+        50364,
+        318,
+        9507,
+        631,
+        476,
+        13307,
+        17680,
+        14040,
+        476,
+        2557,
+        260,
+        11,
+        1769,
+        1956,
+        6125,
+        476,
+        3385,
+        1804,
+        2047,
+        11,
+        1804,
+        25380,
+        13,
+        50639
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10785348191220537,
+      "compression_ratio": 1.6254416961130742,
+      "no_speech_prob": 0.18929888308048248,
+      "confidence": 0.968,
+      "words": [
+        {
+          "text": "Sauf",
+          "start": 25.54,
+          "end": 25.82,
+          "confidence": 0.974
+        },
+        {
+          "text": "que",
+          "start": 25.82,
+          "end": 26.3,
+          "confidence": 0.996
+        },
+        {
+          "text": "le",
+          "start": 26.3,
+          "end": 26.66,
+          "confidence": 0.671
+        },
+        {
+          "text": "smartphone",
+          "start": 26.66,
+          "end": 27.08,
+          "confidence": 0.995
+        },
+        {
+          "text": "ajoute",
+          "start": 27.08,
+          "end": 27.48,
+          "confidence": 0.99
+        },
+        {
+          "text": "le",
+          "start": 27.48,
+          "end": 27.66,
+          "confidence": 0.989
+        },
+        {
+          "text": "toucher,",
+          "start": 27.66,
+          "end": 28.06,
+          "confidence": 0.987
+        },
+        {
+          "text": "ce",
+          "start": 28.14,
+          "end": 28.16,
+          "confidence": 0.952
+        },
+        {
+          "text": "qui",
+          "start": 28.16,
+          "end": 28.3,
+          "confidence": 1.0
+        },
+        {
+          "text": "rend",
+          "start": 28.3,
+          "end": 28.54,
+          "confidence": 0.994
+        },
+        {
+          "text": "le",
+          "start": 28.54,
+          "end": 28.8,
+          "confidence": 0.992
+        },
+        {
+          "text": "contact",
+          "start": 28.8,
+          "end": 29.16,
+          "confidence": 0.999
+        },
+        {
+          "text": "plus",
+          "start": 29.16,
+          "end": 29.58,
+          "confidence": 0.983
+        },
+        {
+          "text": "direct,",
+          "start": 29.58,
+          "end": 30.0,
+          "confidence": 0.991
+        },
+        {
+          "text": "plus",
+          "start": 30.1,
+          "end": 30.24,
+          "confidence": 0.99
+        },
+        {
+          "text": "sensible.",
+          "start": 30.24,
+          "end": 30.64,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 2534,
+      "start": 31.04,
+      "end": 37.82,
+      "text": " Et puis évidemment, il faudrait parler aussi des applications qui permettent de contourner le côté touffu de la navigation web pour aller directement au but.",
+      "tokens": [
+        50639,
+        3790,
+        9093,
+        24724,
+        11,
+        1930,
+        38694,
+        8645,
+        16421,
+        6212,
+        730,
+        5821,
+        1956,
+        21540,
+        317,
+        368,
+        21234,
+        1193,
+        476,
+        18437,
+        10095,
+        602,
+        84,
+        368,
+        635,
+        17346,
+        3670,
+        2016,
+        8722,
+        37297,
+        1609,
+        457,
+        13,
+        50989
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10785348191220537,
+      "compression_ratio": 1.6254416961130742,
+      "no_speech_prob": 0.18929888308048248,
+      "confidence": 0.893,
+      "words": [
+        {
+          "text": "Et",
+          "start": 31.04,
+          "end": 31.24,
+          "confidence": 0.964
+        },
+        {
+          "text": "puis",
+          "start": 31.24,
+          "end": 31.34,
+          "confidence": 0.967
+        },
+        {
+          "text": "évidemment,",
+          "start": 31.34,
+          "end": 31.62,
+          "confidence": 0.87
+        },
+        {
+          "text": "il",
+          "start": 31.66,
+          "end": 31.72,
+          "confidence": 0.99
+        },
+        {
+          "text": "faudrait",
+          "start": 31.72,
+          "end": 31.94,
+          "confidence": 0.996
+        },
+        {
+          "text": "parler",
+          "start": 31.94,
+          "end": 32.16,
+          "confidence": 0.864
+        },
+        {
+          "text": "aussi",
+          "start": 32.16,
+          "end": 32.34,
+          "confidence": 0.971
+        },
+        {
+          "text": "des",
+          "start": 32.34,
+          "end": 32.48,
+          "confidence": 0.993
+        },
+        {
+          "text": "applications",
+          "start": 32.48,
+          "end": 32.92,
+          "confidence": 0.993
+        },
+        {
+          "text": "qui",
+          "start": 32.92,
+          "end": 33.22,
+          "confidence": 0.564
+        },
+        {
+          "text": "permettent",
+          "start": 33.22,
+          "end": 33.76,
+          "confidence": 0.99
+        },
+        {
+          "text": "de",
+          "start": 33.76,
+          "end": 33.98,
+          "confidence": 0.871
+        },
+        {
+          "text": "contourner",
+          "start": 33.98,
+          "end": 34.42,
+          "confidence": 0.953
+        },
+        {
+          "text": "le",
+          "start": 34.42,
+          "end": 34.54,
+          "confidence": 0.75
+        },
+        {
+          "text": "côté",
+          "start": 34.54,
+          "end": 34.78,
+          "confidence": 0.985
+        },
+        {
+          "text": "touffu",
+          "start": 34.78,
+          "end": 35.32,
+          "confidence": 0.726
+        },
+        {
+          "text": "de",
+          "start": 35.32,
+          "end": 35.7,
+          "confidence": 0.882
+        },
+        {
+          "text": "la",
+          "start": 35.7,
+          "end": 35.82,
+          "confidence": 0.991
+        },
+        {
+          "text": "navigation",
+          "start": 35.82,
+          "end": 36.3,
+          "confidence": 0.992
+        },
+        {
+          "text": "web",
+          "start": 36.3,
+          "end": 36.58,
+          "confidence": 0.847
+        },
+        {
+          "text": "pour",
+          "start": 36.58,
+          "end": 36.76,
+          "confidence": 0.59
+        },
+        {
+          "text": "aller",
+          "start": 36.76,
+          "end": 37.16,
+          "confidence": 0.981
+        },
+        {
+          "text": "directement",
+          "start": 37.16,
+          "end": 37.54,
+          "confidence": 0.997
+        },
+        {
+          "text": "au",
+          "start": 37.54,
+          "end": 37.7,
+          "confidence": 0.969
+        },
+        {
+          "text": "but.",
+          "start": 37.7,
+          "end": 37.82,
+          "confidence": 0.995
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 2534,
+      "start": 37.9,
+      "end": 46.6,
+      "text": " Bref, tout ça, ce sont les conditions qui permettent de créer cet objet dont Nicolas dit qu'il est vraisemblablement inédit dans l'histoire de l'humanité.",
+      "tokens": [
+        50989,
+        49957,
+        11,
+        3486,
+        2788,
+        11,
+        1769,
+        4900,
+        1512,
+        4487,
+        1956,
+        21540,
+        317,
+        368,
+        32062,
+        8603,
+        14964,
+        9400,
+        38268,
+        6176,
+        421,
+        6,
+        388,
+        871,
+        6070,
+        271,
+        443,
+        5199,
+        712,
+        518,
+        294,
+        7811,
+        270,
+        2680,
+        287,
+        6,
+        29093,
+        368,
+        287,
+        6,
+        18796,
+        5066,
+        13,
+        51439
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10785348191220537,
+      "compression_ratio": 1.6254416961130742,
+      "no_speech_prob": 0.18929888308048248,
+      "confidence": 0.973,
+      "words": [
+        {
+          "text": "Bref,",
+          "start": 37.9,
+          "end": 38.24,
+          "confidence": 0.984
+        },
+        {
+          "text": "tout",
+          "start": 38.88,
+          "end": 39.02,
+          "confidence": 0.701
+        },
+        {
+          "text": "ça,",
+          "start": 39.02,
+          "end": 39.4,
+          "confidence": 0.995
+        },
+        {
+          "text": "ce",
+          "start": 39.4,
+          "end": 39.72,
+          "confidence": 0.989
+        },
+        {
+          "text": "sont",
+          "start": 39.72,
+          "end": 39.92,
+          "confidence": 0.999
+        },
+        {
+          "text": "les",
+          "start": 39.92,
+          "end": 40.22,
+          "confidence": 0.992
+        },
+        {
+          "text": "conditions",
+          "start": 40.22,
+          "end": 40.7,
+          "confidence": 0.995
+        },
+        {
+          "text": "qui",
+          "start": 40.7,
+          "end": 41.02,
+          "confidence": 0.997
+        },
+        {
+          "text": "permettent",
+          "start": 41.02,
+          "end": 41.44,
+          "confidence": 0.996
+        },
+        {
+          "text": "de",
+          "start": 41.44,
+          "end": 41.74,
+          "confidence": 0.997
+        },
+        {
+          "text": "créer",
+          "start": 41.74,
+          "end": 42.1,
+          "confidence": 0.999
+        },
+        {
+          "text": "cet",
+          "start": 42.1,
+          "end": 42.38,
+          "confidence": 0.997
+        },
+        {
+          "text": "objet",
+          "start": 42.38,
+          "end": 42.64,
+          "confidence": 0.994
+        },
+        {
+          "text": "dont",
+          "start": 42.64,
+          "end": 42.84,
+          "confidence": 0.789
+        },
+        {
+          "text": "Nicolas",
+          "start": 42.84,
+          "end": 43.24,
+          "confidence": 0.988
+        },
+        {
+          "text": "dit",
+          "start": 43.24,
+          "end": 43.52,
+          "confidence": 0.986
+        },
+        {
+          "text": "qu'il",
+          "start": 43.52,
+          "end": 43.74,
+          "confidence": 0.982
+        },
+        {
+          "text": "est",
+          "start": 43.74,
+          "end": 43.94,
+          "confidence": 0.99
+        },
+        {
+          "text": "vraisemblablement",
+          "start": 43.94,
+          "end": 44.86,
+          "confidence": 0.99
+        },
+        {
+          "text": "inédit",
+          "start": 44.86,
+          "end": 45.44,
+          "confidence": 0.98
+        },
+        {
+          "text": "dans",
+          "start": 45.44,
+          "end": 45.72,
+          "confidence": 0.967
+        },
+        {
+          "text": "l'histoire",
+          "start": 45.72,
+          "end": 46.02,
+          "confidence": 0.958
+        },
+        {
+          "text": "de",
+          "start": 46.02,
+          "end": 46.14,
+          "confidence": 0.999
+        },
+        {
+          "text": "l'humanité.",
+          "start": 46.14,
+          "end": 46.6,
+          "confidence": 0.992
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 2534,
+      "start": 47.02,
+      "end": 48.78,
+      "text": " Mais ça, ça soulève une autre interrogation.",
+      "tokens": [
+        51439,
+        6313,
+        2788,
+        11,
+        2788,
+        5133,
+        31397,
+        2251,
+        15081,
+        24871,
+        399,
+        13,
+        51539
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10785348191220537,
+      "compression_ratio": 1.6254416961130742,
+      "no_speech_prob": 0.18929888308048248,
+      "confidence": 0.969,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 47.02,
+          "end": 47.28,
+          "confidence": 0.84
+        },
+        {
+          "text": "ça,",
+          "start": 47.28,
+          "end": 47.48,
+          "confidence": 0.942
+        },
+        {
+          "text": "ça",
+          "start": 47.62,
+          "end": 47.64,
+          "confidence": 0.976
+        },
+        {
+          "text": "soulève",
+          "start": 47.64,
+          "end": 47.86,
+          "confidence": 0.993
+        },
+        {
+          "text": "une",
+          "start": 47.86,
+          "end": 48.02,
+          "confidence": 0.998
+        },
+        {
+          "text": "autre",
+          "start": 48.02,
+          "end": 48.2,
+          "confidence": 0.999
+        },
+        {
+          "text": "interrogation.",
+          "start": 48.2,
+          "end": 48.78,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 4884,
+      "start": 49.36,
+      "end": 55.5,
+      "text": " Est-ce que le fait que cet objet soit inédit induit que notre rapport à lui est aussi un rapport inédit ?",
+      "tokens": [
+        50389,
+        4410,
+        12,
+        384,
+        631,
+        476,
+        3887,
+        631,
+        8603,
+        14964,
+        12703,
+        294,
+        7811,
+        270,
+        13716,
+        270,
+        631,
+        10349,
+        18018,
+        1531,
+        8783,
+        871,
+        6212,
+        517,
+        18018,
+        294,
+        7811,
+        270,
+        2506,
+        50689
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.08241327932058287,
+      "compression_ratio": 1.5960784313725491,
+      "no_speech_prob": 0.09794807434082031,
+      "confidence": 0.986,
+      "words": [
+        {
+          "text": "Est-ce",
+          "start": 49.36,
+          "end": 49.64,
+          "confidence": 0.978
+        },
+        {
+          "text": "que",
+          "start": 49.64,
+          "end": 49.76,
+          "confidence": 0.991
+        },
+        {
+          "text": "le",
+          "start": 49.76,
+          "end": 49.82,
+          "confidence": 0.993
+        },
+        {
+          "text": "fait",
+          "start": 49.82,
+          "end": 50.0,
+          "confidence": 0.999
+        },
+        {
+          "text": "que",
+          "start": 50.0,
+          "end": 50.14,
+          "confidence": 0.991
+        },
+        {
+          "text": "cet",
+          "start": 50.14,
+          "end": 50.32,
+          "confidence": 0.99
+        },
+        {
+          "text": "objet",
+          "start": 50.32,
+          "end": 50.66,
+          "confidence": 0.997
+        },
+        {
+          "text": "soit",
+          "start": 50.66,
+          "end": 51.12,
+          "confidence": 0.995
+        },
+        {
+          "text": "inédit",
+          "start": 51.12,
+          "end": 51.78,
+          "confidence": 0.995
+        },
+        {
+          "text": "induit",
+          "start": 51.78,
+          "end": 52.32,
+          "confidence": 0.955
+        },
+        {
+          "text": "que",
+          "start": 52.32,
+          "end": 52.42,
+          "confidence": 0.984
+        },
+        {
+          "text": "notre",
+          "start": 52.42,
+          "end": 52.78,
+          "confidence": 0.995
+        },
+        {
+          "text": "rapport",
+          "start": 52.78,
+          "end": 53.28,
+          "confidence": 0.997
+        },
+        {
+          "text": "à",
+          "start": 53.28,
+          "end": 53.46,
+          "confidence": 0.978
+        },
+        {
+          "text": "lui",
+          "start": 53.46,
+          "end": 53.68,
+          "confidence": 0.999
+        },
+        {
+          "text": "est",
+          "start": 53.68,
+          "end": 54.14,
+          "confidence": 0.907
+        },
+        {
+          "text": "aussi",
+          "start": 54.14,
+          "end": 54.52,
+          "confidence": 0.996
+        },
+        {
+          "text": "un",
+          "start": 54.52,
+          "end": 54.72,
+          "confidence": 0.994
+        },
+        {
+          "text": "rapport",
+          "start": 54.72,
+          "end": 55.0,
+          "confidence": 0.997
+        },
+        {
+          "text": "inédit ?",
+          "start": 55.0,
+          "end": 55.5,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 4884,
+      "start": 55.76,
+      "end": 63.4,
+      "text": " Je veux dire, est-ce que le rapport qu'on a au smartphone est comparable à celui qu'on entretenait à d'autres objets techniques comme la voiture ou le téléphone ?",
+      "tokens": [
+        50689,
+        2588,
+        16389,
+        1264,
+        11,
+        871,
+        12,
+        384,
+        631,
+        476,
+        18018,
+        421,
+        6,
+        266,
+        257,
+        1609,
+        13307,
+        871,
+        25323,
+        1531,
+        22829,
+        421,
+        6,
+        266,
+        3962,
+        1147,
+        1001,
+        1531,
+        274,
+        6,
+        16752,
+        1111,
+        25349,
+        7512,
+        5173,
+        635,
+        38859,
+        2820,
+        476,
+        47159,
+        2506,
+        51089
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.08241327932058287,
+      "compression_ratio": 1.5960784313725491,
+      "no_speech_prob": 0.09794807434082031,
+      "confidence": 0.96,
+      "words": [
+        {
+          "text": "Je",
+          "start": 55.76,
+          "end": 55.9,
+          "confidence": 0.904
+        },
+        {
+          "text": "veux",
+          "start": 55.9,
+          "end": 56.0,
+          "confidence": 0.989
+        },
+        {
+          "text": "dire,",
+          "start": 56.0,
+          "end": 56.12,
+          "confidence": 0.997
+        },
+        {
+          "text": "est-ce",
+          "start": 56.22,
+          "end": 56.38,
+          "confidence": 0.99
+        },
+        {
+          "text": "que",
+          "start": 56.38,
+          "end": 56.5,
+          "confidence": 0.991
+        },
+        {
+          "text": "le",
+          "start": 56.5,
+          "end": 56.66,
+          "confidence": 0.996
+        },
+        {
+          "text": "rapport",
+          "start": 56.66,
+          "end": 56.86,
+          "confidence": 0.998
+        },
+        {
+          "text": "qu'on",
+          "start": 56.86,
+          "end": 57.08,
+          "confidence": 0.985
+        },
+        {
+          "text": "a",
+          "start": 57.08,
+          "end": 57.16,
+          "confidence": 0.99
+        },
+        {
+          "text": "au",
+          "start": 57.16,
+          "end": 57.28,
+          "confidence": 0.966
+        },
+        {
+          "text": "smartphone",
+          "start": 57.28,
+          "end": 57.6,
+          "confidence": 0.995
+        },
+        {
+          "text": "est",
+          "start": 57.6,
+          "end": 57.86,
+          "confidence": 0.91
+        },
+        {
+          "text": "comparable",
+          "start": 57.86,
+          "end": 58.3,
+          "confidence": 0.996
+        },
+        {
+          "text": "à",
+          "start": 58.3,
+          "end": 58.5,
+          "confidence": 0.946
+        },
+        {
+          "text": "celui",
+          "start": 58.5,
+          "end": 58.66,
+          "confidence": 0.998
+        },
+        {
+          "text": "qu'on",
+          "start": 58.66,
+          "end": 58.96,
+          "confidence": 0.989
+        },
+        {
+          "text": "entretenait",
+          "start": 58.96,
+          "end": 59.36,
+          "confidence": 0.926
+        },
+        {
+          "text": "à",
+          "start": 59.36,
+          "end": 59.48,
+          "confidence": 0.951
+        },
+        {
+          "text": "d'autres",
+          "start": 59.48,
+          "end": 59.7,
+          "confidence": 0.997
+        },
+        {
+          "text": "objets",
+          "start": 59.7,
+          "end": 59.98,
+          "confidence": 0.99
+        },
+        {
+          "text": "techniques",
+          "start": 59.98,
+          "end": 60.44,
+          "confidence": 0.984
+        },
+        {
+          "text": "comme",
+          "start": 60.44,
+          "end": 60.96,
+          "confidence": 0.496
+        },
+        {
+          "text": "la",
+          "start": 60.96,
+          "end": 61.52,
+          "confidence": 0.987
+        },
+        {
+          "text": "voiture",
+          "start": 61.52,
+          "end": 62.08,
+          "confidence": 1.0
+        },
+        {
+          "text": "ou",
+          "start": 62.08,
+          "end": 62.52,
+          "confidence": 0.95
+        },
+        {
+          "text": "le",
+          "start": 62.52,
+          "end": 62.74,
+          "confidence": 0.998
+        },
+        {
+          "text": "téléphone ?",
+          "start": 62.74,
+          "end": 63.4,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 4884,
+      "start": 65.36,
+      "end": 66.62,
+      "text": " Il n'y a pas d'équivalent en fait.",
+      "tokens": [
+        51189,
+        4416,
+        297,
+        6,
+        88,
+        257,
+        1736,
+        274,
+        6,
+        20183,
+        3576,
+        317,
+        465,
+        3887,
+        13,
+        51239
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.08241327932058287,
+      "compression_ratio": 1.5960784313725491,
+      "no_speech_prob": 0.09794807434082031,
+      "confidence": 0.94,
+      "words": [
+        {
+          "text": "Il",
+          "start": 65.36,
+          "end": 65.5,
+          "confidence": 0.849
+        },
+        {
+          "text": "n'y",
+          "start": 65.5,
+          "end": 65.54,
+          "confidence": 0.979
+        },
+        {
+          "text": "a",
+          "start": 65.54,
+          "end": 65.56,
+          "confidence": 0.993
+        },
+        {
+          "text": "pas",
+          "start": 65.56,
+          "end": 65.66,
+          "confidence": 0.999
+        },
+        {
+          "text": "d'équivalent",
+          "start": 65.66,
+          "end": 66.3,
+          "confidence": 0.995
+        },
+        {
+          "text": "en",
+          "start": 66.3,
+          "end": 66.44,
+          "confidence": 0.582
+        },
+        {
+          "text": "fait.",
+          "start": 66.44,
+          "end": 66.62,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 4884,
+      "start": 66.88,
+      "end": 71.24,
+      "text": " Et donc cette espèce de nouveauté dans la relation à l'objet, c'est fascinant et terrifiant.",
+      "tokens": [
+        51239,
+        3790,
+        5926,
+        5550,
+        7089,
+        30236,
+        368,
+        11456,
+        1375,
+        526,
+        2680,
+        635,
+        9721,
+        1531,
+        287,
+        6,
+        996,
+        7108,
+        11,
+        269,
+        6,
+        377,
+        7184,
+        259,
+        394,
+        1030,
+        7245,
+        351,
+        5798,
+        13,
+        51489
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.08241327932058287,
+      "compression_ratio": 1.5960784313725491,
+      "no_speech_prob": 0.09794807434082031,
+      "confidence": 0.957,
+      "words": [
+        {
+          "text": "Et",
+          "start": 66.88,
+          "end": 67.02,
+          "confidence": 0.654
+        },
+        {
+          "text": "donc",
+          "start": 67.02,
+          "end": 67.12,
+          "confidence": 0.901
+        },
+        {
+          "text": "cette",
+          "start": 67.12,
+          "end": 67.3,
+          "confidence": 0.713
+        },
+        {
+          "text": "espèce",
+          "start": 67.3,
+          "end": 67.54,
+          "confidence": 0.996
+        },
+        {
+          "text": "de",
+          "start": 67.54,
+          "end": 67.76,
+          "confidence": 0.999
+        },
+        {
+          "text": "nouveauté",
+          "start": 67.76,
+          "end": 68.48,
+          "confidence": 0.98
+        },
+        {
+          "text": "dans",
+          "start": 68.48,
+          "end": 68.84,
+          "confidence": 0.982
+        },
+        {
+          "text": "la",
+          "start": 68.84,
+          "end": 68.96,
+          "confidence": 0.995
+        },
+        {
+          "text": "relation",
+          "start": 68.96,
+          "end": 69.24,
+          "confidence": 0.998
+        },
+        {
+          "text": "à",
+          "start": 69.24,
+          "end": 69.38,
+          "confidence": 0.997
+        },
+        {
+          "text": "l'objet,",
+          "start": 69.38,
+          "end": 70.0,
+          "confidence": 0.998
+        },
+        {
+          "text": "c'est",
+          "start": 70.28,
+          "end": 70.38,
+          "confidence": 0.977
+        },
+        {
+          "text": "fascinant",
+          "start": 70.38,
+          "end": 70.68,
+          "confidence": 0.98
+        },
+        {
+          "text": "et",
+          "start": 70.68,
+          "end": 70.76,
+          "confidence": 0.973
+        },
+        {
+          "text": "terrifiant.",
+          "start": 70.76,
+          "end": 71.24,
+          "confidence": 0.977
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 7134,
+      "start": 71.62,
+      "end": 76.42,
+      "text": " Parce qu'on a l'impression, comme le disent les utilisateurs et les services, d'être dépendant de cet objet,",
+      "tokens": [
+        50389,
+        20429,
+        421,
+        6,
+        266,
+        257,
+        287,
+        6,
+        36107,
+        11,
+        5173,
+        476,
+        37313,
+        1512,
+        33643,
+        25929,
+        1030,
+        1512,
+        3328,
+        11,
+        274,
+        6,
+        9498,
+        45768,
+        394,
+        368,
+        8603,
+        14964,
+        11,
+        50639
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.11220460018869173,
+      "compression_ratio": 1.5975609756097562,
+      "no_speech_prob": 0.015181643888354301,
+      "confidence": 0.862,
+      "words": [
+        {
+          "text": "Parce",
+          "start": 71.62,
+          "end": 71.9,
+          "confidence": 0.843
+        },
+        {
+          "text": "qu'on",
+          "start": 71.9,
+          "end": 72.4,
+          "confidence": 0.968
+        },
+        {
+          "text": "a",
+          "start": 72.4,
+          "end": 72.54,
+          "confidence": 0.979
+        },
+        {
+          "text": "l'impression,",
+          "start": 72.54,
+          "end": 72.9,
+          "confidence": 0.997
+        },
+        {
+          "text": "comme",
+          "start": 73.66,
+          "end": 73.9,
+          "confidence": 0.982
+        },
+        {
+          "text": "le",
+          "start": 73.9,
+          "end": 74.02,
+          "confidence": 0.984
+        },
+        {
+          "text": "disent",
+          "start": 74.02,
+          "end": 74.22,
+          "confidence": 0.997
+        },
+        {
+          "text": "les",
+          "start": 74.22,
+          "end": 74.52,
+          "confidence": 0.996
+        },
+        {
+          "text": "utilisateurs",
+          "start": 74.52,
+          "end": 74.84,
+          "confidence": 0.998
+        },
+        {
+          "text": "et",
+          "start": 74.84,
+          "end": 74.94,
+          "confidence": 0.845
+        },
+        {
+          "text": "les",
+          "start": 74.94,
+          "end": 75.02,
+          "confidence": 0.783
+        },
+        {
+          "text": "services,",
+          "start": 75.02,
+          "end": 75.18,
+          "confidence": 0.129
+        },
+        {
+          "text": "d'être",
+          "start": 75.22,
+          "end": 75.5,
+          "confidence": 0.935
+        },
+        {
+          "text": "dépendant",
+          "start": 75.5,
+          "end": 75.98,
+          "confidence": 0.709
+        },
+        {
+          "text": "de",
+          "start": 75.98,
+          "end": 76.08,
+          "confidence": 0.977
+        },
+        {
+          "text": "cet",
+          "start": 76.08,
+          "end": 76.26,
+          "confidence": 0.998
+        },
+        {
+          "text": "objet,",
+          "start": 76.26,
+          "end": 76.42,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 7134,
+      "start": 76.42,
+      "end": 83.3,
+      "text": " d'induire en fait une espèce de relation, de médiation avec le monde qui rend de l'ampleur et qui amène aussi à des formes de rejet.",
+      "tokens": [
+        50639,
+        274,
+        6,
+        471,
+        43612,
+        465,
+        3887,
+        2251,
+        7089,
+        30236,
+        368,
+        9721,
+        11,
+        368,
+        42436,
+        399,
+        4163,
+        476,
+        10431,
+        1956,
+        6125,
+        368,
+        287,
+        6,
+        335,
+        781,
+        374,
+        1030,
+        1956,
+        669,
+        18832,
+        6212,
+        1531,
+        730,
+        1254,
+        279,
+        368,
+        319,
+        7108,
+        13,
+        50989
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.11220460018869173,
+      "compression_ratio": 1.5975609756097562,
+      "no_speech_prob": 0.015181643888354301,
+      "confidence": 0.923,
+      "words": [
+        {
+          "text": "d'induire",
+          "start": 76.42,
+          "end": 77.1,
+          "confidence": 0.964
+        },
+        {
+          "text": "en",
+          "start": 77.1,
+          "end": 77.18,
+          "confidence": 0.72
+        },
+        {
+          "text": "fait",
+          "start": 77.18,
+          "end": 77.34,
+          "confidence": 0.997
+        },
+        {
+          "text": "une",
+          "start": 77.34,
+          "end": 77.5,
+          "confidence": 0.979
+        },
+        {
+          "text": "espèce",
+          "start": 77.5,
+          "end": 77.88,
+          "confidence": 0.997
+        },
+        {
+          "text": "de",
+          "start": 77.88,
+          "end": 78.28,
+          "confidence": 0.997
+        },
+        {
+          "text": "relation,",
+          "start": 78.28,
+          "end": 78.54,
+          "confidence": 0.422
+        },
+        {
+          "text": "de",
+          "start": 78.66,
+          "end": 78.96,
+          "confidence": 0.992
+        },
+        {
+          "text": "médiation",
+          "start": 78.96,
+          "end": 79.52,
+          "confidence": 0.997
+        },
+        {
+          "text": "avec",
+          "start": 79.52,
+          "end": 79.76,
+          "confidence": 0.954
+        },
+        {
+          "text": "le",
+          "start": 79.76,
+          "end": 80.02,
+          "confidence": 0.998
+        },
+        {
+          "text": "monde",
+          "start": 80.02,
+          "end": 80.3,
+          "confidence": 0.996
+        },
+        {
+          "text": "qui",
+          "start": 80.3,
+          "end": 81.24,
+          "confidence": 0.661
+        },
+        {
+          "text": "rend",
+          "start": 81.24,
+          "end": 81.66,
+          "confidence": 0.968
+        },
+        {
+          "text": "de",
+          "start": 81.66,
+          "end": 81.74,
+          "confidence": 0.688
+        },
+        {
+          "text": "l'ampleur",
+          "start": 81.74,
+          "end": 82.02,
+          "confidence": 0.995
+        },
+        {
+          "text": "et",
+          "start": 82.02,
+          "end": 82.1,
+          "confidence": 0.952
+        },
+        {
+          "text": "qui",
+          "start": 82.1,
+          "end": 82.2,
+          "confidence": 0.987
+        },
+        {
+          "text": "amène",
+          "start": 82.2,
+          "end": 82.38,
+          "confidence": 0.971
+        },
+        {
+          "text": "aussi",
+          "start": 82.38,
+          "end": 82.54,
+          "confidence": 0.946
+        },
+        {
+          "text": "à",
+          "start": 82.54,
+          "end": 82.62,
+          "confidence": 0.959
+        },
+        {
+          "text": "des",
+          "start": 82.62,
+          "end": 82.7,
+          "confidence": 0.992
+        },
+        {
+          "text": "formes",
+          "start": 82.7,
+          "end": 82.88,
+          "confidence": 0.995
+        },
+        {
+          "text": "de",
+          "start": 82.88,
+          "end": 83.04,
+          "confidence": 0.998
+        },
+        {
+          "text": "rejet.",
+          "start": 83.04,
+          "end": 83.3,
+          "confidence": 0.802
+        }
+      ]
+    },
+    {
+      "id": 17,
+      "seek": 7134,
+      "start": 83.92,
+      "end": 87.7,
+      "text": " Donc à objet inédit, rapport inédit.",
+      "tokens": [
+        50989,
+        7477,
+        1531,
+        14964,
+        294,
+        7811,
+        270,
+        11,
+        18018,
+        294,
+        7811,
+        270,
+        13,
+        51189
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.11220460018869173,
+      "compression_ratio": 1.5975609756097562,
+      "no_speech_prob": 0.015181643888354301,
+      "confidence": 0.901,
+      "words": [
+        {
+          "text": "Donc",
+          "start": 83.92,
+          "end": 84.46,
+          "confidence": 0.984
+        },
+        {
+          "text": "à",
+          "start": 84.46,
+          "end": 84.98,
+          "confidence": 0.483
+        },
+        {
+          "text": "objet",
+          "start": 84.98,
+          "end": 85.46,
+          "confidence": 0.77
+        },
+        {
+          "text": "inédit,",
+          "start": 85.46,
+          "end": 86.2,
+          "confidence": 0.994
+        },
+        {
+          "text": "rapport",
+          "start": 86.54,
+          "end": 86.9,
+          "confidence": 0.986
+        },
+        {
+          "text": "inédit.",
+          "start": 86.9,
+          "end": 87.7,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 18,
+      "seek": 7134,
+      "start": 88.02,
+      "end": 94.92,
+      "text": " Et ce rapport, si j'en crois à Nicolas, serait caractérisé par un mélange de dépendance et de rejet.",
+      "tokens": [
+        51189,
+        3790,
+        1769,
+        18018,
+        11,
+        1511,
+        361,
+        6,
+        268,
+        21724,
+        1531,
+        38268,
+        11,
+        23139,
+        1032,
+        578,
+        4198,
+        22118,
+        971,
+        517,
+        41953,
+        933,
+        368,
+        45768,
+        719,
+        1030,
+        368,
+        319,
+        7108,
+        13,
+        51539
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.11220460018869173,
+      "compression_ratio": 1.5975609756097562,
+      "no_speech_prob": 0.015181643888354301,
+      "confidence": 0.975,
+      "words": [
+        {
+          "text": "Et",
+          "start": 88.02,
+          "end": 88.62,
+          "confidence": 0.989
+        },
+        {
+          "text": "ce",
+          "start": 88.62,
+          "end": 88.9,
+          "confidence": 0.985
+        },
+        {
+          "text": "rapport,",
+          "start": 88.9,
+          "end": 89.32,
+          "confidence": 0.998
+        },
+        {
+          "text": "si",
+          "start": 89.38,
+          "end": 89.56,
+          "confidence": 0.999
+        },
+        {
+          "text": "j'en",
+          "start": 89.56,
+          "end": 89.78,
+          "confidence": 0.997
+        },
+        {
+          "text": "crois",
+          "start": 89.78,
+          "end": 89.88,
+          "confidence": 0.988
+        },
+        {
+          "text": "à",
+          "start": 89.88,
+          "end": 90.06,
+          "confidence": 0.724
+        },
+        {
+          "text": "Nicolas,",
+          "start": 90.06,
+          "end": 90.24,
+          "confidence": 0.997
+        },
+        {
+          "text": "serait",
+          "start": 90.7,
+          "end": 91.0,
+          "confidence": 0.904
+        },
+        {
+          "text": "caractérisé",
+          "start": 91.0,
+          "end": 91.8,
+          "confidence": 0.994
+        },
+        {
+          "text": "par",
+          "start": 91.8,
+          "end": 92.22,
+          "confidence": 0.995
+        },
+        {
+          "text": "un",
+          "start": 92.22,
+          "end": 92.52,
+          "confidence": 0.996
+        },
+        {
+          "text": "mélange",
+          "start": 92.52,
+          "end": 93.04,
+          "confidence": 0.999
+        },
+        {
+          "text": "de",
+          "start": 93.04,
+          "end": 93.46,
+          "confidence": 0.998
+        },
+        {
+          "text": "dépendance",
+          "start": 93.46,
+          "end": 94.12,
+          "confidence": 0.938
+        },
+        {
+          "text": "et",
+          "start": 94.12,
+          "end": 94.54,
+          "confidence": 0.998
+        },
+        {
+          "text": "de",
+          "start": 94.54,
+          "end": 94.72,
+          "confidence": 0.999
+        },
+        {
+          "text": "rejet.",
+          "start": 94.72,
+          "end": 94.92,
+          "confidence": 0.988
+        }
+      ]
+    },
+    {
+      "id": 19,
+      "seek": 9484,
+      "start": 95.74,
+      "end": 102.82,
+      "text": " Bon, en vrai, il faudrait remonter très très finement toute l'histoire des objets techniques et de leur insertion dans nos vies",
+      "tokens": [
+        50389,
+        7368,
+        11,
+        465,
+        17815,
+        11,
+        1930,
+        38694,
+        8645,
+        890,
+        41806,
+        5732,
+        5732,
+        962,
+        1712,
+        14953,
+        287,
+        6,
+        29093,
+        730,
+        1111,
+        25349,
+        7512,
+        1030,
+        368,
+        9580,
+        8969,
+        313,
+        2680,
+        3269,
+        371,
+        530,
+        50739
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.0781538827078683,
+      "compression_ratio": 1.6719745222929936,
+      "no_speech_prob": 0.017434891313314438,
+      "confidence": 0.932,
+      "words": [
+        {
+          "text": "Bon,",
+          "start": 95.74,
+          "end": 96.0,
+          "confidence": 0.751
+        },
+        {
+          "text": "en",
+          "start": 96.34,
+          "end": 96.54,
+          "confidence": 0.992
+        },
+        {
+          "text": "vrai,",
+          "start": 96.54,
+          "end": 96.86,
+          "confidence": 0.991
+        },
+        {
+          "text": "il",
+          "start": 97.06,
+          "end": 97.18,
+          "confidence": 0.992
+        },
+        {
+          "text": "faudrait",
+          "start": 97.18,
+          "end": 97.58,
+          "confidence": 0.996
+        },
+        {
+          "text": "remonter",
+          "start": 97.58,
+          "end": 98.06,
+          "confidence": 0.995
+        },
+        {
+          "text": "très",
+          "start": 98.06,
+          "end": 98.58,
+          "confidence": 0.995
+        },
+        {
+          "text": "très",
+          "start": 98.58,
+          "end": 98.84,
+          "confidence": 0.757
+        },
+        {
+          "text": "finement",
+          "start": 98.84,
+          "end": 99.38,
+          "confidence": 0.823
+        },
+        {
+          "text": "toute",
+          "start": 99.38,
+          "end": 99.7,
+          "confidence": 0.937
+        },
+        {
+          "text": "l'histoire",
+          "start": 99.7,
+          "end": 100.08,
+          "confidence": 0.996
+        },
+        {
+          "text": "des",
+          "start": 100.08,
+          "end": 100.26,
+          "confidence": 0.991
+        },
+        {
+          "text": "objets",
+          "start": 100.26,
+          "end": 100.52,
+          "confidence": 0.998
+        },
+        {
+          "text": "techniques",
+          "start": 100.52,
+          "end": 100.94,
+          "confidence": 0.982
+        },
+        {
+          "text": "et",
+          "start": 100.94,
+          "end": 101.54,
+          "confidence": 0.512
+        },
+        {
+          "text": "de",
+          "start": 101.54,
+          "end": 101.7,
+          "confidence": 0.984
+        },
+        {
+          "text": "leur",
+          "start": 101.7,
+          "end": 101.84,
+          "confidence": 0.818
+        },
+        {
+          "text": "insertion",
+          "start": 101.84,
+          "end": 102.34,
+          "confidence": 0.994
+        },
+        {
+          "text": "dans",
+          "start": 102.34,
+          "end": 102.5,
+          "confidence": 0.969
+        },
+        {
+          "text": "nos",
+          "start": 102.5,
+          "end": 102.66,
+          "confidence": 0.998
+        },
+        {
+          "text": "vies",
+          "start": 102.66,
+          "end": 102.82,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 20,
+      "seek": 9484,
+      "start": 102.86,
+      "end": 105.72,
+      "text": " pour déterminer si ce rapport est totalement inédit.",
+      "tokens": [
+        50739,
+        2016,
+        2795,
+        29725,
+        260,
+        1511,
+        1769,
+        18018,
+        871,
+        45203,
+        294,
+        7811,
+        270,
+        13,
+        50889
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.0781538827078683,
+      "compression_ratio": 1.6719745222929936,
+      "no_speech_prob": 0.017434891313314438,
+      "confidence": 0.995,
+      "words": [
+        {
+          "text": "pour",
+          "start": 102.86,
+          "end": 103.1,
+          "confidence": 0.989
+        },
+        {
+          "text": "déterminer",
+          "start": 103.1,
+          "end": 103.64,
+          "confidence": 0.995
+        },
+        {
+          "text": "si",
+          "start": 103.64,
+          "end": 103.76,
+          "confidence": 0.986
+        },
+        {
+          "text": "ce",
+          "start": 103.76,
+          "end": 103.94,
+          "confidence": 0.991
+        },
+        {
+          "text": "rapport",
+          "start": 103.94,
+          "end": 104.26,
+          "confidence": 0.998
+        },
+        {
+          "text": "est",
+          "start": 104.26,
+          "end": 104.84,
+          "confidence": 0.997
+        },
+        {
+          "text": "totalement",
+          "start": 104.84,
+          "end": 105.3,
+          "confidence": 0.998
+        },
+        {
+          "text": "inédit.",
+          "start": 105.3,
+          "end": 105.72,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 21,
+      "seek": 9484,
+      "start": 106.14,
+      "end": 109.32,
+      "text": " Mais j'ai l'impression comme ça que Nicolas ne se trompe pas vraiment.",
+      "tokens": [
+        50889,
+        6313,
+        361,
+        6,
+        1301,
+        287,
+        6,
+        36107,
+        5173,
+        2788,
+        631,
+        38268,
+        408,
+        369,
+        504,
+        298,
+        494,
+        1736,
+        8322,
+        13,
+        51089
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.0781538827078683,
+      "compression_ratio": 1.6719745222929936,
+      "no_speech_prob": 0.017434891313314438,
+      "confidence": 0.932,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 106.14,
+          "end": 106.4,
+          "confidence": 0.975
+        },
+        {
+          "text": "j'ai",
+          "start": 106.4,
+          "end": 106.92,
+          "confidence": 0.956
+        },
+        {
+          "text": "l'impression",
+          "start": 106.92,
+          "end": 107.38,
+          "confidence": 0.999
+        },
+        {
+          "text": "comme",
+          "start": 107.38,
+          "end": 107.58,
+          "confidence": 0.513
+        },
+        {
+          "text": "ça",
+          "start": 107.58,
+          "end": 107.82,
+          "confidence": 0.969
+        },
+        {
+          "text": "que",
+          "start": 107.82,
+          "end": 108.14,
+          "confidence": 0.973
+        },
+        {
+          "text": "Nicolas",
+          "start": 108.14,
+          "end": 108.48,
+          "confidence": 0.983
+        },
+        {
+          "text": "ne",
+          "start": 108.48,
+          "end": 108.6,
+          "confidence": 0.72
+        },
+        {
+          "text": "se",
+          "start": 108.6,
+          "end": 108.72,
+          "confidence": 0.992
+        },
+        {
+          "text": "trompe",
+          "start": 108.72,
+          "end": 108.88,
+          "confidence": 0.993
+        },
+        {
+          "text": "pas",
+          "start": 108.88,
+          "end": 109.08,
+          "confidence": 0.999
+        },
+        {
+          "text": "vraiment.",
+          "start": 109.08,
+          "end": 109.32,
+          "confidence": 0.989
+        }
+      ]
+    },
+    {
+      "id": 22,
+      "seek": 9484,
+      "start": 109.94,
+      "end": 115.06,
+      "text": " Pour autant que je sache, il y a eu plein de discussions autour de la voiture ou même du téléphone.",
+      "tokens": [
+        51089,
+        8732,
+        34081,
+        631,
+        1506,
+        262,
+        6000,
+        11,
+        1930,
+        288,
+        257,
+        2228,
+        21088,
+        368,
+        11088,
+        30249,
+        368,
+        635,
+        38859,
+        2820,
+        5698,
+        1581,
+        47159,
+        13,
+        51389
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.0781538827078683,
+      "compression_ratio": 1.6719745222929936,
+      "no_speech_prob": 0.017434891313314438,
+      "confidence": 0.964,
+      "words": [
+        {
+          "text": "Pour",
+          "start": 109.94,
+          "end": 110.1,
+          "confidence": 0.995
+        },
+        {
+          "text": "autant",
+          "start": 110.1,
+          "end": 110.24,
+          "confidence": 1.0
+        },
+        {
+          "text": "que",
+          "start": 110.24,
+          "end": 110.38,
+          "confidence": 0.984
+        },
+        {
+          "text": "je",
+          "start": 110.38,
+          "end": 110.52,
+          "confidence": 0.998
+        },
+        {
+          "text": "sache,",
+          "start": 110.52,
+          "end": 110.84,
+          "confidence": 0.952
+        },
+        {
+          "text": "il",
+          "start": 111.08,
+          "end": 111.16,
+          "confidence": 0.994
+        },
+        {
+          "text": "y",
+          "start": 111.16,
+          "end": 111.3,
+          "confidence": 0.995
+        },
+        {
+          "text": "a",
+          "start": 111.3,
+          "end": 111.32,
+          "confidence": 0.993
+        },
+        {
+          "text": "eu",
+          "start": 111.32,
+          "end": 111.62,
+          "confidence": 0.998
+        },
+        {
+          "text": "plein",
+          "start": 111.62,
+          "end": 111.9,
+          "confidence": 0.966
+        },
+        {
+          "text": "de",
+          "start": 111.9,
+          "end": 112.14,
+          "confidence": 0.997
+        },
+        {
+          "text": "discussions",
+          "start": 112.14,
+          "end": 112.66,
+          "confidence": 0.83
+        },
+        {
+          "text": "autour",
+          "start": 112.66,
+          "end": 113.02,
+          "confidence": 0.995
+        },
+        {
+          "text": "de",
+          "start": 113.02,
+          "end": 113.38,
+          "confidence": 0.996
+        },
+        {
+          "text": "la",
+          "start": 113.38,
+          "end": 113.52,
+          "confidence": 0.998
+        },
+        {
+          "text": "voiture",
+          "start": 113.52,
+          "end": 113.88,
+          "confidence": 1.0
+        },
+        {
+          "text": "ou",
+          "start": 113.88,
+          "end": 114.06,
+          "confidence": 0.69
+        },
+        {
+          "text": "même",
+          "start": 114.06,
+          "end": 114.34,
+          "confidence": 0.995
+        },
+        {
+          "text": "du",
+          "start": 114.34,
+          "end": 114.64,
+          "confidence": 0.992
+        },
+        {
+          "text": "téléphone.",
+          "start": 114.64,
+          "end": 115.06,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 23,
+      "seek": 9484,
+      "start": 115.48,
+      "end": 117.7,
+      "text": " Mais la dépendance n'était pas du même ordre.",
+      "tokens": [
+        51389,
+        6313,
+        635,
+        45768,
+        719,
+        297,
+        6,
+        9743,
+        1736,
+        1581,
+        5698,
+        4792,
+        265,
+        13,
+        51489
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.0781538827078683,
+      "compression_ratio": 1.6719745222929936,
+      "no_speech_prob": 0.017434891313314438,
+      "confidence": 0.992,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 115.48,
+          "end": 115.78,
+          "confidence": 0.993
+        },
+        {
+          "text": "la",
+          "start": 115.78,
+          "end": 116.04,
+          "confidence": 0.943
+        },
+        {
+          "text": "dépendance",
+          "start": 116.04,
+          "end": 116.42,
+          "confidence": 0.996
+        },
+        {
+          "text": "n'était",
+          "start": 116.42,
+          "end": 116.7,
+          "confidence": 0.994
+        },
+        {
+          "text": "pas",
+          "start": 116.7,
+          "end": 117.0,
+          "confidence": 0.998
+        },
+        {
+          "text": "du",
+          "start": 117.0,
+          "end": 117.2,
+          "confidence": 0.996
+        },
+        {
+          "text": "même",
+          "start": 117.2,
+          "end": 117.44,
+          "confidence": 0.998
+        },
+        {
+          "text": "ordre.",
+          "start": 117.44,
+          "end": 117.7,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 24,
+      "seek": 9484,
+      "start": 117.72,
+      "end": 119.78,
+      "text": " Donc le rejet non plus n'était pas du même ordre.",
+      "tokens": [
+        51489,
+        7477,
+        476,
+        319,
+        7108,
+        2107,
+        1804,
+        297,
+        6,
+        9743,
+        1736,
+        1581,
+        5698,
+        4792,
+        265,
+        13,
+        51589
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.0781538827078683,
+      "compression_ratio": 1.6719745222929936,
+      "no_speech_prob": 0.017434891313314438,
+      "confidence": 0.979,
+      "words": [
+        {
+          "text": "Donc",
+          "start": 117.72,
+          "end": 118.02,
+          "confidence": 0.959
+        },
+        {
+          "text": "le",
+          "start": 118.02,
+          "end": 118.4,
+          "confidence": 0.819
+        },
+        {
+          "text": "rejet",
+          "start": 118.4,
+          "end": 118.64,
+          "confidence": 0.999
+        },
+        {
+          "text": "non",
+          "start": 118.64,
+          "end": 118.82,
+          "confidence": 0.982
+        },
+        {
+          "text": "plus",
+          "start": 118.82,
+          "end": 118.94,
+          "confidence": 0.994
+        },
+        {
+          "text": "n'était",
+          "start": 118.94,
+          "end": 119.18,
+          "confidence": 0.991
+        },
+        {
+          "text": "pas",
+          "start": 119.18,
+          "end": 119.3,
+          "confidence": 0.998
+        },
+        {
+          "text": "du",
+          "start": 119.3,
+          "end": 119.42,
+          "confidence": 0.995
+        },
+        {
+          "text": "même",
+          "start": 119.42,
+          "end": 119.58,
+          "confidence": 0.999
+        },
+        {
+          "text": "ordre.",
+          "start": 119.58,
+          "end": 119.78,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 25,
+      "seek": 9484,
+      "start": 120.04,
+      "end": 123.1,
+      "text": " On peut adorer sa bagnole, en avoir besoin pour plein de choses.",
+      "tokens": [
+        51589,
+        1282,
+        5977,
+        614,
+        17618,
+        601,
+        3411,
+        1771,
+        306,
+        11,
+        465,
+        10853,
+        19207,
+        2016,
+        21088,
+        368,
+        14488,
+        13,
+        51789
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.0781538827078683,
+      "compression_ratio": 1.6719745222929936,
+      "no_speech_prob": 0.017434891313314438,
+      "confidence": 0.971,
+      "words": [
+        {
+          "text": "On",
+          "start": 120.04,
+          "end": 120.16,
+          "confidence": 0.757
+        },
+        {
+          "text": "peut",
+          "start": 120.16,
+          "end": 120.36,
+          "confidence": 0.997
+        },
+        {
+          "text": "adorer",
+          "start": 120.36,
+          "end": 120.68,
+          "confidence": 0.991
+        },
+        {
+          "text": "sa",
+          "start": 120.68,
+          "end": 120.88,
+          "confidence": 0.98
+        },
+        {
+          "text": "bagnole,",
+          "start": 120.88,
+          "end": 121.34,
+          "confidence": 0.985
+        },
+        {
+          "text": "en",
+          "start": 121.42,
+          "end": 121.56,
+          "confidence": 0.971
+        },
+        {
+          "text": "avoir",
+          "start": 121.56,
+          "end": 121.8,
+          "confidence": 0.997
+        },
+        {
+          "text": "besoin",
+          "start": 121.8,
+          "end": 122.12,
+          "confidence": 0.999
+        },
+        {
+          "text": "pour",
+          "start": 122.12,
+          "end": 122.46,
+          "confidence": 0.989
+        },
+        {
+          "text": "plein",
+          "start": 122.46,
+          "end": 122.7,
+          "confidence": 0.987
+        },
+        {
+          "text": "de",
+          "start": 122.7,
+          "end": 122.78,
+          "confidence": 0.997
+        },
+        {
+          "text": "choses.",
+          "start": 122.78,
+          "end": 123.1,
+          "confidence": 0.99
+        }
+      ]
+    },
+    {
+      "id": 26,
+      "seek": 12334,
+      "start": 123.38,
+      "end": 126.44,
+      "text": " Le soir, quand on va se coucher, on la laisse.",
+      "tokens": [
+        50389,
+        1456,
+        27105,
+        11,
+        6932,
+        322,
+        2773,
+        369,
+        1384,
+        6759,
+        11,
+        322,
+        635,
+        30969,
+        13,
+        50539
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.08272041363662548,
+      "compression_ratio": 1.6818181818181819,
+      "no_speech_prob": 0.01115426979959011,
+      "confidence": 0.94,
+      "words": [
+        {
+          "text": "Le",
+          "start": 123.38,
+          "end": 123.96,
+          "confidence": 0.645
+        },
+        {
+          "text": "soir,",
+          "start": 123.96,
+          "end": 124.54,
+          "confidence": 0.998
+        },
+        {
+          "text": "quand",
+          "start": 124.74,
+          "end": 124.94,
+          "confidence": 0.982
+        },
+        {
+          "text": "on",
+          "start": 124.94,
+          "end": 125.06,
+          "confidence": 0.996
+        },
+        {
+          "text": "va",
+          "start": 125.06,
+          "end": 125.16,
+          "confidence": 0.99
+        },
+        {
+          "text": "se",
+          "start": 125.16,
+          "end": 125.26,
+          "confidence": 0.989
+        },
+        {
+          "text": "coucher,",
+          "start": 125.26,
+          "end": 125.7,
+          "confidence": 0.989
+        },
+        {
+          "text": "on",
+          "start": 125.94,
+          "end": 126.04,
+          "confidence": 0.992
+        },
+        {
+          "text": "la",
+          "start": 126.04,
+          "end": 126.18,
+          "confidence": 0.852
+        },
+        {
+          "text": "laisse.",
+          "start": 126.18,
+          "end": 126.44,
+          "confidence": 0.999
+        }
+      ]
+    },
+    {
+      "id": 27,
+      "seek": 12334,
+      "start": 127.0,
+      "end": 130.3,
+      "text": " On ne l'a pas dans la main quand on est au lit, on ne l'emmène pas au chiottes.",
+      "tokens": [
+        50539,
+        1282,
+        408,
+        287,
+        6,
+        64,
+        1736,
+        2680,
+        635,
+        2135,
+        6932,
+        322,
+        871,
+        1609,
+        7997,
+        11,
+        322,
+        408,
+        287,
+        6,
+        443,
+        76,
+        18832,
+        1736,
+        1609,
+        13228,
+        1521,
+        279,
+        13,
+        50739
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.08272041363662548,
+      "compression_ratio": 1.6818181818181819,
+      "no_speech_prob": 0.01115426979959011,
+      "confidence": 0.918,
+      "words": [
+        {
+          "text": "On",
+          "start": 127.0,
+          "end": 127.34,
+          "confidence": 0.967
+        },
+        {
+          "text": "ne",
+          "start": 127.34,
+          "end": 127.46,
+          "confidence": 0.801
+        },
+        {
+          "text": "l'a",
+          "start": 127.46,
+          "end": 127.56,
+          "confidence": 0.929
+        },
+        {
+          "text": "pas",
+          "start": 127.56,
+          "end": 127.68,
+          "confidence": 0.999
+        },
+        {
+          "text": "dans",
+          "start": 127.68,
+          "end": 127.86,
+          "confidence": 0.992
+        },
+        {
+          "text": "la",
+          "start": 127.86,
+          "end": 128.08,
+          "confidence": 0.996
+        },
+        {
+          "text": "main",
+          "start": 128.08,
+          "end": 128.26,
+          "confidence": 0.999
+        },
+        {
+          "text": "quand",
+          "start": 128.26,
+          "end": 128.48,
+          "confidence": 0.936
+        },
+        {
+          "text": "on",
+          "start": 128.48,
+          "end": 128.6,
+          "confidence": 0.993
+        },
+        {
+          "text": "est",
+          "start": 128.6,
+          "end": 128.74,
+          "confidence": 0.992
+        },
+        {
+          "text": "au",
+          "start": 128.74,
+          "end": 128.94,
+          "confidence": 0.976
+        },
+        {
+          "text": "lit,",
+          "start": 128.94,
+          "end": 129.1,
+          "confidence": 0.999
+        },
+        {
+          "text": "on",
+          "start": 129.16,
+          "end": 129.28,
+          "confidence": 0.43
+        },
+        {
+          "text": "ne",
+          "start": 129.28,
+          "end": 129.3,
+          "confidence": 0.949
+        },
+        {
+          "text": "l'emmène",
+          "start": 129.3,
+          "end": 129.58,
+          "confidence": 0.993
+        },
+        {
+          "text": "pas",
+          "start": 129.58,
+          "end": 129.7,
+          "confidence": 0.997
+        },
+        {
+          "text": "au",
+          "start": 129.7,
+          "end": 129.88,
+          "confidence": 0.72
+        },
+        {
+          "text": "chiottes.",
+          "start": 129.88,
+          "end": 130.3,
+          "confidence": 0.886
+        }
+      ]
+    },
+    {
+      "id": 28,
+      "seek": 12334,
+      "start": 130.84,
+      "end": 136.88,
+      "text": " On pouvait être énervé par son môme qui occupait la ligne de téléphone pendant une heure chaque soir pour discuter avec un copain.",
+      "tokens": [
+        50739,
+        1282,
+        45913,
+        7418,
+        45045,
+        15797,
+        971,
+        1872,
+        275,
+        2851,
+        1398,
+        1956,
+        8073,
+        1001,
+        635,
+        34207,
+        368,
+        47159,
+        17338,
+        2251,
+        30027,
+        18920,
+        27105,
+        2016,
+        2983,
+        20314,
+        4163,
+        517,
+        2971,
+        491,
+        13,
+        51039
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.08272041363662548,
+      "compression_ratio": 1.6818181818181819,
+      "no_speech_prob": 0.01115426979959011,
+      "confidence": 0.925,
+      "words": [
+        {
+          "text": "On",
+          "start": 130.84,
+          "end": 131.06,
+          "confidence": 0.996
+        },
+        {
+          "text": "pouvait",
+          "start": 131.06,
+          "end": 131.26,
+          "confidence": 0.989
+        },
+        {
+          "text": "être",
+          "start": 131.26,
+          "end": 131.58,
+          "confidence": 0.995
+        },
+        {
+          "text": "énervé",
+          "start": 131.58,
+          "end": 132.22,
+          "confidence": 0.896
+        },
+        {
+          "text": "par",
+          "start": 132.22,
+          "end": 132.46,
+          "confidence": 0.992
+        },
+        {
+          "text": "son",
+          "start": 132.46,
+          "end": 132.72,
+          "confidence": 0.998
+        },
+        {
+          "text": "môme",
+          "start": 132.72,
+          "end": 133.08,
+          "confidence": 0.758
+        },
+        {
+          "text": "qui",
+          "start": 133.08,
+          "end": 133.34,
+          "confidence": 0.916
+        },
+        {
+          "text": "occupait",
+          "start": 133.34,
+          "end": 133.74,
+          "confidence": 0.992
+        },
+        {
+          "text": "la",
+          "start": 133.74,
+          "end": 133.86,
+          "confidence": 0.986
+        },
+        {
+          "text": "ligne",
+          "start": 133.86,
+          "end": 134.06,
+          "confidence": 0.999
+        },
+        {
+          "text": "de",
+          "start": 134.06,
+          "end": 134.22,
+          "confidence": 0.995
+        },
+        {
+          "text": "téléphone",
+          "start": 134.22,
+          "end": 134.6,
+          "confidence": 0.992
+        },
+        {
+          "text": "pendant",
+          "start": 134.6,
+          "end": 134.92,
+          "confidence": 0.709
+        },
+        {
+          "text": "une",
+          "start": 134.92,
+          "end": 135.16,
+          "confidence": 0.78
+        },
+        {
+          "text": "heure",
+          "start": 135.16,
+          "end": 135.34,
+          "confidence": 0.995
+        },
+        {
+          "text": "chaque",
+          "start": 135.34,
+          "end": 135.58,
+          "confidence": 0.982
+        },
+        {
+          "text": "soir",
+          "start": 135.58,
+          "end": 135.8,
+          "confidence": 0.995
+        },
+        {
+          "text": "pour",
+          "start": 135.8,
+          "end": 135.98,
+          "confidence": 0.66
+        },
+        {
+          "text": "discuter",
+          "start": 135.98,
+          "end": 136.3,
+          "confidence": 0.997
+        },
+        {
+          "text": "avec",
+          "start": 136.3,
+          "end": 136.5,
+          "confidence": 0.995
+        },
+        {
+          "text": "un",
+          "start": 136.5,
+          "end": 136.66,
+          "confidence": 0.997
+        },
+        {
+          "text": "copain.",
+          "start": 136.66,
+          "end": 136.88,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 29,
+      "seek": 12334,
+      "start": 137.26,
+      "end": 141.86,
+      "text": " Mais ça ne ressemblait pas à ce qu'on peut ressentir à voir ce même môme aujourd'hui,",
+      "tokens": [
+        51039,
+        6313,
+        2788,
+        408,
+        725,
+        15750,
+        35235,
+        1736,
+        1531,
+        1769,
+        421,
+        6,
+        266,
+        5977,
+        24689,
+        317,
+        347,
+        1531,
+        10695,
+        1769,
+        5698,
+        275,
+        2851,
+        1398,
+        14023,
+        6,
+        10556,
+        11,
+        51289
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.08272041363662548,
+      "compression_ratio": 1.6818181818181819,
+      "no_speech_prob": 0.01115426979959011,
+      "confidence": 0.956,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 137.26,
+          "end": 137.5,
+          "confidence": 0.989
+        },
+        {
+          "text": "ça",
+          "start": 137.5,
+          "end": 137.68,
+          "confidence": 0.928
+        },
+        {
+          "text": "ne",
+          "start": 137.68,
+          "end": 137.88,
+          "confidence": 0.999
+        },
+        {
+          "text": "ressemblait",
+          "start": 137.88,
+          "end": 138.42,
+          "confidence": 0.993
+        },
+        {
+          "text": "pas",
+          "start": 138.42,
+          "end": 138.78,
+          "confidence": 0.994
+        },
+        {
+          "text": "à",
+          "start": 138.78,
+          "end": 138.9,
+          "confidence": 0.989
+        },
+        {
+          "text": "ce",
+          "start": 138.9,
+          "end": 138.98,
+          "confidence": 0.998
+        },
+        {
+          "text": "qu'on",
+          "start": 138.98,
+          "end": 139.12,
+          "confidence": 0.976
+        },
+        {
+          "text": "peut",
+          "start": 139.12,
+          "end": 139.48,
+          "confidence": 0.979
+        },
+        {
+          "text": "ressentir",
+          "start": 139.48,
+          "end": 140.1,
+          "confidence": 0.996
+        },
+        {
+          "text": "à",
+          "start": 140.1,
+          "end": 140.32,
+          "confidence": 0.575
+        },
+        {
+          "text": "voir",
+          "start": 140.32,
+          "end": 140.46,
+          "confidence": 0.728
+        },
+        {
+          "text": "ce",
+          "start": 140.46,
+          "end": 140.7,
+          "confidence": 0.985
+        },
+        {
+          "text": "même",
+          "start": 140.7,
+          "end": 140.94,
+          "confidence": 0.982
+        },
+        {
+          "text": "môme",
+          "start": 140.94,
+          "end": 141.28,
+          "confidence": 0.997
+        },
+        {
+          "text": "aujourd'hui,",
+          "start": 141.28,
+          "end": 141.86,
+          "confidence": 0.994
+        }
+      ]
+    },
+    {
+      "id": 30,
+      "seek": 12334,
+      "start": 142.16,
+      "end": 144.22,
+      "text": " continuellement avec son smartphone dans la main,",
+      "tokens": [
+        51289,
+        2354,
+        285,
+        1712,
+        4163,
+        1872,
+        13307,
+        2680,
+        635,
+        2135,
+        11,
+        51414
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.08272041363662548,
+      "compression_ratio": 1.6818181818181819,
+      "no_speech_prob": 0.01115426979959011,
+      "confidence": 0.961,
+      "words": [
+        {
+          "text": "continuellement",
+          "start": 142.16,
+          "end": 142.94,
+          "confidence": 0.963
+        },
+        {
+          "text": "avec",
+          "start": 142.94,
+          "end": 143.2,
+          "confidence": 0.844
+        },
+        {
+          "text": "son",
+          "start": 143.2,
+          "end": 143.42,
+          "confidence": 0.994
+        },
+        {
+          "text": "smartphone",
+          "start": 143.42,
+          "end": 143.76,
+          "confidence": 0.972
+        },
+        {
+          "text": "dans",
+          "start": 143.76,
+          "end": 143.92,
+          "confidence": 0.963
+        },
+        {
+          "text": "la",
+          "start": 143.92,
+          "end": 144.02,
+          "confidence": 0.997
+        },
+        {
+          "text": "main,",
+          "start": 144.02,
+          "end": 144.22,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 31,
+      "seek": 12334,
+      "start": 144.34,
+      "end": 148.8,
+      "text": " comme si c'était une sorte de pacemaker externe, comme si le lâcher allait entraîner sa mort immédiate.",
+      "tokens": [
+        51414,
+        5173,
+        1511,
+        269,
+        6,
+        9743,
+        2251,
+        25559,
+        368,
+        15165,
+        49523,
+        454,
+        391,
+        716,
+        11,
+        5173,
+        1511,
+        476,
+        48835,
+        6759,
+        439,
+        1001,
+        22284,
+        7517,
+        1193,
+        601,
+        6599,
+        3397,
+        526,
+        4504,
+        473,
+        13,
+        51639
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.08272041363662548,
+      "compression_ratio": 1.6818181818181819,
+      "no_speech_prob": 0.01115426979959011,
+      "confidence": 0.973,
+      "words": [
+        {
+          "text": "comme",
+          "start": 144.34,
+          "end": 144.56,
+          "confidence": 0.985
+        },
+        {
+          "text": "si",
+          "start": 144.56,
+          "end": 144.66,
+          "confidence": 0.971
+        },
+        {
+          "text": "c'était",
+          "start": 144.66,
+          "end": 144.86,
+          "confidence": 0.987
+        },
+        {
+          "text": "une",
+          "start": 144.86,
+          "end": 144.98,
+          "confidence": 0.983
+        },
+        {
+          "text": "sorte",
+          "start": 144.98,
+          "end": 145.14,
+          "confidence": 0.992
+        },
+        {
+          "text": "de",
+          "start": 145.14,
+          "end": 145.34,
+          "confidence": 0.989
+        },
+        {
+          "text": "pacemaker",
+          "start": 145.34,
+          "end": 145.82,
+          "confidence": 0.931
+        },
+        {
+          "text": "externe,",
+          "start": 145.82,
+          "end": 146.4,
+          "confidence": 0.99
+        },
+        {
+          "text": "comme",
+          "start": 146.44,
+          "end": 146.6,
+          "confidence": 0.721
+        },
+        {
+          "text": "si",
+          "start": 146.6,
+          "end": 146.74,
+          "confidence": 0.993
+        },
+        {
+          "text": "le",
+          "start": 146.74,
+          "end": 147.0,
+          "confidence": 0.996
+        },
+        {
+          "text": "lâcher",
+          "start": 147.0,
+          "end": 147.36,
+          "confidence": 0.968
+        },
+        {
+          "text": "allait",
+          "start": 147.36,
+          "end": 147.58,
+          "confidence": 0.991
+        },
+        {
+          "text": "entraîner",
+          "start": 147.58,
+          "end": 147.88,
+          "confidence": 0.982
+        },
+        {
+          "text": "sa",
+          "start": 147.88,
+          "end": 148.02,
+          "confidence": 0.999
+        },
+        {
+          "text": "mort",
+          "start": 148.02,
+          "end": 148.3,
+          "confidence": 0.998
+        },
+        {
+          "text": "immédiate.",
+          "start": 148.3,
+          "end": 148.8,
+          "confidence": 0.998
+        }
+      ]
+    },
+    {
+      "id": 32,
+      "seek": 12334,
+      "start": 148.94,
+      "end": 152.02,
+      "text": " Bon, je dis ça pour le môme, mais c'est évidemment valable pour nous aussi.",
+      "tokens": [
+        51639,
+        7368,
+        11,
+        1506,
+        717,
+        2788,
+        2016,
+        476,
+        275,
+        2851,
+        1398,
+        11,
+        2420,
+        269,
+        6,
+        377,
+        24724,
+        1323,
+        712,
+        2016,
+        4666,
+        6212,
+        13,
+        51839
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.08272041363662548,
+      "compression_ratio": 1.6818181818181819,
+      "no_speech_prob": 0.01115426979959011,
+      "confidence": 0.973,
+      "words": [
+        {
+          "text": "Bon,",
+          "start": 148.94,
+          "end": 149.24,
+          "confidence": 0.804
+        },
+        {
+          "text": "je",
+          "start": 149.26,
+          "end": 149.34,
+          "confidence": 0.933
+        },
+        {
+          "text": "dis",
+          "start": 149.34,
+          "end": 149.46,
+          "confidence": 0.982
+        },
+        {
+          "text": "ça",
+          "start": 149.46,
+          "end": 149.64,
+          "confidence": 0.992
+        },
+        {
+          "text": "pour",
+          "start": 149.64,
+          "end": 149.78,
+          "confidence": 0.997
+        },
+        {
+          "text": "le",
+          "start": 149.78,
+          "end": 149.9,
+          "confidence": 0.994
+        },
+        {
+          "text": "môme,",
+          "start": 149.9,
+          "end": 150.1,
+          "confidence": 0.999
+        },
+        {
+          "text": "mais",
+          "start": 150.32,
+          "end": 150.5,
+          "confidence": 0.904
+        },
+        {
+          "text": "c'est",
+          "start": 150.5,
+          "end": 150.84,
+          "confidence": 0.979
+        },
+        {
+          "text": "évidemment",
+          "start": 150.84,
+          "end": 151.18,
+          "confidence": 0.979
+        },
+        {
+          "text": "valable",
+          "start": 151.18,
+          "end": 151.48,
+          "confidence": 0.997
+        },
+        {
+          "text": "pour",
+          "start": 151.48,
+          "end": 151.64,
+          "confidence": 0.996
+        },
+        {
+          "text": "nous",
+          "start": 151.64,
+          "end": 151.78,
+          "confidence": 0.998
+        },
+        {
+          "text": "aussi.",
+          "start": 151.78,
+          "end": 152.02,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 33,
+      "seek": 15284,
+      "start": 153.14,
+      "end": 154.68,
+      "text": " Donc, rapport inédit, d'accord.",
+      "tokens": [
+        50389,
+        7477,
+        11,
+        18018,
+        294,
+        7811,
+        270,
+        11,
+        274,
+        6,
+        19947,
+        13,
+        50489
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12394786888444928,
+      "compression_ratio": 1.6703296703296704,
+      "no_speech_prob": 0.07031125575304031,
+      "confidence": 0.813,
+      "words": [
+        {
+          "text": "Donc,",
+          "start": 153.14,
+          "end": 153.24,
+          "confidence": 0.232
+        },
+        {
+          "text": "rapport",
+          "start": 153.26,
+          "end": 153.62,
+          "confidence": 0.855
+        },
+        {
+          "text": "inédit,",
+          "start": 153.62,
+          "end": 154.18,
+          "confidence": 0.992
+        },
+        {
+          "text": "d'accord.",
+          "start": 154.28,
+          "end": 154.68,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 34,
+      "seek": 15284,
+      "start": 155.64,
+      "end": 158.52,
+      "text": " Mais pourquoi a-t-on l'impression qu'on n'en sortira jamais ?",
+      "tokens": [
+        50489,
+        6313,
+        19934,
+        257,
+        12,
+        83,
+        12,
+        266,
+        287,
+        6,
+        36107,
+        421,
+        6,
+        266,
+        297,
+        6,
+        268,
+        1333,
+        4271,
+        14540,
+        2506,
+        50639
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12394786888444928,
+      "compression_ratio": 1.6703296703296704,
+      "no_speech_prob": 0.07031125575304031,
+      "confidence": 0.958,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 155.64,
+          "end": 155.88,
+          "confidence": 0.991
+        },
+        {
+          "text": "pourquoi",
+          "start": 155.88,
+          "end": 156.36,
+          "confidence": 0.992
+        },
+        {
+          "text": "a-t-on",
+          "start": 156.36,
+          "end": 156.7,
+          "confidence": 0.95
+        },
+        {
+          "text": "l'impression",
+          "start": 156.7,
+          "end": 157.06,
+          "confidence": 0.998
+        },
+        {
+          "text": "qu'on",
+          "start": 157.06,
+          "end": 157.28,
+          "confidence": 0.99
+        },
+        {
+          "text": "n'en",
+          "start": 157.28,
+          "end": 157.5,
+          "confidence": 0.859
+        },
+        {
+          "text": "sortira",
+          "start": 157.5,
+          "end": 157.86,
+          "confidence": 0.974
+        },
+        {
+          "text": "jamais ?",
+          "start": 157.86,
+          "end": 158.52,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 35,
+      "seek": 15284,
+      "start": 159.12,
+      "end": 165.36,
+      "text": " Est-ce qu'il faut en remettre la faute sur les gens qui ont créé cet outil merveilleux et diabolique, et diabolique parce que merveilleux ?",
+      "tokens": [
+        50639,
+        4410,
+        12,
+        384,
+        421,
+        6,
+        388,
+        8487,
+        465,
+        890,
+        40681,
+        635,
+        2050,
+        1169,
+        1022,
+        1512,
+        10668,
+        1956,
+        6592,
+        15609,
+        526,
+        8603,
+        484,
+        388,
+        3551,
+        303,
+        3409,
+        2449,
+        1030,
+        1026,
+        14923,
+        1925,
+        11,
+        1030,
+        1026,
+        14923,
+        1925,
+        6992,
+        631,
+        3551,
+        303,
+        3409,
+        2449,
+        2506,
+        50989
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12394786888444928,
+      "compression_ratio": 1.6703296703296704,
+      "no_speech_prob": 0.07031125575304031,
+      "confidence": 0.959,
+      "words": [
+        {
+          "text": "Est-ce",
+          "start": 159.12,
+          "end": 159.34,
+          "confidence": 0.987
+        },
+        {
+          "text": "qu'il",
+          "start": 159.34,
+          "end": 159.46,
+          "confidence": 0.993
+        },
+        {
+          "text": "faut",
+          "start": 159.46,
+          "end": 159.64,
+          "confidence": 0.998
+        },
+        {
+          "text": "en",
+          "start": 159.64,
+          "end": 159.88,
+          "confidence": 0.961
+        },
+        {
+          "text": "remettre",
+          "start": 159.88,
+          "end": 160.14,
+          "confidence": 0.999
+        },
+        {
+          "text": "la",
+          "start": 160.14,
+          "end": 160.46,
+          "confidence": 0.995
+        },
+        {
+          "text": "faute",
+          "start": 160.46,
+          "end": 160.64,
+          "confidence": 0.986
+        },
+        {
+          "text": "sur",
+          "start": 160.64,
+          "end": 161.06,
+          "confidence": 0.982
+        },
+        {
+          "text": "les",
+          "start": 161.06,
+          "end": 161.3,
+          "confidence": 0.991
+        },
+        {
+          "text": "gens",
+          "start": 161.3,
+          "end": 161.46,
+          "confidence": 0.998
+        },
+        {
+          "text": "qui",
+          "start": 161.46,
+          "end": 161.56,
+          "confidence": 0.724
+        },
+        {
+          "text": "ont",
+          "start": 161.56,
+          "end": 161.82,
+          "confidence": 0.996
+        },
+        {
+          "text": "créé",
+          "start": 161.82,
+          "end": 162.28,
+          "confidence": 0.985
+        },
+        {
+          "text": "cet",
+          "start": 162.28,
+          "end": 162.48,
+          "confidence": 0.816
+        },
+        {
+          "text": "outil",
+          "start": 162.48,
+          "end": 162.78,
+          "confidence": 0.993
+        },
+        {
+          "text": "merveilleux",
+          "start": 162.78,
+          "end": 163.36,
+          "confidence": 0.981
+        },
+        {
+          "text": "et",
+          "start": 163.36,
+          "end": 163.5,
+          "confidence": 0.983
+        },
+        {
+          "text": "diabolique,",
+          "start": 163.5,
+          "end": 163.84,
+          "confidence": 0.991
+        },
+        {
+          "text": "et",
+          "start": 163.86,
+          "end": 164.0,
+          "confidence": 0.555
+        },
+        {
+          "text": "diabolique",
+          "start": 164.0,
+          "end": 164.4,
+          "confidence": 0.949
+        },
+        {
+          "text": "parce",
+          "start": 164.4,
+          "end": 164.66,
+          "confidence": 0.927
+        },
+        {
+          "text": "que",
+          "start": 164.66,
+          "end": 164.86,
+          "confidence": 0.979
+        },
+        {
+          "text": "merveilleux ?",
+          "start": 164.86,
+          "end": 165.36,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 36,
+      "seek": 15284,
+      "start": 166.84,
+      "end": 168.82,
+      "text": " Les économistes parlent de dépendance du sentier.",
+      "tokens": [
+        51039,
+        6965,
+        31171,
+        22368,
+        13734,
+        317,
+        368,
+        45768,
+        719,
+        1581,
+        2279,
+        811,
+        13,
+        51139
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12394786888444928,
+      "compression_ratio": 1.6703296703296704,
+      "no_speech_prob": 0.07031125575304031,
+      "confidence": 0.986,
+      "words": [
+        {
+          "text": "Les",
+          "start": 166.84,
+          "end": 167.08,
+          "confidence": 0.945
+        },
+        {
+          "text": "économistes",
+          "start": 167.08,
+          "end": 167.46,
+          "confidence": 0.997
+        },
+        {
+          "text": "parlent",
+          "start": 167.46,
+          "end": 167.72,
+          "confidence": 0.993
+        },
+        {
+          "text": "de",
+          "start": 167.72,
+          "end": 167.88,
+          "confidence": 0.992
+        },
+        {
+          "text": "dépendance",
+          "start": 167.88,
+          "end": 168.34,
+          "confidence": 0.986
+        },
+        {
+          "text": "du",
+          "start": 168.34,
+          "end": 168.52,
+          "confidence": 0.996
+        },
+        {
+          "text": "sentier.",
+          "start": 168.52,
+          "end": 168.82,
+          "confidence": 0.983
+        }
+      ]
+    },
+    {
+      "id": 37,
+      "seek": 15284,
+      "start": 168.98,
+      "end": 177.38,
+      "text": " C'est l'idée qu'on met sur un sentier qui a été établi, soit volontairement en marchant dessus, soit en définissant des bornes, en définissant une signalétique.",
+      "tokens": [
+        51139,
+        383,
+        6,
+        377,
+        287,
+        6,
+        34281,
+        421,
+        6,
+        266,
+        1131,
+        1022,
+        517,
+        2279,
+        811,
+        1956,
+        257,
+        8862,
+        4823,
+        455,
+        2081,
+        11,
+        12703,
+        40005,
+        9020,
+        518,
+        465,
+        8368,
+        394,
+        30677,
+        11,
+        12703,
+        465,
+        40763,
+        29492,
+        730,
+        4232,
+        279,
+        11,
+        465,
+        40763,
+        29492,
+        2251,
+        6358,
+        42379,
+        13,
+        51589
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.12394786888444928,
+      "compression_ratio": 1.6703296703296704,
+      "no_speech_prob": 0.07031125575304031,
+      "confidence": 0.907,
+      "words": [
+        {
+          "text": "C'est",
+          "start": 168.98,
+          "end": 169.2,
+          "confidence": 0.996
+        },
+        {
+          "text": "l'idée",
+          "start": 169.2,
+          "end": 169.38,
+          "confidence": 0.998
+        },
+        {
+          "text": "qu'on",
+          "start": 169.38,
+          "end": 169.74,
+          "confidence": 0.7
+        },
+        {
+          "text": "met",
+          "start": 169.74,
+          "end": 169.88,
+          "confidence": 0.648
+        },
+        {
+          "text": "sur",
+          "start": 169.88,
+          "end": 170.1,
+          "confidence": 0.995
+        },
+        {
+          "text": "un",
+          "start": 170.1,
+          "end": 170.52,
+          "confidence": 0.997
+        },
+        {
+          "text": "sentier",
+          "start": 170.52,
+          "end": 170.84,
+          "confidence": 0.991
+        },
+        {
+          "text": "qui",
+          "start": 170.84,
+          "end": 170.9,
+          "confidence": 0.955
+        },
+        {
+          "text": "a",
+          "start": 170.9,
+          "end": 171.0,
+          "confidence": 0.969
+        },
+        {
+          "text": "été",
+          "start": 171.0,
+          "end": 171.14,
+          "confidence": 0.994
+        },
+        {
+          "text": "établi,",
+          "start": 171.14,
+          "end": 171.5,
+          "confidence": 0.995
+        },
+        {
+          "text": "soit",
+          "start": 171.76,
+          "end": 172.1,
+          "confidence": 0.527
+        },
+        {
+          "text": "volontairement",
+          "start": 172.1,
+          "end": 172.7,
+          "confidence": 0.987
+        },
+        {
+          "text": "en",
+          "start": 172.7,
+          "end": 172.86,
+          "confidence": 0.927
+        },
+        {
+          "text": "marchant",
+          "start": 172.86,
+          "end": 173.1,
+          "confidence": 0.997
+        },
+        {
+          "text": "dessus,",
+          "start": 173.1,
+          "end": 173.48,
+          "confidence": 0.995
+        },
+        {
+          "text": "soit",
+          "start": 173.86,
+          "end": 174.28,
+          "confidence": 0.749
+        },
+        {
+          "text": "en",
+          "start": 174.28,
+          "end": 175.16,
+          "confidence": 0.967
+        },
+        {
+          "text": "définissant",
+          "start": 175.16,
+          "end": 175.54,
+          "confidence": 0.981
+        },
+        {
+          "text": "des",
+          "start": 175.54,
+          "end": 175.74,
+          "confidence": 0.99
+        },
+        {
+          "text": "bornes,",
+          "start": 175.74,
+          "end": 175.98,
+          "confidence": 0.977
+        },
+        {
+          "text": "en",
+          "start": 176.04,
+          "end": 176.14,
+          "confidence": 0.673
+        },
+        {
+          "text": "définissant",
+          "start": 176.14,
+          "end": 176.66,
+          "confidence": 0.996
+        },
+        {
+          "text": "une",
+          "start": 176.66,
+          "end": 176.94,
+          "confidence": 0.983
+        },
+        {
+          "text": "signalétique.",
+          "start": 176.94,
+          "end": 177.38,
+          "confidence": 0.686
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/naive.cpu/accurate_apollo11.mp3.words.json b/tests/expected/naive.cpu/accurate_apollo11.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..960a425ed608e1568f8c2f523148e8ea33ebb33c
--- /dev/null
+++ b/tests/expected/naive.cpu/accurate_apollo11.mp3.words.json
@@ -0,0 +1,2375 @@
+{
+  "text": " Apollo 11, Houston, we got a recommendation for you on your Soyuz-EA GLEM-E-G-E-A. All right. Okay. Yeah, sir. Yeah, sir. Let's take that camera. Let's say it makes it want to go on the helmet we were going to have in B-1. The other one. And you can put the other one on the mic helmet. We'll show it to you in a quick screen. Over. All right. Yeah, sir. All right. Yeah, sir. There's a better helmet than B-1. That's the other one. Nice. Let's go in there. At least we're safe. We've got them in there. Helmet bags. And, uh, I guess we have helmets in the helmet bag. At least it's in the helmet bag. Right here. Right here. Yeah, we're taking it next day out of the field up. Hey, we were... You want to hack me on this? Hey, we were... You want to hack me on this? With a cover, I tried it already. Okay, fine. We weren't sure of that. Just a suggestion. We thought we'd... You could check it out. It's not much of an order to turn that. So, uh, I guess we're going to come up with this. Let us know. Okay. No problem. Okay. No problem. We'll let you know when the end of... None. Okay.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.64,
+      "end": 6.78,
+      "text": " Apollo 11, Houston, we got a recommendation for you on your Soyuz-EA GLEM-E-G-E-A.",
+      "tokens": [
+        25187,
+        2975,
+        11,
+        18717,
+        11,
+        321,
+        658,
+        257,
+        11879,
+        337,
+        291,
+        322,
+        428,
+        24758,
+        3334,
+        12,
+        36,
+        32,
+        460,
+        2634,
+        44,
+        12,
+        36,
+        12,
+        38,
+        12,
+        36,
+        12,
+        32,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5336953440020161,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.45046156644821167,
+      "confidence": 0.578,
+      "words": [
+        {
+          "text": "Apollo",
+          "start": 0.64,
+          "end": 0.98,
+          "confidence": 0.426
+        },
+        {
+          "text": "11,",
+          "start": 0.98,
+          "end": 1.54,
+          "confidence": 0.842
+        },
+        {
+          "text": "Houston,",
+          "start": 1.54,
+          "end": 1.96,
+          "confidence": 0.666
+        },
+        {
+          "text": "we",
+          "start": 1.96,
+          "end": 2.0,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 2.0,
+          "end": 2.16,
+          "confidence": 0.742
+        },
+        {
+          "text": "a",
+          "start": 2.16,
+          "end": 2.38,
+          "confidence": 0.993
+        },
+        {
+          "text": "recommendation",
+          "start": 2.38,
+          "end": 3.1,
+          "confidence": 0.977
+        },
+        {
+          "text": "for",
+          "start": 3.1,
+          "end": 3.54,
+          "confidence": 0.94
+        },
+        {
+          "text": "you",
+          "start": 3.54,
+          "end": 3.88,
+          "confidence": 0.993
+        },
+        {
+          "text": "on",
+          "start": 3.88,
+          "end": 4.26,
+          "confidence": 0.918
+        },
+        {
+          "text": "your",
+          "start": 4.26,
+          "end": 4.3,
+          "confidence": 0.976
+        },
+        {
+          "text": "Soyuz-EA",
+          "start": 4.3,
+          "end": 5.38,
+          "confidence": 0.453
+        },
+        {
+          "text": "GLEM-E-G-E-A.",
+          "start": 5.38,
+          "end": 6.78,
+          "confidence": 0.436
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 7.78,
+      "end": 10.46,
+      "text": " All right.",
+      "tokens": [
+        1057,
+        558,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5336953440020161,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.45046156644821167,
+      "confidence": 0.158,
+      "words": [
+        {
+          "text": "All",
+          "start": 7.78,
+          "end": 7.82,
+          "confidence": 0.007
+        },
+        {
+          "text": "right.",
+          "start": 7.82,
+          "end": 10.46,
+          "confidence": 0.727
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 10.82,
+      "end": 11.38,
+      "text": " Okay.",
+      "tokens": [
+        1033,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5336953440020161,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.45046156644821167,
+      "confidence": 0.105,
+      "words": [
+        {
+          "text": "Okay.",
+          "start": 10.82,
+          "end": 11.38,
+          "confidence": 0.105
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 12.02,
+      "end": 13.44,
+      "text": " Yeah, sir.",
+      "tokens": [
+        865,
+        11,
+        4735,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5336953440020161,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.45046156644821167,
+      "confidence": 0.101,
+      "words": [
+        {
+          "text": "Yeah,",
+          "start": 12.02,
+          "end": 12.76,
+          "confidence": 0.076
+        },
+        {
+          "text": "sir.",
+          "start": 12.76,
+          "end": 13.44,
+          "confidence": 0.135
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 13.58,
+      "end": 14.02,
+      "text": " Yeah, sir.",
+      "tokens": [
+        865,
+        11,
+        4735,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5336953440020161,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.45046156644821167,
+      "confidence": 0.052,
+      "words": [
+        {
+          "text": "Yeah,",
+          "start": 13.58,
+          "end": 13.84,
+          "confidence": 0.108
+        },
+        {
+          "text": "sir.",
+          "start": 13.84,
+          "end": 14.02,
+          "confidence": 0.025
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 0,
+      "start": 14.04,
+      "end": 14.6,
+      "text": " Let's take that camera.",
+      "tokens": [
+        961,
+        311,
+        747,
+        300,
+        2799,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5336953440020161,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.45046156644821167,
+      "confidence": 0.082,
+      "words": [
+        {
+          "text": "Let's",
+          "start": 14.04,
+          "end": 14.26,
+          "confidence": 0.043
+        },
+        {
+          "text": "take",
+          "start": 14.26,
+          "end": 14.3,
+          "confidence": 0.04
+        },
+        {
+          "text": "that",
+          "start": 14.3,
+          "end": 14.36,
+          "confidence": 0.055
+        },
+        {
+          "text": "camera.",
+          "start": 14.36,
+          "end": 14.6,
+          "confidence": 0.269
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 0,
+      "start": 14.62,
+      "end": 19.16,
+      "text": " Let's say it makes it want to go on the helmet we were going to have in B-1.",
+      "tokens": [
+        961,
+        311,
+        584,
+        309,
+        1669,
+        309,
+        528,
+        281,
+        352,
+        322,
+        264,
+        15922,
+        321,
+        645,
+        516,
+        281,
+        362,
+        294,
+        363,
+        12,
+        16,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5336953440020161,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.45046156644821167,
+      "confidence": 0.311,
+      "words": [
+        {
+          "text": "Let's",
+          "start": 14.62,
+          "end": 15.34,
+          "confidence": 0.181
+        },
+        {
+          "text": "say",
+          "start": 15.34,
+          "end": 15.56,
+          "confidence": 0.451
+        },
+        {
+          "text": "it",
+          "start": 15.56,
+          "end": 15.76,
+          "confidence": 0.043
+        },
+        {
+          "text": "makes",
+          "start": 15.76,
+          "end": 15.8,
+          "confidence": 0.62
+        },
+        {
+          "text": "it",
+          "start": 15.8,
+          "end": 16.04,
+          "confidence": 0.943
+        },
+        {
+          "text": "want",
+          "start": 16.04,
+          "end": 16.22,
+          "confidence": 0.118
+        },
+        {
+          "text": "to",
+          "start": 16.22,
+          "end": 16.34,
+          "confidence": 0.953
+        },
+        {
+          "text": "go",
+          "start": 16.34,
+          "end": 16.46,
+          "confidence": 0.775
+        },
+        {
+          "text": "on",
+          "start": 16.46,
+          "end": 16.74,
+          "confidence": 0.939
+        },
+        {
+          "text": "the",
+          "start": 16.74,
+          "end": 16.88,
+          "confidence": 0.532
+        },
+        {
+          "text": "helmet",
+          "start": 16.88,
+          "end": 17.36,
+          "confidence": 0.003
+        },
+        {
+          "text": "we",
+          "start": 17.36,
+          "end": 17.64,
+          "confidence": 0.018
+        },
+        {
+          "text": "were",
+          "start": 17.64,
+          "end": 17.86,
+          "confidence": 0.255
+        },
+        {
+          "text": "going",
+          "start": 17.86,
+          "end": 18.06,
+          "confidence": 0.654
+        },
+        {
+          "text": "to",
+          "start": 18.06,
+          "end": 18.26,
+          "confidence": 0.966
+        },
+        {
+          "text": "have",
+          "start": 18.26,
+          "end": 18.3,
+          "confidence": 0.967
+        },
+        {
+          "text": "in",
+          "start": 18.3,
+          "end": 18.46,
+          "confidence": 0.899
+        },
+        {
+          "text": "B-1.",
+          "start": 18.46,
+          "end": 19.16,
+          "confidence": 0.489
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 0,
+      "start": 19.4,
+      "end": 19.94,
+      "text": " The other one.",
+      "tokens": [
+        440,
+        661,
+        472,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5336953440020161,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.45046156644821167,
+      "confidence": 0.127,
+      "words": [
+        {
+          "text": "The",
+          "start": 19.4,
+          "end": 19.44,
+          "confidence": 0.004
+        },
+        {
+          "text": "other",
+          "start": 19.44,
+          "end": 19.7,
+          "confidence": 0.144
+        },
+        {
+          "text": "one.",
+          "start": 19.7,
+          "end": 19.94,
+          "confidence": 0.656
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 0,
+      "start": 20.12,
+      "end": 22.92,
+      "text": " And you can put the other one on the mic helmet.",
+      "tokens": [
+        400,
+        291,
+        393,
+        829,
+        264,
+        661,
+        472,
+        322,
+        264,
+        3123,
+        15922,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5336953440020161,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.45046156644821167,
+      "confidence": 0.394,
+      "words": [
+        {
+          "text": "And",
+          "start": 20.12,
+          "end": 20.26,
+          "confidence": 0.358
+        },
+        {
+          "text": "you",
+          "start": 20.26,
+          "end": 20.38,
+          "confidence": 0.915
+        },
+        {
+          "text": "can",
+          "start": 20.38,
+          "end": 20.54,
+          "confidence": 0.122
+        },
+        {
+          "text": "put",
+          "start": 20.54,
+          "end": 20.7,
+          "confidence": 0.92
+        },
+        {
+          "text": "the",
+          "start": 20.7,
+          "end": 20.88,
+          "confidence": 0.981
+        },
+        {
+          "text": "other",
+          "start": 20.88,
+          "end": 21.06,
+          "confidence": 0.997
+        },
+        {
+          "text": "one",
+          "start": 21.06,
+          "end": 21.26,
+          "confidence": 0.97
+        },
+        {
+          "text": "on",
+          "start": 21.26,
+          "end": 22.14,
+          "confidence": 0.971
+        },
+        {
+          "text": "the",
+          "start": 22.14,
+          "end": 22.18,
+          "confidence": 0.085
+        },
+        {
+          "text": "mic",
+          "start": 22.18,
+          "end": 22.62,
+          "confidence": 0.679
+        },
+        {
+          "text": "helmet.",
+          "start": 22.62,
+          "end": 22.92,
+          "confidence": 0.085
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 0,
+      "start": 22.94,
+      "end": 24.58,
+      "text": " We'll show it to you in a quick screen.",
+      "tokens": [
+        492,
+        603,
+        855,
+        309,
+        281,
+        291,
+        294,
+        257,
+        1702,
+        2568,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5336953440020161,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.45046156644821167,
+      "confidence": 0.124,
+      "words": [
+        {
+          "text": "We'll",
+          "start": 22.94,
+          "end": 23.32,
+          "confidence": 0.098
+        },
+        {
+          "text": "show",
+          "start": 23.32,
+          "end": 23.36,
+          "confidence": 0.008
+        },
+        {
+          "text": "it",
+          "start": 23.36,
+          "end": 23.54,
+          "confidence": 0.167
+        },
+        {
+          "text": "to",
+          "start": 23.54,
+          "end": 23.64,
+          "confidence": 0.268
+        },
+        {
+          "text": "you",
+          "start": 23.64,
+          "end": 23.8,
+          "confidence": 0.656
+        },
+        {
+          "text": "in",
+          "start": 23.8,
+          "end": 23.98,
+          "confidence": 0.246
+        },
+        {
+          "text": "a",
+          "start": 23.98,
+          "end": 24.02,
+          "confidence": 0.683
+        },
+        {
+          "text": "quick",
+          "start": 24.02,
+          "end": 24.14,
+          "confidence": 0.022
+        },
+        {
+          "text": "screen.",
+          "start": 24.14,
+          "end": 24.58,
+          "confidence": 0.114
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 0,
+      "start": 24.94,
+      "end": 25.18,
+      "text": " Over.",
+      "tokens": [
+        4886,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5336953440020161,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.45046156644821167,
+      "confidence": 0.117,
+      "words": [
+        {
+          "text": "Over.",
+          "start": 24.94,
+          "end": 25.18,
+          "confidence": 0.117
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 2600,
+      "start": 25.52,
+      "end": 27.48,
+      "text": " All right.",
+      "tokens": [
+        1057,
+        558,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5317274729410807,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011296384036540985,
+      "confidence": 0.094,
+      "words": [
+        {
+          "text": "All",
+          "start": 25.52,
+          "end": 25.56,
+          "confidence": 0.002
+        },
+        {
+          "text": "right.",
+          "start": 25.56,
+          "end": 27.48,
+          "confidence": 0.622
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 2600,
+      "start": 31.32,
+      "end": 32.12,
+      "text": " Yeah, sir.",
+      "tokens": [
+        865,
+        11,
+        4735,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5317274729410807,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011296384036540985,
+      "confidence": 0.045,
+      "words": [
+        {
+          "text": "Yeah,",
+          "start": 31.32,
+          "end": 31.6,
+          "confidence": 0.032
+        },
+        {
+          "text": "sir.",
+          "start": 31.6,
+          "end": 32.12,
+          "confidence": 0.063
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 2600,
+      "start": 32.66,
+      "end": 33.06,
+      "text": " All right.",
+      "tokens": [
+        1057,
+        558,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5317274729410807,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011296384036540985,
+      "confidence": 0.199,
+      "words": [
+        {
+          "text": "All",
+          "start": 32.66,
+          "end": 32.94,
+          "confidence": 0.025
+        },
+        {
+          "text": "right.",
+          "start": 32.94,
+          "end": 33.06,
+          "confidence": 0.56
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 2600,
+      "start": 33.08,
+      "end": 33.56,
+      "text": " Yeah, sir.",
+      "tokens": [
+        865,
+        11,
+        4735,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5317274729410807,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011296384036540985,
+      "confidence": 0.036,
+      "words": [
+        {
+          "text": "Yeah,",
+          "start": 33.08,
+          "end": 33.38,
+          "confidence": 0.145
+        },
+        {
+          "text": "sir.",
+          "start": 33.38,
+          "end": 33.56,
+          "confidence": 0.009
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 2600,
+      "start": 33.58,
+      "end": 35.12,
+      "text": " There's a better helmet than B-1.",
+      "tokens": [
+        821,
+        311,
+        257,
+        1101,
+        15922,
+        813,
+        363,
+        12,
+        16,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5317274729410807,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011296384036540985,
+      "confidence": 0.046,
+      "words": [
+        {
+          "text": "There's",
+          "start": 33.58,
+          "end": 33.96,
+          "confidence": 0.035
+        },
+        {
+          "text": "a",
+          "start": 33.96,
+          "end": 34.0,
+          "confidence": 0.302
+        },
+        {
+          "text": "better",
+          "start": 34.0,
+          "end": 34.04,
+          "confidence": 0.037
+        },
+        {
+          "text": "helmet",
+          "start": 34.04,
+          "end": 34.36,
+          "confidence": 0.009
+        },
+        {
+          "text": "than",
+          "start": 34.36,
+          "end": 34.7,
+          "confidence": 0.386
+        },
+        {
+          "text": "B-1.",
+          "start": 34.7,
+          "end": 35.12,
+          "confidence": 0.031
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 2600,
+      "start": 35.14,
+      "end": 35.96,
+      "text": " That's the other one.",
+      "tokens": [
+        663,
+        311,
+        264,
+        661,
+        472,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5317274729410807,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011296384036540985,
+      "confidence": 0.259,
+      "words": [
+        {
+          "text": "That's",
+          "start": 35.14,
+          "end": 35.48,
+          "confidence": 0.114
+        },
+        {
+          "text": "the",
+          "start": 35.48,
+          "end": 35.52,
+          "confidence": 0.609
+        },
+        {
+          "text": "other",
+          "start": 35.52,
+          "end": 35.7,
+          "confidence": 0.954
+        },
+        {
+          "text": "one.",
+          "start": 35.7,
+          "end": 35.96,
+          "confidence": 0.2
+        }
+      ]
+    },
+    {
+      "id": 17,
+      "seek": 2600,
+      "start": 35.98,
+      "end": 36.24,
+      "text": " Nice.",
+      "tokens": [
+        5490,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5317274729410807,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011296384036540985,
+      "confidence": 0.008,
+      "words": [
+        {
+          "text": "Nice.",
+          "start": 35.98,
+          "end": 36.24,
+          "confidence": 0.008
+        }
+      ]
+    },
+    {
+      "id": 18,
+      "seek": 2600,
+      "start": 37.5,
+      "end": 38.44,
+      "text": " Let's go in there.",
+      "tokens": [
+        961,
+        311,
+        352,
+        294,
+        456,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5317274729410807,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011296384036540985,
+      "confidence": 0.127,
+      "words": [
+        {
+          "text": "Let's",
+          "start": 37.5,
+          "end": 38.16,
+          "confidence": 0.024
+        },
+        {
+          "text": "go",
+          "start": 38.16,
+          "end": 38.2,
+          "confidence": 0.624
+        },
+        {
+          "text": "in",
+          "start": 38.2,
+          "end": 38.3,
+          "confidence": 0.037
+        },
+        {
+          "text": "there.",
+          "start": 38.3,
+          "end": 38.44,
+          "confidence": 0.571
+        }
+      ]
+    },
+    {
+      "id": 19,
+      "seek": 2600,
+      "start": 38.6,
+      "end": 39.26,
+      "text": " At least we're safe.",
+      "tokens": [
+        1711,
+        1935,
+        321,
+        434,
+        3273,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5317274729410807,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011296384036540985,
+      "confidence": 0.14,
+      "words": [
+        {
+          "text": "At",
+          "start": 38.6,
+          "end": 38.64,
+          "confidence": 0.002
+        },
+        {
+          "text": "least",
+          "start": 38.64,
+          "end": 38.84,
+          "confidence": 0.269
+        },
+        {
+          "text": "we're",
+          "start": 38.84,
+          "end": 39.18,
+          "confidence": 0.138
+        },
+        {
+          "text": "safe.",
+          "start": 39.18,
+          "end": 39.26,
+          "confidence": 0.802
+        }
+      ]
+    },
+    {
+      "id": 20,
+      "seek": 2600,
+      "start": 39.92,
+      "end": 40.52,
+      "text": " We've got them in there.",
+      "tokens": [
+        492,
+        600,
+        658,
+        552,
+        294,
+        456,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5317274729410807,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011296384036540985,
+      "confidence": 0.071,
+      "words": [
+        {
+          "text": "We've",
+          "start": 39.92,
+          "end": 40.36,
+          "confidence": 0.042
+        },
+        {
+          "text": "got",
+          "start": 40.36,
+          "end": 40.4,
+          "confidence": 0.682
+        },
+        {
+          "text": "them",
+          "start": 40.4,
+          "end": 40.44,
+          "confidence": 0.004
+        },
+        {
+          "text": "in",
+          "start": 40.44,
+          "end": 40.48,
+          "confidence": 0.041
+        },
+        {
+          "text": "there.",
+          "start": 40.48,
+          "end": 40.52,
+          "confidence": 0.216
+        }
+      ]
+    },
+    {
+      "id": 21,
+      "seek": 2600,
+      "start": 40.52,
+      "end": 41.1,
+      "text": " Helmet bags.",
+      "tokens": [
+        6128,
+        5537,
+        10405,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5317274729410807,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011296384036540985,
+      "confidence": 0.002,
+      "words": [
+        {
+          "text": "Helmet",
+          "start": 40.52,
+          "end": 40.8,
+          "confidence": 0.002
+        },
+        {
+          "text": "bags.",
+          "start": 40.8,
+          "end": 41.1,
+          "confidence": 0.002
+        }
+      ]
+    },
+    {
+      "id": 22,
+      "seek": 2600,
+      "start": 41.12,
+      "end": 43.1,
+      "text": " And, uh, I guess we have helmets in the helmet bag.",
+      "tokens": [
+        400,
+        11,
+        2232,
+        11,
+        286,
+        2041,
+        321,
+        362,
+        42022,
+        294,
+        264,
+        15922,
+        3411,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5317274729410807,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011296384036540985,
+      "confidence": 0.036,
+      "words": [
+        {
+          "text": "And,",
+          "start": 41.12,
+          "end": 41.5,
+          "confidence": 0.02
+        },
+        {
+          "text": "uh,",
+          "start": 41.5,
+          "end": 41.54,
+          "confidence": 0.55
+        },
+        {
+          "text": "I",
+          "start": 41.54,
+          "end": 41.58,
+          "confidence": 0.409
+        },
+        {
+          "text": "guess",
+          "start": 41.58,
+          "end": 41.64,
+          "confidence": 0.031
+        },
+        {
+          "text": "we",
+          "start": 41.64,
+          "end": 41.68,
+          "confidence": 0.059
+        },
+        {
+          "text": "have",
+          "start": 41.68,
+          "end": 41.72,
+          "confidence": 0.018
+        },
+        {
+          "text": "helmets",
+          "start": 41.72,
+          "end": 41.76,
+          "confidence": 0.0
+        },
+        {
+          "text": "in",
+          "start": 41.76,
+          "end": 42.08,
+          "confidence": 0.025
+        },
+        {
+          "text": "the",
+          "start": 42.08,
+          "end": 42.38,
+          "confidence": 0.214
+        },
+        {
+          "text": "helmet",
+          "start": 42.38,
+          "end": 43.06,
+          "confidence": 0.001
+        },
+        {
+          "text": "bag.",
+          "start": 43.06,
+          "end": 43.1,
+          "confidence": 0.611
+        }
+      ]
+    },
+    {
+      "id": 23,
+      "seek": 2600,
+      "start": 43.56,
+      "end": 47.42,
+      "text": " At least it's in the helmet bag.",
+      "tokens": [
+        1711,
+        1935,
+        309,
+        311,
+        294,
+        264,
+        15922,
+        3411,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5317274729410807,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011296384036540985,
+      "confidence": 0.051,
+      "words": [
+        {
+          "text": "At",
+          "start": 43.56,
+          "end": 44.06,
+          "confidence": 0.001
+        },
+        {
+          "text": "least",
+          "start": 44.06,
+          "end": 44.32,
+          "confidence": 0.325
+        },
+        {
+          "text": "it's",
+          "start": 44.32,
+          "end": 44.9,
+          "confidence": 0.169
+        },
+        {
+          "text": "in",
+          "start": 44.9,
+          "end": 45.46,
+          "confidence": 0.03
+        },
+        {
+          "text": "the",
+          "start": 45.46,
+          "end": 45.5,
+          "confidence": 0.345
+        },
+        {
+          "text": "helmet",
+          "start": 45.5,
+          "end": 46.54,
+          "confidence": 0.004
+        },
+        {
+          "text": "bag.",
+          "start": 46.54,
+          "end": 47.42,
+          "confidence": 0.095
+        }
+      ]
+    },
+    {
+      "id": 24,
+      "seek": 2600,
+      "start": 48.22,
+      "end": 48.44,
+      "text": " Right here.",
+      "tokens": [
+        1779,
+        510,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5317274729410807,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011296384036540985,
+      "confidence": 0.02,
+      "words": [
+        {
+          "text": "Right",
+          "start": 48.22,
+          "end": 48.26,
+          "confidence": 0.0
+        },
+        {
+          "text": "here.",
+          "start": 48.26,
+          "end": 48.44,
+          "confidence": 0.167
+        }
+      ]
+    },
+    {
+      "id": 25,
+      "seek": 2600,
+      "start": 48.46,
+      "end": 48.76,
+      "text": " Right here.",
+      "tokens": [
+        1779,
+        510,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5317274729410807,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011296384036540985,
+      "confidence": 0.018,
+      "words": [
+        {
+          "text": "Right",
+          "start": 48.46,
+          "end": 48.56,
+          "confidence": 0.001
+        },
+        {
+          "text": "here.",
+          "start": 48.56,
+          "end": 48.76,
+          "confidence": 0.078
+        }
+      ]
+    },
+    {
+      "id": 26,
+      "seek": 2600,
+      "start": 48.78,
+      "end": 55.4,
+      "text": " Yeah, we're taking it next day out of the field up.",
+      "tokens": [
+        865,
+        11,
+        321,
+        434,
+        1940,
+        309,
+        958,
+        786,
+        484,
+        295,
+        264,
+        2519,
+        493,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5317274729410807,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011296384036540985,
+      "confidence": 0.285,
+      "words": [
+        {
+          "text": "Yeah,",
+          "start": 48.78,
+          "end": 52.1,
+          "confidence": 0.124
+        },
+        {
+          "text": "we're",
+          "start": 52.1,
+          "end": 53.64,
+          "confidence": 0.622
+        },
+        {
+          "text": "taking",
+          "start": 53.64,
+          "end": 53.68,
+          "confidence": 0.352
+        },
+        {
+          "text": "it",
+          "start": 53.68,
+          "end": 53.76,
+          "confidence": 0.114
+        },
+        {
+          "text": "next",
+          "start": 53.76,
+          "end": 53.98,
+          "confidence": 0.411
+        },
+        {
+          "text": "day",
+          "start": 53.98,
+          "end": 54.2,
+          "confidence": 0.888
+        },
+        {
+          "text": "out",
+          "start": 54.2,
+          "end": 54.32,
+          "confidence": 0.322
+        },
+        {
+          "text": "of",
+          "start": 54.32,
+          "end": 54.56,
+          "confidence": 0.473
+        },
+        {
+          "text": "the",
+          "start": 54.56,
+          "end": 54.7,
+          "confidence": 0.357
+        },
+        {
+          "text": "field",
+          "start": 54.7,
+          "end": 55.2,
+          "confidence": 0.051
+        },
+        {
+          "text": "up.",
+          "start": 55.2,
+          "end": 55.4,
+          "confidence": 0.31
+        }
+      ]
+    },
+    {
+      "id": 27,
+      "seek": 5500,
+      "start": 55.42,
+      "end": 56.32,
+      "text": " Hey, we were...",
+      "tokens": [
+        1911,
+        11,
+        321,
+        645,
+        485
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.32385124256408293,
+      "compression_ratio": 1.7088607594936709,
+      "no_speech_prob": 0.0003275917551945895,
+      "confidence": 0.009,
+      "words": [
+        {
+          "text": "Hey,",
+          "start": 55.42,
+          "end": 56.24,
+          "confidence": 0.015
+        },
+        {
+          "text": "we",
+          "start": 56.24,
+          "end": 56.28,
+          "confidence": 0.014
+        },
+        {
+          "text": "were...",
+          "start": 56.28,
+          "end": 56.32,
+          "confidence": 0.004
+        }
+      ]
+    },
+    {
+      "id": 28,
+      "seek": 5500,
+      "start": 56.5,
+      "end": 57.52,
+      "text": " You want to hack me on this?",
+      "tokens": [
+        509,
+        528,
+        281,
+        10339,
+        385,
+        322,
+        341,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.32385124256408293,
+      "compression_ratio": 1.7088607594936709,
+      "no_speech_prob": 0.0003275917551945895,
+      "confidence": 0.022,
+      "words": [
+        {
+          "text": "You",
+          "start": 56.5,
+          "end": 56.64,
+          "confidence": 0.006
+        },
+        {
+          "text": "want",
+          "start": 56.64,
+          "end": 57.02,
+          "confidence": 0.007
+        },
+        {
+          "text": "to",
+          "start": 57.02,
+          "end": 57.36,
+          "confidence": 0.345
+        },
+        {
+          "text": "hack",
+          "start": 57.36,
+          "end": 57.4,
+          "confidence": 0.0
+        },
+        {
+          "text": "me",
+          "start": 57.4,
+          "end": 57.44,
+          "confidence": 0.088
+        },
+        {
+          "text": "on",
+          "start": 57.44,
+          "end": 57.48,
+          "confidence": 0.004
+        },
+        {
+          "text": "this?",
+          "start": 57.48,
+          "end": 57.52,
+          "confidence": 0.177
+        }
+      ]
+    },
+    {
+      "id": 29,
+      "seek": 5500,
+      "start": 57.52,
+      "end": 58.44,
+      "text": " Hey, we were...",
+      "tokens": [
+        1911,
+        11,
+        321,
+        645,
+        485
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.32385124256408293,
+      "compression_ratio": 1.7088607594936709,
+      "no_speech_prob": 0.0003275917551945895,
+      "confidence": 0.048,
+      "words": [
+        {
+          "text": "Hey,",
+          "start": 57.52,
+          "end": 57.98,
+          "confidence": 0.033
+        },
+        {
+          "text": "we",
+          "start": 57.98,
+          "end": 58.14,
+          "confidence": 0.391
+        },
+        {
+          "text": "were...",
+          "start": 58.14,
+          "end": 58.44,
+          "confidence": 0.024
+        }
+      ]
+    },
+    {
+      "id": 30,
+      "seek": 5500,
+      "start": 58.46,
+      "end": 59.44,
+      "text": " You want to hack me on this?",
+      "tokens": [
+        509,
+        528,
+        281,
+        10339,
+        385,
+        322,
+        341,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.32385124256408293,
+      "compression_ratio": 1.7088607594936709,
+      "no_speech_prob": 0.0003275917551945895,
+      "confidence": 0.04,
+      "words": [
+        {
+          "text": "You",
+          "start": 58.46,
+          "end": 58.7,
+          "confidence": 0.014
+        },
+        {
+          "text": "want",
+          "start": 58.7,
+          "end": 58.74,
+          "confidence": 0.017
+        },
+        {
+          "text": "to",
+          "start": 58.74,
+          "end": 58.78,
+          "confidence": 0.336
+        },
+        {
+          "text": "hack",
+          "start": 58.78,
+          "end": 58.82,
+          "confidence": 0.0
+        },
+        {
+          "text": "me",
+          "start": 58.82,
+          "end": 59.0,
+          "confidence": 0.417
+        },
+        {
+          "text": "on",
+          "start": 59.0,
+          "end": 59.2,
+          "confidence": 0.277
+        },
+        {
+          "text": "this?",
+          "start": 59.2,
+          "end": 59.44,
+          "confidence": 0.138
+        }
+      ]
+    },
+    {
+      "id": 31,
+      "seek": 5500,
+      "start": 59.76,
+      "end": 61.48,
+      "text": " With a cover, I tried it already.",
+      "tokens": [
+        2022,
+        257,
+        2060,
+        11,
+        286,
+        3031,
+        309,
+        1217,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.32385124256408293,
+      "compression_ratio": 1.7088607594936709,
+      "no_speech_prob": 0.0003275917551945895,
+      "confidence": 0.064,
+      "words": [
+        {
+          "text": "With",
+          "start": 59.76,
+          "end": 60.12,
+          "confidence": 0.027
+        },
+        {
+          "text": "a",
+          "start": 60.12,
+          "end": 60.84,
+          "confidence": 0.553
+        },
+        {
+          "text": "cover,",
+          "start": 60.84,
+          "end": 61.32,
+          "confidence": 0.167
+        },
+        {
+          "text": "I",
+          "start": 61.32,
+          "end": 61.36,
+          "confidence": 0.846
+        },
+        {
+          "text": "tried",
+          "start": 61.36,
+          "end": 61.4,
+          "confidence": 0.046
+        },
+        {
+          "text": "it",
+          "start": 61.4,
+          "end": 61.44,
+          "confidence": 0.011
+        },
+        {
+          "text": "already.",
+          "start": 61.44,
+          "end": 61.48,
+          "confidence": 0.01
+        }
+      ]
+    },
+    {
+      "id": 32,
+      "seek": 5500,
+      "start": 62.38,
+      "end": 62.46,
+      "text": " Okay, fine.",
+      "tokens": [
+        1033,
+        11,
+        2489,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.32385124256408293,
+      "compression_ratio": 1.7088607594936709,
+      "no_speech_prob": 0.0003275917551945895,
+      "confidence": 0.062,
+      "words": [
+        {
+          "text": "Okay,",
+          "start": 62.38,
+          "end": 62.42,
+          "confidence": 0.06
+        },
+        {
+          "text": "fine.",
+          "start": 62.42,
+          "end": 62.46,
+          "confidence": 0.065
+        }
+      ]
+    },
+    {
+      "id": 33,
+      "seek": 5500,
+      "start": 62.56,
+      "end": 63.44,
+      "text": " We weren't sure of that.",
+      "tokens": [
+        492,
+        4999,
+        380,
+        988,
+        295,
+        300,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.32385124256408293,
+      "compression_ratio": 1.7088607594936709,
+      "no_speech_prob": 0.0003275917551945895,
+      "confidence": 0.043,
+      "words": [
+        {
+          "text": "We",
+          "start": 62.56,
+          "end": 63.06,
+          "confidence": 0.003
+        },
+        {
+          "text": "weren't",
+          "start": 63.06,
+          "end": 63.1,
+          "confidence": 0.155
+        },
+        {
+          "text": "sure",
+          "start": 63.1,
+          "end": 63.14,
+          "confidence": 0.01
+        },
+        {
+          "text": "of",
+          "start": 63.14,
+          "end": 63.18,
+          "confidence": 0.018
+        },
+        {
+          "text": "that.",
+          "start": 63.18,
+          "end": 63.44,
+          "confidence": 0.144
+        }
+      ]
+    },
+    {
+      "id": 34,
+      "seek": 5500,
+      "start": 63.46,
+      "end": 63.78,
+      "text": " Just a suggestion.",
+      "tokens": [
+        1449,
+        257,
+        16541,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.32385124256408293,
+      "compression_ratio": 1.7088607594936709,
+      "no_speech_prob": 0.0003275917551945895,
+      "confidence": 0.004,
+      "words": [
+        {
+          "text": "Just",
+          "start": 63.46,
+          "end": 63.5,
+          "confidence": 0.003
+        },
+        {
+          "text": "a",
+          "start": 63.5,
+          "end": 63.74,
+          "confidence": 0.015
+        },
+        {
+          "text": "suggestion.",
+          "start": 63.74,
+          "end": 63.78,
+          "confidence": 0.002
+        }
+      ]
+    },
+    {
+      "id": 35,
+      "seek": 5500,
+      "start": 63.78,
+      "end": 65.26,
+      "text": " We thought we'd...",
+      "tokens": [
+        492,
+        1194,
+        321,
+        1116,
+        485
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.32385124256408293,
+      "compression_ratio": 1.7088607594936709,
+      "no_speech_prob": 0.0003275917551945895,
+      "confidence": 0.011,
+      "words": [
+        {
+          "text": "We",
+          "start": 63.78,
+          "end": 64.9,
+          "confidence": 0.003
+        },
+        {
+          "text": "thought",
+          "start": 64.9,
+          "end": 65.2,
+          "confidence": 0.001
+        },
+        {
+          "text": "we'd...",
+          "start": 65.2,
+          "end": 65.26,
+          "confidence": 0.036
+        }
+      ]
+    },
+    {
+      "id": 36,
+      "seek": 5500,
+      "start": 66.26,
+      "end": 66.46,
+      "text": " You could check it out.",
+      "tokens": [
+        509,
+        727,
+        1520,
+        309,
+        484,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.32385124256408293,
+      "compression_ratio": 1.7088607594936709,
+      "no_speech_prob": 0.0003275917551945895,
+      "confidence": 0.03,
+      "words": [
+        {
+          "text": "You",
+          "start": 66.26,
+          "end": 66.3,
+          "confidence": 0.004
+        },
+        {
+          "text": "could",
+          "start": 66.3,
+          "end": 66.34,
+          "confidence": 0.002
+        },
+        {
+          "text": "check",
+          "start": 66.34,
+          "end": 66.38,
+          "confidence": 0.003
+        },
+        {
+          "text": "it",
+          "start": 66.38,
+          "end": 66.42,
+          "confidence": 0.16
+        },
+        {
+          "text": "out.",
+          "start": 66.42,
+          "end": 66.46,
+          "confidence": 0.442
+        }
+      ]
+    },
+    {
+      "id": 37,
+      "seek": 5500,
+      "start": 66.82,
+      "end": 69.34,
+      "text": " It's not much of an order to turn that.",
+      "tokens": [
+        467,
+        311,
+        406,
+        709,
+        295,
+        364,
+        1668,
+        281,
+        1261,
+        300,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.32385124256408293,
+      "compression_ratio": 1.7088607594936709,
+      "no_speech_prob": 0.0003275917551945895,
+      "confidence": 0.136,
+      "words": [
+        {
+          "text": "It's",
+          "start": 66.82,
+          "end": 67.32,
+          "confidence": 0.035
+        },
+        {
+          "text": "not",
+          "start": 67.32,
+          "end": 68.36,
+          "confidence": 0.025
+        },
+        {
+          "text": "much",
+          "start": 68.36,
+          "end": 68.62,
+          "confidence": 0.683
+        },
+        {
+          "text": "of",
+          "start": 68.62,
+          "end": 68.8,
+          "confidence": 0.59
+        },
+        {
+          "text": "an",
+          "start": 68.8,
+          "end": 68.86,
+          "confidence": 0.137
+        },
+        {
+          "text": "order",
+          "start": 68.86,
+          "end": 68.96,
+          "confidence": 0.142
+        },
+        {
+          "text": "to",
+          "start": 68.96,
+          "end": 69.16,
+          "confidence": 0.043
+        },
+        {
+          "text": "turn",
+          "start": 69.16,
+          "end": 69.2,
+          "confidence": 0.1
+        },
+        {
+          "text": "that.",
+          "start": 69.2,
+          "end": 69.34,
+          "confidence": 0.536
+        }
+      ]
+    },
+    {
+      "id": 38,
+      "seek": 5500,
+      "start": 70.32,
+      "end": 72.02,
+      "text": " So, uh, I guess we're going to come up with this.",
+      "tokens": [
+        407,
+        11,
+        2232,
+        11,
+        286,
+        2041,
+        321,
+        434,
+        516,
+        281,
+        808,
+        493,
+        365,
+        341,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.32385124256408293,
+      "compression_ratio": 1.7088607594936709,
+      "no_speech_prob": 0.0003275917551945895,
+      "confidence": 0.495,
+      "words": [
+        {
+          "text": "So,",
+          "start": 70.32,
+          "end": 70.36,
+          "confidence": 0.528
+        },
+        {
+          "text": "uh,",
+          "start": 70.36,
+          "end": 70.5,
+          "confidence": 0.497
+        },
+        {
+          "text": "I",
+          "start": 70.5,
+          "end": 70.54,
+          "confidence": 0.958
+        },
+        {
+          "text": "guess",
+          "start": 70.54,
+          "end": 70.84,
+          "confidence": 0.986
+        },
+        {
+          "text": "we're",
+          "start": 70.84,
+          "end": 71.12,
+          "confidence": 0.504
+        },
+        {
+          "text": "going",
+          "start": 71.12,
+          "end": 71.3,
+          "confidence": 0.143
+        },
+        {
+          "text": "to",
+          "start": 71.3,
+          "end": 71.48,
+          "confidence": 0.956
+        },
+        {
+          "text": "come",
+          "start": 71.48,
+          "end": 71.52,
+          "confidence": 0.547
+        },
+        {
+          "text": "up",
+          "start": 71.52,
+          "end": 71.7,
+          "confidence": 0.796
+        },
+        {
+          "text": "with",
+          "start": 71.7,
+          "end": 71.88,
+          "confidence": 0.807
+        },
+        {
+          "text": "this.",
+          "start": 71.88,
+          "end": 72.02,
+          "confidence": 0.181
+        }
+      ]
+    },
+    {
+      "id": 39,
+      "seek": 5500,
+      "start": 72.04,
+      "end": 72.52,
+      "text": " Let us know.",
+      "tokens": [
+        961,
+        505,
+        458,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.32385124256408293,
+      "compression_ratio": 1.7088607594936709,
+      "no_speech_prob": 0.0003275917551945895,
+      "confidence": 0.323,
+      "words": [
+        {
+          "text": "Let",
+          "start": 72.04,
+          "end": 72.14,
+          "confidence": 0.076
+        },
+        {
+          "text": "us",
+          "start": 72.14,
+          "end": 72.34,
+          "confidence": 0.304
+        },
+        {
+          "text": "know.",
+          "start": 72.34,
+          "end": 72.52,
+          "confidence": 0.686
+        }
+      ]
+    },
+    {
+      "id": 40,
+      "seek": 5500,
+      "start": 72.54,
+      "end": 72.7,
+      "text": " Okay.",
+      "tokens": [
+        1033,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.32385124256408293,
+      "compression_ratio": 1.7088607594936709,
+      "no_speech_prob": 0.0003275917551945895,
+      "confidence": 0.026,
+      "words": [
+        {
+          "text": "Okay.",
+          "start": 72.54,
+          "end": 72.7,
+          "confidence": 0.026
+        }
+      ]
+    },
+    {
+      "id": 41,
+      "seek": 5500,
+      "start": 74.2,
+      "end": 75.16,
+      "text": " No problem.",
+      "tokens": [
+        883,
+        1154,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.32385124256408293,
+      "compression_ratio": 1.7088607594936709,
+      "no_speech_prob": 0.0003275917551945895,
+      "confidence": 0.082,
+      "words": [
+        {
+          "text": "No",
+          "start": 74.2,
+          "end": 74.42,
+          "confidence": 0.004
+        },
+        {
+          "text": "problem.",
+          "start": 74.42,
+          "end": 75.16,
+          "confidence": 0.351
+        }
+      ]
+    },
+    {
+      "id": 42,
+      "seek": 5500,
+      "start": 75.18,
+      "end": 75.9,
+      "text": " Okay.",
+      "tokens": [
+        1033,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.32385124256408293,
+      "compression_ratio": 1.7088607594936709,
+      "no_speech_prob": 0.0003275917551945895,
+      "confidence": 0.237,
+      "words": [
+        {
+          "text": "Okay.",
+          "start": 75.18,
+          "end": 75.9,
+          "confidence": 0.237
+        }
+      ]
+    },
+    {
+      "id": 43,
+      "seek": 5500,
+      "start": 75.92,
+      "end": 76.64,
+      "text": " No problem.",
+      "tokens": [
+        883,
+        1154,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.32385124256408293,
+      "compression_ratio": 1.7088607594936709,
+      "no_speech_prob": 0.0003275917551945895,
+      "confidence": 0.56,
+      "words": [
+        {
+          "text": "No",
+          "start": 75.92,
+          "end": 76.22,
+          "confidence": 0.366
+        },
+        {
+          "text": "problem.",
+          "start": 76.22,
+          "end": 76.64,
+          "confidence": 0.692
+        }
+      ]
+    },
+    {
+      "id": 44,
+      "seek": 5500,
+      "start": 76.66,
+      "end": 78.1,
+      "text": " We'll let you know when the end of...",
+      "tokens": [
+        492,
+        603,
+        718,
+        291,
+        458,
+        562,
+        264,
+        917,
+        295,
+        485
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.32385124256408293,
+      "compression_ratio": 1.7088607594936709,
+      "no_speech_prob": 0.0003275917551945895,
+      "confidence": 0.367,
+      "words": [
+        {
+          "text": "We'll",
+          "start": 76.66,
+          "end": 76.82,
+          "confidence": 0.091
+        },
+        {
+          "text": "let",
+          "start": 76.82,
+          "end": 77.04,
+          "confidence": 0.723
+        },
+        {
+          "text": "you",
+          "start": 77.04,
+          "end": 77.18,
+          "confidence": 0.296
+        },
+        {
+          "text": "know",
+          "start": 77.18,
+          "end": 77.26,
+          "confidence": 0.984
+        },
+        {
+          "text": "when",
+          "start": 77.26,
+          "end": 77.38,
+          "confidence": 0.596
+        },
+        {
+          "text": "the",
+          "start": 77.38,
+          "end": 77.44,
+          "confidence": 0.683
+        },
+        {
+          "text": "end",
+          "start": 77.44,
+          "end": 77.56,
+          "confidence": 0.937
+        },
+        {
+          "text": "of...",
+          "start": 77.56,
+          "end": 78.1,
+          "confidence": 0.257
+        }
+      ]
+    },
+    {
+      "id": 45,
+      "seek": 5500,
+      "start": 78.12,
+      "end": 78.34,
+      "text": " None.",
+      "tokens": [
+        14492,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.32385124256408293,
+      "compression_ratio": 1.7088607594936709,
+      "no_speech_prob": 0.0003275917551945895,
+      "confidence": 0.017,
+      "words": [
+        {
+          "text": "None.",
+          "start": 78.12,
+          "end": 78.34,
+          "confidence": 0.017
+        }
+      ]
+    },
+    {
+      "id": 46,
+      "seek": 7900,
+      "start": 78.52,
+      "end": 82.18,
+      "text": " Okay.",
+      "tokens": [
+        50364,
+        1033,
+        13,
+        50714
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7262506484985352,
+      "compression_ratio": 0.38461538461538464,
+      "no_speech_prob": 0.0013847488444298506,
+      "confidence": 0.036,
+      "words": [
+        {
+          "text": "Okay.",
+          "start": 78.52,
+          "end": 82.18,
+          "confidence": 0.036
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/naive.cpu/naive_apollo11.mp3.words.json b/tests/expected/naive.cpu/naive_apollo11.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..e4eef5136cb849167d2c3d19c38438515c0e4232
--- /dev/null
+++ b/tests/expected/naive.cpu/naive_apollo11.mp3.words.json
@@ -0,0 +1,3814 @@
+{
+  "text": " Apollo 11, Houston we got a recommendation for you on your Soyuz-VA GLEME GVA. Alright, okay, we like to say that they make the one that's on the helmet we're going to have in B1. And you can put the other one on the mic helmet with those GVA blizzard frames. Alright, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.64,
+      "end": 6.68,
+      "text": " Apollo 11, Houston we got a recommendation for you on your Soyuz-VA GLEME GVA.",
+      "tokens": [
+        25187,
+        2975,
+        11,
+        18717,
+        321,
+        658,
+        257,
+        11879,
+        337,
+        291,
+        322,
+        428,
+        24758,
+        3334,
+        12,
+        20914,
+        460,
+        2634,
+        15454,
+        460,
+        20914,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7224321867290296,
+      "compression_ratio": 1.39247311827957,
+      "no_speech_prob": 0.45045843720436096,
+      "confidence": 0.49,
+      "words": [
+        {
+          "text": "Apollo",
+          "start": 0.64,
+          "end": 0.98,
+          "confidence": 0.426
+        },
+        {
+          "text": "11,",
+          "start": 0.98,
+          "end": 1.54,
+          "confidence": 0.842
+        },
+        {
+          "text": "Houston",
+          "start": 1.54,
+          "end": 1.8,
+          "confidence": 0.974
+        },
+        {
+          "text": "we",
+          "start": 1.8,
+          "end": 1.98,
+          "confidence": 0.453
+        },
+        {
+          "text": "got",
+          "start": 1.98,
+          "end": 2.16,
+          "confidence": 0.789
+        },
+        {
+          "text": "a",
+          "start": 2.16,
+          "end": 2.36,
+          "confidence": 0.992
+        },
+        {
+          "text": "recommendation",
+          "start": 2.36,
+          "end": 3.1,
+          "confidence": 0.971
+        },
+        {
+          "text": "for",
+          "start": 3.1,
+          "end": 3.54,
+          "confidence": 0.944
+        },
+        {
+          "text": "you",
+          "start": 3.54,
+          "end": 3.88,
+          "confidence": 0.99
+        },
+        {
+          "text": "on",
+          "start": 3.88,
+          "end": 4.26,
+          "confidence": 0.935
+        },
+        {
+          "text": "your",
+          "start": 4.26,
+          "end": 4.3,
+          "confidence": 0.974
+        },
+        {
+          "text": "Soyuz-VA",
+          "start": 4.3,
+          "end": 5.38,
+          "confidence": 0.325
+        },
+        {
+          "text": "GLEME",
+          "start": 5.38,
+          "end": 6.02,
+          "confidence": 0.171
+        },
+        {
+          "text": "GVA.",
+          "start": 6.02,
+          "end": 6.68,
+          "confidence": 0.318
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 6.7,
+      "end": 19.16,
+      "text": " Alright, okay, we like to say that they make the one that's on the helmet we're going to have in B1.",
+      "tokens": [
+        2798,
+        11,
+        1392,
+        11,
+        321,
+        411,
+        281,
+        584,
+        300,
+        436,
+        652,
+        264,
+        472,
+        300,
+        311,
+        322,
+        264,
+        15922,
+        321,
+        434,
+        516,
+        281,
+        362,
+        294,
+        363,
+        16,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7224321867290296,
+      "compression_ratio": 1.39247311827957,
+      "no_speech_prob": 0.45045843720436096,
+      "confidence": 0.324,
+      "words": [
+        {
+          "text": "Alright,",
+          "start": 6.7,
+          "end": 12.02,
+          "confidence": 0.083
+        },
+        {
+          "text": "okay,",
+          "start": 12.02,
+          "end": 12.82,
+          "confidence": 0.321
+        },
+        {
+          "text": "we",
+          "start": 12.82,
+          "end": 13.04,
+          "confidence": 0.365
+        },
+        {
+          "text": "like",
+          "start": 13.04,
+          "end": 13.5,
+          "confidence": 0.475
+        },
+        {
+          "text": "to",
+          "start": 13.5,
+          "end": 13.68,
+          "confidence": 0.124
+        },
+        {
+          "text": "say",
+          "start": 13.68,
+          "end": 14.98,
+          "confidence": 0.127
+        },
+        {
+          "text": "that",
+          "start": 14.98,
+          "end": 15.56,
+          "confidence": 0.244
+        },
+        {
+          "text": "they",
+          "start": 15.56,
+          "end": 15.6,
+          "confidence": 0.387
+        },
+        {
+          "text": "make",
+          "start": 15.6,
+          "end": 15.78,
+          "confidence": 0.155
+        },
+        {
+          "text": "the",
+          "start": 15.78,
+          "end": 15.92,
+          "confidence": 0.172
+        },
+        {
+          "text": "one",
+          "start": 15.92,
+          "end": 16.1,
+          "confidence": 0.507
+        },
+        {
+          "text": "that's",
+          "start": 16.1,
+          "end": 16.36,
+          "confidence": 0.385
+        },
+        {
+          "text": "on",
+          "start": 16.36,
+          "end": 16.6,
+          "confidence": 0.324
+        },
+        {
+          "text": "the",
+          "start": 16.6,
+          "end": 16.84,
+          "confidence": 0.35
+        },
+        {
+          "text": "helmet",
+          "start": 16.84,
+          "end": 17.36,
+          "confidence": 0.218
+        },
+        {
+          "text": "we're",
+          "start": 17.36,
+          "end": 17.86,
+          "confidence": 0.361
+        },
+        {
+          "text": "going",
+          "start": 17.86,
+          "end": 18.06,
+          "confidence": 0.435
+        },
+        {
+          "text": "to",
+          "start": 18.06,
+          "end": 18.22,
+          "confidence": 0.496
+        },
+        {
+          "text": "have",
+          "start": 18.22,
+          "end": 18.26,
+          "confidence": 0.831
+        },
+        {
+          "text": "in",
+          "start": 18.26,
+          "end": 18.48,
+          "confidence": 0.761
+        },
+        {
+          "text": "B1.",
+          "start": 18.48,
+          "end": 19.16,
+          "confidence": 0.731
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 20.12,
+      "end": 24.64,
+      "text": " And you can put the other one on the mic helmet with those GVA blizzard frames.",
+      "tokens": [
+        400,
+        291,
+        393,
+        829,
+        264,
+        661,
+        472,
+        322,
+        264,
+        3123,
+        15922,
+        365,
+        729,
+        460,
+        20914,
+        888,
+        31062,
+        12083,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7224321867290296,
+      "compression_ratio": 1.39247311827957,
+      "no_speech_prob": 0.45045843720436096,
+      "confidence": 0.119,
+      "words": [
+        {
+          "text": "And",
+          "start": 20.12,
+          "end": 20.16,
+          "confidence": 0.27
+        },
+        {
+          "text": "you",
+          "start": 20.16,
+          "end": 20.36,
+          "confidence": 0.884
+        },
+        {
+          "text": "can",
+          "start": 20.36,
+          "end": 20.54,
+          "confidence": 0.388
+        },
+        {
+          "text": "put",
+          "start": 20.54,
+          "end": 20.72,
+          "confidence": 0.929
+        },
+        {
+          "text": "the",
+          "start": 20.72,
+          "end": 20.9,
+          "confidence": 0.98
+        },
+        {
+          "text": "other",
+          "start": 20.9,
+          "end": 21.06,
+          "confidence": 0.995
+        },
+        {
+          "text": "one",
+          "start": 21.06,
+          "end": 21.26,
+          "confidence": 0.964
+        },
+        {
+          "text": "on",
+          "start": 21.26,
+          "end": 21.8,
+          "confidence": 0.962
+        },
+        {
+          "text": "the",
+          "start": 21.8,
+          "end": 21.84,
+          "confidence": 0.185
+        },
+        {
+          "text": "mic",
+          "start": 21.84,
+          "end": 22.6,
+          "confidence": 0.682
+        },
+        {
+          "text": "helmet",
+          "start": 22.6,
+          "end": 22.96,
+          "confidence": 0.011
+        },
+        {
+          "text": "with",
+          "start": 22.96,
+          "end": 23.2,
+          "confidence": 0.055
+        },
+        {
+          "text": "those",
+          "start": 23.2,
+          "end": 23.46,
+          "confidence": 0.084
+        },
+        {
+          "text": "GVA",
+          "start": 23.46,
+          "end": 23.88,
+          "confidence": 0.0
+        },
+        {
+          "text": "blizzard",
+          "start": 23.88,
+          "end": 24.36,
+          "confidence": 0.026
+        },
+        {
+          "text": "frames.",
+          "start": 24.36,
+          "end": 24.64,
+          "confidence": 0.179
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 2500,
+      "start": 24.86,
+      "end": 54.62,
+      "text": " Alright, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them",
+      "tokens": [
+        50364,
+        2798,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1079042222764757,
+      "compression_ratio": 24.096774193548388,
+      "no_speech_prob": 0.00111382023897022,
+      "confidence": 0.887,
+      "words": [
+        {
+          "text": "Alright,",
+          "start": 24.86,
+          "end": 32.0,
+          "confidence": 0.092
+        },
+        {
+          "text": "got",
+          "start": 32.0,
+          "end": 32.04,
+          "confidence": 0.107
+        },
+        {
+          "text": "them,",
+          "start": 32.04,
+          "end": 32.58,
+          "confidence": 0.194
+        },
+        {
+          "text": "got",
+          "start": 32.58,
+          "end": 33.06,
+          "confidence": 0.39
+        },
+        {
+          "text": "them,",
+          "start": 33.06,
+          "end": 33.78,
+          "confidence": 0.616
+        },
+        {
+          "text": "got",
+          "start": 33.78,
+          "end": 33.82,
+          "confidence": 0.641
+        },
+        {
+          "text": "them,",
+          "start": 33.82,
+          "end": 34.52,
+          "confidence": 0.506
+        },
+        {
+          "text": "got",
+          "start": 34.52,
+          "end": 34.74,
+          "confidence": 0.662
+        },
+        {
+          "text": "them,",
+          "start": 34.74,
+          "end": 34.78,
+          "confidence": 0.507
+        },
+        {
+          "text": "got",
+          "start": 34.78,
+          "end": 35.02,
+          "confidence": 0.754
+        },
+        {
+          "text": "them,",
+          "start": 35.02,
+          "end": 35.06,
+          "confidence": 0.589
+        },
+        {
+          "text": "got",
+          "start": 35.06,
+          "end": 35.1,
+          "confidence": 0.779
+        },
+        {
+          "text": "them,",
+          "start": 35.1,
+          "end": 35.14,
+          "confidence": 0.705
+        },
+        {
+          "text": "got",
+          "start": 35.14,
+          "end": 35.34,
+          "confidence": 0.86
+        },
+        {
+          "text": "them,",
+          "start": 35.34,
+          "end": 35.98,
+          "confidence": 0.82
+        },
+        {
+          "text": "got",
+          "start": 35.98,
+          "end": 36.02,
+          "confidence": 0.916
+        },
+        {
+          "text": "them,",
+          "start": 36.02,
+          "end": 36.06,
+          "confidence": 0.76
+        },
+        {
+          "text": "got",
+          "start": 36.06,
+          "end": 36.1,
+          "confidence": 0.479
+        },
+        {
+          "text": "them,",
+          "start": 36.1,
+          "end": 36.14,
+          "confidence": 0.846
+        },
+        {
+          "text": "got",
+          "start": 36.14,
+          "end": 36.18,
+          "confidence": 0.916
+        },
+        {
+          "text": "them,",
+          "start": 36.18,
+          "end": 36.22,
+          "confidence": 0.89
+        },
+        {
+          "text": "got",
+          "start": 36.22,
+          "end": 36.26,
+          "confidence": 0.928
+        },
+        {
+          "text": "them,",
+          "start": 36.26,
+          "end": 36.3,
+          "confidence": 0.903
+        },
+        {
+          "text": "got",
+          "start": 36.3,
+          "end": 36.34,
+          "confidence": 0.932
+        },
+        {
+          "text": "them,",
+          "start": 36.34,
+          "end": 36.38,
+          "confidence": 0.91
+        },
+        {
+          "text": "got",
+          "start": 36.38,
+          "end": 36.42,
+          "confidence": 0.944
+        },
+        {
+          "text": "them,",
+          "start": 36.42,
+          "end": 36.46,
+          "confidence": 0.904
+        },
+        {
+          "text": "got",
+          "start": 36.46,
+          "end": 36.5,
+          "confidence": 0.942
+        },
+        {
+          "text": "them,",
+          "start": 36.5,
+          "end": 36.54,
+          "confidence": 0.903
+        },
+        {
+          "text": "got",
+          "start": 36.54,
+          "end": 36.58,
+          "confidence": 0.935
+        },
+        {
+          "text": "them,",
+          "start": 36.58,
+          "end": 36.62,
+          "confidence": 0.912
+        },
+        {
+          "text": "got",
+          "start": 36.62,
+          "end": 36.66,
+          "confidence": 0.93
+        },
+        {
+          "text": "them,",
+          "start": 36.66,
+          "end": 36.7,
+          "confidence": 0.918
+        },
+        {
+          "text": "got",
+          "start": 36.7,
+          "end": 36.74,
+          "confidence": 0.93
+        },
+        {
+          "text": "them,",
+          "start": 36.74,
+          "end": 36.78,
+          "confidence": 0.923
+        },
+        {
+          "text": "got",
+          "start": 36.78,
+          "end": 36.82,
+          "confidence": 0.936
+        },
+        {
+          "text": "them,",
+          "start": 36.82,
+          "end": 36.86,
+          "confidence": 0.93
+        },
+        {
+          "text": "got",
+          "start": 36.86,
+          "end": 36.9,
+          "confidence": 0.938
+        },
+        {
+          "text": "them,",
+          "start": 36.9,
+          "end": 36.94,
+          "confidence": 0.937
+        },
+        {
+          "text": "got",
+          "start": 36.94,
+          "end": 36.98,
+          "confidence": 0.944
+        },
+        {
+          "text": "them,",
+          "start": 36.98,
+          "end": 37.02,
+          "confidence": 0.942
+        },
+        {
+          "text": "got",
+          "start": 37.02,
+          "end": 37.06,
+          "confidence": 0.946
+        },
+        {
+          "text": "them,",
+          "start": 37.06,
+          "end": 37.1,
+          "confidence": 0.945
+        },
+        {
+          "text": "got",
+          "start": 37.1,
+          "end": 37.14,
+          "confidence": 0.949
+        },
+        {
+          "text": "them,",
+          "start": 37.14,
+          "end": 37.18,
+          "confidence": 0.948
+        },
+        {
+          "text": "got",
+          "start": 37.18,
+          "end": 37.22,
+          "confidence": 0.95
+        },
+        {
+          "text": "them,",
+          "start": 37.22,
+          "end": 37.26,
+          "confidence": 0.951
+        },
+        {
+          "text": "got",
+          "start": 37.26,
+          "end": 37.3,
+          "confidence": 0.952
+        },
+        {
+          "text": "them,",
+          "start": 37.3,
+          "end": 37.34,
+          "confidence": 0.953
+        },
+        {
+          "text": "got",
+          "start": 37.34,
+          "end": 37.38,
+          "confidence": 0.953
+        },
+        {
+          "text": "them,",
+          "start": 37.38,
+          "end": 37.42,
+          "confidence": 0.956
+        },
+        {
+          "text": "got",
+          "start": 37.42,
+          "end": 37.46,
+          "confidence": 0.953
+        },
+        {
+          "text": "them,",
+          "start": 37.46,
+          "end": 37.5,
+          "confidence": 0.957
+        },
+        {
+          "text": "got",
+          "start": 37.5,
+          "end": 37.54,
+          "confidence": 0.955
+        },
+        {
+          "text": "them,",
+          "start": 37.54,
+          "end": 37.58,
+          "confidence": 0.958
+        },
+        {
+          "text": "got",
+          "start": 37.58,
+          "end": 37.62,
+          "confidence": 0.956
+        },
+        {
+          "text": "them,",
+          "start": 37.62,
+          "end": 37.66,
+          "confidence": 0.961
+        },
+        {
+          "text": "got",
+          "start": 37.66,
+          "end": 37.7,
+          "confidence": 0.956
+        },
+        {
+          "text": "them,",
+          "start": 37.7,
+          "end": 37.74,
+          "confidence": 0.961
+        },
+        {
+          "text": "got",
+          "start": 37.74,
+          "end": 37.78,
+          "confidence": 0.957
+        },
+        {
+          "text": "them,",
+          "start": 37.78,
+          "end": 37.82,
+          "confidence": 0.962
+        },
+        {
+          "text": "got",
+          "start": 37.82,
+          "end": 37.86,
+          "confidence": 0.957
+        },
+        {
+          "text": "them,",
+          "start": 37.86,
+          "end": 37.9,
+          "confidence": 0.964
+        },
+        {
+          "text": "got",
+          "start": 37.9,
+          "end": 37.94,
+          "confidence": 0.958
+        },
+        {
+          "text": "them,",
+          "start": 37.94,
+          "end": 37.98,
+          "confidence": 0.965
+        },
+        {
+          "text": "got",
+          "start": 37.98,
+          "end": 38.02,
+          "confidence": 0.959
+        },
+        {
+          "text": "them,",
+          "start": 38.02,
+          "end": 38.06,
+          "confidence": 0.966
+        },
+        {
+          "text": "got",
+          "start": 38.06,
+          "end": 38.1,
+          "confidence": 0.961
+        },
+        {
+          "text": "them,",
+          "start": 38.1,
+          "end": 38.14,
+          "confidence": 0.968
+        },
+        {
+          "text": "got",
+          "start": 38.14,
+          "end": 38.18,
+          "confidence": 0.963
+        },
+        {
+          "text": "them,",
+          "start": 38.18,
+          "end": 38.22,
+          "confidence": 0.969
+        },
+        {
+          "text": "got",
+          "start": 38.22,
+          "end": 38.26,
+          "confidence": 0.963
+        },
+        {
+          "text": "them,",
+          "start": 38.26,
+          "end": 38.3,
+          "confidence": 0.968
+        },
+        {
+          "text": "got",
+          "start": 38.3,
+          "end": 38.34,
+          "confidence": 0.964
+        },
+        {
+          "text": "them,",
+          "start": 38.34,
+          "end": 38.38,
+          "confidence": 0.971
+        },
+        {
+          "text": "got",
+          "start": 38.38,
+          "end": 38.42,
+          "confidence": 0.967
+        },
+        {
+          "text": "them,",
+          "start": 38.42,
+          "end": 38.46,
+          "confidence": 0.972
+        },
+        {
+          "text": "got",
+          "start": 38.46,
+          "end": 38.5,
+          "confidence": 0.968
+        },
+        {
+          "text": "them,",
+          "start": 38.5,
+          "end": 38.54,
+          "confidence": 0.974
+        },
+        {
+          "text": "got",
+          "start": 38.54,
+          "end": 38.58,
+          "confidence": 0.969
+        },
+        {
+          "text": "them,",
+          "start": 38.58,
+          "end": 38.62,
+          "confidence": 0.974
+        },
+        {
+          "text": "got",
+          "start": 38.62,
+          "end": 38.66,
+          "confidence": 0.971
+        },
+        {
+          "text": "them,",
+          "start": 38.66,
+          "end": 38.7,
+          "confidence": 0.974
+        },
+        {
+          "text": "got",
+          "start": 38.7,
+          "end": 38.74,
+          "confidence": 0.974
+        },
+        {
+          "text": "them,",
+          "start": 38.74,
+          "end": 38.78,
+          "confidence": 0.976
+        },
+        {
+          "text": "got",
+          "start": 38.78,
+          "end": 38.82,
+          "confidence": 0.976
+        },
+        {
+          "text": "them,",
+          "start": 38.82,
+          "end": 38.86,
+          "confidence": 0.977
+        },
+        {
+          "text": "got",
+          "start": 38.86,
+          "end": 38.9,
+          "confidence": 0.977
+        },
+        {
+          "text": "them,",
+          "start": 38.9,
+          "end": 38.94,
+          "confidence": 0.978
+        },
+        {
+          "text": "got",
+          "start": 38.94,
+          "end": 38.98,
+          "confidence": 0.978
+        },
+        {
+          "text": "them,",
+          "start": 38.98,
+          "end": 39.02,
+          "confidence": 0.978
+        },
+        {
+          "text": "got",
+          "start": 39.02,
+          "end": 39.06,
+          "confidence": 0.98
+        },
+        {
+          "text": "them,",
+          "start": 39.06,
+          "end": 39.1,
+          "confidence": 0.979
+        },
+        {
+          "text": "got",
+          "start": 39.1,
+          "end": 39.14,
+          "confidence": 0.982
+        },
+        {
+          "text": "them,",
+          "start": 39.14,
+          "end": 39.18,
+          "confidence": 0.981
+        },
+        {
+          "text": "got",
+          "start": 39.18,
+          "end": 39.22,
+          "confidence": 0.984
+        },
+        {
+          "text": "them,",
+          "start": 39.22,
+          "end": 39.26,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 39.26,
+          "end": 39.3,
+          "confidence": 0.984
+        },
+        {
+          "text": "them,",
+          "start": 39.3,
+          "end": 39.34,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 39.34,
+          "end": 39.38,
+          "confidence": 0.986
+        },
+        {
+          "text": "them,",
+          "start": 39.38,
+          "end": 39.42,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 39.42,
+          "end": 39.46,
+          "confidence": 0.988
+        },
+        {
+          "text": "them,",
+          "start": 39.46,
+          "end": 39.5,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 39.5,
+          "end": 39.54,
+          "confidence": 0.989
+        },
+        {
+          "text": "them,",
+          "start": 39.54,
+          "end": 39.58,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 39.58,
+          "end": 39.62,
+          "confidence": 0.99
+        },
+        {
+          "text": "them,",
+          "start": 39.62,
+          "end": 39.66,
+          "confidence": 0.984
+        },
+        {
+          "text": "got",
+          "start": 39.66,
+          "end": 39.7,
+          "confidence": 0.99
+        },
+        {
+          "text": "them,",
+          "start": 39.7,
+          "end": 39.74,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 39.74,
+          "end": 39.78,
+          "confidence": 0.991
+        },
+        {
+          "text": "them,",
+          "start": 39.78,
+          "end": 39.82,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 39.82,
+          "end": 39.86,
+          "confidence": 0.991
+        },
+        {
+          "text": "them,",
+          "start": 39.86,
+          "end": 39.9,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 39.9,
+          "end": 39.94,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 39.94,
+          "end": 39.98,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 39.98,
+          "end": 40.02,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 40.02,
+          "end": 40.06,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 40.06,
+          "end": 40.1,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 40.1,
+          "end": 40.14,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 40.14,
+          "end": 40.18,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 40.18,
+          "end": 40.22,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 40.22,
+          "end": 40.26,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 40.26,
+          "end": 40.3,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 40.3,
+          "end": 40.34,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 40.34,
+          "end": 40.38,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 40.38,
+          "end": 40.42,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 40.42,
+          "end": 40.46,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 40.46,
+          "end": 40.5,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 40.5,
+          "end": 40.54,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 40.54,
+          "end": 40.58,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 40.58,
+          "end": 40.76,
+          "confidence": 0.988
+        },
+        {
+          "text": "got",
+          "start": 40.76,
+          "end": 40.8,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 40.8,
+          "end": 40.84,
+          "confidence": 0.988
+        },
+        {
+          "text": "got",
+          "start": 40.84,
+          "end": 40.88,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 40.88,
+          "end": 40.92,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 40.92,
+          "end": 40.96,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 40.96,
+          "end": 41.0,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 41.0,
+          "end": 41.04,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 41.04,
+          "end": 41.08,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 41.08,
+          "end": 41.12,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 41.12,
+          "end": 42.32,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 42.32,
+          "end": 42.68,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 42.68,
+          "end": 42.9,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 42.9,
+          "end": 44.08,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 44.08,
+          "end": 44.96,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 44.96,
+          "end": 46.9,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 46.9,
+          "end": 47.82,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 47.82,
+          "end": 48.56,
+          "confidence": 0.994
+        },
+        {
+          "text": "them",
+          "start": 48.56,
+          "end": 54.62,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 5500,
+      "start": 54.64,
+      "end": 84.6,
+      "text": " got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them",
+      "tokens": [
+        50364,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.053046889369263245,
+      "compression_ratio": 29.52,
+      "no_speech_prob": 0.24410122632980347,
+      "confidence": 0.839,
+      "words": [
+        {
+          "text": "got",
+          "start": 54.64,
+          "end": 54.82,
+          "confidence": 0.004
+        },
+        {
+          "text": "them,",
+          "start": 54.82,
+          "end": 56.36,
+          "confidence": 0.007
+        },
+        {
+          "text": "got",
+          "start": 56.36,
+          "end": 58.46,
+          "confidence": 0.037
+        },
+        {
+          "text": "them,",
+          "start": 58.46,
+          "end": 59.7,
+          "confidence": 0.349
+        },
+        {
+          "text": "got",
+          "start": 59.7,
+          "end": 60.0,
+          "confidence": 0.616
+        },
+        {
+          "text": "them,",
+          "start": 60.0,
+          "end": 60.04,
+          "confidence": 0.574
+        },
+        {
+          "text": "got",
+          "start": 60.04,
+          "end": 60.08,
+          "confidence": 0.808
+        },
+        {
+          "text": "them,",
+          "start": 60.08,
+          "end": 60.12,
+          "confidence": 0.636
+        },
+        {
+          "text": "got",
+          "start": 60.12,
+          "end": 60.16,
+          "confidence": 0.875
+        },
+        {
+          "text": "them,",
+          "start": 60.16,
+          "end": 60.2,
+          "confidence": 0.676
+        },
+        {
+          "text": "got",
+          "start": 60.2,
+          "end": 60.24,
+          "confidence": 0.9
+        },
+        {
+          "text": "them,",
+          "start": 60.24,
+          "end": 60.42,
+          "confidence": 0.689
+        },
+        {
+          "text": "got",
+          "start": 60.42,
+          "end": 60.46,
+          "confidence": 0.871
+        },
+        {
+          "text": "them,",
+          "start": 60.46,
+          "end": 60.5,
+          "confidence": 0.757
+        },
+        {
+          "text": "got",
+          "start": 60.5,
+          "end": 60.62,
+          "confidence": 0.904
+        },
+        {
+          "text": "them,",
+          "start": 60.62,
+          "end": 61.78,
+          "confidence": 0.825
+        },
+        {
+          "text": "got",
+          "start": 61.78,
+          "end": 61.82,
+          "confidence": 0.926
+        },
+        {
+          "text": "them,",
+          "start": 61.82,
+          "end": 61.86,
+          "confidence": 0.58
+        },
+        {
+          "text": "got",
+          "start": 61.86,
+          "end": 61.9,
+          "confidence": 0.123
+        },
+        {
+          "text": "them,",
+          "start": 61.9,
+          "end": 61.94,
+          "confidence": 0.75
+        },
+        {
+          "text": "got",
+          "start": 61.94,
+          "end": 61.98,
+          "confidence": 0.772
+        },
+        {
+          "text": "them,",
+          "start": 61.98,
+          "end": 62.02,
+          "confidence": 0.81
+        },
+        {
+          "text": "got",
+          "start": 62.02,
+          "end": 62.06,
+          "confidence": 0.808
+        },
+        {
+          "text": "them,",
+          "start": 62.06,
+          "end": 62.1,
+          "confidence": 0.828
+        },
+        {
+          "text": "got",
+          "start": 62.1,
+          "end": 62.14,
+          "confidence": 0.82
+        },
+        {
+          "text": "them,",
+          "start": 62.14,
+          "end": 62.18,
+          "confidence": 0.852
+        },
+        {
+          "text": "got",
+          "start": 62.18,
+          "end": 62.22,
+          "confidence": 0.858
+        },
+        {
+          "text": "them,",
+          "start": 62.22,
+          "end": 62.26,
+          "confidence": 0.886
+        },
+        {
+          "text": "got",
+          "start": 62.26,
+          "end": 62.3,
+          "confidence": 0.899
+        },
+        {
+          "text": "them,",
+          "start": 62.3,
+          "end": 62.34,
+          "confidence": 0.901
+        },
+        {
+          "text": "got",
+          "start": 62.34,
+          "end": 62.38,
+          "confidence": 0.89
+        },
+        {
+          "text": "them,",
+          "start": 62.38,
+          "end": 62.42,
+          "confidence": 0.905
+        },
+        {
+          "text": "got",
+          "start": 62.42,
+          "end": 62.46,
+          "confidence": 0.868
+        },
+        {
+          "text": "them,",
+          "start": 62.46,
+          "end": 62.5,
+          "confidence": 0.919
+        },
+        {
+          "text": "got",
+          "start": 62.5,
+          "end": 62.54,
+          "confidence": 0.881
+        },
+        {
+          "text": "them,",
+          "start": 62.54,
+          "end": 62.58,
+          "confidence": 0.929
+        },
+        {
+          "text": "got",
+          "start": 62.58,
+          "end": 62.62,
+          "confidence": 0.893
+        },
+        {
+          "text": "them,",
+          "start": 62.62,
+          "end": 62.66,
+          "confidence": 0.938
+        },
+        {
+          "text": "got",
+          "start": 62.66,
+          "end": 62.7,
+          "confidence": 0.906
+        },
+        {
+          "text": "them,",
+          "start": 62.7,
+          "end": 62.74,
+          "confidence": 0.943
+        },
+        {
+          "text": "got",
+          "start": 62.74,
+          "end": 62.78,
+          "confidence": 0.913
+        },
+        {
+          "text": "them,",
+          "start": 62.78,
+          "end": 62.82,
+          "confidence": 0.949
+        },
+        {
+          "text": "got",
+          "start": 62.82,
+          "end": 62.86,
+          "confidence": 0.919
+        },
+        {
+          "text": "them,",
+          "start": 62.86,
+          "end": 62.9,
+          "confidence": 0.952
+        },
+        {
+          "text": "got",
+          "start": 62.9,
+          "end": 62.94,
+          "confidence": 0.926
+        },
+        {
+          "text": "them,",
+          "start": 62.94,
+          "end": 62.98,
+          "confidence": 0.956
+        },
+        {
+          "text": "got",
+          "start": 62.98,
+          "end": 63.02,
+          "confidence": 0.932
+        },
+        {
+          "text": "them,",
+          "start": 63.02,
+          "end": 63.06,
+          "confidence": 0.958
+        },
+        {
+          "text": "got",
+          "start": 63.06,
+          "end": 63.1,
+          "confidence": 0.936
+        },
+        {
+          "text": "them,",
+          "start": 63.1,
+          "end": 63.14,
+          "confidence": 0.961
+        },
+        {
+          "text": "got",
+          "start": 63.14,
+          "end": 63.18,
+          "confidence": 0.938
+        },
+        {
+          "text": "them,",
+          "start": 63.18,
+          "end": 63.22,
+          "confidence": 0.964
+        },
+        {
+          "text": "got",
+          "start": 63.22,
+          "end": 63.26,
+          "confidence": 0.939
+        },
+        {
+          "text": "them,",
+          "start": 63.26,
+          "end": 63.3,
+          "confidence": 0.964
+        },
+        {
+          "text": "got",
+          "start": 63.3,
+          "end": 63.34,
+          "confidence": 0.941
+        },
+        {
+          "text": "them,",
+          "start": 63.34,
+          "end": 63.38,
+          "confidence": 0.965
+        },
+        {
+          "text": "got",
+          "start": 63.38,
+          "end": 63.42,
+          "confidence": 0.943
+        },
+        {
+          "text": "them,",
+          "start": 63.42,
+          "end": 63.46,
+          "confidence": 0.967
+        },
+        {
+          "text": "got",
+          "start": 63.46,
+          "end": 63.5,
+          "confidence": 0.944
+        },
+        {
+          "text": "them,",
+          "start": 63.5,
+          "end": 63.54,
+          "confidence": 0.968
+        },
+        {
+          "text": "got",
+          "start": 63.54,
+          "end": 63.58,
+          "confidence": 0.945
+        },
+        {
+          "text": "them,",
+          "start": 63.58,
+          "end": 63.62,
+          "confidence": 0.968
+        },
+        {
+          "text": "got",
+          "start": 63.62,
+          "end": 63.66,
+          "confidence": 0.947
+        },
+        {
+          "text": "them,",
+          "start": 63.66,
+          "end": 63.7,
+          "confidence": 0.97
+        },
+        {
+          "text": "got",
+          "start": 63.7,
+          "end": 63.74,
+          "confidence": 0.947
+        },
+        {
+          "text": "them,",
+          "start": 63.74,
+          "end": 63.78,
+          "confidence": 0.971
+        },
+        {
+          "text": "got",
+          "start": 63.78,
+          "end": 63.82,
+          "confidence": 0.949
+        },
+        {
+          "text": "them,",
+          "start": 63.82,
+          "end": 63.86,
+          "confidence": 0.971
+        },
+        {
+          "text": "got",
+          "start": 63.86,
+          "end": 63.9,
+          "confidence": 0.95
+        },
+        {
+          "text": "them,",
+          "start": 63.9,
+          "end": 63.94,
+          "confidence": 0.971
+        },
+        {
+          "text": "got",
+          "start": 63.94,
+          "end": 63.98,
+          "confidence": 0.952
+        },
+        {
+          "text": "them,",
+          "start": 63.98,
+          "end": 64.02,
+          "confidence": 0.97
+        },
+        {
+          "text": "got",
+          "start": 64.02,
+          "end": 64.06,
+          "confidence": 0.953
+        },
+        {
+          "text": "them,",
+          "start": 64.06,
+          "end": 64.1,
+          "confidence": 0.972
+        },
+        {
+          "text": "got",
+          "start": 64.1,
+          "end": 64.14,
+          "confidence": 0.955
+        },
+        {
+          "text": "them,",
+          "start": 64.14,
+          "end": 64.18,
+          "confidence": 0.972
+        },
+        {
+          "text": "got",
+          "start": 64.18,
+          "end": 64.22,
+          "confidence": 0.957
+        },
+        {
+          "text": "them,",
+          "start": 64.22,
+          "end": 64.26,
+          "confidence": 0.973
+        },
+        {
+          "text": "got",
+          "start": 64.26,
+          "end": 64.3,
+          "confidence": 0.958
+        },
+        {
+          "text": "them,",
+          "start": 64.3,
+          "end": 64.34,
+          "confidence": 0.974
+        },
+        {
+          "text": "got",
+          "start": 64.34,
+          "end": 64.38,
+          "confidence": 0.959
+        },
+        {
+          "text": "them,",
+          "start": 64.38,
+          "end": 64.42,
+          "confidence": 0.974
+        },
+        {
+          "text": "got",
+          "start": 64.42,
+          "end": 64.46,
+          "confidence": 0.961
+        },
+        {
+          "text": "them,",
+          "start": 64.46,
+          "end": 64.5,
+          "confidence": 0.974
+        },
+        {
+          "text": "got",
+          "start": 64.5,
+          "end": 64.54,
+          "confidence": 0.964
+        },
+        {
+          "text": "them,",
+          "start": 64.54,
+          "end": 64.58,
+          "confidence": 0.974
+        },
+        {
+          "text": "got",
+          "start": 64.58,
+          "end": 64.62,
+          "confidence": 0.965
+        },
+        {
+          "text": "them,",
+          "start": 64.62,
+          "end": 64.66,
+          "confidence": 0.975
+        },
+        {
+          "text": "got",
+          "start": 64.66,
+          "end": 64.7,
+          "confidence": 0.967
+        },
+        {
+          "text": "them,",
+          "start": 64.7,
+          "end": 64.74,
+          "confidence": 0.975
+        },
+        {
+          "text": "got",
+          "start": 64.74,
+          "end": 64.78,
+          "confidence": 0.97
+        },
+        {
+          "text": "them,",
+          "start": 64.78,
+          "end": 64.82,
+          "confidence": 0.977
+        },
+        {
+          "text": "got",
+          "start": 64.82,
+          "end": 64.86,
+          "confidence": 0.971
+        },
+        {
+          "text": "them,",
+          "start": 64.86,
+          "end": 64.9,
+          "confidence": 0.977
+        },
+        {
+          "text": "got",
+          "start": 64.9,
+          "end": 64.94,
+          "confidence": 0.973
+        },
+        {
+          "text": "them,",
+          "start": 64.94,
+          "end": 64.98,
+          "confidence": 0.976
+        },
+        {
+          "text": "got",
+          "start": 64.98,
+          "end": 65.02,
+          "confidence": 0.975
+        },
+        {
+          "text": "them,",
+          "start": 65.02,
+          "end": 65.06,
+          "confidence": 0.976
+        },
+        {
+          "text": "got",
+          "start": 65.06,
+          "end": 65.1,
+          "confidence": 0.976
+        },
+        {
+          "text": "them,",
+          "start": 65.1,
+          "end": 65.14,
+          "confidence": 0.978
+        },
+        {
+          "text": "got",
+          "start": 65.14,
+          "end": 65.18,
+          "confidence": 0.978
+        },
+        {
+          "text": "them,",
+          "start": 65.18,
+          "end": 65.22,
+          "confidence": 0.978
+        },
+        {
+          "text": "got",
+          "start": 65.22,
+          "end": 65.26,
+          "confidence": 0.978
+        },
+        {
+          "text": "them,",
+          "start": 65.26,
+          "end": 65.3,
+          "confidence": 0.979
+        },
+        {
+          "text": "got",
+          "start": 65.3,
+          "end": 65.34,
+          "confidence": 0.98
+        },
+        {
+          "text": "them,",
+          "start": 65.34,
+          "end": 65.38,
+          "confidence": 0.979
+        },
+        {
+          "text": "got",
+          "start": 65.38,
+          "end": 65.42,
+          "confidence": 0.981
+        },
+        {
+          "text": "them,",
+          "start": 65.42,
+          "end": 65.46,
+          "confidence": 0.978
+        },
+        {
+          "text": "got",
+          "start": 65.46,
+          "end": 65.5,
+          "confidence": 0.982
+        },
+        {
+          "text": "them,",
+          "start": 65.5,
+          "end": 65.54,
+          "confidence": 0.98
+        },
+        {
+          "text": "got",
+          "start": 65.54,
+          "end": 65.58,
+          "confidence": 0.983
+        },
+        {
+          "text": "them,",
+          "start": 65.58,
+          "end": 65.62,
+          "confidence": 0.979
+        },
+        {
+          "text": "got",
+          "start": 65.62,
+          "end": 65.66,
+          "confidence": 0.984
+        },
+        {
+          "text": "them,",
+          "start": 65.66,
+          "end": 65.7,
+          "confidence": 0.98
+        },
+        {
+          "text": "got",
+          "start": 65.7,
+          "end": 65.74,
+          "confidence": 0.985
+        },
+        {
+          "text": "them,",
+          "start": 65.74,
+          "end": 65.78,
+          "confidence": 0.98
+        },
+        {
+          "text": "got",
+          "start": 65.78,
+          "end": 65.82,
+          "confidence": 0.986
+        },
+        {
+          "text": "them,",
+          "start": 65.82,
+          "end": 65.86,
+          "confidence": 0.981
+        },
+        {
+          "text": "got",
+          "start": 65.86,
+          "end": 65.9,
+          "confidence": 0.986
+        },
+        {
+          "text": "them,",
+          "start": 65.9,
+          "end": 65.94,
+          "confidence": 0.98
+        },
+        {
+          "text": "got",
+          "start": 65.94,
+          "end": 65.98,
+          "confidence": 0.987
+        },
+        {
+          "text": "them,",
+          "start": 65.98,
+          "end": 66.02,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 66.02,
+          "end": 66.3,
+          "confidence": 0.987
+        },
+        {
+          "text": "them,",
+          "start": 66.3,
+          "end": 66.34,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 66.34,
+          "end": 66.54,
+          "confidence": 0.987
+        },
+        {
+          "text": "them,",
+          "start": 66.54,
+          "end": 66.58,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 66.58,
+          "end": 66.62,
+          "confidence": 0.988
+        },
+        {
+          "text": "them,",
+          "start": 66.62,
+          "end": 66.66,
+          "confidence": 0.981
+        },
+        {
+          "text": "got",
+          "start": 66.66,
+          "end": 67.38,
+          "confidence": 0.989
+        },
+        {
+          "text": "them,",
+          "start": 67.38,
+          "end": 67.42,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 67.42,
+          "end": 67.46,
+          "confidence": 0.989
+        },
+        {
+          "text": "them,",
+          "start": 67.46,
+          "end": 67.5,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 67.5,
+          "end": 67.54,
+          "confidence": 0.99
+        },
+        {
+          "text": "them,",
+          "start": 67.54,
+          "end": 67.72,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 67.72,
+          "end": 67.76,
+          "confidence": 0.99
+        },
+        {
+          "text": "them,",
+          "start": 67.76,
+          "end": 67.8,
+          "confidence": 0.984
+        },
+        {
+          "text": "got",
+          "start": 67.8,
+          "end": 68.9,
+          "confidence": 0.991
+        },
+        {
+          "text": "them,",
+          "start": 68.9,
+          "end": 69.8,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 69.8,
+          "end": 70.66,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 70.66,
+          "end": 70.94,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 70.94,
+          "end": 71.08,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 71.08,
+          "end": 72.02,
+          "confidence": 0.984
+        },
+        {
+          "text": "got",
+          "start": 72.02,
+          "end": 72.08,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 72.08,
+          "end": 72.84,
+          "confidence": 0.984
+        },
+        {
+          "text": "got",
+          "start": 72.84,
+          "end": 77.32,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 77.32,
+          "end": 79.8,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 79.8,
+          "end": 79.84,
+          "confidence": 0.992
+        },
+        {
+          "text": "them",
+          "start": 79.84,
+          "end": 84.6,
+          "confidence": 0.994
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 8500,
+      "start": 85.24,
+      "end": 91.16,
+      "text": " got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them",
+      "tokens": [
+        50364,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.04965524716227578,
+      "compression_ratio": 29.52,
+      "no_speech_prob": 0.6971923112869263,
+      "confidence": 0.851,
+      "words": [
+        {
+          "text": "got",
+          "start": 85.24,
+          "end": 85.28,
+          "confidence": 0.0
+        },
+        {
+          "text": "them,",
+          "start": 85.28,
+          "end": 85.32,
+          "confidence": 0.024
+        },
+        {
+          "text": "got",
+          "start": 85.32,
+          "end": 85.36,
+          "confidence": 0.839
+        },
+        {
+          "text": "them,",
+          "start": 85.36,
+          "end": 85.4,
+          "confidence": 0.564
+        },
+        {
+          "text": "got",
+          "start": 85.4,
+          "end": 85.44,
+          "confidence": 0.755
+        },
+        {
+          "text": "them,",
+          "start": 85.44,
+          "end": 85.48,
+          "confidence": 0.442
+        },
+        {
+          "text": "got",
+          "start": 85.48,
+          "end": 85.52,
+          "confidence": 0.859
+        },
+        {
+          "text": "them,",
+          "start": 85.52,
+          "end": 85.56,
+          "confidence": 0.389
+        },
+        {
+          "text": "got",
+          "start": 85.56,
+          "end": 85.6,
+          "confidence": 0.895
+        },
+        {
+          "text": "them,",
+          "start": 85.6,
+          "end": 85.64,
+          "confidence": 0.376
+        },
+        {
+          "text": "got",
+          "start": 85.64,
+          "end": 85.68,
+          "confidence": 0.896
+        },
+        {
+          "text": "them,",
+          "start": 85.68,
+          "end": 85.72,
+          "confidence": 0.39
+        },
+        {
+          "text": "got",
+          "start": 85.72,
+          "end": 85.76,
+          "confidence": 0.871
+        },
+        {
+          "text": "them,",
+          "start": 85.76,
+          "end": 85.8,
+          "confidence": 0.468
+        },
+        {
+          "text": "got",
+          "start": 85.8,
+          "end": 85.84,
+          "confidence": 0.894
+        },
+        {
+          "text": "them,",
+          "start": 85.84,
+          "end": 85.88,
+          "confidence": 0.576
+        },
+        {
+          "text": "got",
+          "start": 85.88,
+          "end": 85.92,
+          "confidence": 0.914
+        },
+        {
+          "text": "them,",
+          "start": 85.92,
+          "end": 85.96,
+          "confidence": 0.645
+        },
+        {
+          "text": "got",
+          "start": 85.96,
+          "end": 86.0,
+          "confidence": 0.633
+        },
+        {
+          "text": "them,",
+          "start": 86.0,
+          "end": 86.04,
+          "confidence": 0.746
+        },
+        {
+          "text": "got",
+          "start": 86.04,
+          "end": 86.08,
+          "confidence": 0.829
+        },
+        {
+          "text": "them,",
+          "start": 86.08,
+          "end": 86.12,
+          "confidence": 0.842
+        },
+        {
+          "text": "got",
+          "start": 86.12,
+          "end": 86.16,
+          "confidence": 0.906
+        },
+        {
+          "text": "them,",
+          "start": 86.16,
+          "end": 86.2,
+          "confidence": 0.89
+        },
+        {
+          "text": "got",
+          "start": 86.2,
+          "end": 86.24,
+          "confidence": 0.924
+        },
+        {
+          "text": "them,",
+          "start": 86.24,
+          "end": 86.28,
+          "confidence": 0.916
+        },
+        {
+          "text": "got",
+          "start": 86.28,
+          "end": 86.32,
+          "confidence": 0.94
+        },
+        {
+          "text": "them,",
+          "start": 86.32,
+          "end": 86.36,
+          "confidence": 0.934
+        },
+        {
+          "text": "got",
+          "start": 86.36,
+          "end": 86.4,
+          "confidence": 0.95
+        },
+        {
+          "text": "them,",
+          "start": 86.4,
+          "end": 86.44,
+          "confidence": 0.946
+        },
+        {
+          "text": "got",
+          "start": 86.44,
+          "end": 86.48,
+          "confidence": 0.954
+        },
+        {
+          "text": "them,",
+          "start": 86.48,
+          "end": 86.52,
+          "confidence": 0.946
+        },
+        {
+          "text": "got",
+          "start": 86.52,
+          "end": 86.56,
+          "confidence": 0.955
+        },
+        {
+          "text": "them,",
+          "start": 86.56,
+          "end": 86.6,
+          "confidence": 0.946
+        },
+        {
+          "text": "got",
+          "start": 86.6,
+          "end": 86.64,
+          "confidence": 0.947
+        },
+        {
+          "text": "them,",
+          "start": 86.64,
+          "end": 86.68,
+          "confidence": 0.948
+        },
+        {
+          "text": "got",
+          "start": 86.68,
+          "end": 86.72,
+          "confidence": 0.941
+        },
+        {
+          "text": "them,",
+          "start": 86.72,
+          "end": 86.76,
+          "confidence": 0.953
+        },
+        {
+          "text": "got",
+          "start": 86.76,
+          "end": 86.8,
+          "confidence": 0.942
+        },
+        {
+          "text": "them,",
+          "start": 86.8,
+          "end": 86.84,
+          "confidence": 0.956
+        },
+        {
+          "text": "got",
+          "start": 86.84,
+          "end": 86.88,
+          "confidence": 0.942
+        },
+        {
+          "text": "them,",
+          "start": 86.88,
+          "end": 86.92,
+          "confidence": 0.961
+        },
+        {
+          "text": "got",
+          "start": 86.92,
+          "end": 86.96,
+          "confidence": 0.942
+        },
+        {
+          "text": "them,",
+          "start": 86.96,
+          "end": 87.0,
+          "confidence": 0.964
+        },
+        {
+          "text": "got",
+          "start": 87.0,
+          "end": 87.04,
+          "confidence": 0.945
+        },
+        {
+          "text": "them,",
+          "start": 87.04,
+          "end": 87.08,
+          "confidence": 0.967
+        },
+        {
+          "text": "got",
+          "start": 87.08,
+          "end": 87.12,
+          "confidence": 0.948
+        },
+        {
+          "text": "them,",
+          "start": 87.12,
+          "end": 87.16,
+          "confidence": 0.969
+        },
+        {
+          "text": "got",
+          "start": 87.16,
+          "end": 87.2,
+          "confidence": 0.951
+        },
+        {
+          "text": "them,",
+          "start": 87.2,
+          "end": 87.24,
+          "confidence": 0.972
+        },
+        {
+          "text": "got",
+          "start": 87.24,
+          "end": 87.28,
+          "confidence": 0.951
+        },
+        {
+          "text": "them,",
+          "start": 87.28,
+          "end": 87.32,
+          "confidence": 0.976
+        },
+        {
+          "text": "got",
+          "start": 87.32,
+          "end": 87.36,
+          "confidence": 0.951
+        },
+        {
+          "text": "them,",
+          "start": 87.36,
+          "end": 87.4,
+          "confidence": 0.976
+        },
+        {
+          "text": "got",
+          "start": 87.4,
+          "end": 87.44,
+          "confidence": 0.951
+        },
+        {
+          "text": "them,",
+          "start": 87.44,
+          "end": 87.48,
+          "confidence": 0.977
+        },
+        {
+          "text": "got",
+          "start": 87.48,
+          "end": 87.52,
+          "confidence": 0.954
+        },
+        {
+          "text": "them,",
+          "start": 87.52,
+          "end": 87.56,
+          "confidence": 0.978
+        },
+        {
+          "text": "got",
+          "start": 87.56,
+          "end": 87.6,
+          "confidence": 0.954
+        },
+        {
+          "text": "them,",
+          "start": 87.6,
+          "end": 87.64,
+          "confidence": 0.98
+        },
+        {
+          "text": "got",
+          "start": 87.64,
+          "end": 87.68,
+          "confidence": 0.956
+        },
+        {
+          "text": "them,",
+          "start": 87.68,
+          "end": 87.72,
+          "confidence": 0.98
+        },
+        {
+          "text": "got",
+          "start": 87.72,
+          "end": 87.76,
+          "confidence": 0.957
+        },
+        {
+          "text": "them,",
+          "start": 87.76,
+          "end": 87.8,
+          "confidence": 0.981
+        },
+        {
+          "text": "got",
+          "start": 87.8,
+          "end": 87.84,
+          "confidence": 0.958
+        },
+        {
+          "text": "them,",
+          "start": 87.84,
+          "end": 87.88,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 87.88,
+          "end": 87.92,
+          "confidence": 0.959
+        },
+        {
+          "text": "them,",
+          "start": 87.92,
+          "end": 87.96,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 87.96,
+          "end": 88.0,
+          "confidence": 0.961
+        },
+        {
+          "text": "them,",
+          "start": 88.0,
+          "end": 88.04,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 88.04,
+          "end": 88.08,
+          "confidence": 0.963
+        },
+        {
+          "text": "them,",
+          "start": 88.08,
+          "end": 88.12,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 88.12,
+          "end": 88.16,
+          "confidence": 0.965
+        },
+        {
+          "text": "them,",
+          "start": 88.16,
+          "end": 88.2,
+          "confidence": 0.984
+        },
+        {
+          "text": "got",
+          "start": 88.2,
+          "end": 88.24,
+          "confidence": 0.966
+        },
+        {
+          "text": "them,",
+          "start": 88.24,
+          "end": 88.28,
+          "confidence": 0.984
+        },
+        {
+          "text": "got",
+          "start": 88.28,
+          "end": 88.32,
+          "confidence": 0.968
+        },
+        {
+          "text": "them,",
+          "start": 88.32,
+          "end": 88.36,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 88.36,
+          "end": 88.4,
+          "confidence": 0.97
+        },
+        {
+          "text": "them,",
+          "start": 88.4,
+          "end": 88.44,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 88.44,
+          "end": 88.48,
+          "confidence": 0.971
+        },
+        {
+          "text": "them,",
+          "start": 88.48,
+          "end": 88.52,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 88.52,
+          "end": 88.56,
+          "confidence": 0.973
+        },
+        {
+          "text": "them,",
+          "start": 88.56,
+          "end": 88.6,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 88.6,
+          "end": 88.64,
+          "confidence": 0.975
+        },
+        {
+          "text": "them,",
+          "start": 88.64,
+          "end": 88.68,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 88.68,
+          "end": 88.72,
+          "confidence": 0.977
+        },
+        {
+          "text": "them,",
+          "start": 88.72,
+          "end": 88.76,
+          "confidence": 0.988
+        },
+        {
+          "text": "got",
+          "start": 88.76,
+          "end": 88.8,
+          "confidence": 0.978
+        },
+        {
+          "text": "them,",
+          "start": 88.8,
+          "end": 88.84,
+          "confidence": 0.988
+        },
+        {
+          "text": "got",
+          "start": 88.84,
+          "end": 88.88,
+          "confidence": 0.981
+        },
+        {
+          "text": "them,",
+          "start": 88.88,
+          "end": 88.92,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 88.92,
+          "end": 88.96,
+          "confidence": 0.982
+        },
+        {
+          "text": "them,",
+          "start": 88.96,
+          "end": 89.0,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 89.0,
+          "end": 89.04,
+          "confidence": 0.983
+        },
+        {
+          "text": "them,",
+          "start": 89.04,
+          "end": 89.08,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 89.08,
+          "end": 89.12,
+          "confidence": 0.985
+        },
+        {
+          "text": "them,",
+          "start": 89.12,
+          "end": 89.16,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 89.16,
+          "end": 89.2,
+          "confidence": 0.987
+        },
+        {
+          "text": "them,",
+          "start": 89.2,
+          "end": 89.24,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 89.24,
+          "end": 89.28,
+          "confidence": 0.988
+        },
+        {
+          "text": "them,",
+          "start": 89.28,
+          "end": 89.32,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 89.32,
+          "end": 89.36,
+          "confidence": 0.988
+        },
+        {
+          "text": "them,",
+          "start": 89.36,
+          "end": 89.4,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 89.4,
+          "end": 89.44,
+          "confidence": 0.99
+        },
+        {
+          "text": "them,",
+          "start": 89.44,
+          "end": 89.48,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 89.48,
+          "end": 89.52,
+          "confidence": 0.99
+        },
+        {
+          "text": "them,",
+          "start": 89.52,
+          "end": 89.56,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 89.56,
+          "end": 89.6,
+          "confidence": 0.991
+        },
+        {
+          "text": "them,",
+          "start": 89.6,
+          "end": 89.64,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 89.64,
+          "end": 89.68,
+          "confidence": 0.991
+        },
+        {
+          "text": "them,",
+          "start": 89.68,
+          "end": 89.72,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 89.72,
+          "end": 89.76,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 89.76,
+          "end": 89.8,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 89.8,
+          "end": 89.84,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 89.84,
+          "end": 89.88,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 89.88,
+          "end": 89.92,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 89.92,
+          "end": 89.96,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 89.96,
+          "end": 90.0,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 90.0,
+          "end": 90.04,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 90.04,
+          "end": 90.08,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 90.08,
+          "end": 90.12,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 90.12,
+          "end": 90.16,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 90.16,
+          "end": 90.2,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 90.2,
+          "end": 90.24,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 90.24,
+          "end": 90.28,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 90.28,
+          "end": 90.32,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 90.32,
+          "end": 90.36,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 90.36,
+          "end": 90.4,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 90.4,
+          "end": 90.44,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 90.44,
+          "end": 90.48,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 90.48,
+          "end": 90.52,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 90.52,
+          "end": 90.56,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 90.56,
+          "end": 90.6,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 90.6,
+          "end": 90.64,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 90.64,
+          "end": 90.68,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 90.68,
+          "end": 90.72,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 90.72,
+          "end": 90.76,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 90.76,
+          "end": 90.8,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 90.8,
+          "end": 90.84,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 90.84,
+          "end": 90.88,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 90.88,
+          "end": 90.92,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 90.92,
+          "end": 90.96,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 90.96,
+          "end": 91.0,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 91.0,
+          "end": 91.04,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 91.04,
+          "end": 91.08,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 91.08,
+          "end": 91.12,
+          "confidence": 0.995
+        },
+        {
+          "text": "them",
+          "start": 91.12,
+          "end": 91.16,
+          "confidence": 0.998
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/naive.cuda/accurate_apollo11.mp3.words.json b/tests/expected/naive.cuda/accurate_apollo11.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..5541228558b3a625658b695ccc9b63cdd745f928
--- /dev/null
+++ b/tests/expected/naive.cuda/accurate_apollo11.mp3.words.json
@@ -0,0 +1,2438 @@
+{
+  "text": " Apollo 11, Houston, we got a recommendation for you on your Soyuz-EA GLEM-E-G-E-A. All right. Okay. Yeah, sir. Yeah, sir. Let's take that camera. Let's say it makes it want to go on the helmet we were going to have in B-1. The other one. And you can put the other one on the mic helmet. We'll show it to you in a quick screen. Over. All right. Yeah, sir. All right. Yeah, sir. There's a better helmet than B-1. That's the other one. Nice. Let's go in there. At least we're safe. We've got them in there. Helmet bags. And, uh, I guess we have helmets in the helmet bag. At least it's in the helmet bag. Right here. Right here. Yeah, we're taking it next day out of the field up. Yeah, we were. You want to hack me on that? Yeah, we were. You want to hack me on that? With the cover, I tried it already. Okay, fine. We weren't sure of that. Just a suggestion. We thought we'd, uh, say you could check it out. It's not much of an order to turn that. So, uh, I guess we're going to come up with this. Let us know. Okay. No problem. Okay. No problem. No problem. No problem. No problem. No problem. No problem. No problem.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.64,
+      "end": 6.76,
+      "text": " Apollo 11, Houston, we got a recommendation for you on your Soyuz-EA GLEM-E-G-E-A.",
+      "tokens": [
+        25187,
+        2975,
+        11,
+        18717,
+        11,
+        321,
+        658,
+        257,
+        11879,
+        337,
+        291,
+        322,
+        428,
+        24758,
+        3334,
+        12,
+        36,
+        32,
+        460,
+        2634,
+        44,
+        12,
+        36,
+        12,
+        38,
+        12,
+        36,
+        12,
+        32,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5338267664755544,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.4499393105506897,
+      "confidence": 0.578,
+      "words": [
+        {
+          "text": "Apollo",
+          "start": 0.64,
+          "end": 0.98,
+          "confidence": 0.425
+        },
+        {
+          "text": "11,",
+          "start": 0.98,
+          "end": 1.52,
+          "confidence": 0.842
+        },
+        {
+          "text": "Houston,",
+          "start": 1.52,
+          "end": 1.94,
+          "confidence": 0.665
+        },
+        {
+          "text": "we",
+          "start": 1.94,
+          "end": 1.98,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 1.98,
+          "end": 2.16,
+          "confidence": 0.743
+        },
+        {
+          "text": "a",
+          "start": 2.16,
+          "end": 2.32,
+          "confidence": 0.993
+        },
+        {
+          "text": "recommendation",
+          "start": 2.32,
+          "end": 3.08,
+          "confidence": 0.977
+        },
+        {
+          "text": "for",
+          "start": 3.08,
+          "end": 3.5,
+          "confidence": 0.94
+        },
+        {
+          "text": "you",
+          "start": 3.5,
+          "end": 3.72,
+          "confidence": 0.993
+        },
+        {
+          "text": "on",
+          "start": 3.72,
+          "end": 4.26,
+          "confidence": 0.918
+        },
+        {
+          "text": "your",
+          "start": 4.26,
+          "end": 4.3,
+          "confidence": 0.976
+        },
+        {
+          "text": "Soyuz-EA",
+          "start": 4.3,
+          "end": 5.36,
+          "confidence": 0.455
+        },
+        {
+          "text": "GLEM-E-G-E-A.",
+          "start": 5.36,
+          "end": 6.76,
+          "confidence": 0.436
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 10.82,
+      "end": 10.9,
+      "text": " All right.",
+      "tokens": [
+        1057,
+        558,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5338267664755544,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.4499393105506897,
+      "confidence": 0.149,
+      "words": [
+        {
+          "text": "All",
+          "start": 10.82,
+          "end": 10.86,
+          "confidence": 0.006
+        },
+        {
+          "text": "right.",
+          "start": 10.86,
+          "end": 10.9,
+          "confidence": 0.72
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 12.02,
+      "end": 12.06,
+      "text": " Okay.",
+      "tokens": [
+        1033,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5338267664755544,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.4499393105506897,
+      "confidence": 0.168,
+      "words": [
+        {
+          "text": "Okay.",
+          "start": 12.02,
+          "end": 12.06,
+          "confidence": 0.168
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 12.08,
+      "end": 13.44,
+      "text": " Yeah, sir.",
+      "tokens": [
+        865,
+        11,
+        4735,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5338267664755544,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.4499393105506897,
+      "confidence": 0.131,
+      "words": [
+        {
+          "text": "Yeah,",
+          "start": 12.08,
+          "end": 12.68,
+          "confidence": 0.079
+        },
+        {
+          "text": "sir.",
+          "start": 12.68,
+          "end": 13.44,
+          "confidence": 0.218
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 13.66,
+      "end": 14.28,
+      "text": " Yeah, sir.",
+      "tokens": [
+        865,
+        11,
+        4735,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5338267664755544,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.4499393105506897,
+      "confidence": 0.047,
+      "words": [
+        {
+          "text": "Yeah,",
+          "start": 13.66,
+          "end": 13.82,
+          "confidence": 0.11
+        },
+        {
+          "text": "sir.",
+          "start": 13.82,
+          "end": 14.28,
+          "confidence": 0.02
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 0,
+      "start": 14.3,
+      "end": 14.98,
+      "text": " Let's take that camera.",
+      "tokens": [
+        961,
+        311,
+        747,
+        300,
+        2799,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5338267664755544,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.4499393105506897,
+      "confidence": 0.033,
+      "words": [
+        {
+          "text": "Let's",
+          "start": 14.3,
+          "end": 14.54,
+          "confidence": 0.036
+        },
+        {
+          "text": "take",
+          "start": 14.54,
+          "end": 14.58,
+          "confidence": 0.026
+        },
+        {
+          "text": "that",
+          "start": 14.58,
+          "end": 14.62,
+          "confidence": 0.031
+        },
+        {
+          "text": "camera.",
+          "start": 14.62,
+          "end": 14.98,
+          "confidence": 0.034
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 0,
+      "start": 15.0,
+      "end": 19.22,
+      "text": " Let's say it makes it want to go on the helmet we were going to have in B-1.",
+      "tokens": [
+        961,
+        311,
+        584,
+        309,
+        1669,
+        309,
+        528,
+        281,
+        352,
+        322,
+        264,
+        15922,
+        321,
+        645,
+        516,
+        281,
+        362,
+        294,
+        363,
+        12,
+        16,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5338267664755544,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.4499393105506897,
+      "confidence": 0.299,
+      "words": [
+        {
+          "text": "Let's",
+          "start": 15.0,
+          "end": 15.38,
+          "confidence": 0.273
+        },
+        {
+          "text": "say",
+          "start": 15.38,
+          "end": 15.58,
+          "confidence": 0.349
+        },
+        {
+          "text": "it",
+          "start": 15.58,
+          "end": 15.76,
+          "confidence": 0.01
+        },
+        {
+          "text": "makes",
+          "start": 15.76,
+          "end": 15.8,
+          "confidence": 0.736
+        },
+        {
+          "text": "it",
+          "start": 15.8,
+          "end": 16.04,
+          "confidence": 0.921
+        },
+        {
+          "text": "want",
+          "start": 16.04,
+          "end": 16.16,
+          "confidence": 0.297
+        },
+        {
+          "text": "to",
+          "start": 16.16,
+          "end": 16.34,
+          "confidence": 0.97
+        },
+        {
+          "text": "go",
+          "start": 16.34,
+          "end": 16.44,
+          "confidence": 0.932
+        },
+        {
+          "text": "on",
+          "start": 16.44,
+          "end": 16.74,
+          "confidence": 0.912
+        },
+        {
+          "text": "the",
+          "start": 16.74,
+          "end": 16.86,
+          "confidence": 0.496
+        },
+        {
+          "text": "helmet",
+          "start": 16.86,
+          "end": 17.34,
+          "confidence": 0.005
+        },
+        {
+          "text": "we",
+          "start": 17.34,
+          "end": 17.64,
+          "confidence": 0.01
+        },
+        {
+          "text": "were",
+          "start": 17.64,
+          "end": 17.86,
+          "confidence": 0.08
+        },
+        {
+          "text": "going",
+          "start": 17.86,
+          "end": 18.04,
+          "confidence": 0.658
+        },
+        {
+          "text": "to",
+          "start": 18.04,
+          "end": 18.2,
+          "confidence": 0.966
+        },
+        {
+          "text": "have",
+          "start": 18.2,
+          "end": 18.26,
+          "confidence": 0.957
+        },
+        {
+          "text": "in",
+          "start": 18.26,
+          "end": 18.64,
+          "confidence": 0.863
+        },
+        {
+          "text": "B-1.",
+          "start": 18.64,
+          "end": 19.22,
+          "confidence": 0.506
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 0,
+      "start": 19.38,
+      "end": 19.98,
+      "text": " The other one.",
+      "tokens": [
+        440,
+        661,
+        472,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5338267664755544,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.4499393105506897,
+      "confidence": 0.13,
+      "words": [
+        {
+          "text": "The",
+          "start": 19.38,
+          "end": 19.42,
+          "confidence": 0.005
+        },
+        {
+          "text": "other",
+          "start": 19.42,
+          "end": 19.68,
+          "confidence": 0.186
+        },
+        {
+          "text": "one.",
+          "start": 19.68,
+          "end": 19.98,
+          "confidence": 0.586
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 0,
+      "start": 20.12,
+      "end": 22.9,
+      "text": " And you can put the other one on the mic helmet.",
+      "tokens": [
+        400,
+        291,
+        393,
+        829,
+        264,
+        661,
+        472,
+        322,
+        264,
+        3123,
+        15922,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5338267664755544,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.4499393105506897,
+      "confidence": 0.366,
+      "words": [
+        {
+          "text": "And",
+          "start": 20.12,
+          "end": 20.26,
+          "confidence": 0.343
+        },
+        {
+          "text": "you",
+          "start": 20.26,
+          "end": 20.38,
+          "confidence": 0.89
+        },
+        {
+          "text": "can",
+          "start": 20.38,
+          "end": 20.54,
+          "confidence": 0.087
+        },
+        {
+          "text": "put",
+          "start": 20.54,
+          "end": 20.7,
+          "confidence": 0.901
+        },
+        {
+          "text": "the",
+          "start": 20.7,
+          "end": 20.86,
+          "confidence": 0.979
+        },
+        {
+          "text": "other",
+          "start": 20.86,
+          "end": 21.06,
+          "confidence": 0.997
+        },
+        {
+          "text": "one",
+          "start": 21.06,
+          "end": 21.26,
+          "confidence": 0.973
+        },
+        {
+          "text": "on",
+          "start": 21.26,
+          "end": 21.9,
+          "confidence": 0.968
+        },
+        {
+          "text": "the",
+          "start": 21.9,
+          "end": 21.94,
+          "confidence": 0.09
+        },
+        {
+          "text": "mic",
+          "start": 21.94,
+          "end": 22.58,
+          "confidence": 0.682
+        },
+        {
+          "text": "helmet.",
+          "start": 22.58,
+          "end": 22.9,
+          "confidence": 0.066
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 0,
+      "start": 22.92,
+      "end": 24.8,
+      "text": " We'll show it to you in a quick screen.",
+      "tokens": [
+        492,
+        603,
+        855,
+        309,
+        281,
+        291,
+        294,
+        257,
+        1702,
+        2568,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5338267664755544,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.4499393105506897,
+      "confidence": 0.122,
+      "words": [
+        {
+          "text": "We'll",
+          "start": 22.92,
+          "end": 23.22,
+          "confidence": 0.08
+        },
+        {
+          "text": "show",
+          "start": 23.22,
+          "end": 23.32,
+          "confidence": 0.011
+        },
+        {
+          "text": "it",
+          "start": 23.32,
+          "end": 23.54,
+          "confidence": 0.15
+        },
+        {
+          "text": "to",
+          "start": 23.54,
+          "end": 23.64,
+          "confidence": 0.255
+        },
+        {
+          "text": "you",
+          "start": 23.64,
+          "end": 23.78,
+          "confidence": 0.703
+        },
+        {
+          "text": "in",
+          "start": 23.78,
+          "end": 23.96,
+          "confidence": 0.231
+        },
+        {
+          "text": "a",
+          "start": 23.96,
+          "end": 24.12,
+          "confidence": 0.736
+        },
+        {
+          "text": "quick",
+          "start": 24.12,
+          "end": 24.16,
+          "confidence": 0.018
+        },
+        {
+          "text": "screen.",
+          "start": 24.16,
+          "end": 24.8,
+          "confidence": 0.122
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 0,
+      "start": 24.94,
+      "end": 25.26,
+      "text": " Over.",
+      "tokens": [
+        4886,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5338267664755544,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.4499393105506897,
+      "confidence": 0.125,
+      "words": [
+        {
+          "text": "Over.",
+          "start": 24.94,
+          "end": 25.26,
+          "confidence": 0.125
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 2600,
+      "start": 25.52,
+      "end": 27.52,
+      "text": " All right.",
+      "tokens": [
+        1057,
+        558,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5128642573501124,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011020583333447576,
+      "confidence": 0.108,
+      "words": [
+        {
+          "text": "All",
+          "start": 25.52,
+          "end": 26.14,
+          "confidence": 0.003
+        },
+        {
+          "text": "right.",
+          "start": 26.14,
+          "end": 27.52,
+          "confidence": 0.677
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 2600,
+      "start": 31.32,
+      "end": 32.48,
+      "text": " Yeah, sir.",
+      "tokens": [
+        865,
+        11,
+        4735,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5128642573501124,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011020583333447576,
+      "confidence": 0.045,
+      "words": [
+        {
+          "text": "Yeah,",
+          "start": 31.32,
+          "end": 31.56,
+          "confidence": 0.033
+        },
+        {
+          "text": "sir.",
+          "start": 31.56,
+          "end": 32.48,
+          "confidence": 0.062
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 2600,
+      "start": 32.66,
+      "end": 33.06,
+      "text": " All right.",
+      "tokens": [
+        1057,
+        558,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5128642573501124,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011020583333447576,
+      "confidence": 0.223,
+      "words": [
+        {
+          "text": "All",
+          "start": 32.66,
+          "end": 32.94,
+          "confidence": 0.047
+        },
+        {
+          "text": "right.",
+          "start": 32.94,
+          "end": 33.06,
+          "confidence": 0.488
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 2600,
+      "start": 33.08,
+      "end": 34.2,
+      "text": " Yeah, sir.",
+      "tokens": [
+        865,
+        11,
+        4735,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5128642573501124,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011020583333447576,
+      "confidence": 0.035,
+      "words": [
+        {
+          "text": "Yeah,",
+          "start": 33.08,
+          "end": 33.36,
+          "confidence": 0.144
+        },
+        {
+          "text": "sir.",
+          "start": 33.36,
+          "end": 34.2,
+          "confidence": 0.009
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 2600,
+      "start": 34.52,
+      "end": 35.4,
+      "text": " There's a better helmet than B-1.",
+      "tokens": [
+        821,
+        311,
+        257,
+        1101,
+        15922,
+        813,
+        363,
+        12,
+        16,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5128642573501124,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011020583333447576,
+      "confidence": 0.014,
+      "words": [
+        {
+          "text": "There's",
+          "start": 34.52,
+          "end": 34.56,
+          "confidence": 0.046
+        },
+        {
+          "text": "a",
+          "start": 34.56,
+          "end": 34.64,
+          "confidence": 0.037
+        },
+        {
+          "text": "better",
+          "start": 34.64,
+          "end": 34.94,
+          "confidence": 0.0
+        },
+        {
+          "text": "helmet",
+          "start": 34.94,
+          "end": 34.98,
+          "confidence": 0.0
+        },
+        {
+          "text": "than",
+          "start": 34.98,
+          "end": 35.02,
+          "confidence": 0.179
+        },
+        {
+          "text": "B-1.",
+          "start": 35.02,
+          "end": 35.4,
+          "confidence": 0.033
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 2600,
+      "start": 35.42,
+      "end": 35.94,
+      "text": " That's the other one.",
+      "tokens": [
+        663,
+        311,
+        264,
+        661,
+        472,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5128642573501124,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011020583333447576,
+      "confidence": 0.162,
+      "words": [
+        {
+          "text": "That's",
+          "start": 35.42,
+          "end": 35.48,
+          "confidence": 0.082
+        },
+        {
+          "text": "the",
+          "start": 35.48,
+          "end": 35.52,
+          "confidence": 0.167
+        },
+        {
+          "text": "other",
+          "start": 35.52,
+          "end": 35.68,
+          "confidence": 0.412
+        },
+        {
+          "text": "one.",
+          "start": 35.68,
+          "end": 35.94,
+          "confidence": 0.197
+        }
+      ]
+    },
+    {
+      "id": 17,
+      "seek": 2600,
+      "start": 35.96,
+      "end": 36.34,
+      "text": " Nice.",
+      "tokens": [
+        5490,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5128642573501124,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011020583333447576,
+      "confidence": 0.007,
+      "words": [
+        {
+          "text": "Nice.",
+          "start": 35.96,
+          "end": 36.34,
+          "confidence": 0.007
+        }
+      ]
+    },
+    {
+      "id": 18,
+      "seek": 2600,
+      "start": 37.68,
+      "end": 38.48,
+      "text": " Let's go in there.",
+      "tokens": [
+        961,
+        311,
+        352,
+        294,
+        456,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5128642573501124,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011020583333447576,
+      "confidence": 0.125,
+      "words": [
+        {
+          "text": "Let's",
+          "start": 37.68,
+          "end": 38.16,
+          "confidence": 0.022
+        },
+        {
+          "text": "go",
+          "start": 38.16,
+          "end": 38.2,
+          "confidence": 0.626
+        },
+        {
+          "text": "in",
+          "start": 38.2,
+          "end": 38.24,
+          "confidence": 0.037
+        },
+        {
+          "text": "there.",
+          "start": 38.24,
+          "end": 38.48,
+          "confidence": 0.579
+        }
+      ]
+    },
+    {
+      "id": 19,
+      "seek": 2600,
+      "start": 38.6,
+      "end": 39.24,
+      "text": " At least we're safe.",
+      "tokens": [
+        1711,
+        1935,
+        321,
+        434,
+        3273,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5128642573501124,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011020583333447576,
+      "confidence": 0.125,
+      "words": [
+        {
+          "text": "At",
+          "start": 38.6,
+          "end": 38.64,
+          "confidence": 0.001
+        },
+        {
+          "text": "least",
+          "start": 38.64,
+          "end": 38.86,
+          "confidence": 0.311
+        },
+        {
+          "text": "we're",
+          "start": 38.86,
+          "end": 39.08,
+          "confidence": 0.12
+        },
+        {
+          "text": "safe.",
+          "start": 39.08,
+          "end": 39.24,
+          "confidence": 0.799
+        }
+      ]
+    },
+    {
+      "id": 20,
+      "seek": 2600,
+      "start": 39.94,
+      "end": 40.54,
+      "text": " We've got them in there.",
+      "tokens": [
+        492,
+        600,
+        658,
+        552,
+        294,
+        456,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5128642573501124,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011020583333447576,
+      "confidence": 0.076,
+      "words": [
+        {
+          "text": "We've",
+          "start": 39.94,
+          "end": 40.38,
+          "confidence": 0.06
+        },
+        {
+          "text": "got",
+          "start": 40.38,
+          "end": 40.42,
+          "confidence": 0.737
+        },
+        {
+          "text": "them",
+          "start": 40.42,
+          "end": 40.46,
+          "confidence": 0.004
+        },
+        {
+          "text": "in",
+          "start": 40.46,
+          "end": 40.5,
+          "confidence": 0.039
+        },
+        {
+          "text": "there.",
+          "start": 40.5,
+          "end": 40.54,
+          "confidence": 0.198
+        }
+      ]
+    },
+    {
+      "id": 21,
+      "seek": 2600,
+      "start": 40.54,
+      "end": 41.28,
+      "text": " Helmet bags.",
+      "tokens": [
+        6128,
+        5537,
+        10405,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5128642573501124,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011020583333447576,
+      "confidence": 0.001,
+      "words": [
+        {
+          "text": "Helmet",
+          "start": 40.54,
+          "end": 40.78,
+          "confidence": 0.001
+        },
+        {
+          "text": "bags.",
+          "start": 40.78,
+          "end": 41.28,
+          "confidence": 0.002
+        }
+      ]
+    },
+    {
+      "id": 22,
+      "seek": 2600,
+      "start": 43.52,
+      "end": 47.74,
+      "text": " And, uh, I guess we have helmets in the helmet bag.",
+      "tokens": [
+        400,
+        11,
+        2232,
+        11,
+        286,
+        2041,
+        321,
+        362,
+        42022,
+        294,
+        264,
+        15922,
+        3411,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5128642573501124,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011020583333447576,
+      "confidence": 0.208,
+      "words": [
+        {
+          "text": "And,",
+          "start": 43.52,
+          "end": 43.56,
+          "confidence": 0.087
+        },
+        {
+          "text": "uh,",
+          "start": 43.56,
+          "end": 44.02,
+          "confidence": 0.767
+        },
+        {
+          "text": "I",
+          "start": 44.02,
+          "end": 44.06,
+          "confidence": 0.321
+        },
+        {
+          "text": "guess",
+          "start": 44.06,
+          "end": 44.32,
+          "confidence": 0.236
+        },
+        {
+          "text": "we",
+          "start": 44.32,
+          "end": 45.0,
+          "confidence": 0.078
+        },
+        {
+          "text": "have",
+          "start": 45.0,
+          "end": 45.6,
+          "confidence": 0.06
+        },
+        {
+          "text": "helmets",
+          "start": 45.6,
+          "end": 46.62,
+          "confidence": 0.004
+        },
+        {
+          "text": "in",
+          "start": 46.62,
+          "end": 46.82,
+          "confidence": 0.6
+        },
+        {
+          "text": "the",
+          "start": 46.82,
+          "end": 46.98,
+          "confidence": 0.614
+        },
+        {
+          "text": "helmet",
+          "start": 46.98,
+          "end": 47.2,
+          "confidence": 0.823
+        },
+        {
+          "text": "bag.",
+          "start": 47.2,
+          "end": 47.74,
+          "confidence": 0.363
+        }
+      ]
+    },
+    {
+      "id": 23,
+      "seek": 2600,
+      "start": 48.24,
+      "end": 49.84,
+      "text": " At least it's in the helmet bag.",
+      "tokens": [
+        1711,
+        1935,
+        309,
+        311,
+        294,
+        264,
+        15922,
+        3411,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5128642573501124,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011020583333447576,
+      "confidence": 0.112,
+      "words": [
+        {
+          "text": "At",
+          "start": 48.24,
+          "end": 48.38,
+          "confidence": 0.064
+        },
+        {
+          "text": "least",
+          "start": 48.38,
+          "end": 48.66,
+          "confidence": 0.795
+        },
+        {
+          "text": "it's",
+          "start": 48.66,
+          "end": 49.02,
+          "confidence": 0.347
+        },
+        {
+          "text": "in",
+          "start": 49.02,
+          "end": 49.06,
+          "confidence": 0.172
+        },
+        {
+          "text": "the",
+          "start": 49.06,
+          "end": 49.1,
+          "confidence": 0.242
+        },
+        {
+          "text": "helmet",
+          "start": 49.1,
+          "end": 49.22,
+          "confidence": 0.003
+        },
+        {
+          "text": "bag.",
+          "start": 49.22,
+          "end": 49.84,
+          "confidence": 0.062
+        }
+      ]
+    },
+    {
+      "id": 24,
+      "seek": 2600,
+      "start": 50.22,
+      "end": 50.94,
+      "text": " Right here.",
+      "tokens": [
+        1779,
+        510,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5128642573501124,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011020583333447576,
+      "confidence": 0.099,
+      "words": [
+        {
+          "text": "Right",
+          "start": 50.22,
+          "end": 50.48,
+          "confidence": 0.006
+        },
+        {
+          "text": "here.",
+          "start": 50.48,
+          "end": 50.94,
+          "confidence": 0.416
+        }
+      ]
+    },
+    {
+      "id": 25,
+      "seek": 2600,
+      "start": 51.54,
+      "end": 52.24,
+      "text": " Right here.",
+      "tokens": [
+        1779,
+        510,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5128642573501124,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011020583333447576,
+      "confidence": 0.04,
+      "words": [
+        {
+          "text": "Right",
+          "start": 51.54,
+          "end": 51.8,
+          "confidence": 0.008
+        },
+        {
+          "text": "here.",
+          "start": 51.8,
+          "end": 52.24,
+          "confidence": 0.091
+        }
+      ]
+    },
+    {
+      "id": 26,
+      "seek": 2600,
+      "start": 53.2,
+      "end": 55.42,
+      "text": " Yeah, we're taking it next day out of the field up.",
+      "tokens": [
+        865,
+        11,
+        321,
+        434,
+        1940,
+        309,
+        958,
+        786,
+        484,
+        295,
+        264,
+        2519,
+        493,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5128642573501124,
+      "compression_ratio": 1.728643216080402,
+      "no_speech_prob": 0.0011020583333447576,
+      "confidence": 0.367,
+      "words": [
+        {
+          "text": "Yeah,",
+          "start": 53.2,
+          "end": 53.38,
+          "confidence": 0.47
+        },
+        {
+          "text": "we're",
+          "start": 53.38,
+          "end": 53.7,
+          "confidence": 0.742
+        },
+        {
+          "text": "taking",
+          "start": 53.7,
+          "end": 53.74,
+          "confidence": 0.322
+        },
+        {
+          "text": "it",
+          "start": 53.74,
+          "end": 53.86,
+          "confidence": 0.082
+        },
+        {
+          "text": "next",
+          "start": 53.86,
+          "end": 53.96,
+          "confidence": 0.545
+        },
+        {
+          "text": "day",
+          "start": 53.96,
+          "end": 54.16,
+          "confidence": 0.817
+        },
+        {
+          "text": "out",
+          "start": 54.16,
+          "end": 54.32,
+          "confidence": 0.29
+        },
+        {
+          "text": "of",
+          "start": 54.32,
+          "end": 54.54,
+          "confidence": 0.351
+        },
+        {
+          "text": "the",
+          "start": 54.54,
+          "end": 54.68,
+          "confidence": 0.432
+        },
+        {
+          "text": "field",
+          "start": 54.68,
+          "end": 55.2,
+          "confidence": 0.233
+        },
+        {
+          "text": "up.",
+          "start": 55.2,
+          "end": 55.42,
+          "confidence": 0.235
+        }
+      ]
+    },
+    {
+      "id": 27,
+      "seek": 5500,
+      "start": 55.44,
+      "end": 56.12,
+      "text": " Yeah, we were.",
+      "tokens": [
+        865,
+        11,
+        321,
+        645,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.31608172647314137,
+      "compression_ratio": 1.8318181818181818,
+      "no_speech_prob": 0.00039152163662947714,
+      "confidence": 0.02,
+      "words": [
+        {
+          "text": "Yeah,",
+          "start": 55.44,
+          "end": 55.48,
+          "confidence": 0.024
+        },
+        {
+          "text": "we",
+          "start": 55.48,
+          "end": 55.52,
+          "confidence": 0.022
+        },
+        {
+          "text": "were.",
+          "start": 55.52,
+          "end": 56.12,
+          "confidence": 0.017
+        }
+      ]
+    },
+    {
+      "id": 28,
+      "seek": 5500,
+      "start": 56.5,
+      "end": 57.48,
+      "text": " You want to hack me on that?",
+      "tokens": [
+        509,
+        528,
+        281,
+        10339,
+        385,
+        322,
+        300,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.31608172647314137,
+      "compression_ratio": 1.8318181818181818,
+      "no_speech_prob": 0.00039152163662947714,
+      "confidence": 0.019,
+      "words": [
+        {
+          "text": "You",
+          "start": 56.5,
+          "end": 56.62,
+          "confidence": 0.007
+        },
+        {
+          "text": "want",
+          "start": 56.62,
+          "end": 57.0,
+          "confidence": 0.01
+        },
+        {
+          "text": "to",
+          "start": 57.0,
+          "end": 57.22,
+          "confidence": 0.257
+        },
+        {
+          "text": "hack",
+          "start": 57.22,
+          "end": 57.36,
+          "confidence": 0.0
+        },
+        {
+          "text": "me",
+          "start": 57.36,
+          "end": 57.4,
+          "confidence": 0.054
+        },
+        {
+          "text": "on",
+          "start": 57.4,
+          "end": 57.44,
+          "confidence": 0.005
+        },
+        {
+          "text": "that?",
+          "start": 57.44,
+          "end": 57.48,
+          "confidence": 0.22
+        }
+      ]
+    },
+    {
+      "id": 29,
+      "seek": 5500,
+      "start": 57.48,
+      "end": 58.26,
+      "text": " Yeah, we were.",
+      "tokens": [
+        865,
+        11,
+        321,
+        645,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.31608172647314137,
+      "compression_ratio": 1.8318181818181818,
+      "no_speech_prob": 0.00039152163662947714,
+      "confidence": 0.047,
+      "words": [
+        {
+          "text": "Yeah,",
+          "start": 57.48,
+          "end": 57.96,
+          "confidence": 0.029
+        },
+        {
+          "text": "we",
+          "start": 57.96,
+          "end": 58.06,
+          "confidence": 0.096
+        },
+        {
+          "text": "were.",
+          "start": 58.06,
+          "end": 58.26,
+          "confidence": 0.053
+        }
+      ]
+    },
+    {
+      "id": 30,
+      "seek": 5500,
+      "start": 58.28,
+      "end": 59.48,
+      "text": " You want to hack me on that?",
+      "tokens": [
+        509,
+        528,
+        281,
+        10339,
+        385,
+        322,
+        300,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.31608172647314137,
+      "compression_ratio": 1.8318181818181818,
+      "no_speech_prob": 0.00039152163662947714,
+      "confidence": 0.055,
+      "words": [
+        {
+          "text": "You",
+          "start": 58.28,
+          "end": 58.46,
+          "confidence": 0.029
+        },
+        {
+          "text": "want",
+          "start": 58.46,
+          "end": 58.6,
+          "confidence": 0.107
+        },
+        {
+          "text": "to",
+          "start": 58.6,
+          "end": 58.64,
+          "confidence": 0.376
+        },
+        {
+          "text": "hack",
+          "start": 58.64,
+          "end": 58.76,
+          "confidence": 0.0
+        },
+        {
+          "text": "me",
+          "start": 58.76,
+          "end": 58.96,
+          "confidence": 0.442
+        },
+        {
+          "text": "on",
+          "start": 58.96,
+          "end": 59.18,
+          "confidence": 0.266
+        },
+        {
+          "text": "that?",
+          "start": 59.18,
+          "end": 59.48,
+          "confidence": 0.186
+        }
+      ]
+    },
+    {
+      "id": 31,
+      "seek": 5500,
+      "start": 59.5,
+      "end": 61.96,
+      "text": " With the cover, I tried it already.",
+      "tokens": [
+        2022,
+        264,
+        2060,
+        11,
+        286,
+        3031,
+        309,
+        1217,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.31608172647314137,
+      "compression_ratio": 1.8318181818181818,
+      "no_speech_prob": 0.00039152163662947714,
+      "confidence": 0.202,
+      "words": [
+        {
+          "text": "With",
+          "start": 59.5,
+          "end": 60.1,
+          "confidence": 0.012
+        },
+        {
+          "text": "the",
+          "start": 60.1,
+          "end": 60.82,
+          "confidence": 0.238
+        },
+        {
+          "text": "cover,",
+          "start": 60.82,
+          "end": 61.3,
+          "confidence": 0.165
+        },
+        {
+          "text": "I",
+          "start": 61.3,
+          "end": 61.34,
+          "confidence": 0.826
+        },
+        {
+          "text": "tried",
+          "start": 61.34,
+          "end": 61.52,
+          "confidence": 0.019
+        },
+        {
+          "text": "it",
+          "start": 61.52,
+          "end": 61.72,
+          "confidence": 0.699
+        },
+        {
+          "text": "already.",
+          "start": 61.72,
+          "end": 61.96,
+          "confidence": 0.832
+        }
+      ]
+    },
+    {
+      "id": 32,
+      "seek": 5500,
+      "start": 62.56,
+      "end": 63.16,
+      "text": " Okay, fine.",
+      "tokens": [
+        1033,
+        11,
+        2489,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.31608172647314137,
+      "compression_ratio": 1.8318181818181818,
+      "no_speech_prob": 0.00039152163662947714,
+      "confidence": 0.542,
+      "words": [
+        {
+          "text": "Okay,",
+          "start": 62.56,
+          "end": 62.98,
+          "confidence": 0.49
+        },
+        {
+          "text": "fine.",
+          "start": 62.98,
+          "end": 63.16,
+          "confidence": 0.601
+        }
+      ]
+    },
+    {
+      "id": 33,
+      "seek": 5500,
+      "start": 63.2,
+      "end": 64.16,
+      "text": " We weren't sure of that.",
+      "tokens": [
+        492,
+        4999,
+        380,
+        988,
+        295,
+        300,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.31608172647314137,
+      "compression_ratio": 1.8318181818181818,
+      "no_speech_prob": 0.00039152163662947714,
+      "confidence": 0.75,
+      "words": [
+        {
+          "text": "We",
+          "start": 63.2,
+          "end": 63.36,
+          "confidence": 0.468
+        },
+        {
+          "text": "weren't",
+          "start": 63.36,
+          "end": 63.6,
+          "confidence": 0.939
+        },
+        {
+          "text": "sure",
+          "start": 63.6,
+          "end": 63.8,
+          "confidence": 0.916
+        },
+        {
+          "text": "of",
+          "start": 63.8,
+          "end": 63.88,
+          "confidence": 0.594
+        },
+        {
+          "text": "that.",
+          "start": 63.88,
+          "end": 64.16,
+          "confidence": 0.771
+        }
+      ]
+    },
+    {
+      "id": 34,
+      "seek": 5500,
+      "start": 64.48,
+      "end": 65.14,
+      "text": " Just a suggestion.",
+      "tokens": [
+        1449,
+        257,
+        16541,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.31608172647314137,
+      "compression_ratio": 1.8318181818181818,
+      "no_speech_prob": 0.00039152163662947714,
+      "confidence": 0.163,
+      "words": [
+        {
+          "text": "Just",
+          "start": 64.48,
+          "end": 64.64,
+          "confidence": 0.011
+        },
+        {
+          "text": "a",
+          "start": 64.64,
+          "end": 64.78,
+          "confidence": 0.428
+        },
+        {
+          "text": "suggestion.",
+          "start": 64.78,
+          "end": 65.14,
+          "confidence": 0.386
+        }
+      ]
+    },
+    {
+      "id": 35,
+      "seek": 5500,
+      "start": 65.16,
+      "end": 68.04,
+      "text": " We thought we'd, uh, say you could check it out.",
+      "tokens": [
+        492,
+        1194,
+        321,
+        1116,
+        11,
+        2232,
+        11,
+        584,
+        291,
+        727,
+        1520,
+        309,
+        484,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.31608172647314137,
+      "compression_ratio": 1.8318181818181818,
+      "no_speech_prob": 0.00039152163662947714,
+      "confidence": 0.546,
+      "words": [
+        {
+          "text": "We",
+          "start": 65.16,
+          "end": 65.42,
+          "confidence": 0.164
+        },
+        {
+          "text": "thought",
+          "start": 65.42,
+          "end": 65.62,
+          "confidence": 0.835
+        },
+        {
+          "text": "we'd,",
+          "start": 65.62,
+          "end": 66.14,
+          "confidence": 0.391
+        },
+        {
+          "text": "uh,",
+          "start": 66.14,
+          "end": 66.96,
+          "confidence": 0.678
+        },
+        {
+          "text": "say",
+          "start": 66.96,
+          "end": 67.0,
+          "confidence": 0.181
+        },
+        {
+          "text": "you",
+          "start": 67.0,
+          "end": 67.14,
+          "confidence": 0.825
+        },
+        {
+          "text": "could",
+          "start": 67.14,
+          "end": 67.3,
+          "confidence": 0.715
+        },
+        {
+          "text": "check",
+          "start": 67.3,
+          "end": 67.44,
+          "confidence": 0.637
+        },
+        {
+          "text": "it",
+          "start": 67.44,
+          "end": 67.66,
+          "confidence": 0.982
+        },
+        {
+          "text": "out.",
+          "start": 67.66,
+          "end": 68.04,
+          "confidence": 0.908
+        }
+      ]
+    },
+    {
+      "id": 36,
+      "seek": 5500,
+      "start": 68.24,
+      "end": 69.46,
+      "text": " It's not much of an order to turn that.",
+      "tokens": [
+        467,
+        311,
+        406,
+        709,
+        295,
+        364,
+        1668,
+        281,
+        1261,
+        300,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.31608172647314137,
+      "compression_ratio": 1.8318181818181818,
+      "no_speech_prob": 0.00039152163662947714,
+      "confidence": 0.139,
+      "words": [
+        {
+          "text": "It's",
+          "start": 68.24,
+          "end": 68.46,
+          "confidence": 0.077
+        },
+        {
+          "text": "not",
+          "start": 68.46,
+          "end": 68.5,
+          "confidence": 0.09
+        },
+        {
+          "text": "much",
+          "start": 68.5,
+          "end": 68.64,
+          "confidence": 0.342
+        },
+        {
+          "text": "of",
+          "start": 68.64,
+          "end": 68.78,
+          "confidence": 0.388
+        },
+        {
+          "text": "an",
+          "start": 68.78,
+          "end": 68.9,
+          "confidence": 0.399
+        },
+        {
+          "text": "order",
+          "start": 68.9,
+          "end": 68.94,
+          "confidence": 0.018
+        },
+        {
+          "text": "to",
+          "start": 68.94,
+          "end": 69.14,
+          "confidence": 0.122
+        },
+        {
+          "text": "turn",
+          "start": 69.14,
+          "end": 69.18,
+          "confidence": 0.447
+        },
+        {
+          "text": "that.",
+          "start": 69.18,
+          "end": 69.46,
+          "confidence": 0.116
+        }
+      ]
+    },
+    {
+      "id": 37,
+      "seek": 5500,
+      "start": 70.38,
+      "end": 71.98,
+      "text": " So, uh, I guess we're going to come up with this.",
+      "tokens": [
+        407,
+        11,
+        2232,
+        11,
+        286,
+        2041,
+        321,
+        434,
+        516,
+        281,
+        808,
+        493,
+        365,
+        341,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.31608172647314137,
+      "compression_ratio": 1.8318181818181818,
+      "no_speech_prob": 0.00039152163662947714,
+      "confidence": 0.449,
+      "words": [
+        {
+          "text": "So,",
+          "start": 70.38,
+          "end": 70.42,
+          "confidence": 0.514
+        },
+        {
+          "text": "uh,",
+          "start": 70.42,
+          "end": 70.5,
+          "confidence": 0.38
+        },
+        {
+          "text": "I",
+          "start": 70.5,
+          "end": 70.54,
+          "confidence": 0.946
+        },
+        {
+          "text": "guess",
+          "start": 70.54,
+          "end": 70.8,
+          "confidence": 0.99
+        },
+        {
+          "text": "we're",
+          "start": 70.8,
+          "end": 71.1,
+          "confidence": 0.534
+        },
+        {
+          "text": "going",
+          "start": 71.1,
+          "end": 71.28,
+          "confidence": 0.106
+        },
+        {
+          "text": "to",
+          "start": 71.28,
+          "end": 71.42,
+          "confidence": 0.915
+        },
+        {
+          "text": "come",
+          "start": 71.42,
+          "end": 71.48,
+          "confidence": 0.48
+        },
+        {
+          "text": "up",
+          "start": 71.48,
+          "end": 71.68,
+          "confidence": 0.579
+        },
+        {
+          "text": "with",
+          "start": 71.68,
+          "end": 71.88,
+          "confidence": 0.809
+        },
+        {
+          "text": "this.",
+          "start": 71.88,
+          "end": 71.98,
+          "confidence": 0.166
+        }
+      ]
+    },
+    {
+      "id": 38,
+      "seek": 5500,
+      "start": 72.0,
+      "end": 72.8,
+      "text": " Let us know.",
+      "tokens": [
+        961,
+        505,
+        458,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.31608172647314137,
+      "compression_ratio": 1.8318181818181818,
+      "no_speech_prob": 0.00039152163662947714,
+      "confidence": 0.45,
+      "words": [
+        {
+          "text": "Let",
+          "start": 72.0,
+          "end": 72.14,
+          "confidence": 0.221
+        },
+        {
+          "text": "us",
+          "start": 72.14,
+          "end": 72.3,
+          "confidence": 0.272
+        },
+        {
+          "text": "know.",
+          "start": 72.3,
+          "end": 72.8,
+          "confidence": 0.826
+        }
+      ]
+    },
+    {
+      "id": 39,
+      "seek": 5500,
+      "start": 72.82,
+      "end": 73.02,
+      "text": " Okay.",
+      "tokens": [
+        1033,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.31608172647314137,
+      "compression_ratio": 1.8318181818181818,
+      "no_speech_prob": 0.00039152163662947714,
+      "confidence": 0.049,
+      "words": [
+        {
+          "text": "Okay.",
+          "start": 72.82,
+          "end": 73.02,
+          "confidence": 0.049
+        }
+      ]
+    },
+    {
+      "id": 40,
+      "seek": 5500,
+      "start": 74.2,
+      "end": 75.48,
+      "text": " No problem.",
+      "tokens": [
+        883,
+        1154,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.31608172647314137,
+      "compression_ratio": 1.8318181818181818,
+      "no_speech_prob": 0.00039152163662947714,
+      "confidence": 0.077,
+      "words": [
+        {
+          "text": "No",
+          "start": 74.2,
+          "end": 74.24,
+          "confidence": 0.005
+        },
+        {
+          "text": "problem.",
+          "start": 74.24,
+          "end": 75.48,
+          "confidence": 0.295
+        }
+      ]
+    },
+    {
+      "id": 41,
+      "seek": 5500,
+      "start": 75.72,
+      "end": 75.94,
+      "text": " Okay.",
+      "tokens": [
+        1033,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.31608172647314137,
+      "compression_ratio": 1.8318181818181818,
+      "no_speech_prob": 0.00039152163662947714,
+      "confidence": 0.263,
+      "words": [
+        {
+          "text": "Okay.",
+          "start": 75.72,
+          "end": 75.94,
+          "confidence": 0.263
+        }
+      ]
+    },
+    {
+      "id": 42,
+      "seek": 5500,
+      "start": 75.96,
+      "end": 76.66,
+      "text": " No problem.",
+      "tokens": [
+        883,
+        1154,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.31608172647314137,
+      "compression_ratio": 1.8318181818181818,
+      "no_speech_prob": 0.00039152163662947714,
+      "confidence": 0.588,
+      "words": [
+        {
+          "text": "No",
+          "start": 75.96,
+          "end": 76.24,
+          "confidence": 0.447
+        },
+        {
+          "text": "problem.",
+          "start": 76.24,
+          "end": 76.66,
+          "confidence": 0.673
+        }
+      ]
+    },
+    {
+      "id": 43,
+      "seek": 5500,
+      "start": 78.42,
+      "end": 78.5,
+      "text": " No problem.",
+      "tokens": [
+        883,
+        1154,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.31608172647314137,
+      "compression_ratio": 1.8318181818181818,
+      "no_speech_prob": 0.00039152163662947714,
+      "confidence": 0.031,
+      "words": [
+        {
+          "text": "No",
+          "start": 78.42,
+          "end": 78.46,
+          "confidence": 0.032
+        },
+        {
+          "text": "problem.",
+          "start": 78.46,
+          "end": 78.5,
+          "confidence": 0.03
+        }
+      ]
+    },
+    {
+      "id": 44,
+      "seek": 5500,
+      "start": 78.5,
+      "end": 79.28,
+      "text": " No problem.",
+      "tokens": [
+        883,
+        1154,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.31608172647314137,
+      "compression_ratio": 1.8318181818181818,
+      "no_speech_prob": 0.00039152163662947714,
+      "confidence": 0.013,
+      "words": [
+        {
+          "text": "No",
+          "start": 78.5,
+          "end": 78.7,
+          "confidence": 0.001
+        },
+        {
+          "text": "problem.",
+          "start": 78.7,
+          "end": 79.28,
+          "confidence": 0.044
+        }
+      ]
+    },
+    {
+      "id": 45,
+      "seek": 5500,
+      "start": 79.3,
+      "end": 80.3,
+      "text": " No problem.",
+      "tokens": [
+        883,
+        1154,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.31608172647314137,
+      "compression_ratio": 1.8318181818181818,
+      "no_speech_prob": 0.00039152163662947714,
+      "confidence": 0.017,
+      "words": [
+        {
+          "text": "No",
+          "start": 79.3,
+          "end": 79.48,
+          "confidence": 0.002
+        },
+        {
+          "text": "problem.",
+          "start": 79.48,
+          "end": 80.3,
+          "confidence": 0.056
+        }
+      ]
+    },
+    {
+      "id": 46,
+      "seek": 8000,
+      "start": 80.32,
+      "end": 84.94,
+      "text": " No problem.",
+      "tokens": [
+        883,
+        1154,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3978840112686157,
+      "compression_ratio": 1.5217391304347827,
+      "no_speech_prob": 0.0009465877083130181,
+      "confidence": 0.029,
+      "words": [
+        {
+          "text": "No",
+          "start": 80.32,
+          "end": 80.54,
+          "confidence": 0.004
+        },
+        {
+          "text": "problem.",
+          "start": 80.54,
+          "end": 84.94,
+          "confidence": 0.082
+        }
+      ]
+    },
+    {
+      "id": 47,
+      "seek": 8000,
+      "start": 85.24,
+      "end": 87.1,
+      "text": " No problem.",
+      "tokens": [
+        883,
+        1154,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3978840112686157,
+      "compression_ratio": 1.5217391304347827,
+      "no_speech_prob": 0.0009465877083130181,
+      "confidence": 0.03,
+      "words": [
+        {
+          "text": "No",
+          "start": 85.24,
+          "end": 85.4,
+          "confidence": 0.002
+        },
+        {
+          "text": "problem.",
+          "start": 85.4,
+          "end": 87.1,
+          "confidence": 0.128
+        }
+      ]
+    },
+    {
+      "id": 48,
+      "seek": 8800,
+      "start": 87.52,
+      "end": 88.98,
+      "text": " No problem.",
+      "tokens": [
+        50364,
+        883,
+        1154,
+        13,
+        51464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.649966835975647,
+      "compression_ratio": 0.5789473684210527,
+      "no_speech_prob": 0.0005261301412247121,
+      "confidence": 0.037,
+      "words": [
+        {
+          "text": "No",
+          "start": 87.52,
+          "end": 88.9,
+          "confidence": 0.003
+        },
+        {
+          "text": "problem.",
+          "start": 88.9,
+          "end": 88.98,
+          "confidence": 0.137
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/naive.cuda/naive_apollo11.mp3.words.json b/tests/expected/naive.cuda/naive_apollo11.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d7628fb1df3720ce20a998436c90ebb59cb86c7
--- /dev/null
+++ b/tests/expected/naive.cuda/naive_apollo11.mp3.words.json
@@ -0,0 +1,3814 @@
+{
+  "text": " Apollo 11, Houston we got a recommendation for you on your Soyuz-VA GLEME GVA. Alright, okay, we like to say that they make the one that's on the helmet we're going to have in B1. And you can put the other one on the mic helmet with those GVA blizzard frames. Alright, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.64,
+      "end": 6.84,
+      "text": " Apollo 11, Houston we got a recommendation for you on your Soyuz-VA GLEME GVA.",
+      "tokens": [
+        25187,
+        2975,
+        11,
+        18717,
+        321,
+        658,
+        257,
+        11879,
+        337,
+        291,
+        322,
+        428,
+        24758,
+        3334,
+        12,
+        20914,
+        460,
+        2634,
+        15454,
+        460,
+        20914,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7235679626464844,
+      "compression_ratio": 1.39247311827957,
+      "no_speech_prob": 0.44993799924850464,
+      "confidence": 0.494,
+      "words": [
+        {
+          "text": "Apollo",
+          "start": 0.64,
+          "end": 0.98,
+          "confidence": 0.425
+        },
+        {
+          "text": "11,",
+          "start": 0.98,
+          "end": 1.52,
+          "confidence": 0.842
+        },
+        {
+          "text": "Houston",
+          "start": 1.52,
+          "end": 1.78,
+          "confidence": 0.974
+        },
+        {
+          "text": "we",
+          "start": 1.78,
+          "end": 1.98,
+          "confidence": 0.453
+        },
+        {
+          "text": "got",
+          "start": 1.98,
+          "end": 2.16,
+          "confidence": 0.791
+        },
+        {
+          "text": "a",
+          "start": 2.16,
+          "end": 2.32,
+          "confidence": 0.992
+        },
+        {
+          "text": "recommendation",
+          "start": 2.32,
+          "end": 3.08,
+          "confidence": 0.97
+        },
+        {
+          "text": "for",
+          "start": 3.08,
+          "end": 3.5,
+          "confidence": 0.945
+        },
+        {
+          "text": "you",
+          "start": 3.5,
+          "end": 3.72,
+          "confidence": 0.99
+        },
+        {
+          "text": "on",
+          "start": 3.72,
+          "end": 4.2,
+          "confidence": 0.935
+        },
+        {
+          "text": "your",
+          "start": 4.2,
+          "end": 4.24,
+          "confidence": 0.974
+        },
+        {
+          "text": "Soyuz-VA",
+          "start": 4.24,
+          "end": 5.32,
+          "confidence": 0.327
+        },
+        {
+          "text": "GLEME",
+          "start": 5.32,
+          "end": 6.02,
+          "confidence": 0.178
+        },
+        {
+          "text": "GVA.",
+          "start": 6.02,
+          "end": 6.84,
+          "confidence": 0.321
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 10.82,
+      "end": 19.28,
+      "text": " Alright, okay, we like to say that they make the one that's on the helmet we're going to have in B1.",
+      "tokens": [
+        2798,
+        11,
+        1392,
+        11,
+        321,
+        411,
+        281,
+        584,
+        300,
+        436,
+        652,
+        264,
+        472,
+        300,
+        311,
+        322,
+        264,
+        15922,
+        321,
+        434,
+        516,
+        281,
+        362,
+        294,
+        363,
+        16,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7235679626464844,
+      "compression_ratio": 1.39247311827957,
+      "no_speech_prob": 0.44993799924850464,
+      "confidence": 0.335,
+      "words": [
+        {
+          "text": "Alright,",
+          "start": 10.82,
+          "end": 12.06,
+          "confidence": 0.126
+        },
+        {
+          "text": "okay,",
+          "start": 12.06,
+          "end": 13.06,
+          "confidence": 0.394
+        },
+        {
+          "text": "we",
+          "start": 13.06,
+          "end": 13.1,
+          "confidence": 0.478
+        },
+        {
+          "text": "like",
+          "start": 13.1,
+          "end": 13.48,
+          "confidence": 0.493
+        },
+        {
+          "text": "to",
+          "start": 13.48,
+          "end": 13.66,
+          "confidence": 0.128
+        },
+        {
+          "text": "say",
+          "start": 13.66,
+          "end": 14.94,
+          "confidence": 0.084
+        },
+        {
+          "text": "that",
+          "start": 14.94,
+          "end": 15.54,
+          "confidence": 0.225
+        },
+        {
+          "text": "they",
+          "start": 15.54,
+          "end": 15.58,
+          "confidence": 0.328
+        },
+        {
+          "text": "make",
+          "start": 15.58,
+          "end": 15.78,
+          "confidence": 0.162
+        },
+        {
+          "text": "the",
+          "start": 15.78,
+          "end": 15.92,
+          "confidence": 0.226
+        },
+        {
+          "text": "one",
+          "start": 15.92,
+          "end": 16.1,
+          "confidence": 0.559
+        },
+        {
+          "text": "that's",
+          "start": 16.1,
+          "end": 16.36,
+          "confidence": 0.367
+        },
+        {
+          "text": "on",
+          "start": 16.36,
+          "end": 16.6,
+          "confidence": 0.387
+        },
+        {
+          "text": "the",
+          "start": 16.6,
+          "end": 16.84,
+          "confidence": 0.354
+        },
+        {
+          "text": "helmet",
+          "start": 16.84,
+          "end": 17.36,
+          "confidence": 0.205
+        },
+        {
+          "text": "we're",
+          "start": 17.36,
+          "end": 17.84,
+          "confidence": 0.297
+        },
+        {
+          "text": "going",
+          "start": 17.84,
+          "end": 18.04,
+          "confidence": 0.432
+        },
+        {
+          "text": "to",
+          "start": 18.04,
+          "end": 18.18,
+          "confidence": 0.448
+        },
+        {
+          "text": "have",
+          "start": 18.18,
+          "end": 18.24,
+          "confidence": 0.761
+        },
+        {
+          "text": "in",
+          "start": 18.24,
+          "end": 18.46,
+          "confidence": 0.743
+        },
+        {
+          "text": "B1.",
+          "start": 18.46,
+          "end": 19.28,
+          "confidence": 0.753
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 19.38,
+      "end": 24.7,
+      "text": " And you can put the other one on the mic helmet with those GVA blizzard frames.",
+      "tokens": [
+        400,
+        291,
+        393,
+        829,
+        264,
+        661,
+        472,
+        322,
+        264,
+        3123,
+        15922,
+        365,
+        729,
+        460,
+        20914,
+        888,
+        31062,
+        12083,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7235679626464844,
+      "compression_ratio": 1.39247311827957,
+      "no_speech_prob": 0.44993799924850464,
+      "confidence": 0.123,
+      "words": [
+        {
+          "text": "And",
+          "start": 19.38,
+          "end": 20.14,
+          "confidence": 0.321
+        },
+        {
+          "text": "you",
+          "start": 20.14,
+          "end": 20.36,
+          "confidence": 0.904
+        },
+        {
+          "text": "can",
+          "start": 20.36,
+          "end": 20.54,
+          "confidence": 0.363
+        },
+        {
+          "text": "put",
+          "start": 20.54,
+          "end": 20.72,
+          "confidence": 0.939
+        },
+        {
+          "text": "the",
+          "start": 20.72,
+          "end": 20.86,
+          "confidence": 0.978
+        },
+        {
+          "text": "other",
+          "start": 20.86,
+          "end": 21.06,
+          "confidence": 0.995
+        },
+        {
+          "text": "one",
+          "start": 21.06,
+          "end": 21.26,
+          "confidence": 0.965
+        },
+        {
+          "text": "on",
+          "start": 21.26,
+          "end": 21.68,
+          "confidence": 0.961
+        },
+        {
+          "text": "the",
+          "start": 21.68,
+          "end": 21.74,
+          "confidence": 0.199
+        },
+        {
+          "text": "mic",
+          "start": 21.74,
+          "end": 22.58,
+          "confidence": 0.694
+        },
+        {
+          "text": "helmet",
+          "start": 22.58,
+          "end": 22.94,
+          "confidence": 0.007
+        },
+        {
+          "text": "with",
+          "start": 22.94,
+          "end": 23.2,
+          "confidence": 0.059
+        },
+        {
+          "text": "those",
+          "start": 23.2,
+          "end": 23.46,
+          "confidence": 0.046
+        },
+        {
+          "text": "GVA",
+          "start": 23.46,
+          "end": 23.86,
+          "confidence": 0.001
+        },
+        {
+          "text": "blizzard",
+          "start": 23.86,
+          "end": 24.32,
+          "confidence": 0.032
+        },
+        {
+          "text": "frames.",
+          "start": 24.32,
+          "end": 24.7,
+          "confidence": 0.231
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 2500,
+      "start": 31.36,
+      "end": 54.68,
+      "text": " Alright, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them",
+      "tokens": [
+        50364,
+        2798,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.10793833414713541,
+      "compression_ratio": 24.096774193548388,
+      "no_speech_prob": 0.0011014570482075214,
+      "confidence": 0.887,
+      "words": [
+        {
+          "text": "Alright,",
+          "start": 31.36,
+          "end": 31.98,
+          "confidence": 0.077
+        },
+        {
+          "text": "got",
+          "start": 31.98,
+          "end": 32.02,
+          "confidence": 0.169
+        },
+        {
+          "text": "them,",
+          "start": 32.02,
+          "end": 32.52,
+          "confidence": 0.189
+        },
+        {
+          "text": "got",
+          "start": 32.52,
+          "end": 33.0,
+          "confidence": 0.429
+        },
+        {
+          "text": "them,",
+          "start": 33.0,
+          "end": 33.78,
+          "confidence": 0.613
+        },
+        {
+          "text": "got",
+          "start": 33.78,
+          "end": 33.82,
+          "confidence": 0.67
+        },
+        {
+          "text": "them,",
+          "start": 33.82,
+          "end": 34.56,
+          "confidence": 0.495
+        },
+        {
+          "text": "got",
+          "start": 34.56,
+          "end": 34.74,
+          "confidence": 0.664
+        },
+        {
+          "text": "them,",
+          "start": 34.74,
+          "end": 34.78,
+          "confidence": 0.486
+        },
+        {
+          "text": "got",
+          "start": 34.78,
+          "end": 35.02,
+          "confidence": 0.756
+        },
+        {
+          "text": "them,",
+          "start": 35.02,
+          "end": 35.06,
+          "confidence": 0.565
+        },
+        {
+          "text": "got",
+          "start": 35.06,
+          "end": 35.1,
+          "confidence": 0.781
+        },
+        {
+          "text": "them,",
+          "start": 35.1,
+          "end": 35.14,
+          "confidence": 0.684
+        },
+        {
+          "text": "got",
+          "start": 35.14,
+          "end": 35.32,
+          "confidence": 0.858
+        },
+        {
+          "text": "them,",
+          "start": 35.32,
+          "end": 35.98,
+          "confidence": 0.803
+        },
+        {
+          "text": "got",
+          "start": 35.98,
+          "end": 36.02,
+          "confidence": 0.917
+        },
+        {
+          "text": "them,",
+          "start": 36.02,
+          "end": 36.06,
+          "confidence": 0.767
+        },
+        {
+          "text": "got",
+          "start": 36.06,
+          "end": 36.1,
+          "confidence": 0.584
+        },
+        {
+          "text": "them,",
+          "start": 36.1,
+          "end": 36.14,
+          "confidence": 0.843
+        },
+        {
+          "text": "got",
+          "start": 36.14,
+          "end": 36.18,
+          "confidence": 0.926
+        },
+        {
+          "text": "them,",
+          "start": 36.18,
+          "end": 36.22,
+          "confidence": 0.887
+        },
+        {
+          "text": "got",
+          "start": 36.22,
+          "end": 36.26,
+          "confidence": 0.936
+        },
+        {
+          "text": "them,",
+          "start": 36.26,
+          "end": 36.4,
+          "confidence": 0.903
+        },
+        {
+          "text": "got",
+          "start": 36.4,
+          "end": 36.44,
+          "confidence": 0.939
+        },
+        {
+          "text": "them,",
+          "start": 36.44,
+          "end": 36.48,
+          "confidence": 0.909
+        },
+        {
+          "text": "got",
+          "start": 36.48,
+          "end": 36.52,
+          "confidence": 0.948
+        },
+        {
+          "text": "them,",
+          "start": 36.52,
+          "end": 36.56,
+          "confidence": 0.902
+        },
+        {
+          "text": "got",
+          "start": 36.56,
+          "end": 36.6,
+          "confidence": 0.942
+        },
+        {
+          "text": "them,",
+          "start": 36.6,
+          "end": 36.64,
+          "confidence": 0.904
+        },
+        {
+          "text": "got",
+          "start": 36.64,
+          "end": 36.68,
+          "confidence": 0.938
+        },
+        {
+          "text": "them,",
+          "start": 36.68,
+          "end": 36.72,
+          "confidence": 0.911
+        },
+        {
+          "text": "got",
+          "start": 36.72,
+          "end": 36.76,
+          "confidence": 0.932
+        },
+        {
+          "text": "them,",
+          "start": 36.76,
+          "end": 36.8,
+          "confidence": 0.918
+        },
+        {
+          "text": "got",
+          "start": 36.8,
+          "end": 36.84,
+          "confidence": 0.932
+        },
+        {
+          "text": "them,",
+          "start": 36.84,
+          "end": 36.88,
+          "confidence": 0.923
+        },
+        {
+          "text": "got",
+          "start": 36.88,
+          "end": 36.92,
+          "confidence": 0.937
+        },
+        {
+          "text": "them,",
+          "start": 36.92,
+          "end": 36.96,
+          "confidence": 0.93
+        },
+        {
+          "text": "got",
+          "start": 36.96,
+          "end": 37.0,
+          "confidence": 0.938
+        },
+        {
+          "text": "them,",
+          "start": 37.0,
+          "end": 37.04,
+          "confidence": 0.936
+        },
+        {
+          "text": "got",
+          "start": 37.04,
+          "end": 37.08,
+          "confidence": 0.943
+        },
+        {
+          "text": "them,",
+          "start": 37.08,
+          "end": 37.12,
+          "confidence": 0.941
+        },
+        {
+          "text": "got",
+          "start": 37.12,
+          "end": 37.16,
+          "confidence": 0.945
+        },
+        {
+          "text": "them,",
+          "start": 37.16,
+          "end": 37.2,
+          "confidence": 0.944
+        },
+        {
+          "text": "got",
+          "start": 37.2,
+          "end": 37.24,
+          "confidence": 0.948
+        },
+        {
+          "text": "them,",
+          "start": 37.24,
+          "end": 37.28,
+          "confidence": 0.947
+        },
+        {
+          "text": "got",
+          "start": 37.28,
+          "end": 37.32,
+          "confidence": 0.949
+        },
+        {
+          "text": "them,",
+          "start": 37.32,
+          "end": 37.36,
+          "confidence": 0.95
+        },
+        {
+          "text": "got",
+          "start": 37.36,
+          "end": 37.4,
+          "confidence": 0.95
+        },
+        {
+          "text": "them,",
+          "start": 37.4,
+          "end": 37.44,
+          "confidence": 0.953
+        },
+        {
+          "text": "got",
+          "start": 37.44,
+          "end": 37.48,
+          "confidence": 0.951
+        },
+        {
+          "text": "them,",
+          "start": 37.48,
+          "end": 37.52,
+          "confidence": 0.956
+        },
+        {
+          "text": "got",
+          "start": 37.52,
+          "end": 37.56,
+          "confidence": 0.951
+        },
+        {
+          "text": "them,",
+          "start": 37.56,
+          "end": 37.6,
+          "confidence": 0.956
+        },
+        {
+          "text": "got",
+          "start": 37.6,
+          "end": 37.64,
+          "confidence": 0.953
+        },
+        {
+          "text": "them,",
+          "start": 37.64,
+          "end": 37.68,
+          "confidence": 0.957
+        },
+        {
+          "text": "got",
+          "start": 37.68,
+          "end": 37.72,
+          "confidence": 0.954
+        },
+        {
+          "text": "them,",
+          "start": 37.72,
+          "end": 37.76,
+          "confidence": 0.961
+        },
+        {
+          "text": "got",
+          "start": 37.76,
+          "end": 37.8,
+          "confidence": 0.954
+        },
+        {
+          "text": "them,",
+          "start": 37.8,
+          "end": 37.84,
+          "confidence": 0.961
+        },
+        {
+          "text": "got",
+          "start": 37.84,
+          "end": 37.88,
+          "confidence": 0.955
+        },
+        {
+          "text": "them,",
+          "start": 37.88,
+          "end": 37.92,
+          "confidence": 0.962
+        },
+        {
+          "text": "got",
+          "start": 37.92,
+          "end": 37.96,
+          "confidence": 0.955
+        },
+        {
+          "text": "them,",
+          "start": 37.96,
+          "end": 38.0,
+          "confidence": 0.964
+        },
+        {
+          "text": "got",
+          "start": 38.0,
+          "end": 38.04,
+          "confidence": 0.956
+        },
+        {
+          "text": "them,",
+          "start": 38.04,
+          "end": 38.08,
+          "confidence": 0.965
+        },
+        {
+          "text": "got",
+          "start": 38.08,
+          "end": 38.12,
+          "confidence": 0.957
+        },
+        {
+          "text": "them,",
+          "start": 38.12,
+          "end": 38.16,
+          "confidence": 0.965
+        },
+        {
+          "text": "got",
+          "start": 38.16,
+          "end": 38.2,
+          "confidence": 0.959
+        },
+        {
+          "text": "them,",
+          "start": 38.2,
+          "end": 38.24,
+          "confidence": 0.968
+        },
+        {
+          "text": "got",
+          "start": 38.24,
+          "end": 38.28,
+          "confidence": 0.961
+        },
+        {
+          "text": "them,",
+          "start": 38.28,
+          "end": 38.32,
+          "confidence": 0.969
+        },
+        {
+          "text": "got",
+          "start": 38.32,
+          "end": 38.36,
+          "confidence": 0.961
+        },
+        {
+          "text": "them,",
+          "start": 38.36,
+          "end": 38.4,
+          "confidence": 0.968
+        },
+        {
+          "text": "got",
+          "start": 38.4,
+          "end": 38.44,
+          "confidence": 0.963
+        },
+        {
+          "text": "them,",
+          "start": 38.44,
+          "end": 38.48,
+          "confidence": 0.971
+        },
+        {
+          "text": "got",
+          "start": 38.48,
+          "end": 38.52,
+          "confidence": 0.965
+        },
+        {
+          "text": "them,",
+          "start": 38.52,
+          "end": 38.56,
+          "confidence": 0.972
+        },
+        {
+          "text": "got",
+          "start": 38.56,
+          "end": 38.6,
+          "confidence": 0.966
+        },
+        {
+          "text": "them,",
+          "start": 38.6,
+          "end": 38.64,
+          "confidence": 0.974
+        },
+        {
+          "text": "got",
+          "start": 38.64,
+          "end": 38.68,
+          "confidence": 0.967
+        },
+        {
+          "text": "them,",
+          "start": 38.68,
+          "end": 38.72,
+          "confidence": 0.974
+        },
+        {
+          "text": "got",
+          "start": 38.72,
+          "end": 38.76,
+          "confidence": 0.969
+        },
+        {
+          "text": "them,",
+          "start": 38.76,
+          "end": 38.8,
+          "confidence": 0.974
+        },
+        {
+          "text": "got",
+          "start": 38.8,
+          "end": 38.84,
+          "confidence": 0.972
+        },
+        {
+          "text": "them,",
+          "start": 38.84,
+          "end": 38.88,
+          "confidence": 0.976
+        },
+        {
+          "text": "got",
+          "start": 38.88,
+          "end": 38.92,
+          "confidence": 0.974
+        },
+        {
+          "text": "them,",
+          "start": 38.92,
+          "end": 38.96,
+          "confidence": 0.978
+        },
+        {
+          "text": "got",
+          "start": 38.96,
+          "end": 39.0,
+          "confidence": 0.975
+        },
+        {
+          "text": "them,",
+          "start": 39.0,
+          "end": 39.04,
+          "confidence": 0.978
+        },
+        {
+          "text": "got",
+          "start": 39.04,
+          "end": 39.08,
+          "confidence": 0.977
+        },
+        {
+          "text": "them,",
+          "start": 39.08,
+          "end": 39.12,
+          "confidence": 0.979
+        },
+        {
+          "text": "got",
+          "start": 39.12,
+          "end": 39.16,
+          "confidence": 0.979
+        },
+        {
+          "text": "them,",
+          "start": 39.16,
+          "end": 39.2,
+          "confidence": 0.979
+        },
+        {
+          "text": "got",
+          "start": 39.2,
+          "end": 39.24,
+          "confidence": 0.981
+        },
+        {
+          "text": "them,",
+          "start": 39.24,
+          "end": 39.28,
+          "confidence": 0.981
+        },
+        {
+          "text": "got",
+          "start": 39.28,
+          "end": 39.32,
+          "confidence": 0.982
+        },
+        {
+          "text": "them,",
+          "start": 39.32,
+          "end": 39.36,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 39.36,
+          "end": 39.4,
+          "confidence": 0.983
+        },
+        {
+          "text": "them,",
+          "start": 39.4,
+          "end": 39.44,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 39.44,
+          "end": 39.48,
+          "confidence": 0.985
+        },
+        {
+          "text": "them,",
+          "start": 39.48,
+          "end": 39.52,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 39.52,
+          "end": 39.56,
+          "confidence": 0.987
+        },
+        {
+          "text": "them,",
+          "start": 39.56,
+          "end": 39.6,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 39.6,
+          "end": 39.64,
+          "confidence": 0.988
+        },
+        {
+          "text": "them,",
+          "start": 39.64,
+          "end": 39.68,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 39.68,
+          "end": 39.72,
+          "confidence": 0.989
+        },
+        {
+          "text": "them,",
+          "start": 39.72,
+          "end": 39.76,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 39.76,
+          "end": 39.8,
+          "confidence": 0.989
+        },
+        {
+          "text": "them,",
+          "start": 39.8,
+          "end": 39.84,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 39.84,
+          "end": 39.88,
+          "confidence": 0.99
+        },
+        {
+          "text": "them,",
+          "start": 39.88,
+          "end": 39.92,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 39.92,
+          "end": 39.96,
+          "confidence": 0.991
+        },
+        {
+          "text": "them,",
+          "start": 39.96,
+          "end": 40.0,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 40.0,
+          "end": 40.04,
+          "confidence": 0.991
+        },
+        {
+          "text": "them,",
+          "start": 40.04,
+          "end": 40.08,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 40.08,
+          "end": 40.12,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 40.12,
+          "end": 40.16,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 40.16,
+          "end": 40.2,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 40.2,
+          "end": 40.24,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 40.24,
+          "end": 40.28,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 40.28,
+          "end": 40.32,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 40.32,
+          "end": 40.36,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 40.36,
+          "end": 40.4,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 40.4,
+          "end": 40.44,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 40.44,
+          "end": 40.48,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 40.48,
+          "end": 40.52,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 40.52,
+          "end": 40.56,
+          "confidence": 0.988
+        },
+        {
+          "text": "got",
+          "start": 40.56,
+          "end": 40.6,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 40.6,
+          "end": 40.64,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 40.64,
+          "end": 40.68,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 40.68,
+          "end": 40.86,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 40.86,
+          "end": 40.9,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 40.9,
+          "end": 40.94,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 40.94,
+          "end": 40.98,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 40.98,
+          "end": 41.24,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 41.24,
+          "end": 41.36,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 41.36,
+          "end": 42.3,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 42.3,
+          "end": 42.5,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 42.5,
+          "end": 42.98,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 42.98,
+          "end": 44.02,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 44.02,
+          "end": 44.42,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 44.42,
+          "end": 44.78,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 44.78,
+          "end": 45.16,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 45.16,
+          "end": 46.22,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 46.22,
+          "end": 46.52,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 46.52,
+          "end": 46.72,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 46.72,
+          "end": 47.72,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 47.72,
+          "end": 48.58,
+          "confidence": 0.993
+        },
+        {
+          "text": "them",
+          "start": 48.58,
+          "end": 54.68,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 5500,
+      "start": 72.0,
+      "end": 84.66,
+      "text": " got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them",
+      "tokens": [
+        50364,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.05313390894321048,
+      "compression_ratio": 29.52,
+      "no_speech_prob": 0.24548843502998352,
+      "confidence": 0.84,
+      "words": [
+        {
+          "text": "got",
+          "start": 72.0,
+          "end": 72.04,
+          "confidence": 0.005
+        },
+        {
+          "text": "them,",
+          "start": 72.04,
+          "end": 72.08,
+          "confidence": 0.007
+        },
+        {
+          "text": "got",
+          "start": 72.08,
+          "end": 72.12,
+          "confidence": 0.049
+        },
+        {
+          "text": "them,",
+          "start": 72.12,
+          "end": 72.16,
+          "confidence": 0.35
+        },
+        {
+          "text": "got",
+          "start": 72.16,
+          "end": 72.2,
+          "confidence": 0.65
+        },
+        {
+          "text": "them,",
+          "start": 72.2,
+          "end": 72.24,
+          "confidence": 0.549
+        },
+        {
+          "text": "got",
+          "start": 72.24,
+          "end": 72.28,
+          "confidence": 0.837
+        },
+        {
+          "text": "them,",
+          "start": 72.28,
+          "end": 72.32,
+          "confidence": 0.614
+        },
+        {
+          "text": "got",
+          "start": 72.32,
+          "end": 72.36,
+          "confidence": 0.891
+        },
+        {
+          "text": "them,",
+          "start": 72.36,
+          "end": 72.4,
+          "confidence": 0.665
+        },
+        {
+          "text": "got",
+          "start": 72.4,
+          "end": 72.44,
+          "confidence": 0.909
+        },
+        {
+          "text": "them,",
+          "start": 72.44,
+          "end": 72.48,
+          "confidence": 0.689
+        },
+        {
+          "text": "got",
+          "start": 72.48,
+          "end": 72.52,
+          "confidence": 0.861
+        },
+        {
+          "text": "them,",
+          "start": 72.52,
+          "end": 72.56,
+          "confidence": 0.772
+        },
+        {
+          "text": "got",
+          "start": 72.56,
+          "end": 72.6,
+          "confidence": 0.91
+        },
+        {
+          "text": "them,",
+          "start": 72.6,
+          "end": 72.64,
+          "confidence": 0.84
+        },
+        {
+          "text": "got",
+          "start": 72.64,
+          "end": 72.68,
+          "confidence": 0.933
+        },
+        {
+          "text": "them,",
+          "start": 72.68,
+          "end": 72.72,
+          "confidence": 0.633
+        },
+        {
+          "text": "got",
+          "start": 72.72,
+          "end": 72.76,
+          "confidence": 0.173
+        },
+        {
+          "text": "them,",
+          "start": 72.76,
+          "end": 72.8,
+          "confidence": 0.776
+        },
+        {
+          "text": "got",
+          "start": 72.8,
+          "end": 72.84,
+          "confidence": 0.824
+        },
+        {
+          "text": "them,",
+          "start": 72.84,
+          "end": 72.88,
+          "confidence": 0.832
+        },
+        {
+          "text": "got",
+          "start": 72.88,
+          "end": 72.92,
+          "confidence": 0.846
+        },
+        {
+          "text": "them,",
+          "start": 72.92,
+          "end": 72.96,
+          "confidence": 0.849
+        },
+        {
+          "text": "got",
+          "start": 72.96,
+          "end": 73.0,
+          "confidence": 0.846
+        },
+        {
+          "text": "them,",
+          "start": 73.0,
+          "end": 73.04,
+          "confidence": 0.867
+        },
+        {
+          "text": "got",
+          "start": 73.04,
+          "end": 73.08,
+          "confidence": 0.87
+        },
+        {
+          "text": "them,",
+          "start": 73.08,
+          "end": 73.12,
+          "confidence": 0.893
+        },
+        {
+          "text": "got",
+          "start": 73.12,
+          "end": 73.16,
+          "confidence": 0.902
+        },
+        {
+          "text": "them,",
+          "start": 73.16,
+          "end": 73.2,
+          "confidence": 0.905
+        },
+        {
+          "text": "got",
+          "start": 73.2,
+          "end": 73.24,
+          "confidence": 0.898
+        },
+        {
+          "text": "them,",
+          "start": 73.24,
+          "end": 73.28,
+          "confidence": 0.906
+        },
+        {
+          "text": "got",
+          "start": 73.28,
+          "end": 73.32,
+          "confidence": 0.876
+        },
+        {
+          "text": "them,",
+          "start": 73.32,
+          "end": 73.36,
+          "confidence": 0.916
+        },
+        {
+          "text": "got",
+          "start": 73.36,
+          "end": 73.4,
+          "confidence": 0.885
+        },
+        {
+          "text": "them,",
+          "start": 73.4,
+          "end": 73.44,
+          "confidence": 0.923
+        },
+        {
+          "text": "got",
+          "start": 73.44,
+          "end": 73.48,
+          "confidence": 0.892
+        },
+        {
+          "text": "them,",
+          "start": 73.48,
+          "end": 73.52,
+          "confidence": 0.931
+        },
+        {
+          "text": "got",
+          "start": 73.52,
+          "end": 73.56,
+          "confidence": 0.902
+        },
+        {
+          "text": "them,",
+          "start": 73.56,
+          "end": 73.6,
+          "confidence": 0.935
+        },
+        {
+          "text": "got",
+          "start": 73.6,
+          "end": 73.64,
+          "confidence": 0.908
+        },
+        {
+          "text": "them,",
+          "start": 73.64,
+          "end": 73.68,
+          "confidence": 0.941
+        },
+        {
+          "text": "got",
+          "start": 73.68,
+          "end": 73.72,
+          "confidence": 0.912
+        },
+        {
+          "text": "them,",
+          "start": 73.72,
+          "end": 73.76,
+          "confidence": 0.944
+        },
+        {
+          "text": "got",
+          "start": 73.76,
+          "end": 73.8,
+          "confidence": 0.918
+        },
+        {
+          "text": "them,",
+          "start": 73.8,
+          "end": 73.84,
+          "confidence": 0.948
+        },
+        {
+          "text": "got",
+          "start": 73.84,
+          "end": 73.88,
+          "confidence": 0.923
+        },
+        {
+          "text": "them,",
+          "start": 73.88,
+          "end": 73.92,
+          "confidence": 0.95
+        },
+        {
+          "text": "got",
+          "start": 73.92,
+          "end": 73.96,
+          "confidence": 0.926
+        },
+        {
+          "text": "them,",
+          "start": 73.96,
+          "end": 74.0,
+          "confidence": 0.953
+        },
+        {
+          "text": "got",
+          "start": 74.0,
+          "end": 74.04,
+          "confidence": 0.927
+        },
+        {
+          "text": "them,",
+          "start": 74.04,
+          "end": 74.08,
+          "confidence": 0.956
+        },
+        {
+          "text": "got",
+          "start": 74.08,
+          "end": 74.12,
+          "confidence": 0.927
+        },
+        {
+          "text": "them,",
+          "start": 74.12,
+          "end": 74.16,
+          "confidence": 0.956
+        },
+        {
+          "text": "got",
+          "start": 74.16,
+          "end": 74.2,
+          "confidence": 0.928
+        },
+        {
+          "text": "them,",
+          "start": 74.2,
+          "end": 74.24,
+          "confidence": 0.957
+        },
+        {
+          "text": "got",
+          "start": 74.24,
+          "end": 74.28,
+          "confidence": 0.93
+        },
+        {
+          "text": "them,",
+          "start": 74.28,
+          "end": 74.32,
+          "confidence": 0.959
+        },
+        {
+          "text": "got",
+          "start": 74.32,
+          "end": 74.36,
+          "confidence": 0.93
+        },
+        {
+          "text": "them,",
+          "start": 74.36,
+          "end": 74.4,
+          "confidence": 0.96
+        },
+        {
+          "text": "got",
+          "start": 74.4,
+          "end": 74.44,
+          "confidence": 0.931
+        },
+        {
+          "text": "them,",
+          "start": 74.44,
+          "end": 74.48,
+          "confidence": 0.961
+        },
+        {
+          "text": "got",
+          "start": 74.48,
+          "end": 74.52,
+          "confidence": 0.933
+        },
+        {
+          "text": "them,",
+          "start": 74.52,
+          "end": 74.56,
+          "confidence": 0.962
+        },
+        {
+          "text": "got",
+          "start": 74.56,
+          "end": 74.6,
+          "confidence": 0.933
+        },
+        {
+          "text": "them,",
+          "start": 74.6,
+          "end": 74.64,
+          "confidence": 0.963
+        },
+        {
+          "text": "got",
+          "start": 74.64,
+          "end": 74.68,
+          "confidence": 0.934
+        },
+        {
+          "text": "them,",
+          "start": 74.68,
+          "end": 74.72,
+          "confidence": 0.963
+        },
+        {
+          "text": "got",
+          "start": 74.72,
+          "end": 74.76,
+          "confidence": 0.935
+        },
+        {
+          "text": "them,",
+          "start": 74.76,
+          "end": 74.8,
+          "confidence": 0.964
+        },
+        {
+          "text": "got",
+          "start": 74.8,
+          "end": 74.84,
+          "confidence": 0.937
+        },
+        {
+          "text": "them,",
+          "start": 74.84,
+          "end": 74.88,
+          "confidence": 0.964
+        },
+        {
+          "text": "got",
+          "start": 74.88,
+          "end": 74.92,
+          "confidence": 0.939
+        },
+        {
+          "text": "them,",
+          "start": 74.92,
+          "end": 74.96,
+          "confidence": 0.965
+        },
+        {
+          "text": "got",
+          "start": 74.96,
+          "end": 75.0,
+          "confidence": 0.941
+        },
+        {
+          "text": "them,",
+          "start": 75.0,
+          "end": 75.04,
+          "confidence": 0.966
+        },
+        {
+          "text": "got",
+          "start": 75.04,
+          "end": 75.08,
+          "confidence": 0.943
+        },
+        {
+          "text": "them,",
+          "start": 75.08,
+          "end": 75.12,
+          "confidence": 0.967
+        },
+        {
+          "text": "got",
+          "start": 75.12,
+          "end": 75.16,
+          "confidence": 0.945
+        },
+        {
+          "text": "them,",
+          "start": 75.16,
+          "end": 75.2,
+          "confidence": 0.968
+        },
+        {
+          "text": "got",
+          "start": 75.2,
+          "end": 75.24,
+          "confidence": 0.946
+        },
+        {
+          "text": "them,",
+          "start": 75.24,
+          "end": 75.28,
+          "confidence": 0.968
+        },
+        {
+          "text": "got",
+          "start": 75.28,
+          "end": 75.32,
+          "confidence": 0.949
+        },
+        {
+          "text": "them,",
+          "start": 75.32,
+          "end": 75.36,
+          "confidence": 0.969
+        },
+        {
+          "text": "got",
+          "start": 75.36,
+          "end": 75.4,
+          "confidence": 0.952
+        },
+        {
+          "text": "them,",
+          "start": 75.4,
+          "end": 75.44,
+          "confidence": 0.969
+        },
+        {
+          "text": "got",
+          "start": 75.44,
+          "end": 75.48,
+          "confidence": 0.954
+        },
+        {
+          "text": "them,",
+          "start": 75.48,
+          "end": 75.52,
+          "confidence": 0.97
+        },
+        {
+          "text": "got",
+          "start": 75.52,
+          "end": 75.56,
+          "confidence": 0.957
+        },
+        {
+          "text": "them,",
+          "start": 75.56,
+          "end": 75.6,
+          "confidence": 0.971
+        },
+        {
+          "text": "got",
+          "start": 75.6,
+          "end": 75.64,
+          "confidence": 0.96
+        },
+        {
+          "text": "them,",
+          "start": 75.64,
+          "end": 75.68,
+          "confidence": 0.973
+        },
+        {
+          "text": "got",
+          "start": 75.68,
+          "end": 75.72,
+          "confidence": 0.963
+        },
+        {
+          "text": "them,",
+          "start": 75.72,
+          "end": 75.76,
+          "confidence": 0.973
+        },
+        {
+          "text": "got",
+          "start": 75.76,
+          "end": 75.8,
+          "confidence": 0.965
+        },
+        {
+          "text": "them,",
+          "start": 75.8,
+          "end": 75.84,
+          "confidence": 0.973
+        },
+        {
+          "text": "got",
+          "start": 75.84,
+          "end": 75.88,
+          "confidence": 0.967
+        },
+        {
+          "text": "them,",
+          "start": 75.88,
+          "end": 75.92,
+          "confidence": 0.973
+        },
+        {
+          "text": "got",
+          "start": 75.92,
+          "end": 75.96,
+          "confidence": 0.969
+        },
+        {
+          "text": "them,",
+          "start": 75.96,
+          "end": 76.0,
+          "confidence": 0.975
+        },
+        {
+          "text": "got",
+          "start": 76.0,
+          "end": 76.04,
+          "confidence": 0.971
+        },
+        {
+          "text": "them,",
+          "start": 76.04,
+          "end": 76.08,
+          "confidence": 0.975
+        },
+        {
+          "text": "got",
+          "start": 76.08,
+          "end": 76.12,
+          "confidence": 0.972
+        },
+        {
+          "text": "them,",
+          "start": 76.12,
+          "end": 76.16,
+          "confidence": 0.976
+        },
+        {
+          "text": "got",
+          "start": 76.16,
+          "end": 76.2,
+          "confidence": 0.975
+        },
+        {
+          "text": "them,",
+          "start": 76.2,
+          "end": 76.24,
+          "confidence": 0.976
+        },
+        {
+          "text": "got",
+          "start": 76.24,
+          "end": 76.28,
+          "confidence": 0.975
+        },
+        {
+          "text": "them,",
+          "start": 76.28,
+          "end": 76.32,
+          "confidence": 0.975
+        },
+        {
+          "text": "got",
+          "start": 76.32,
+          "end": 76.36,
+          "confidence": 0.977
+        },
+        {
+          "text": "them,",
+          "start": 76.36,
+          "end": 76.4,
+          "confidence": 0.977
+        },
+        {
+          "text": "got",
+          "start": 76.4,
+          "end": 76.44,
+          "confidence": 0.978
+        },
+        {
+          "text": "them,",
+          "start": 76.44,
+          "end": 76.48,
+          "confidence": 0.977
+        },
+        {
+          "text": "got",
+          "start": 76.48,
+          "end": 76.52,
+          "confidence": 0.98
+        },
+        {
+          "text": "them,",
+          "start": 76.52,
+          "end": 76.56,
+          "confidence": 0.978
+        },
+        {
+          "text": "got",
+          "start": 76.56,
+          "end": 76.6,
+          "confidence": 0.981
+        },
+        {
+          "text": "them,",
+          "start": 76.6,
+          "end": 76.64,
+          "confidence": 0.978
+        },
+        {
+          "text": "got",
+          "start": 76.64,
+          "end": 76.68,
+          "confidence": 0.982
+        },
+        {
+          "text": "them,",
+          "start": 76.68,
+          "end": 76.72,
+          "confidence": 0.979
+        },
+        {
+          "text": "got",
+          "start": 76.72,
+          "end": 76.76,
+          "confidence": 0.982
+        },
+        {
+          "text": "them,",
+          "start": 76.76,
+          "end": 76.8,
+          "confidence": 0.978
+        },
+        {
+          "text": "got",
+          "start": 76.8,
+          "end": 76.84,
+          "confidence": 0.983
+        },
+        {
+          "text": "them,",
+          "start": 76.84,
+          "end": 76.88,
+          "confidence": 0.98
+        },
+        {
+          "text": "got",
+          "start": 76.88,
+          "end": 76.92,
+          "confidence": 0.984
+        },
+        {
+          "text": "them,",
+          "start": 76.92,
+          "end": 76.96,
+          "confidence": 0.98
+        },
+        {
+          "text": "got",
+          "start": 76.96,
+          "end": 77.0,
+          "confidence": 0.985
+        },
+        {
+          "text": "them,",
+          "start": 77.0,
+          "end": 77.04,
+          "confidence": 0.98
+        },
+        {
+          "text": "got",
+          "start": 77.04,
+          "end": 77.08,
+          "confidence": 0.986
+        },
+        {
+          "text": "them,",
+          "start": 77.08,
+          "end": 77.12,
+          "confidence": 0.98
+        },
+        {
+          "text": "got",
+          "start": 77.12,
+          "end": 77.16,
+          "confidence": 0.986
+        },
+        {
+          "text": "them,",
+          "start": 77.16,
+          "end": 77.2,
+          "confidence": 0.98
+        },
+        {
+          "text": "got",
+          "start": 77.2,
+          "end": 77.24,
+          "confidence": 0.987
+        },
+        {
+          "text": "them,",
+          "start": 77.24,
+          "end": 77.28,
+          "confidence": 0.981
+        },
+        {
+          "text": "got",
+          "start": 77.28,
+          "end": 77.32,
+          "confidence": 0.988
+        },
+        {
+          "text": "them,",
+          "start": 77.32,
+          "end": 77.36,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 77.36,
+          "end": 77.4,
+          "confidence": 0.988
+        },
+        {
+          "text": "them,",
+          "start": 77.4,
+          "end": 77.44,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 77.44,
+          "end": 77.48,
+          "confidence": 0.989
+        },
+        {
+          "text": "them,",
+          "start": 77.48,
+          "end": 77.52,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 77.52,
+          "end": 77.56,
+          "confidence": 0.99
+        },
+        {
+          "text": "them,",
+          "start": 77.56,
+          "end": 77.6,
+          "confidence": 0.984
+        },
+        {
+          "text": "got",
+          "start": 77.6,
+          "end": 77.64,
+          "confidence": 0.99
+        },
+        {
+          "text": "them,",
+          "start": 77.64,
+          "end": 78.74,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 78.74,
+          "end": 78.8,
+          "confidence": 0.991
+        },
+        {
+          "text": "them,",
+          "start": 78.8,
+          "end": 79.8,
+          "confidence": 0.984
+        },
+        {
+          "text": "got",
+          "start": 79.8,
+          "end": 80.08,
+          "confidence": 0.991
+        },
+        {
+          "text": "them,",
+          "start": 80.08,
+          "end": 83.98,
+          "confidence": 0.984
+        },
+        {
+          "text": "got",
+          "start": 83.98,
+          "end": 84.16,
+          "confidence": 0.991
+        },
+        {
+          "text": "them",
+          "start": 84.16,
+          "end": 84.66,
+          "confidence": 0.994
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 8500,
+      "start": 84.68,
+      "end": 94.48,
+      "text": " got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them",
+      "tokens": [
+        50364,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.04979915789959142,
+      "compression_ratio": 29.52,
+      "no_speech_prob": 0.6971050500869751,
+      "confidence": 0.848,
+      "words": [
+        {
+          "text": "got",
+          "start": 84.68,
+          "end": 85.42,
+          "confidence": 0.0
+        },
+        {
+          "text": "them,",
+          "start": 85.42,
+          "end": 85.92,
+          "confidence": 0.023
+        },
+        {
+          "text": "got",
+          "start": 85.92,
+          "end": 86.74,
+          "confidence": 0.821
+        },
+        {
+          "text": "them,",
+          "start": 86.74,
+          "end": 87.2,
+          "confidence": 0.604
+        },
+        {
+          "text": "got",
+          "start": 87.2,
+          "end": 88.62,
+          "confidence": 0.84
+        },
+        {
+          "text": "them,",
+          "start": 88.62,
+          "end": 88.66,
+          "confidence": 0.451
+        },
+        {
+          "text": "got",
+          "start": 88.66,
+          "end": 88.84,
+          "confidence": 0.887
+        },
+        {
+          "text": "them,",
+          "start": 88.84,
+          "end": 88.88,
+          "confidence": 0.382
+        },
+        {
+          "text": "got",
+          "start": 88.88,
+          "end": 88.92,
+          "confidence": 0.902
+        },
+        {
+          "text": "them,",
+          "start": 88.92,
+          "end": 88.96,
+          "confidence": 0.353
+        },
+        {
+          "text": "got",
+          "start": 88.96,
+          "end": 89.0,
+          "confidence": 0.896
+        },
+        {
+          "text": "them,",
+          "start": 89.0,
+          "end": 89.04,
+          "confidence": 0.352
+        },
+        {
+          "text": "got",
+          "start": 89.04,
+          "end": 89.08,
+          "confidence": 0.869
+        },
+        {
+          "text": "them,",
+          "start": 89.08,
+          "end": 89.12,
+          "confidence": 0.423
+        },
+        {
+          "text": "got",
+          "start": 89.12,
+          "end": 89.16,
+          "confidence": 0.889
+        },
+        {
+          "text": "them,",
+          "start": 89.16,
+          "end": 89.2,
+          "confidence": 0.528
+        },
+        {
+          "text": "got",
+          "start": 89.2,
+          "end": 89.24,
+          "confidence": 0.91
+        },
+        {
+          "text": "them,",
+          "start": 89.24,
+          "end": 89.28,
+          "confidence": 0.619
+        },
+        {
+          "text": "got",
+          "start": 89.28,
+          "end": 89.32,
+          "confidence": 0.65
+        },
+        {
+          "text": "them,",
+          "start": 89.32,
+          "end": 89.36,
+          "confidence": 0.71
+        },
+        {
+          "text": "got",
+          "start": 89.36,
+          "end": 89.4,
+          "confidence": 0.835
+        },
+        {
+          "text": "them,",
+          "start": 89.4,
+          "end": 89.44,
+          "confidence": 0.815
+        },
+        {
+          "text": "got",
+          "start": 89.44,
+          "end": 89.48,
+          "confidence": 0.908
+        },
+        {
+          "text": "them,",
+          "start": 89.48,
+          "end": 89.52,
+          "confidence": 0.874
+        },
+        {
+          "text": "got",
+          "start": 89.52,
+          "end": 89.56,
+          "confidence": 0.925
+        },
+        {
+          "text": "them,",
+          "start": 89.56,
+          "end": 89.6,
+          "confidence": 0.907
+        },
+        {
+          "text": "got",
+          "start": 89.6,
+          "end": 89.64,
+          "confidence": 0.941
+        },
+        {
+          "text": "them,",
+          "start": 89.64,
+          "end": 89.68,
+          "confidence": 0.927
+        },
+        {
+          "text": "got",
+          "start": 89.68,
+          "end": 89.72,
+          "confidence": 0.951
+        },
+        {
+          "text": "them,",
+          "start": 89.72,
+          "end": 89.76,
+          "confidence": 0.941
+        },
+        {
+          "text": "got",
+          "start": 89.76,
+          "end": 89.8,
+          "confidence": 0.956
+        },
+        {
+          "text": "them,",
+          "start": 89.8,
+          "end": 89.84,
+          "confidence": 0.942
+        },
+        {
+          "text": "got",
+          "start": 89.84,
+          "end": 89.88,
+          "confidence": 0.957
+        },
+        {
+          "text": "them,",
+          "start": 89.88,
+          "end": 89.92,
+          "confidence": 0.943
+        },
+        {
+          "text": "got",
+          "start": 89.92,
+          "end": 89.96,
+          "confidence": 0.95
+        },
+        {
+          "text": "them,",
+          "start": 89.96,
+          "end": 90.0,
+          "confidence": 0.945
+        },
+        {
+          "text": "got",
+          "start": 90.0,
+          "end": 90.04,
+          "confidence": 0.945
+        },
+        {
+          "text": "them,",
+          "start": 90.04,
+          "end": 90.08,
+          "confidence": 0.952
+        },
+        {
+          "text": "got",
+          "start": 90.08,
+          "end": 90.12,
+          "confidence": 0.946
+        },
+        {
+          "text": "them,",
+          "start": 90.12,
+          "end": 90.16,
+          "confidence": 0.955
+        },
+        {
+          "text": "got",
+          "start": 90.16,
+          "end": 90.2,
+          "confidence": 0.947
+        },
+        {
+          "text": "them,",
+          "start": 90.2,
+          "end": 90.24,
+          "confidence": 0.961
+        },
+        {
+          "text": "got",
+          "start": 90.24,
+          "end": 90.28,
+          "confidence": 0.946
+        },
+        {
+          "text": "them,",
+          "start": 90.28,
+          "end": 90.32,
+          "confidence": 0.964
+        },
+        {
+          "text": "got",
+          "start": 90.32,
+          "end": 90.36,
+          "confidence": 0.949
+        },
+        {
+          "text": "them,",
+          "start": 90.36,
+          "end": 90.4,
+          "confidence": 0.967
+        },
+        {
+          "text": "got",
+          "start": 90.4,
+          "end": 90.44,
+          "confidence": 0.952
+        },
+        {
+          "text": "them,",
+          "start": 90.44,
+          "end": 90.48,
+          "confidence": 0.97
+        },
+        {
+          "text": "got",
+          "start": 90.48,
+          "end": 90.52,
+          "confidence": 0.954
+        },
+        {
+          "text": "them,",
+          "start": 90.52,
+          "end": 90.56,
+          "confidence": 0.973
+        },
+        {
+          "text": "got",
+          "start": 90.56,
+          "end": 90.6,
+          "confidence": 0.954
+        },
+        {
+          "text": "them,",
+          "start": 90.6,
+          "end": 90.64,
+          "confidence": 0.977
+        },
+        {
+          "text": "got",
+          "start": 90.64,
+          "end": 90.68,
+          "confidence": 0.953
+        },
+        {
+          "text": "them,",
+          "start": 90.68,
+          "end": 90.72,
+          "confidence": 0.977
+        },
+        {
+          "text": "got",
+          "start": 90.72,
+          "end": 90.76,
+          "confidence": 0.953
+        },
+        {
+          "text": "them,",
+          "start": 90.76,
+          "end": 90.8,
+          "confidence": 0.978
+        },
+        {
+          "text": "got",
+          "start": 90.8,
+          "end": 90.84,
+          "confidence": 0.955
+        },
+        {
+          "text": "them,",
+          "start": 90.84,
+          "end": 90.88,
+          "confidence": 0.979
+        },
+        {
+          "text": "got",
+          "start": 90.88,
+          "end": 90.92,
+          "confidence": 0.956
+        },
+        {
+          "text": "them,",
+          "start": 90.92,
+          "end": 90.96,
+          "confidence": 0.981
+        },
+        {
+          "text": "got",
+          "start": 90.96,
+          "end": 91.0,
+          "confidence": 0.957
+        },
+        {
+          "text": "them,",
+          "start": 91.0,
+          "end": 91.04,
+          "confidence": 0.981
+        },
+        {
+          "text": "got",
+          "start": 91.04,
+          "end": 91.08,
+          "confidence": 0.958
+        },
+        {
+          "text": "them,",
+          "start": 91.08,
+          "end": 91.12,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 91.12,
+          "end": 91.16,
+          "confidence": 0.958
+        },
+        {
+          "text": "them,",
+          "start": 91.16,
+          "end": 91.2,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 91.2,
+          "end": 91.24,
+          "confidence": 0.959
+        },
+        {
+          "text": "them,",
+          "start": 91.24,
+          "end": 91.28,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 91.28,
+          "end": 91.32,
+          "confidence": 0.96
+        },
+        {
+          "text": "them,",
+          "start": 91.32,
+          "end": 91.36,
+          "confidence": 0.984
+        },
+        {
+          "text": "got",
+          "start": 91.36,
+          "end": 91.4,
+          "confidence": 0.962
+        },
+        {
+          "text": "them,",
+          "start": 91.4,
+          "end": 91.44,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 91.44,
+          "end": 91.48,
+          "confidence": 0.964
+        },
+        {
+          "text": "them,",
+          "start": 91.48,
+          "end": 91.52,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 91.52,
+          "end": 91.56,
+          "confidence": 0.965
+        },
+        {
+          "text": "them,",
+          "start": 91.56,
+          "end": 91.6,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 91.6,
+          "end": 91.64,
+          "confidence": 0.967
+        },
+        {
+          "text": "them,",
+          "start": 91.64,
+          "end": 91.68,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 91.68,
+          "end": 91.72,
+          "confidence": 0.969
+        },
+        {
+          "text": "them,",
+          "start": 91.72,
+          "end": 91.76,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 91.76,
+          "end": 91.8,
+          "confidence": 0.969
+        },
+        {
+          "text": "them,",
+          "start": 91.8,
+          "end": 91.84,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 91.84,
+          "end": 91.88,
+          "confidence": 0.972
+        },
+        {
+          "text": "them,",
+          "start": 91.88,
+          "end": 91.92,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 91.92,
+          "end": 91.96,
+          "confidence": 0.974
+        },
+        {
+          "text": "them,",
+          "start": 91.96,
+          "end": 92.0,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 92.0,
+          "end": 92.04,
+          "confidence": 0.975
+        },
+        {
+          "text": "them,",
+          "start": 92.04,
+          "end": 92.08,
+          "confidence": 0.988
+        },
+        {
+          "text": "got",
+          "start": 92.08,
+          "end": 92.12,
+          "confidence": 0.977
+        },
+        {
+          "text": "them,",
+          "start": 92.12,
+          "end": 92.16,
+          "confidence": 0.988
+        },
+        {
+          "text": "got",
+          "start": 92.16,
+          "end": 92.2,
+          "confidence": 0.979
+        },
+        {
+          "text": "them,",
+          "start": 92.2,
+          "end": 92.24,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 92.24,
+          "end": 92.28,
+          "confidence": 0.981
+        },
+        {
+          "text": "them,",
+          "start": 92.28,
+          "end": 92.32,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 92.32,
+          "end": 92.36,
+          "confidence": 0.982
+        },
+        {
+          "text": "them,",
+          "start": 92.36,
+          "end": 92.4,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 92.4,
+          "end": 92.44,
+          "confidence": 0.984
+        },
+        {
+          "text": "them,",
+          "start": 92.44,
+          "end": 92.48,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 92.48,
+          "end": 92.52,
+          "confidence": 0.985
+        },
+        {
+          "text": "them,",
+          "start": 92.52,
+          "end": 92.56,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 92.56,
+          "end": 92.6,
+          "confidence": 0.986
+        },
+        {
+          "text": "them,",
+          "start": 92.6,
+          "end": 92.64,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 92.64,
+          "end": 92.68,
+          "confidence": 0.987
+        },
+        {
+          "text": "them,",
+          "start": 92.68,
+          "end": 92.72,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 92.72,
+          "end": 92.76,
+          "confidence": 0.989
+        },
+        {
+          "text": "them,",
+          "start": 92.76,
+          "end": 92.8,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 92.8,
+          "end": 92.84,
+          "confidence": 0.989
+        },
+        {
+          "text": "them,",
+          "start": 92.84,
+          "end": 92.88,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 92.88,
+          "end": 92.92,
+          "confidence": 0.99
+        },
+        {
+          "text": "them,",
+          "start": 92.92,
+          "end": 92.96,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 92.96,
+          "end": 93.0,
+          "confidence": 0.991
+        },
+        {
+          "text": "them,",
+          "start": 93.0,
+          "end": 93.04,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 93.04,
+          "end": 93.08,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 93.08,
+          "end": 93.12,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 93.12,
+          "end": 93.16,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 93.16,
+          "end": 93.2,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 93.2,
+          "end": 93.24,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 93.24,
+          "end": 93.28,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 93.28,
+          "end": 93.32,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 93.32,
+          "end": 93.36,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 93.36,
+          "end": 93.4,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 93.4,
+          "end": 93.44,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 93.44,
+          "end": 93.48,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 93.48,
+          "end": 93.52,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 93.52,
+          "end": 93.56,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 93.56,
+          "end": 93.6,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 93.6,
+          "end": 93.64,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 93.64,
+          "end": 93.68,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 93.68,
+          "end": 93.72,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 93.72,
+          "end": 93.76,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 93.76,
+          "end": 93.8,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 93.8,
+          "end": 93.84,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 93.84,
+          "end": 93.88,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 93.88,
+          "end": 93.92,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 93.92,
+          "end": 93.96,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 93.96,
+          "end": 94.0,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 94.0,
+          "end": 94.04,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 94.04,
+          "end": 94.08,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 94.08,
+          "end": 94.12,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 94.12,
+          "end": 94.16,
+          "confidence": 0.995
+        },
+        {
+          "text": "got",
+          "start": 94.16,
+          "end": 94.2,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 94.2,
+          "end": 94.24,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 94.24,
+          "end": 94.28,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 94.28,
+          "end": 94.32,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 94.32,
+          "end": 94.36,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 94.36,
+          "end": 94.4,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 94.4,
+          "end": 94.44,
+          "confidence": 0.995
+        },
+        {
+          "text": "them",
+          "start": 94.44,
+          "end": 94.48,
+          "confidence": 0.998
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/naive/accurate_apollo11.mp3.words.json b/tests/expected/naive/accurate_apollo11.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..1f11dd18ce3fb73e4522e0caf68bd4780a40a3f3
--- /dev/null
+++ b/tests/expected/naive/accurate_apollo11.mp3.words.json
@@ -0,0 +1,2288 @@
+{
+  "text": " Apollo 11, Houston, we got a recommendation for you on your Soyuz-EA GLEM-E-G-E-A. All right. Okay. Yeah, sir. Yeah, sir. Let's take that camera. Let's say it makes it want to go on the helmet we were going to have in B-1. The other one. And you can put the other one on the mic helmet. We'll show it to you in a quick screen. Over. All right. Yeah, sir. All right. Yeah, sir. There's a better helmet than B-1. That's the other one. Nice. Let's go in there. At least we're safe. We've got them in there. Helmet bags. And, uh, I guess we have helmets in the helmet bag. At least it's in the helmet bag. Right here. Right here. Yeah, we're taking it next day. Yeah, we're taking it next day. We're gonna hang me on the cover. I tried it already. Okay, fine. We weren't sure that, uh, just a suggestion. We thought we'd, uh, that you could check it out. It's not much of an order, sir. And so, uh, I guess we're gonna come up with this. Let us know. Okay. No problem. Okay. No problem. No problem. No worry. None. Thank you.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.54,
+      "end": 6.66,
+      "text": " Apollo 11, Houston, we got a recommendation for you on your Soyuz-EA GLEM-E-G-E-A.",
+      "tokens": [
+        50364,
+        25187,
+        2975,
+        11,
+        18717,
+        11,
+        321,
+        658,
+        257,
+        11879,
+        337,
+        291,
+        322,
+        428,
+        24758,
+        3334,
+        12,
+        36,
+        32,
+        460,
+        2634,
+        44,
+        12,
+        36,
+        12,
+        38,
+        12,
+        36,
+        12,
+        32,
+        13,
+        50714
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5319976806640625,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.44995221495628357,
+      "confidence": 0.578,
+      "words": [
+        {
+          "text": "Apollo",
+          "start": 0.54,
+          "end": 0.92,
+          "confidence": 0.425
+        },
+        {
+          "text": "11,",
+          "start": 0.92,
+          "end": 1.26,
+          "confidence": 0.842
+        },
+        {
+          "text": "Houston,",
+          "start": 1.52,
+          "end": 1.72,
+          "confidence": 0.665
+        },
+        {
+          "text": "we",
+          "start": 1.9,
+          "end": 1.94,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 1.94,
+          "end": 2.1,
+          "confidence": 0.743
+        },
+        {
+          "text": "a",
+          "start": 2.1,
+          "end": 2.26,
+          "confidence": 0.993
+        },
+        {
+          "text": "recommendation",
+          "start": 2.26,
+          "end": 2.86,
+          "confidence": 0.977
+        },
+        {
+          "text": "for",
+          "start": 2.86,
+          "end": 3.44,
+          "confidence": 0.94
+        },
+        {
+          "text": "you",
+          "start": 3.44,
+          "end": 3.6,
+          "confidence": 0.993
+        },
+        {
+          "text": "on",
+          "start": 3.6,
+          "end": 3.74,
+          "confidence": 0.918
+        },
+        {
+          "text": "your",
+          "start": 3.74,
+          "end": 3.94,
+          "confidence": 0.976
+        },
+        {
+          "text": "Soyuz-EA",
+          "start": 3.94,
+          "end": 5.26,
+          "confidence": 0.455
+        },
+        {
+          "text": "GLEM-E-G-E-A.",
+          "start": 5.26,
+          "end": 6.66,
+          "confidence": 0.436
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 10.8,
+      "end": 11.08,
+      "text": " All right.",
+      "tokens": [
+        50714,
+        1057,
+        558,
+        13,
+        50914
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5319976806640625,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.44995221495628357,
+      "confidence": 0.14,
+      "words": [
+        {
+          "text": "All",
+          "start": 10.8,
+          "end": 10.82,
+          "confidence": 0.005
+        },
+        {
+          "text": "right.",
+          "start": 10.82,
+          "end": 11.08,
+          "confidence": 0.747
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 12.2,
+      "end": 12.22,
+      "text": " Okay.",
+      "tokens": [
+        50914,
+        1033,
+        13,
+        50964
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5319976806640625,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.44995221495628357,
+      "confidence": 0.287,
+      "words": [
+        {
+          "text": "Okay.",
+          "start": 12.2,
+          "end": 12.22,
+          "confidence": 0.287
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 12.22,
+      "end": 13.38,
+      "text": " Yeah, sir.",
+      "tokens": [
+        50964,
+        865,
+        11,
+        4735,
+        13,
+        51014
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5319976806640625,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.44995221495628357,
+      "confidence": 0.124,
+      "words": [
+        {
+          "text": "Yeah,",
+          "start": 12.22,
+          "end": 12.64,
+          "confidence": 0.113
+        },
+        {
+          "text": "sir.",
+          "start": 12.76,
+          "end": 13.38,
+          "confidence": 0.137
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 13.38,
+      "end": 13.92,
+      "text": " Yeah, sir.",
+      "tokens": [
+        51014,
+        865,
+        11,
+        4735,
+        13,
+        51064
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5319976806640625,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.44995221495628357,
+      "confidence": 0.048,
+      "words": [
+        {
+          "text": "Yeah,",
+          "start": 13.38,
+          "end": 13.48,
+          "confidence": 0.089
+        },
+        {
+          "text": "sir.",
+          "start": 13.64,
+          "end": 13.92,
+          "confidence": 0.026
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 0,
+      "start": 13.92,
+      "end": 14.52,
+      "text": " Let's take that camera.",
+      "tokens": [
+        51064,
+        961,
+        311,
+        747,
+        300,
+        2799,
+        13,
+        51114
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5319976806640625,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.44995221495628357,
+      "confidence": 0.054,
+      "words": [
+        {
+          "text": "Let's",
+          "start": 13.92,
+          "end": 14.04,
+          "confidence": 0.035
+        },
+        {
+          "text": "take",
+          "start": 14.04,
+          "end": 14.14,
+          "confidence": 0.027
+        },
+        {
+          "text": "that",
+          "start": 14.14,
+          "end": 14.22,
+          "confidence": 0.037
+        },
+        {
+          "text": "camera.",
+          "start": 14.22,
+          "end": 14.52,
+          "confidence": 0.14
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 0,
+      "start": 14.52,
+      "end": 19.08,
+      "text": " Let's say it makes it want to go on the helmet we were going to have in B-1.",
+      "tokens": [
+        51114,
+        961,
+        311,
+        584,
+        309,
+        1669,
+        309,
+        528,
+        281,
+        352,
+        322,
+        264,
+        15922,
+        321,
+        645,
+        516,
+        281,
+        362,
+        294,
+        363,
+        12,
+        16,
+        13,
+        51314
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5319976806640625,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.44995221495628357,
+      "confidence": 0.29,
+      "words": [
+        {
+          "text": "Let's",
+          "start": 14.52,
+          "end": 14.82,
+          "confidence": 0.124
+        },
+        {
+          "text": "say",
+          "start": 14.82,
+          "end": 14.98,
+          "confidence": 0.29
+        },
+        {
+          "text": "it",
+          "start": 14.98,
+          "end": 15.04,
+          "confidence": 0.029
+        },
+        {
+          "text": "makes",
+          "start": 15.04,
+          "end": 15.64,
+          "confidence": 0.633
+        },
+        {
+          "text": "it",
+          "start": 15.64,
+          "end": 15.86,
+          "confidence": 0.948
+        },
+        {
+          "text": "want",
+          "start": 15.86,
+          "end": 16.08,
+          "confidence": 0.249
+        },
+        {
+          "text": "to",
+          "start": 16.08,
+          "end": 16.18,
+          "confidence": 0.969
+        },
+        {
+          "text": "go",
+          "start": 16.18,
+          "end": 16.38,
+          "confidence": 0.816
+        },
+        {
+          "text": "on",
+          "start": 16.38,
+          "end": 16.6,
+          "confidence": 0.935
+        },
+        {
+          "text": "the",
+          "start": 16.6,
+          "end": 16.76,
+          "confidence": 0.449
+        },
+        {
+          "text": "helmet",
+          "start": 16.76,
+          "end": 17.24,
+          "confidence": 0.003
+        },
+        {
+          "text": "we",
+          "start": 17.24,
+          "end": 17.54,
+          "confidence": 0.019
+        },
+        {
+          "text": "were",
+          "start": 17.54,
+          "end": 17.78,
+          "confidence": 0.181
+        },
+        {
+          "text": "going",
+          "start": 17.78,
+          "end": 17.96,
+          "confidence": 0.637
+        },
+        {
+          "text": "to",
+          "start": 17.96,
+          "end": 18.12,
+          "confidence": 0.965
+        },
+        {
+          "text": "have",
+          "start": 18.12,
+          "end": 18.18,
+          "confidence": 0.967
+        },
+        {
+          "text": "in",
+          "start": 18.18,
+          "end": 18.36,
+          "confidence": 0.902
+        },
+        {
+          "text": "B-1.",
+          "start": 18.36,
+          "end": 19.08,
+          "confidence": 0.471
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 0,
+      "start": 19.08,
+      "end": 19.84,
+      "text": " The other one.",
+      "tokens": [
+        51314,
+        440,
+        661,
+        472,
+        13,
+        51364
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5319976806640625,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.44995221495628357,
+      "confidence": 0.126,
+      "words": [
+        {
+          "text": "The",
+          "start": 19.08,
+          "end": 19.38,
+          "confidence": 0.004
+        },
+        {
+          "text": "other",
+          "start": 19.38,
+          "end": 19.62,
+          "confidence": 0.141
+        },
+        {
+          "text": "one.",
+          "start": 19.62,
+          "end": 19.84,
+          "confidence": 0.691
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 0,
+      "start": 20.04,
+      "end": 22.8,
+      "text": " And you can put the other one on the mic helmet.",
+      "tokens": [
+        51364,
+        400,
+        291,
+        393,
+        829,
+        264,
+        661,
+        472,
+        322,
+        264,
+        3123,
+        15922,
+        13,
+        51514
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5319976806640625,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.44995221495628357,
+      "confidence": 0.405,
+      "words": [
+        {
+          "text": "And",
+          "start": 20.04,
+          "end": 20.22,
+          "confidence": 0.344
+        },
+        {
+          "text": "you",
+          "start": 20.22,
+          "end": 20.32,
+          "confidence": 0.892
+        },
+        {
+          "text": "can",
+          "start": 20.32,
+          "end": 20.48,
+          "confidence": 0.126
+        },
+        {
+          "text": "put",
+          "start": 20.48,
+          "end": 20.64,
+          "confidence": 0.894
+        },
+        {
+          "text": "the",
+          "start": 20.64,
+          "end": 20.84,
+          "confidence": 0.979
+        },
+        {
+          "text": "other",
+          "start": 20.84,
+          "end": 21.0,
+          "confidence": 0.996
+        },
+        {
+          "text": "one",
+          "start": 21.0,
+          "end": 21.18,
+          "confidence": 0.972
+        },
+        {
+          "text": "on",
+          "start": 21.18,
+          "end": 21.38,
+          "confidence": 0.969
+        },
+        {
+          "text": "the",
+          "start": 21.38,
+          "end": 21.66,
+          "confidence": 0.09
+        },
+        {
+          "text": "mic",
+          "start": 21.66,
+          "end": 22.48,
+          "confidence": 0.616
+        },
+        {
+          "text": "helmet.",
+          "start": 22.48,
+          "end": 22.8,
+          "confidence": 0.105
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 0,
+      "start": 22.8,
+      "end": 24.36,
+      "text": " We'll show it to you in a quick screen.",
+      "tokens": [
+        51514,
+        492,
+        603,
+        855,
+        309,
+        281,
+        291,
+        294,
+        257,
+        1702,
+        2568,
+        13,
+        51614
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5319976806640625,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.44995221495628357,
+      "confidence": 0.121,
+      "words": [
+        {
+          "text": "We'll",
+          "start": 22.8,
+          "end": 23.02,
+          "confidence": 0.08
+        },
+        {
+          "text": "show",
+          "start": 23.02,
+          "end": 23.24,
+          "confidence": 0.013
+        },
+        {
+          "text": "it",
+          "start": 23.24,
+          "end": 23.36,
+          "confidence": 0.12
+        },
+        {
+          "text": "to",
+          "start": 23.36,
+          "end": 23.52,
+          "confidence": 0.356
+        },
+        {
+          "text": "you",
+          "start": 23.52,
+          "end": 23.64,
+          "confidence": 0.609
+        },
+        {
+          "text": "in",
+          "start": 23.64,
+          "end": 23.86,
+          "confidence": 0.287
+        },
+        {
+          "text": "a",
+          "start": 23.86,
+          "end": 23.88,
+          "confidence": 0.723
+        },
+        {
+          "text": "quick",
+          "start": 23.88,
+          "end": 24.04,
+          "confidence": 0.016
+        },
+        {
+          "text": "screen.",
+          "start": 24.04,
+          "end": 24.36,
+          "confidence": 0.109
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 0,
+      "start": 24.84,
+      "end": 25.1,
+      "text": " Over.",
+      "tokens": [
+        51614,
+        4886,
+        13,
+        51664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5319976806640625,
+      "compression_ratio": 1.4690265486725664,
+      "no_speech_prob": 0.44995221495628357,
+      "confidence": 0.062,
+      "words": [
+        {
+          "text": "Over.",
+          "start": 24.84,
+          "end": 25.1,
+          "confidence": 0.062
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 2600,
+      "start": 31.32,
+      "end": 31.36,
+      "text": " All right.",
+      "tokens": [
+        50364,
+        1057,
+        558,
+        13,
+        50614
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5039673957271852,
+      "compression_ratio": 1.9243243243243244,
+      "no_speech_prob": 0.08131810277700424,
+      "confidence": 0.108,
+      "words": [
+        {
+          "text": "All",
+          "start": 31.32,
+          "end": 31.34,
+          "confidence": 0.003
+        },
+        {
+          "text": "right.",
+          "start": 31.34,
+          "end": 31.36,
+          "confidence": 0.677
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 2600,
+      "start": 31.36,
+      "end": 32.06,
+      "text": " Yeah, sir.",
+      "tokens": [
+        50614,
+        865,
+        11,
+        4735,
+        13,
+        50664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5039673957271852,
+      "compression_ratio": 1.9243243243243244,
+      "no_speech_prob": 0.08131810277700424,
+      "confidence": 0.035,
+      "words": [
+        {
+          "text": "Yeah,",
+          "start": 31.36,
+          "end": 31.56,
+          "confidence": 0.033
+        },
+        {
+          "text": "sir.",
+          "start": 31.56,
+          "end": 32.06,
+          "confidence": 0.036
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 2600,
+      "start": 32.26,
+      "end": 33.0,
+      "text": " All right.",
+      "tokens": [
+        50664,
+        1057,
+        558,
+        13,
+        50714
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5039673957271852,
+      "compression_ratio": 1.9243243243243244,
+      "no_speech_prob": 0.08131810277700424,
+      "confidence": 0.201,
+      "words": [
+        {
+          "text": "All",
+          "start": 32.26,
+          "end": 32.86,
+          "confidence": 0.022
+        },
+        {
+          "text": "right.",
+          "start": 32.86,
+          "end": 33.0,
+          "confidence": 0.607
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 2600,
+      "start": 33.0,
+      "end": 33.5,
+      "text": " Yeah, sir.",
+      "tokens": [
+        50714,
+        865,
+        11,
+        4735,
+        13,
+        50764
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5039673957271852,
+      "compression_ratio": 1.9243243243243244,
+      "no_speech_prob": 0.08131810277700424,
+      "confidence": 0.044,
+      "words": [
+        {
+          "text": "Yeah,",
+          "start": 33.0,
+          "end": 33.16,
+          "confidence": 0.208
+        },
+        {
+          "text": "sir.",
+          "start": 33.22,
+          "end": 33.5,
+          "confidence": 0.009
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 2600,
+      "start": 33.5,
+      "end": 34.98,
+      "text": " There's a better helmet than B-1.",
+      "tokens": [
+        50764,
+        821,
+        311,
+        257,
+        1101,
+        15922,
+        813,
+        363,
+        12,
+        16,
+        13,
+        50814
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5039673957271852,
+      "compression_ratio": 1.9243243243243244,
+      "no_speech_prob": 0.08131810277700424,
+      "confidence": 0.04,
+      "words": [
+        {
+          "text": "There's",
+          "start": 33.5,
+          "end": 33.9,
+          "confidence": 0.022
+        },
+        {
+          "text": "a",
+          "start": 33.9,
+          "end": 33.92,
+          "confidence": 0.264
+        },
+        {
+          "text": "better",
+          "start": 33.92,
+          "end": 33.94,
+          "confidence": 0.227
+        },
+        {
+          "text": "helmet",
+          "start": 33.94,
+          "end": 34.2,
+          "confidence": 0.004
+        },
+        {
+          "text": "than",
+          "start": 34.2,
+          "end": 34.6,
+          "confidence": 0.352
+        },
+        {
+          "text": "B-1.",
+          "start": 34.6,
+          "end": 34.98,
+          "confidence": 0.022
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 2600,
+      "start": 35.0,
+      "end": 35.8,
+      "text": " That's the other one.",
+      "tokens": [
+        50814,
+        663,
+        311,
+        264,
+        661,
+        472,
+        13,
+        50864
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5039673957271852,
+      "compression_ratio": 1.9243243243243244,
+      "no_speech_prob": 0.08131810277700424,
+      "confidence": 0.277,
+      "words": [
+        {
+          "text": "That's",
+          "start": 35.0,
+          "end": 35.38,
+          "confidence": 0.161
+        },
+        {
+          "text": "the",
+          "start": 35.38,
+          "end": 35.48,
+          "confidence": 0.514
+        },
+        {
+          "text": "other",
+          "start": 35.48,
+          "end": 35.6,
+          "confidence": 0.965
+        },
+        {
+          "text": "one.",
+          "start": 35.6,
+          "end": 35.8,
+          "confidence": 0.189
+        }
+      ]
+    },
+    {
+      "id": 17,
+      "seek": 2600,
+      "start": 35.8,
+      "end": 36.04,
+      "text": " Nice.",
+      "tokens": [
+        50864,
+        5490,
+        13,
+        50914
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5039673957271852,
+      "compression_ratio": 1.9243243243243244,
+      "no_speech_prob": 0.08131810277700424,
+      "confidence": 0.011,
+      "words": [
+        {
+          "text": "Nice.",
+          "start": 35.8,
+          "end": 36.04,
+          "confidence": 0.011
+        }
+      ]
+    },
+    {
+      "id": 18,
+      "seek": 2600,
+      "start": 37.62,
+      "end": 38.38,
+      "text": " Let's go in there.",
+      "tokens": [
+        50914,
+        961,
+        311,
+        352,
+        294,
+        456,
+        13,
+        50964
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5039673957271852,
+      "compression_ratio": 1.9243243243243244,
+      "no_speech_prob": 0.08131810277700424,
+      "confidence": 0.125,
+      "words": [
+        {
+          "text": "Let's",
+          "start": 37.62,
+          "end": 38.1,
+          "confidence": 0.022
+        },
+        {
+          "text": "go",
+          "start": 38.1,
+          "end": 38.12,
+          "confidence": 0.626
+        },
+        {
+          "text": "in",
+          "start": 38.12,
+          "end": 38.26,
+          "confidence": 0.037
+        },
+        {
+          "text": "there.",
+          "start": 38.26,
+          "end": 38.38,
+          "confidence": 0.579
+        }
+      ]
+    },
+    {
+      "id": 19,
+      "seek": 2600,
+      "start": 38.38,
+      "end": 39.2,
+      "text": " At least we're safe.",
+      "tokens": [
+        50964,
+        1711,
+        1935,
+        321,
+        434,
+        3273,
+        13,
+        51014
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5039673957271852,
+      "compression_ratio": 1.9243243243243244,
+      "no_speech_prob": 0.08131810277700424,
+      "confidence": 0.107,
+      "words": [
+        {
+          "text": "At",
+          "start": 38.38,
+          "end": 38.44,
+          "confidence": 0.003
+        },
+        {
+          "text": "least",
+          "start": 38.44,
+          "end": 38.72,
+          "confidence": 0.125
+        },
+        {
+          "text": "we're",
+          "start": 38.72,
+          "end": 38.98,
+          "confidence": 0.091
+        },
+        {
+          "text": "safe.",
+          "start": 38.98,
+          "end": 39.2,
+          "confidence": 0.715
+        }
+      ]
+    },
+    {
+      "id": 20,
+      "seek": 2600,
+      "start": 39.88,
+      "end": 40.54,
+      "text": " We've got them in there.",
+      "tokens": [
+        51014,
+        492,
+        600,
+        658,
+        552,
+        294,
+        456,
+        13,
+        51064
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5039673957271852,
+      "compression_ratio": 1.9243243243243244,
+      "no_speech_prob": 0.08131810277700424,
+      "confidence": 0.077,
+      "words": [
+        {
+          "text": "We've",
+          "start": 39.88,
+          "end": 40.36,
+          "confidence": 0.055
+        },
+        {
+          "text": "got",
+          "start": 40.36,
+          "end": 40.48,
+          "confidence": 0.749
+        },
+        {
+          "text": "them",
+          "start": 40.48,
+          "end": 40.5,
+          "confidence": 0.003
+        },
+        {
+          "text": "in",
+          "start": 40.5,
+          "end": 40.52,
+          "confidence": 0.053
+        },
+        {
+          "text": "there.",
+          "start": 40.52,
+          "end": 40.54,
+          "confidence": 0.211
+        }
+      ]
+    },
+    {
+      "id": 21,
+      "seek": 2600,
+      "start": 40.54,
+      "end": 41.04,
+      "text": " Helmet bags.",
+      "tokens": [
+        51064,
+        6128,
+        5537,
+        10405,
+        13,
+        51114
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5039673957271852,
+      "compression_ratio": 1.9243243243243244,
+      "no_speech_prob": 0.08131810277700424,
+      "confidence": 0.001,
+      "words": [
+        {
+          "text": "Helmet",
+          "start": 40.54,
+          "end": 40.66,
+          "confidence": 0.001
+        },
+        {
+          "text": "bags.",
+          "start": 40.66,
+          "end": 41.04,
+          "confidence": 0.002
+        }
+      ]
+    },
+    {
+      "id": 22,
+      "seek": 2600,
+      "start": 43.18,
+      "end": 47.4,
+      "text": " And, uh, I guess we have helmets in the helmet bag.",
+      "tokens": [
+        51114,
+        400,
+        11,
+        2232,
+        11,
+        286,
+        2041,
+        321,
+        362,
+        42022,
+        294,
+        264,
+        15922,
+        3411,
+        13,
+        51464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5039673957271852,
+      "compression_ratio": 1.9243243243243244,
+      "no_speech_prob": 0.08131810277700424,
+      "confidence": 0.175,
+      "words": [
+        {
+          "text": "And,",
+          "start": 43.18,
+          "end": 43.2,
+          "confidence": 0.052
+        },
+        {
+          "text": "uh,",
+          "start": 43.48,
+          "end": 43.74,
+          "confidence": 0.745
+        },
+        {
+          "text": "I",
+          "start": 43.86,
+          "end": 44.04,
+          "confidence": 0.341
+        },
+        {
+          "text": "guess",
+          "start": 44.04,
+          "end": 44.2,
+          "confidence": 0.283
+        },
+        {
+          "text": "we",
+          "start": 44.2,
+          "end": 44.52,
+          "confidence": 0.055
+        },
+        {
+          "text": "have",
+          "start": 44.52,
+          "end": 45.48,
+          "confidence": 0.053
+        },
+        {
+          "text": "helmets",
+          "start": 45.48,
+          "end": 46.5,
+          "confidence": 0.005
+        },
+        {
+          "text": "in",
+          "start": 46.5,
+          "end": 46.72,
+          "confidence": 0.216
+        },
+        {
+          "text": "the",
+          "start": 46.72,
+          "end": 46.92,
+          "confidence": 0.619
+        },
+        {
+          "text": "helmet",
+          "start": 46.92,
+          "end": 47.08,
+          "confidence": 0.831
+        },
+        {
+          "text": "bag.",
+          "start": 47.08,
+          "end": 47.4,
+          "confidence": 0.329
+        }
+      ]
+    },
+    {
+      "id": 23,
+      "seek": 2600,
+      "start": 48.2,
+      "end": 49.52,
+      "text": " At least it's in the helmet bag.",
+      "tokens": [
+        51464,
+        1711,
+        1935,
+        309,
+        311,
+        294,
+        264,
+        15922,
+        3411,
+        13,
+        51564
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5039673957271852,
+      "compression_ratio": 1.9243243243243244,
+      "no_speech_prob": 0.08131810277700424,
+      "confidence": 0.122,
+      "words": [
+        {
+          "text": "At",
+          "start": 48.2,
+          "end": 48.34,
+          "confidence": 0.095
+        },
+        {
+          "text": "least",
+          "start": 48.34,
+          "end": 48.6,
+          "confidence": 0.76
+        },
+        {
+          "text": "it's",
+          "start": 48.6,
+          "end": 48.86,
+          "confidence": 0.339
+        },
+        {
+          "text": "in",
+          "start": 48.86,
+          "end": 48.96,
+          "confidence": 0.151
+        },
+        {
+          "text": "the",
+          "start": 48.96,
+          "end": 49.1,
+          "confidence": 0.223
+        },
+        {
+          "text": "helmet",
+          "start": 49.1,
+          "end": 49.18,
+          "confidence": 0.006
+        },
+        {
+          "text": "bag.",
+          "start": 49.18,
+          "end": 49.52,
+          "confidence": 0.06
+        }
+      ]
+    },
+    {
+      "id": 24,
+      "seek": 2600,
+      "start": 49.52,
+      "end": 50.38,
+      "text": " Right here.",
+      "tokens": [
+        51564,
+        1779,
+        510,
+        13,
+        51614
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5039673957271852,
+      "compression_ratio": 1.9243243243243244,
+      "no_speech_prob": 0.08131810277700424,
+      "confidence": 0.059,
+      "words": [
+        {
+          "text": "Right",
+          "start": 49.52,
+          "end": 49.62,
+          "confidence": 0.027
+        },
+        {
+          "text": "here.",
+          "start": 49.62,
+          "end": 50.38,
+          "confidence": 0.088
+        }
+      ]
+    },
+    {
+      "id": 25,
+      "seek": 2600,
+      "start": 51.52,
+      "end": 51.98,
+      "text": " Right here.",
+      "tokens": [
+        51614,
+        1779,
+        510,
+        13,
+        51664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5039673957271852,
+      "compression_ratio": 1.9243243243243244,
+      "no_speech_prob": 0.08131810277700424,
+      "confidence": 0.017,
+      "words": [
+        {
+          "text": "Right",
+          "start": 51.52,
+          "end": 51.72,
+          "confidence": 0.001
+        },
+        {
+          "text": "here.",
+          "start": 51.72,
+          "end": 51.98,
+          "confidence": 0.067
+        }
+      ]
+    },
+    {
+      "id": 26,
+      "seek": 2600,
+      "start": 51.98,
+      "end": 52.74,
+      "text": " Yeah, we're taking it next day.",
+      "tokens": [
+        51664,
+        865,
+        11,
+        321,
+        434,
+        1940,
+        309,
+        958,
+        786,
+        13,
+        51714
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5039673957271852,
+      "compression_ratio": 1.9243243243243244,
+      "no_speech_prob": 0.08131810277700424,
+      "confidence": 0.047,
+      "words": [
+        {
+          "text": "Yeah,",
+          "start": 51.98,
+          "end": 52.28,
+          "confidence": 0.043
+        },
+        {
+          "text": "we're",
+          "start": 52.28,
+          "end": 52.3,
+          "confidence": 0.288
+        },
+        {
+          "text": "taking",
+          "start": 52.3,
+          "end": 52.32,
+          "confidence": 0.005
+        },
+        {
+          "text": "it",
+          "start": 52.32,
+          "end": 52.34,
+          "confidence": 0.052
+        },
+        {
+          "text": "next",
+          "start": 52.34,
+          "end": 52.52,
+          "confidence": 0.002
+        },
+        {
+          "text": "day.",
+          "start": 52.52,
+          "end": 52.74,
+          "confidence": 0.113
+        }
+      ]
+    },
+    {
+      "id": 27,
+      "seek": 2600,
+      "start": 52.74,
+      "end": 54.1,
+      "text": " Yeah, we're taking it next day.",
+      "tokens": [
+        51714,
+        865,
+        11,
+        321,
+        434,
+        1940,
+        309,
+        958,
+        786,
+        13,
+        51764
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5039673957271852,
+      "compression_ratio": 1.9243243243243244,
+      "no_speech_prob": 0.08131810277700424,
+      "confidence": 0.41,
+      "words": [
+        {
+          "text": "Yeah,",
+          "start": 52.74,
+          "end": 53.24,
+          "confidence": 0.601
+        },
+        {
+          "text": "we're",
+          "start": 53.34,
+          "end": 53.44,
+          "confidence": 0.703
+        },
+        {
+          "text": "taking",
+          "start": 53.44,
+          "end": 53.62,
+          "confidence": 0.261
+        },
+        {
+          "text": "it",
+          "start": 53.62,
+          "end": 53.76,
+          "confidence": 0.247
+        },
+        {
+          "text": "next",
+          "start": 53.76,
+          "end": 53.88,
+          "confidence": 0.405
+        },
+        {
+          "text": "day.",
+          "start": 53.88,
+          "end": 54.1,
+          "confidence": 0.266
+        }
+      ]
+    },
+    {
+      "id": 28,
+      "seek": 5400,
+      "start": 56.68,
+      "end": 58.34,
+      "text": " We're gonna hang me on the cover.",
+      "tokens": [
+        50364,
+        492,
+        434,
+        799,
+        3967,
+        385,
+        322,
+        264,
+        2060,
+        13,
+        50614
+      ],
+      "temperature": 0.6000000000000001,
+      "avg_logprob": -0.46983818116226816,
+      "compression_ratio": 1.5763546798029557,
+      "no_speech_prob": 0.2010825127363205,
+      "confidence": 0.117,
+      "words": [
+        {
+          "text": "We're",
+          "start": 56.68,
+          "end": 56.8,
+          "confidence": 0.047
+        },
+        {
+          "text": "gonna",
+          "start": 56.8,
+          "end": 57.12,
+          "confidence": 0.472
+        },
+        {
+          "text": "hang",
+          "start": 57.12,
+          "end": 57.36,
+          "confidence": 0.421
+        },
+        {
+          "text": "me",
+          "start": 57.36,
+          "end": 57.58,
+          "confidence": 0.657
+        },
+        {
+          "text": "on",
+          "start": 57.58,
+          "end": 57.74,
+          "confidence": 0.88
+        },
+        {
+          "text": "the",
+          "start": 57.74,
+          "end": 57.88,
+          "confidence": 0.115
+        },
+        {
+          "text": "cover.",
+          "start": 57.88,
+          "end": 58.34,
+          "confidence": 0.012
+        }
+      ]
+    },
+    {
+      "id": 29,
+      "seek": 5400,
+      "start": 61.3,
+      "end": 61.8,
+      "text": " I tried it already.",
+      "tokens": [
+        50614,
+        286,
+        3031,
+        309,
+        1217,
+        13,
+        50764
+      ],
+      "temperature": 0.6000000000000001,
+      "avg_logprob": -0.46983818116226816,
+      "compression_ratio": 1.5763546798029557,
+      "no_speech_prob": 0.2010825127363205,
+      "confidence": 0.042,
+      "words": [
+        {
+          "text": "I",
+          "start": 61.3,
+          "end": 61.32,
+          "confidence": 0.095
+        },
+        {
+          "text": "tried",
+          "start": 61.32,
+          "end": 61.34,
+          "confidence": 0.0
+        },
+        {
+          "text": "it",
+          "start": 61.34,
+          "end": 61.44,
+          "confidence": 0.078
+        },
+        {
+          "text": "already.",
+          "start": 61.44,
+          "end": 61.8,
+          "confidence": 0.365
+        }
+      ]
+    },
+    {
+      "id": 30,
+      "seek": 5400,
+      "start": 62.52,
+      "end": 63.06,
+      "text": " Okay, fine.",
+      "tokens": [
+        50764,
+        1033,
+        11,
+        2489,
+        13,
+        50814
+      ],
+      "temperature": 0.6000000000000001,
+      "avg_logprob": -0.46983818116226816,
+      "compression_ratio": 1.5763546798029557,
+      "no_speech_prob": 0.2010825127363205,
+      "confidence": 0.482,
+      "words": [
+        {
+          "text": "Okay,",
+          "start": 62.52,
+          "end": 62.76,
+          "confidence": 0.39
+        },
+        {
+          "text": "fine.",
+          "start": 62.88,
+          "end": 63.06,
+          "confidence": 0.595
+        }
+      ]
+    },
+    {
+      "id": 31,
+      "seek": 5400,
+      "start": 63.06,
+      "end": 65.1,
+      "text": " We weren't sure that, uh, just a suggestion.",
+      "tokens": [
+        50814,
+        492,
+        4999,
+        380,
+        988,
+        300,
+        11,
+        2232,
+        11,
+        445,
+        257,
+        16541,
+        13,
+        50914
+      ],
+      "temperature": 0.6000000000000001,
+      "avg_logprob": -0.46983818116226816,
+      "compression_ratio": 1.5763546798029557,
+      "no_speech_prob": 0.2010825127363205,
+      "confidence": 0.489,
+      "words": [
+        {
+          "text": "We",
+          "start": 63.06,
+          "end": 63.26,
+          "confidence": 0.274
+        },
+        {
+          "text": "weren't",
+          "start": 63.26,
+          "end": 63.58,
+          "confidence": 0.918
+        },
+        {
+          "text": "sure",
+          "start": 63.58,
+          "end": 63.72,
+          "confidence": 0.976
+        },
+        {
+          "text": "that,",
+          "start": 63.72,
+          "end": 63.98,
+          "confidence": 0.293
+        },
+        {
+          "text": "uh,",
+          "start": 64.08,
+          "end": 64.32,
+          "confidence": 0.628
+        },
+        {
+          "text": "just",
+          "start": 64.34,
+          "end": 64.6,
+          "confidence": 0.34
+        },
+        {
+          "text": "a",
+          "start": 64.6,
+          "end": 64.76,
+          "confidence": 0.297
+        },
+        {
+          "text": "suggestion.",
+          "start": 64.76,
+          "end": 65.1,
+          "confidence": 0.493
+        }
+      ]
+    },
+    {
+      "id": 32,
+      "seek": 5400,
+      "start": 65.1,
+      "end": 67.5,
+      "text": " We thought we'd, uh, that you could check it out.",
+      "tokens": [
+        50914,
+        492,
+        1194,
+        321,
+        1116,
+        11,
+        2232,
+        11,
+        300,
+        291,
+        727,
+        1520,
+        309,
+        484,
+        13,
+        51014
+      ],
+      "temperature": 0.6000000000000001,
+      "avg_logprob": -0.46983818116226816,
+      "compression_ratio": 1.5763546798029557,
+      "no_speech_prob": 0.2010825127363205,
+      "confidence": 0.36,
+      "words": [
+        {
+          "text": "We",
+          "start": 65.1,
+          "end": 65.3,
+          "confidence": 0.11
+        },
+        {
+          "text": "thought",
+          "start": 65.3,
+          "end": 65.54,
+          "confidence": 0.863
+        },
+        {
+          "text": "we'd,",
+          "start": 65.54,
+          "end": 65.84,
+          "confidence": 0.408
+        },
+        {
+          "text": "uh,",
+          "start": 65.9,
+          "end": 66.02,
+          "confidence": 0.641
+        },
+        {
+          "text": "that",
+          "start": 66.78,
+          "end": 66.92,
+          "confidence": 0.043
+        },
+        {
+          "text": "you",
+          "start": 66.92,
+          "end": 67.08,
+          "confidence": 0.967
+        },
+        {
+          "text": "could",
+          "start": 67.08,
+          "end": 67.24,
+          "confidence": 0.851
+        },
+        {
+          "text": "check",
+          "start": 67.24,
+          "end": 67.4,
+          "confidence": 0.13
+        },
+        {
+          "text": "it",
+          "start": 67.4,
+          "end": 67.48,
+          "confidence": 0.176
+        },
+        {
+          "text": "out.",
+          "start": 67.48,
+          "end": 67.5,
+          "confidence": 0.53
+        }
+      ]
+    },
+    {
+      "id": 33,
+      "seek": 5400,
+      "start": 68.18,
+      "end": 69.08,
+      "text": " It's not much of an order, sir.",
+      "tokens": [
+        51014,
+        467,
+        311,
+        406,
+        709,
+        295,
+        364,
+        1668,
+        11,
+        4735,
+        13,
+        51114
+      ],
+      "temperature": 0.6000000000000001,
+      "avg_logprob": -0.46983818116226816,
+      "compression_ratio": 1.5763546798029557,
+      "no_speech_prob": 0.2010825127363205,
+      "confidence": 0.173,
+      "words": [
+        {
+          "text": "It's",
+          "start": 68.18,
+          "end": 68.22,
+          "confidence": 0.069
+        },
+        {
+          "text": "not",
+          "start": 68.22,
+          "end": 68.38,
+          "confidence": 0.17
+        },
+        {
+          "text": "much",
+          "start": 68.38,
+          "end": 68.54,
+          "confidence": 0.29
+        },
+        {
+          "text": "of",
+          "start": 68.54,
+          "end": 68.68,
+          "confidence": 0.474
+        },
+        {
+          "text": "an",
+          "start": 68.68,
+          "end": 68.84,
+          "confidence": 0.246
+        },
+        {
+          "text": "order,",
+          "start": 68.84,
+          "end": 68.88,
+          "confidence": 0.317
+        },
+        {
+          "text": "sir.",
+          "start": 69.02,
+          "end": 69.08,
+          "confidence": 0.094
+        }
+      ]
+    },
+    {
+      "id": 34,
+      "seek": 5400,
+      "start": 69.08,
+      "end": 71.92,
+      "text": " And so, uh, I guess we're gonna come up with this.",
+      "tokens": [
+        51114,
+        400,
+        370,
+        11,
+        2232,
+        11,
+        286,
+        2041,
+        321,
+        434,
+        799,
+        808,
+        493,
+        365,
+        341,
+        13,
+        51264
+      ],
+      "temperature": 0.6000000000000001,
+      "avg_logprob": -0.46983818116226816,
+      "compression_ratio": 1.5763546798029557,
+      "no_speech_prob": 0.2010825127363205,
+      "confidence": 0.393,
+      "words": [
+        {
+          "text": "And",
+          "start": 69.08,
+          "end": 69.24,
+          "confidence": 0.078
+        },
+        {
+          "text": "so,",
+          "start": 69.24,
+          "end": 69.6,
+          "confidence": 0.546
+        },
+        {
+          "text": "uh,",
+          "start": 69.72,
+          "end": 69.84,
+          "confidence": 0.387
+        },
+        {
+          "text": "I",
+          "start": 70.36,
+          "end": 70.5,
+          "confidence": 0.938
+        },
+        {
+          "text": "guess",
+          "start": 70.5,
+          "end": 70.66,
+          "confidence": 0.976
+        },
+        {
+          "text": "we're",
+          "start": 70.66,
+          "end": 71.08,
+          "confidence": 0.4
+        },
+        {
+          "text": "gonna",
+          "start": 71.08,
+          "end": 71.26,
+          "confidence": 0.375
+        },
+        {
+          "text": "come",
+          "start": 71.26,
+          "end": 71.42,
+          "confidence": 0.171
+        },
+        {
+          "text": "up",
+          "start": 71.42,
+          "end": 71.62,
+          "confidence": 0.79
+        },
+        {
+          "text": "with",
+          "start": 71.62,
+          "end": 71.78,
+          "confidence": 0.86
+        },
+        {
+          "text": "this.",
+          "start": 71.78,
+          "end": 71.92,
+          "confidence": 0.192
+        }
+      ]
+    },
+    {
+      "id": 35,
+      "seek": 5400,
+      "start": 71.92,
+      "end": 72.46,
+      "text": " Let us know.",
+      "tokens": [
+        51264,
+        961,
+        505,
+        458,
+        13,
+        51314
+      ],
+      "temperature": 0.6000000000000001,
+      "avg_logprob": -0.46983818116226816,
+      "compression_ratio": 1.5763546798029557,
+      "no_speech_prob": 0.2010825127363205,
+      "confidence": 0.405,
+      "words": [
+        {
+          "text": "Let",
+          "start": 71.92,
+          "end": 72.08,
+          "confidence": 0.09
+        },
+        {
+          "text": "us",
+          "start": 72.08,
+          "end": 72.24,
+          "confidence": 0.457
+        },
+        {
+          "text": "know.",
+          "start": 72.24,
+          "end": 72.46,
+          "confidence": 0.809
+        }
+      ]
+    },
+    {
+      "id": 36,
+      "seek": 5400,
+      "start": 74.16,
+      "end": 74.18,
+      "text": " Okay.",
+      "tokens": [
+        51314,
+        1033,
+        13,
+        51364
+      ],
+      "temperature": 0.6000000000000001,
+      "avg_logprob": -0.46983818116226816,
+      "compression_ratio": 1.5763546798029557,
+      "no_speech_prob": 0.2010825127363205,
+      "confidence": 0.024,
+      "words": [
+        {
+          "text": "Okay.",
+          "start": 74.16,
+          "end": 74.18,
+          "confidence": 0.024
+        }
+      ]
+    },
+    {
+      "id": 37,
+      "seek": 5400,
+      "start": 74.18,
+      "end": 75.06,
+      "text": " No problem.",
+      "tokens": [
+        51364,
+        883,
+        1154,
+        13,
+        51414
+      ],
+      "temperature": 0.6000000000000001,
+      "avg_logprob": -0.46983818116226816,
+      "compression_ratio": 1.5763546798029557,
+      "no_speech_prob": 0.2010825127363205,
+      "confidence": 0.041,
+      "words": [
+        {
+          "text": "No",
+          "start": 74.18,
+          "end": 74.4,
+          "confidence": 0.004
+        },
+        {
+          "text": "problem.",
+          "start": 74.4,
+          "end": 75.06,
+          "confidence": 0.124
+        }
+      ]
+    },
+    {
+      "id": 38,
+      "seek": 5400,
+      "start": 75.2,
+      "end": 75.82,
+      "text": " Okay.",
+      "tokens": [
+        51414,
+        1033,
+        13,
+        51464
+      ],
+      "temperature": 0.6000000000000001,
+      "avg_logprob": -0.46983818116226816,
+      "compression_ratio": 1.5763546798029557,
+      "no_speech_prob": 0.2010825127363205,
+      "confidence": 0.236,
+      "words": [
+        {
+          "text": "Okay.",
+          "start": 75.2,
+          "end": 75.82,
+          "confidence": 0.236
+        }
+      ]
+    },
+    {
+      "id": 39,
+      "seek": 5400,
+      "start": 75.82,
+      "end": 76.52,
+      "text": " No problem.",
+      "tokens": [
+        51464,
+        883,
+        1154,
+        13,
+        51514
+      ],
+      "temperature": 0.6000000000000001,
+      "avg_logprob": -0.46983818116226816,
+      "compression_ratio": 1.5763546798029557,
+      "no_speech_prob": 0.2010825127363205,
+      "confidence": 0.456,
+      "words": [
+        {
+          "text": "No",
+          "start": 75.82,
+          "end": 76.16,
+          "confidence": 0.216
+        },
+        {
+          "text": "problem.",
+          "start": 76.16,
+          "end": 76.52,
+          "confidence": 0.663
+        }
+      ]
+    },
+    {
+      "id": 40,
+      "seek": 5400,
+      "start": 78.48,
+      "end": 78.52,
+      "text": " No problem.",
+      "tokens": [
+        51514,
+        883,
+        1154,
+        13,
+        51564
+      ],
+      "temperature": 0.6000000000000001,
+      "avg_logprob": -0.46983818116226816,
+      "compression_ratio": 1.5763546798029557,
+      "no_speech_prob": 0.2010825127363205,
+      "confidence": 0.021,
+      "words": [
+        {
+          "text": "No",
+          "start": 78.48,
+          "end": 78.5,
+          "confidence": 0.016
+        },
+        {
+          "text": "problem.",
+          "start": 78.5,
+          "end": 78.52,
+          "confidence": 0.024
+        }
+      ]
+    },
+    {
+      "id": 41,
+      "seek": 5400,
+      "start": 78.52,
+      "end": 79.3,
+      "text": " No worry.",
+      "tokens": [
+        51564,
+        883,
+        3292,
+        13,
+        51614
+      ],
+      "temperature": 0.6000000000000001,
+      "avg_logprob": -0.46983818116226816,
+      "compression_ratio": 1.5763546798029557,
+      "no_speech_prob": 0.2010825127363205,
+      "confidence": 0.003,
+      "words": [
+        {
+          "text": "No",
+          "start": 78.52,
+          "end": 78.7,
+          "confidence": 0.001
+        },
+        {
+          "text": "worry.",
+          "start": 78.7,
+          "end": 79.3,
+          "confidence": 0.005
+        }
+      ]
+    },
+    {
+      "id": 42,
+      "seek": 5400,
+      "start": 79.3,
+      "end": 80.04,
+      "text": " None.",
+      "tokens": [
+        51614,
+        14492,
+        13,
+        51664
+      ],
+      "temperature": 0.6000000000000001,
+      "avg_logprob": -0.46983818116226816,
+      "compression_ratio": 1.5763546798029557,
+      "no_speech_prob": 0.2010825127363205,
+      "confidence": 0.002,
+      "words": [
+        {
+          "text": "None.",
+          "start": 79.3,
+          "end": 80.04,
+          "confidence": 0.002
+        }
+      ]
+    },
+    {
+      "id": 43,
+      "seek": 8000,
+      "start": 88.8,
+      "end": 88.98,
+      "text": " Thank you.",
+      "tokens": [
+        50364,
+        1044,
+        291,
+        13,
+        50818
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9733104705810547,
+      "compression_ratio": 0.5555555555555556,
+      "no_speech_prob": 0.4526429772377014,
+      "confidence": 0.261,
+      "words": [
+        {
+          "text": "Thank",
+          "start": 88.8,
+          "end": 88.92,
+          "confidence": 0.026
+        },
+        {
+          "text": "you.",
+          "start": 88.92,
+          "end": 88.98,
+          "confidence": 0.83
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/naive/naive_apollo11.mp3.words.json b/tests/expected/naive/naive_apollo11.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..97affdfce771a65f33d19d1dce35134b2c1677a1
--- /dev/null
+++ b/tests/expected/naive/naive_apollo11.mp3.words.json
@@ -0,0 +1,3820 @@
+{
+  "text": " Apollo 11, Houston we got a recommendation for you on your Soyuz-VA GLEME GVA. Alright, okay, we like to say that they make the one that's on the helmet we're going to have in B1. And you can put the other one on the mic helmet with those GVA blizzard frames. Alright, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.54,
+      "end": 6.56,
+      "text": " Apollo 11, Houston we got a recommendation for you on your Soyuz-VA GLEME GVA.",
+      "tokens": [
+        50364,
+        25187,
+        2975,
+        11,
+        18717,
+        321,
+        658,
+        257,
+        11879,
+        337,
+        291,
+        322,
+        428,
+        24758,
+        3334,
+        12,
+        20914,
+        460,
+        2634,
+        15454,
+        460,
+        20914,
+        13,
+        50714
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7225757398103413,
+      "compression_ratio": 1.39247311827957,
+      "no_speech_prob": 0.44998496770858765,
+      "confidence": 0.494,
+      "words": [
+        {
+          "text": "Apollo",
+          "start": 0.54,
+          "end": 0.92,
+          "confidence": 0.425
+        },
+        {
+          "text": "11,",
+          "start": 0.92,
+          "end": 1.26,
+          "confidence": 0.842
+        },
+        {
+          "text": "Houston",
+          "start": 1.52,
+          "end": 1.72,
+          "confidence": 0.974
+        },
+        {
+          "text": "we",
+          "start": 1.72,
+          "end": 1.92,
+          "confidence": 0.453
+        },
+        {
+          "text": "got",
+          "start": 1.92,
+          "end": 2.1,
+          "confidence": 0.791
+        },
+        {
+          "text": "a",
+          "start": 2.1,
+          "end": 2.26,
+          "confidence": 0.992
+        },
+        {
+          "text": "recommendation",
+          "start": 2.26,
+          "end": 2.86,
+          "confidence": 0.97
+        },
+        {
+          "text": "for",
+          "start": 2.86,
+          "end": 3.44,
+          "confidence": 0.945
+        },
+        {
+          "text": "you",
+          "start": 3.44,
+          "end": 3.6,
+          "confidence": 0.99
+        },
+        {
+          "text": "on",
+          "start": 3.6,
+          "end": 3.72,
+          "confidence": 0.935
+        },
+        {
+          "text": "your",
+          "start": 3.72,
+          "end": 3.92,
+          "confidence": 0.974
+        },
+        {
+          "text": "Soyuz-VA",
+          "start": 3.92,
+          "end": 5.16,
+          "confidence": 0.327
+        },
+        {
+          "text": "GLEME",
+          "start": 5.16,
+          "end": 5.72,
+          "confidence": 0.178
+        },
+        {
+          "text": "GVA.",
+          "start": 5.72,
+          "end": 6.56,
+          "confidence": 0.321
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 10.8,
+      "end": 19.08,
+      "text": " Alright, okay, we like to say that they make the one that's on the helmet we're going to have in B1.",
+      "tokens": [
+        50714,
+        2798,
+        11,
+        1392,
+        11,
+        321,
+        411,
+        281,
+        584,
+        300,
+        436,
+        652,
+        264,
+        472,
+        300,
+        311,
+        322,
+        264,
+        15922,
+        321,
+        434,
+        516,
+        281,
+        362,
+        294,
+        363,
+        16,
+        13,
+        51314
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7225757398103413,
+      "compression_ratio": 1.39247311827957,
+      "no_speech_prob": 0.44998496770858765,
+      "confidence": 0.311,
+      "words": [
+        {
+          "text": "Alright,",
+          "start": 10.8,
+          "end": 10.82,
+          "confidence": 0.055
+        },
+        {
+          "text": "okay,",
+          "start": 11.46,
+          "end": 12.2,
+          "confidence": 0.359
+        },
+        {
+          "text": "we",
+          "start": 12.44,
+          "end": 12.96,
+          "confidence": 0.347
+        },
+        {
+          "text": "like",
+          "start": 12.96,
+          "end": 13.28,
+          "confidence": 0.512
+        },
+        {
+          "text": "to",
+          "start": 13.28,
+          "end": 13.6,
+          "confidence": 0.156
+        },
+        {
+          "text": "say",
+          "start": 13.6,
+          "end": 14.9,
+          "confidence": 0.086
+        },
+        {
+          "text": "that",
+          "start": 14.9,
+          "end": 15.32,
+          "confidence": 0.273
+        },
+        {
+          "text": "they",
+          "start": 15.32,
+          "end": 15.46,
+          "confidence": 0.358
+        },
+        {
+          "text": "make",
+          "start": 15.46,
+          "end": 15.7,
+          "confidence": 0.127
+        },
+        {
+          "text": "the",
+          "start": 15.7,
+          "end": 15.86,
+          "confidence": 0.165
+        },
+        {
+          "text": "one",
+          "start": 15.86,
+          "end": 16.08,
+          "confidence": 0.428
+        },
+        {
+          "text": "that's",
+          "start": 16.08,
+          "end": 16.26,
+          "confidence": 0.357
+        },
+        {
+          "text": "on",
+          "start": 16.26,
+          "end": 16.46,
+          "confidence": 0.314
+        },
+        {
+          "text": "the",
+          "start": 16.46,
+          "end": 16.76,
+          "confidence": 0.498
+        },
+        {
+          "text": "helmet",
+          "start": 16.76,
+          "end": 17.26,
+          "confidence": 0.306
+        },
+        {
+          "text": "we're",
+          "start": 17.26,
+          "end": 17.78,
+          "confidence": 0.256
+        },
+        {
+          "text": "going",
+          "start": 17.78,
+          "end": 17.94,
+          "confidence": 0.478
+        },
+        {
+          "text": "to",
+          "start": 17.94,
+          "end": 18.1,
+          "confidence": 0.522
+        },
+        {
+          "text": "have",
+          "start": 18.1,
+          "end": 18.18,
+          "confidence": 0.804
+        },
+        {
+          "text": "in",
+          "start": 18.18,
+          "end": 18.36,
+          "confidence": 0.772
+        },
+        {
+          "text": "B1.",
+          "start": 18.36,
+          "end": 19.08,
+          "confidence": 0.738
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 19.08,
+      "end": 24.54,
+      "text": " And you can put the other one on the mic helmet with those GVA blizzard frames.",
+      "tokens": [
+        51314,
+        400,
+        291,
+        393,
+        829,
+        264,
+        661,
+        472,
+        322,
+        264,
+        3123,
+        15922,
+        365,
+        729,
+        460,
+        20914,
+        888,
+        31062,
+        12083,
+        13,
+        51614
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7225757398103413,
+      "compression_ratio": 1.39247311827957,
+      "no_speech_prob": 0.44998496770858765,
+      "confidence": 0.129,
+      "words": [
+        {
+          "text": "And",
+          "start": 19.08,
+          "end": 20.14,
+          "confidence": 0.232
+        },
+        {
+          "text": "you",
+          "start": 20.14,
+          "end": 20.32,
+          "confidence": 0.905
+        },
+        {
+          "text": "can",
+          "start": 20.32,
+          "end": 20.5,
+          "confidence": 0.422
+        },
+        {
+          "text": "put",
+          "start": 20.5,
+          "end": 20.64,
+          "confidence": 0.942
+        },
+        {
+          "text": "the",
+          "start": 20.64,
+          "end": 20.82,
+          "confidence": 0.983
+        },
+        {
+          "text": "other",
+          "start": 20.82,
+          "end": 21.0,
+          "confidence": 0.994
+        },
+        {
+          "text": "one",
+          "start": 21.0,
+          "end": 21.18,
+          "confidence": 0.965
+        },
+        {
+          "text": "on",
+          "start": 21.18,
+          "end": 21.36,
+          "confidence": 0.965
+        },
+        {
+          "text": "the",
+          "start": 21.36,
+          "end": 21.78,
+          "confidence": 0.187
+        },
+        {
+          "text": "mic",
+          "start": 21.78,
+          "end": 22.48,
+          "confidence": 0.586
+        },
+        {
+          "text": "helmet",
+          "start": 22.48,
+          "end": 22.82,
+          "confidence": 0.029
+        },
+        {
+          "text": "with",
+          "start": 22.82,
+          "end": 23.06,
+          "confidence": 0.047
+        },
+        {
+          "text": "those",
+          "start": 23.06,
+          "end": 23.3,
+          "confidence": 0.036
+        },
+        {
+          "text": "GVA",
+          "start": 23.3,
+          "end": 23.74,
+          "confidence": 0.001
+        },
+        {
+          "text": "blizzard",
+          "start": 23.74,
+          "end": 24.18,
+          "confidence": 0.022
+        },
+        {
+          "text": "frames.",
+          "start": 24.18,
+          "end": 24.54,
+          "confidence": 0.225
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 2500,
+      "start": 31.34,
+      "end": 54.52,
+      "text": " Alright, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them",
+      "tokens": [
+        50364,
+        2798,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.11148937649197048,
+      "compression_ratio": 24.096774193548388,
+      "no_speech_prob": 0.4302051365375519,
+      "confidence": 0.885,
+      "words": [
+        {
+          "text": "Alright,",
+          "start": 31.34,
+          "end": 31.52,
+          "confidence": 0.069
+        },
+        {
+          "text": "got",
+          "start": 31.82,
+          "end": 31.86,
+          "confidence": 0.144
+        },
+        {
+          "text": "them,",
+          "start": 31.86,
+          "end": 32.1,
+          "confidence": 0.194
+        },
+        {
+          "text": "got",
+          "start": 32.38,
+          "end": 32.88,
+          "confidence": 0.473
+        },
+        {
+          "text": "them,",
+          "start": 32.88,
+          "end": 33.48,
+          "confidence": 0.611
+        },
+        {
+          "text": "got",
+          "start": 33.5,
+          "end": 33.52,
+          "confidence": 0.574
+        },
+        {
+          "text": "them,",
+          "start": 33.52,
+          "end": 33.54,
+          "confidence": 0.51
+        },
+        {
+          "text": "got",
+          "start": 33.76,
+          "end": 33.78,
+          "confidence": 0.599
+        },
+        {
+          "text": "them,",
+          "start": 33.78,
+          "end": 33.88,
+          "confidence": 0.488
+        },
+        {
+          "text": "got",
+          "start": 34.12,
+          "end": 34.14,
+          "confidence": 0.724
+        },
+        {
+          "text": "them,",
+          "start": 34.14,
+          "end": 34.16,
+          "confidence": 0.567
+        },
+        {
+          "text": "got",
+          "start": 34.16,
+          "end": 34.18,
+          "confidence": 0.761
+        },
+        {
+          "text": "them,",
+          "start": 34.18,
+          "end": 34.34,
+          "confidence": 0.689
+        },
+        {
+          "text": "got",
+          "start": 34.34,
+          "end": 34.36,
+          "confidence": 0.851
+        },
+        {
+          "text": "them,",
+          "start": 34.36,
+          "end": 34.5,
+          "confidence": 0.813
+        },
+        {
+          "text": "got",
+          "start": 34.5,
+          "end": 34.64,
+          "confidence": 0.916
+        },
+        {
+          "text": "them,",
+          "start": 34.64,
+          "end": 34.66,
+          "confidence": 0.756
+        },
+        {
+          "text": "got",
+          "start": 34.82,
+          "end": 34.92,
+          "confidence": 0.467
+        },
+        {
+          "text": "them,",
+          "start": 34.92,
+          "end": 35.0,
+          "confidence": 0.851
+        },
+        {
+          "text": "got",
+          "start": 35.0,
+          "end": 35.02,
+          "confidence": 0.917
+        },
+        {
+          "text": "them,",
+          "start": 35.02,
+          "end": 35.1,
+          "confidence": 0.897
+        },
+        {
+          "text": "got",
+          "start": 35.1,
+          "end": 35.28,
+          "confidence": 0.923
+        },
+        {
+          "text": "them,",
+          "start": 35.28,
+          "end": 35.64,
+          "confidence": 0.911
+        },
+        {
+          "text": "got",
+          "start": 35.66,
+          "end": 35.68,
+          "confidence": 0.923
+        },
+        {
+          "text": "them,",
+          "start": 35.68,
+          "end": 35.7,
+          "confidence": 0.917
+        },
+        {
+          "text": "got",
+          "start": 35.74,
+          "end": 35.76,
+          "confidence": 0.935
+        },
+        {
+          "text": "them,",
+          "start": 35.76,
+          "end": 35.78,
+          "confidence": 0.915
+        },
+        {
+          "text": "got",
+          "start": 36.04,
+          "end": 36.36,
+          "confidence": 0.944
+        },
+        {
+          "text": "them,",
+          "start": 36.36,
+          "end": 36.68,
+          "confidence": 0.91
+        },
+        {
+          "text": "got",
+          "start": 36.68,
+          "end": 36.7,
+          "confidence": 0.934
+        },
+        {
+          "text": "them,",
+          "start": 36.7,
+          "end": 36.72,
+          "confidence": 0.916
+        },
+        {
+          "text": "got",
+          "start": 36.72,
+          "end": 36.74,
+          "confidence": 0.926
+        },
+        {
+          "text": "them,",
+          "start": 36.74,
+          "end": 36.76,
+          "confidence": 0.92
+        },
+        {
+          "text": "got",
+          "start": 36.76,
+          "end": 36.78,
+          "confidence": 0.926
+        },
+        {
+          "text": "them,",
+          "start": 36.78,
+          "end": 36.8,
+          "confidence": 0.924
+        },
+        {
+          "text": "got",
+          "start": 36.8,
+          "end": 36.82,
+          "confidence": 0.932
+        },
+        {
+          "text": "them,",
+          "start": 36.82,
+          "end": 36.84,
+          "confidence": 0.93
+        },
+        {
+          "text": "got",
+          "start": 36.84,
+          "end": 36.86,
+          "confidence": 0.935
+        },
+        {
+          "text": "them,",
+          "start": 36.86,
+          "end": 36.88,
+          "confidence": 0.937
+        },
+        {
+          "text": "got",
+          "start": 36.88,
+          "end": 37.46,
+          "confidence": 0.941
+        },
+        {
+          "text": "them,",
+          "start": 37.46,
+          "end": 37.82,
+          "confidence": 0.942
+        },
+        {
+          "text": "got",
+          "start": 37.82,
+          "end": 37.84,
+          "confidence": 0.943
+        },
+        {
+          "text": "them,",
+          "start": 37.84,
+          "end": 38.12,
+          "confidence": 0.945
+        },
+        {
+          "text": "got",
+          "start": 38.12,
+          "end": 38.14,
+          "confidence": 0.947
+        },
+        {
+          "text": "them,",
+          "start": 38.14,
+          "end": 38.16,
+          "confidence": 0.948
+        },
+        {
+          "text": "got",
+          "start": 38.16,
+          "end": 38.18,
+          "confidence": 0.948
+        },
+        {
+          "text": "them,",
+          "start": 38.18,
+          "end": 38.2,
+          "confidence": 0.951
+        },
+        {
+          "text": "got",
+          "start": 38.2,
+          "end": 38.22,
+          "confidence": 0.95
+        },
+        {
+          "text": "them,",
+          "start": 38.22,
+          "end": 38.54,
+          "confidence": 0.953
+        },
+        {
+          "text": "got",
+          "start": 38.54,
+          "end": 38.56,
+          "confidence": 0.952
+        },
+        {
+          "text": "them,",
+          "start": 38.56,
+          "end": 38.58,
+          "confidence": 0.956
+        },
+        {
+          "text": "got",
+          "start": 38.58,
+          "end": 38.6,
+          "confidence": 0.952
+        },
+        {
+          "text": "them,",
+          "start": 38.6,
+          "end": 38.62,
+          "confidence": 0.956
+        },
+        {
+          "text": "got",
+          "start": 38.62,
+          "end": 38.64,
+          "confidence": 0.954
+        },
+        {
+          "text": "them,",
+          "start": 38.64,
+          "end": 38.66,
+          "confidence": 0.958
+        },
+        {
+          "text": "got",
+          "start": 38.66,
+          "end": 38.68,
+          "confidence": 0.956
+        },
+        {
+          "text": "them,",
+          "start": 38.68,
+          "end": 38.7,
+          "confidence": 0.961
+        },
+        {
+          "text": "got",
+          "start": 38.7,
+          "end": 38.72,
+          "confidence": 0.956
+        },
+        {
+          "text": "them,",
+          "start": 38.72,
+          "end": 38.74,
+          "confidence": 0.961
+        },
+        {
+          "text": "got",
+          "start": 38.74,
+          "end": 38.76,
+          "confidence": 0.957
+        },
+        {
+          "text": "them,",
+          "start": 38.76,
+          "end": 38.78,
+          "confidence": 0.962
+        },
+        {
+          "text": "got",
+          "start": 38.78,
+          "end": 38.8,
+          "confidence": 0.957
+        },
+        {
+          "text": "them,",
+          "start": 38.8,
+          "end": 38.82,
+          "confidence": 0.964
+        },
+        {
+          "text": "got",
+          "start": 38.82,
+          "end": 38.84,
+          "confidence": 0.958
+        },
+        {
+          "text": "them,",
+          "start": 38.84,
+          "end": 38.86,
+          "confidence": 0.964
+        },
+        {
+          "text": "got",
+          "start": 38.86,
+          "end": 38.88,
+          "confidence": 0.959
+        },
+        {
+          "text": "them,",
+          "start": 38.88,
+          "end": 38.9,
+          "confidence": 0.965
+        },
+        {
+          "text": "got",
+          "start": 38.9,
+          "end": 38.92,
+          "confidence": 0.961
+        },
+        {
+          "text": "them,",
+          "start": 38.92,
+          "end": 38.94,
+          "confidence": 0.968
+        },
+        {
+          "text": "got",
+          "start": 38.94,
+          "end": 38.96,
+          "confidence": 0.964
+        },
+        {
+          "text": "them,",
+          "start": 38.96,
+          "end": 38.98,
+          "confidence": 0.969
+        },
+        {
+          "text": "got",
+          "start": 38.98,
+          "end": 39.0,
+          "confidence": 0.964
+        },
+        {
+          "text": "them,",
+          "start": 39.0,
+          "end": 39.02,
+          "confidence": 0.968
+        },
+        {
+          "text": "got",
+          "start": 39.02,
+          "end": 39.04,
+          "confidence": 0.965
+        },
+        {
+          "text": "them,",
+          "start": 39.04,
+          "end": 39.06,
+          "confidence": 0.971
+        },
+        {
+          "text": "got",
+          "start": 39.06,
+          "end": 39.08,
+          "confidence": 0.967
+        },
+        {
+          "text": "them,",
+          "start": 39.08,
+          "end": 39.1,
+          "confidence": 0.971
+        },
+        {
+          "text": "got",
+          "start": 39.1,
+          "end": 39.12,
+          "confidence": 0.969
+        },
+        {
+          "text": "them,",
+          "start": 39.12,
+          "end": 39.14,
+          "confidence": 0.974
+        },
+        {
+          "text": "got",
+          "start": 39.14,
+          "end": 39.16,
+          "confidence": 0.97
+        },
+        {
+          "text": "them,",
+          "start": 39.16,
+          "end": 39.18,
+          "confidence": 0.974
+        },
+        {
+          "text": "got",
+          "start": 39.18,
+          "end": 39.2,
+          "confidence": 0.972
+        },
+        {
+          "text": "them,",
+          "start": 39.2,
+          "end": 39.22,
+          "confidence": 0.975
+        },
+        {
+          "text": "got",
+          "start": 39.22,
+          "end": 39.24,
+          "confidence": 0.975
+        },
+        {
+          "text": "them,",
+          "start": 39.24,
+          "end": 39.26,
+          "confidence": 0.976
+        },
+        {
+          "text": "got",
+          "start": 39.26,
+          "end": 39.28,
+          "confidence": 0.977
+        },
+        {
+          "text": "them,",
+          "start": 39.28,
+          "end": 39.3,
+          "confidence": 0.978
+        },
+        {
+          "text": "got",
+          "start": 39.3,
+          "end": 39.32,
+          "confidence": 0.978
+        },
+        {
+          "text": "them,",
+          "start": 39.32,
+          "end": 39.34,
+          "confidence": 0.979
+        },
+        {
+          "text": "got",
+          "start": 39.34,
+          "end": 39.36,
+          "confidence": 0.979
+        },
+        {
+          "text": "them,",
+          "start": 39.36,
+          "end": 39.38,
+          "confidence": 0.979
+        },
+        {
+          "text": "got",
+          "start": 39.38,
+          "end": 39.4,
+          "confidence": 0.981
+        },
+        {
+          "text": "them,",
+          "start": 39.4,
+          "end": 39.42,
+          "confidence": 0.98
+        },
+        {
+          "text": "got",
+          "start": 39.42,
+          "end": 39.44,
+          "confidence": 0.983
+        },
+        {
+          "text": "them,",
+          "start": 39.44,
+          "end": 39.46,
+          "confidence": 0.981
+        },
+        {
+          "text": "got",
+          "start": 39.46,
+          "end": 39.48,
+          "confidence": 0.984
+        },
+        {
+          "text": "them,",
+          "start": 39.48,
+          "end": 39.5,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 39.5,
+          "end": 39.52,
+          "confidence": 0.985
+        },
+        {
+          "text": "them,",
+          "start": 39.52,
+          "end": 39.54,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 39.54,
+          "end": 39.56,
+          "confidence": 0.987
+        },
+        {
+          "text": "them,",
+          "start": 39.56,
+          "end": 39.58,
+          "confidence": 0.984
+        },
+        {
+          "text": "got",
+          "start": 39.58,
+          "end": 39.6,
+          "confidence": 0.989
+        },
+        {
+          "text": "them,",
+          "start": 39.6,
+          "end": 39.62,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 39.62,
+          "end": 39.64,
+          "confidence": 0.99
+        },
+        {
+          "text": "them,",
+          "start": 39.64,
+          "end": 39.66,
+          "confidence": 0.984
+        },
+        {
+          "text": "got",
+          "start": 39.66,
+          "end": 39.68,
+          "confidence": 0.99
+        },
+        {
+          "text": "them,",
+          "start": 39.68,
+          "end": 39.7,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 39.7,
+          "end": 39.72,
+          "confidence": 0.991
+        },
+        {
+          "text": "them,",
+          "start": 39.72,
+          "end": 39.74,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 39.74,
+          "end": 39.76,
+          "confidence": 0.991
+        },
+        {
+          "text": "them,",
+          "start": 39.76,
+          "end": 39.78,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 39.78,
+          "end": 39.8,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 39.8,
+          "end": 39.82,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 39.82,
+          "end": 39.84,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 39.84,
+          "end": 39.86,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 39.86,
+          "end": 39.88,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 39.88,
+          "end": 39.9,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 39.9,
+          "end": 39.92,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 39.92,
+          "end": 39.94,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 39.94,
+          "end": 39.96,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 39.96,
+          "end": 39.98,
+          "confidence": 0.988
+        },
+        {
+          "text": "got",
+          "start": 39.98,
+          "end": 40.0,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 40.0,
+          "end": 40.02,
+          "confidence": 0.988
+        },
+        {
+          "text": "got",
+          "start": 40.02,
+          "end": 40.42,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 40.42,
+          "end": 40.68,
+          "confidence": 0.988
+        },
+        {
+          "text": "got",
+          "start": 41.04,
+          "end": 41.06,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 41.06,
+          "end": 41.54,
+          "confidence": 0.988
+        },
+        {
+          "text": "got",
+          "start": 41.88,
+          "end": 41.9,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 41.9,
+          "end": 42.48,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 42.68,
+          "end": 42.7,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 42.7,
+          "end": 43.0,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 43.54,
+          "end": 44.06,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 44.06,
+          "end": 45.16,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 45.16,
+          "end": 45.46,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 45.46,
+          "end": 45.8,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 45.82,
+          "end": 46.22,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 46.22,
+          "end": 46.38,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 46.6,
+          "end": 47.0,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 47.0,
+          "end": 47.76,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 48.18,
+          "end": 48.46,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 48.46,
+          "end": 48.9,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 48.9,
+          "end": 49.2,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 49.2,
+          "end": 49.84,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 50.36,
+          "end": 50.38,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 50.38,
+          "end": 50.76,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 51.5,
+          "end": 51.74,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 51.74,
+          "end": 52.34,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 52.44,
+          "end": 53.28,
+          "confidence": 0.994
+        },
+        {
+          "text": "them",
+          "start": 53.28,
+          "end": 54.52,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 5500,
+      "start": 54.52,
+      "end": 84.46,
+      "text": " got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them",
+      "tokens": [
+        50364,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.05314932168866487,
+      "compression_ratio": 29.52,
+      "no_speech_prob": 0.2454655021429062,
+      "confidence": 0.844,
+      "words": [
+        {
+          "text": "got",
+          "start": 54.52,
+          "end": 54.82,
+          "confidence": 0.002
+        },
+        {
+          "text": "them,",
+          "start": 54.82,
+          "end": 54.84,
+          "confidence": 0.016
+        },
+        {
+          "text": "got",
+          "start": 54.84,
+          "end": 55.14,
+          "confidence": 0.039
+        },
+        {
+          "text": "them,",
+          "start": 55.14,
+          "end": 55.56,
+          "confidence": 0.421
+        },
+        {
+          "text": "got",
+          "start": 55.56,
+          "end": 56.58,
+          "confidence": 0.645
+        },
+        {
+          "text": "them,",
+          "start": 56.58,
+          "end": 56.6,
+          "confidence": 0.595
+        },
+        {
+          "text": "got",
+          "start": 56.6,
+          "end": 57.36,
+          "confidence": 0.78
+        },
+        {
+          "text": "them,",
+          "start": 57.36,
+          "end": 57.52,
+          "confidence": 0.639
+        },
+        {
+          "text": "got",
+          "start": 57.76,
+          "end": 58.22,
+          "confidence": 0.846
+        },
+        {
+          "text": "them,",
+          "start": 58.22,
+          "end": 58.26,
+          "confidence": 0.668
+        },
+        {
+          "text": "got",
+          "start": 58.74,
+          "end": 58.78,
+          "confidence": 0.876
+        },
+        {
+          "text": "them,",
+          "start": 58.78,
+          "end": 59.46,
+          "confidence": 0.672
+        },
+        {
+          "text": "got",
+          "start": 59.88,
+          "end": 59.9,
+          "confidence": 0.836
+        },
+        {
+          "text": "them,",
+          "start": 59.9,
+          "end": 60.32,
+          "confidence": 0.74
+        },
+        {
+          "text": "got",
+          "start": 60.52,
+          "end": 60.6,
+          "confidence": 0.884
+        },
+        {
+          "text": "them,",
+          "start": 60.6,
+          "end": 60.7,
+          "confidence": 0.814
+        },
+        {
+          "text": "got",
+          "start": 60.8,
+          "end": 60.98,
+          "confidence": 0.911
+        },
+        {
+          "text": "them,",
+          "start": 60.98,
+          "end": 61.78,
+          "confidence": 0.567
+        },
+        {
+          "text": "got",
+          "start": 61.78,
+          "end": 61.8,
+          "confidence": 0.122
+        },
+        {
+          "text": "them,",
+          "start": 61.8,
+          "end": 61.82,
+          "confidence": 0.748
+        },
+        {
+          "text": "got",
+          "start": 61.82,
+          "end": 61.84,
+          "confidence": 0.75
+        },
+        {
+          "text": "them,",
+          "start": 61.84,
+          "end": 61.86,
+          "confidence": 0.818
+        },
+        {
+          "text": "got",
+          "start": 61.86,
+          "end": 61.88,
+          "confidence": 0.797
+        },
+        {
+          "text": "them,",
+          "start": 61.88,
+          "end": 61.9,
+          "confidence": 0.841
+        },
+        {
+          "text": "got",
+          "start": 61.9,
+          "end": 61.92,
+          "confidence": 0.81
+        },
+        {
+          "text": "them,",
+          "start": 61.92,
+          "end": 61.94,
+          "confidence": 0.864
+        },
+        {
+          "text": "got",
+          "start": 61.94,
+          "end": 61.96,
+          "confidence": 0.846
+        },
+        {
+          "text": "them,",
+          "start": 61.96,
+          "end": 61.98,
+          "confidence": 0.893
+        },
+        {
+          "text": "got",
+          "start": 61.98,
+          "end": 62.0,
+          "confidence": 0.889
+        },
+        {
+          "text": "them,",
+          "start": 62.0,
+          "end": 62.02,
+          "confidence": 0.91
+        },
+        {
+          "text": "got",
+          "start": 62.02,
+          "end": 62.04,
+          "confidence": 0.896
+        },
+        {
+          "text": "them,",
+          "start": 62.04,
+          "end": 62.06,
+          "confidence": 0.912
+        },
+        {
+          "text": "got",
+          "start": 62.06,
+          "end": 62.08,
+          "confidence": 0.877
+        },
+        {
+          "text": "them,",
+          "start": 62.08,
+          "end": 62.1,
+          "confidence": 0.923
+        },
+        {
+          "text": "got",
+          "start": 62.1,
+          "end": 62.12,
+          "confidence": 0.888
+        },
+        {
+          "text": "them,",
+          "start": 62.12,
+          "end": 62.14,
+          "confidence": 0.932
+        },
+        {
+          "text": "got",
+          "start": 62.14,
+          "end": 62.16,
+          "confidence": 0.896
+        },
+        {
+          "text": "them,",
+          "start": 62.16,
+          "end": 62.18,
+          "confidence": 0.94
+        },
+        {
+          "text": "got",
+          "start": 62.5,
+          "end": 62.72,
+          "confidence": 0.906
+        },
+        {
+          "text": "them,",
+          "start": 62.72,
+          "end": 62.74,
+          "confidence": 0.945
+        },
+        {
+          "text": "got",
+          "start": 62.74,
+          "end": 62.76,
+          "confidence": 0.912
+        },
+        {
+          "text": "them,",
+          "start": 62.76,
+          "end": 62.78,
+          "confidence": 0.95
+        },
+        {
+          "text": "got",
+          "start": 62.78,
+          "end": 62.8,
+          "confidence": 0.917
+        },
+        {
+          "text": "them,",
+          "start": 62.8,
+          "end": 62.82,
+          "confidence": 0.954
+        },
+        {
+          "text": "got",
+          "start": 62.82,
+          "end": 62.84,
+          "confidence": 0.923
+        },
+        {
+          "text": "them,",
+          "start": 62.84,
+          "end": 62.86,
+          "confidence": 0.957
+        },
+        {
+          "text": "got",
+          "start": 62.86,
+          "end": 62.88,
+          "confidence": 0.929
+        },
+        {
+          "text": "them,",
+          "start": 62.88,
+          "end": 62.9,
+          "confidence": 0.959
+        },
+        {
+          "text": "got",
+          "start": 62.9,
+          "end": 62.92,
+          "confidence": 0.933
+        },
+        {
+          "text": "them,",
+          "start": 62.92,
+          "end": 62.94,
+          "confidence": 0.962
+        },
+        {
+          "text": "got",
+          "start": 62.94,
+          "end": 62.96,
+          "confidence": 0.934
+        },
+        {
+          "text": "them,",
+          "start": 62.96,
+          "end": 62.98,
+          "confidence": 0.965
+        },
+        {
+          "text": "got",
+          "start": 62.98,
+          "end": 63.0,
+          "confidence": 0.935
+        },
+        {
+          "text": "them,",
+          "start": 63.0,
+          "end": 63.02,
+          "confidence": 0.965
+        },
+        {
+          "text": "got",
+          "start": 63.02,
+          "end": 63.04,
+          "confidence": 0.937
+        },
+        {
+          "text": "them,",
+          "start": 63.04,
+          "end": 63.06,
+          "confidence": 0.966
+        },
+        {
+          "text": "got",
+          "start": 63.06,
+          "end": 63.08,
+          "confidence": 0.94
+        },
+        {
+          "text": "them,",
+          "start": 63.08,
+          "end": 63.1,
+          "confidence": 0.967
+        },
+        {
+          "text": "got",
+          "start": 63.1,
+          "end": 63.12,
+          "confidence": 0.94
+        },
+        {
+          "text": "them,",
+          "start": 63.12,
+          "end": 63.14,
+          "confidence": 0.969
+        },
+        {
+          "text": "got",
+          "start": 63.14,
+          "end": 63.16,
+          "confidence": 0.942
+        },
+        {
+          "text": "them,",
+          "start": 63.16,
+          "end": 63.18,
+          "confidence": 0.969
+        },
+        {
+          "text": "got",
+          "start": 63.18,
+          "end": 63.2,
+          "confidence": 0.943
+        },
+        {
+          "text": "them,",
+          "start": 63.2,
+          "end": 63.22,
+          "confidence": 0.97
+        },
+        {
+          "text": "got",
+          "start": 63.22,
+          "end": 63.24,
+          "confidence": 0.944
+        },
+        {
+          "text": "them,",
+          "start": 63.24,
+          "end": 63.26,
+          "confidence": 0.971
+        },
+        {
+          "text": "got",
+          "start": 63.26,
+          "end": 63.28,
+          "confidence": 0.946
+        },
+        {
+          "text": "them,",
+          "start": 63.28,
+          "end": 63.3,
+          "confidence": 0.971
+        },
+        {
+          "text": "got",
+          "start": 63.3,
+          "end": 63.32,
+          "confidence": 0.947
+        },
+        {
+          "text": "them,",
+          "start": 63.32,
+          "end": 63.34,
+          "confidence": 0.972
+        },
+        {
+          "text": "got",
+          "start": 63.34,
+          "end": 63.36,
+          "confidence": 0.949
+        },
+        {
+          "text": "them,",
+          "start": 63.36,
+          "end": 63.38,
+          "confidence": 0.971
+        },
+        {
+          "text": "got",
+          "start": 63.38,
+          "end": 63.4,
+          "confidence": 0.951
+        },
+        {
+          "text": "them,",
+          "start": 63.4,
+          "end": 63.42,
+          "confidence": 0.973
+        },
+        {
+          "text": "got",
+          "start": 63.42,
+          "end": 63.44,
+          "confidence": 0.953
+        },
+        {
+          "text": "them,",
+          "start": 63.44,
+          "end": 63.46,
+          "confidence": 0.973
+        },
+        {
+          "text": "got",
+          "start": 63.46,
+          "end": 63.48,
+          "confidence": 0.955
+        },
+        {
+          "text": "them,",
+          "start": 63.48,
+          "end": 63.5,
+          "confidence": 0.974
+        },
+        {
+          "text": "got",
+          "start": 63.5,
+          "end": 63.52,
+          "confidence": 0.956
+        },
+        {
+          "text": "them,",
+          "start": 63.52,
+          "end": 63.54,
+          "confidence": 0.974
+        },
+        {
+          "text": "got",
+          "start": 63.54,
+          "end": 63.56,
+          "confidence": 0.957
+        },
+        {
+          "text": "them,",
+          "start": 63.56,
+          "end": 63.58,
+          "confidence": 0.975
+        },
+        {
+          "text": "got",
+          "start": 63.58,
+          "end": 63.6,
+          "confidence": 0.959
+        },
+        {
+          "text": "them,",
+          "start": 63.6,
+          "end": 63.62,
+          "confidence": 0.975
+        },
+        {
+          "text": "got",
+          "start": 63.62,
+          "end": 63.64,
+          "confidence": 0.962
+        },
+        {
+          "text": "them,",
+          "start": 63.64,
+          "end": 63.66,
+          "confidence": 0.975
+        },
+        {
+          "text": "got",
+          "start": 63.66,
+          "end": 63.68,
+          "confidence": 0.963
+        },
+        {
+          "text": "them,",
+          "start": 63.68,
+          "end": 63.7,
+          "confidence": 0.976
+        },
+        {
+          "text": "got",
+          "start": 63.7,
+          "end": 63.72,
+          "confidence": 0.965
+        },
+        {
+          "text": "them,",
+          "start": 63.72,
+          "end": 63.74,
+          "confidence": 0.976
+        },
+        {
+          "text": "got",
+          "start": 63.74,
+          "end": 63.76,
+          "confidence": 0.968
+        },
+        {
+          "text": "them,",
+          "start": 63.76,
+          "end": 63.78,
+          "confidence": 0.977
+        },
+        {
+          "text": "got",
+          "start": 63.78,
+          "end": 63.8,
+          "confidence": 0.97
+        },
+        {
+          "text": "them,",
+          "start": 63.8,
+          "end": 63.82,
+          "confidence": 0.977
+        },
+        {
+          "text": "got",
+          "start": 63.82,
+          "end": 63.84,
+          "confidence": 0.971
+        },
+        {
+          "text": "them,",
+          "start": 63.84,
+          "end": 63.86,
+          "confidence": 0.977
+        },
+        {
+          "text": "got",
+          "start": 63.86,
+          "end": 63.88,
+          "confidence": 0.973
+        },
+        {
+          "text": "them,",
+          "start": 63.88,
+          "end": 63.9,
+          "confidence": 0.977
+        },
+        {
+          "text": "got",
+          "start": 63.9,
+          "end": 63.92,
+          "confidence": 0.975
+        },
+        {
+          "text": "them,",
+          "start": 63.92,
+          "end": 63.94,
+          "confidence": 0.979
+        },
+        {
+          "text": "got",
+          "start": 63.94,
+          "end": 63.96,
+          "confidence": 0.976
+        },
+        {
+          "text": "them,",
+          "start": 63.96,
+          "end": 63.98,
+          "confidence": 0.979
+        },
+        {
+          "text": "got",
+          "start": 63.98,
+          "end": 64.0,
+          "confidence": 0.977
+        },
+        {
+          "text": "them,",
+          "start": 64.0,
+          "end": 64.02,
+          "confidence": 0.979
+        },
+        {
+          "text": "got",
+          "start": 64.02,
+          "end": 64.04,
+          "confidence": 0.979
+        },
+        {
+          "text": "them,",
+          "start": 64.04,
+          "end": 64.06,
+          "confidence": 0.979
+        },
+        {
+          "text": "got",
+          "start": 64.06,
+          "end": 64.08,
+          "confidence": 0.979
+        },
+        {
+          "text": "them,",
+          "start": 64.08,
+          "end": 64.1,
+          "confidence": 0.979
+        },
+        {
+          "text": "got",
+          "start": 64.1,
+          "end": 64.12,
+          "confidence": 0.981
+        },
+        {
+          "text": "them,",
+          "start": 64.12,
+          "end": 64.4,
+          "confidence": 0.98
+        },
+        {
+          "text": "got",
+          "start": 64.42,
+          "end": 64.58,
+          "confidence": 0.981
+        },
+        {
+          "text": "them,",
+          "start": 64.58,
+          "end": 64.64,
+          "confidence": 0.98
+        },
+        {
+          "text": "got",
+          "start": 64.74,
+          "end": 65.06,
+          "confidence": 0.982
+        },
+        {
+          "text": "them,",
+          "start": 65.06,
+          "end": 65.22,
+          "confidence": 0.98
+        },
+        {
+          "text": "got",
+          "start": 65.22,
+          "end": 65.98,
+          "confidence": 0.984
+        },
+        {
+          "text": "them,",
+          "start": 65.98,
+          "end": 66.26,
+          "confidence": 0.981
+        },
+        {
+          "text": "got",
+          "start": 66.28,
+          "end": 67.32,
+          "confidence": 0.984
+        },
+        {
+          "text": "them,",
+          "start": 67.32,
+          "end": 67.44,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 67.68,
+          "end": 67.7,
+          "confidence": 0.984
+        },
+        {
+          "text": "them,",
+          "start": 67.7,
+          "end": 67.88,
+          "confidence": 0.981
+        },
+        {
+          "text": "got",
+          "start": 67.92,
+          "end": 68.8,
+          "confidence": 0.985
+        },
+        {
+          "text": "them,",
+          "start": 68.8,
+          "end": 69.12,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 69.26,
+          "end": 69.28,
+          "confidence": 0.986
+        },
+        {
+          "text": "them,",
+          "start": 69.28,
+          "end": 69.42,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 69.82,
+          "end": 69.84,
+          "confidence": 0.986
+        },
+        {
+          "text": "them,",
+          "start": 69.84,
+          "end": 70.16,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 70.16,
+          "end": 70.52,
+          "confidence": 0.987
+        },
+        {
+          "text": "them,",
+          "start": 70.52,
+          "end": 71.38,
+          "confidence": 0.981
+        },
+        {
+          "text": "got",
+          "start": 71.38,
+          "end": 71.58,
+          "confidence": 0.988
+        },
+        {
+          "text": "them,",
+          "start": 71.58,
+          "end": 71.94,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 71.94,
+          "end": 72.12,
+          "confidence": 0.989
+        },
+        {
+          "text": "them,",
+          "start": 72.12,
+          "end": 72.76,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 72.9,
+          "end": 73.56,
+          "confidence": 0.989
+        },
+        {
+          "text": "them,",
+          "start": 73.56,
+          "end": 74.08,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 74.68,
+          "end": 75.08,
+          "confidence": 0.99
+        },
+        {
+          "text": "them,",
+          "start": 75.08,
+          "end": 75.18,
+          "confidence": 0.984
+        },
+        {
+          "text": "got",
+          "start": 75.2,
+          "end": 76.42,
+          "confidence": 0.99
+        },
+        {
+          "text": "them,",
+          "start": 76.42,
+          "end": 76.6,
+          "confidence": 0.983
+        },
+        {
+          "text": "got",
+          "start": 76.6,
+          "end": 76.8,
+          "confidence": 0.991
+        },
+        {
+          "text": "them,",
+          "start": 76.8,
+          "end": 77.06,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 77.06,
+          "end": 77.44,
+          "confidence": 0.991
+        },
+        {
+          "text": "them,",
+          "start": 77.44,
+          "end": 77.78,
+          "confidence": 0.984
+        },
+        {
+          "text": "got",
+          "start": 78.22,
+          "end": 78.24,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 78.24,
+          "end": 78.44,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 79.86,
+          "end": 79.9,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 79.9,
+          "end": 82.46,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 82.46,
+          "end": 84.44,
+          "confidence": 0.992
+        },
+        {
+          "text": "them",
+          "start": 84.44,
+          "end": 84.46,
+          "confidence": 0.994
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 8500,
+      "start": 85.2,
+      "end": 91.86,
+      "text": " got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them, got them",
+      "tokens": [
+        50364,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552,
+        11,
+        658,
+        552
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.042715128227199674,
+      "compression_ratio": 29.52,
+      "no_speech_prob": 0.6358686685562134,
+      "confidence": 0.854,
+      "words": [
+        {
+          "text": "got",
+          "start": 85.2,
+          "end": 85.36,
+          "confidence": 0.0
+        },
+        {
+          "text": "them,",
+          "start": 85.36,
+          "end": 85.42,
+          "confidence": 0.024
+        },
+        {
+          "text": "got",
+          "start": 85.68,
+          "end": 86.68,
+          "confidence": 0.791
+        },
+        {
+          "text": "them,",
+          "start": 86.68,
+          "end": 86.82,
+          "confidence": 0.583
+        },
+        {
+          "text": "got",
+          "start": 87.4,
+          "end": 87.6,
+          "confidence": 0.828
+        },
+        {
+          "text": "them,",
+          "start": 87.6,
+          "end": 88.02,
+          "confidence": 0.486
+        },
+        {
+          "text": "got",
+          "start": 88.02,
+          "end": 88.88,
+          "confidence": 0.881
+        },
+        {
+          "text": "them,",
+          "start": 88.88,
+          "end": 88.9,
+          "confidence": 0.425
+        },
+        {
+          "text": "got",
+          "start": 88.92,
+          "end": 88.94,
+          "confidence": 0.902
+        },
+        {
+          "text": "them,",
+          "start": 88.94,
+          "end": 88.96,
+          "confidence": 0.397
+        },
+        {
+          "text": "got",
+          "start": 88.96,
+          "end": 88.98,
+          "confidence": 0.897
+        },
+        {
+          "text": "them,",
+          "start": 88.98,
+          "end": 89.0,
+          "confidence": 0.4
+        },
+        {
+          "text": "got",
+          "start": 89.0,
+          "end": 89.02,
+          "confidence": 0.869
+        },
+        {
+          "text": "them,",
+          "start": 89.02,
+          "end": 89.06,
+          "confidence": 0.47
+        },
+        {
+          "text": "got",
+          "start": 89.18,
+          "end": 89.2,
+          "confidence": 0.89
+        },
+        {
+          "text": "them,",
+          "start": 89.2,
+          "end": 89.22,
+          "confidence": 0.57
+        },
+        {
+          "text": "got",
+          "start": 89.22,
+          "end": 89.24,
+          "confidence": 0.91
+        },
+        {
+          "text": "them,",
+          "start": 89.24,
+          "end": 89.26,
+          "confidence": 0.632
+        },
+        {
+          "text": "got",
+          "start": 89.26,
+          "end": 89.28,
+          "confidence": 0.598
+        },
+        {
+          "text": "them,",
+          "start": 89.28,
+          "end": 89.3,
+          "confidence": 0.743
+        },
+        {
+          "text": "got",
+          "start": 89.3,
+          "end": 89.32,
+          "confidence": 0.819
+        },
+        {
+          "text": "them,",
+          "start": 89.32,
+          "end": 89.34,
+          "confidence": 0.84
+        },
+        {
+          "text": "got",
+          "start": 89.34,
+          "end": 89.36,
+          "confidence": 0.899
+        },
+        {
+          "text": "them,",
+          "start": 89.36,
+          "end": 89.38,
+          "confidence": 0.888
+        },
+        {
+          "text": "got",
+          "start": 89.38,
+          "end": 89.4,
+          "confidence": 0.918
+        },
+        {
+          "text": "them,",
+          "start": 89.4,
+          "end": 89.42,
+          "confidence": 0.914
+        },
+        {
+          "text": "got",
+          "start": 89.42,
+          "end": 89.44,
+          "confidence": 0.936
+        },
+        {
+          "text": "them,",
+          "start": 89.44,
+          "end": 89.46,
+          "confidence": 0.932
+        },
+        {
+          "text": "got",
+          "start": 89.46,
+          "end": 89.48,
+          "confidence": 0.947
+        },
+        {
+          "text": "them,",
+          "start": 89.48,
+          "end": 89.5,
+          "confidence": 0.944
+        },
+        {
+          "text": "got",
+          "start": 89.5,
+          "end": 89.52,
+          "confidence": 0.953
+        },
+        {
+          "text": "them,",
+          "start": 89.52,
+          "end": 89.54,
+          "confidence": 0.945
+        },
+        {
+          "text": "got",
+          "start": 89.54,
+          "end": 89.56,
+          "confidence": 0.955
+        },
+        {
+          "text": "them,",
+          "start": 89.56,
+          "end": 89.58,
+          "confidence": 0.944
+        },
+        {
+          "text": "got",
+          "start": 89.58,
+          "end": 89.6,
+          "confidence": 0.947
+        },
+        {
+          "text": "them,",
+          "start": 89.6,
+          "end": 89.62,
+          "confidence": 0.946
+        },
+        {
+          "text": "got",
+          "start": 89.62,
+          "end": 89.64,
+          "confidence": 0.94
+        },
+        {
+          "text": "them,",
+          "start": 89.64,
+          "end": 89.66,
+          "confidence": 0.952
+        },
+        {
+          "text": "got",
+          "start": 89.66,
+          "end": 89.68,
+          "confidence": 0.941
+        },
+        {
+          "text": "them,",
+          "start": 89.68,
+          "end": 89.7,
+          "confidence": 0.954
+        },
+        {
+          "text": "got",
+          "start": 89.7,
+          "end": 89.72,
+          "confidence": 0.941
+        },
+        {
+          "text": "them,",
+          "start": 89.72,
+          "end": 89.74,
+          "confidence": 0.96
+        },
+        {
+          "text": "got",
+          "start": 89.74,
+          "end": 89.76,
+          "confidence": 0.941
+        },
+        {
+          "text": "them,",
+          "start": 89.76,
+          "end": 89.78,
+          "confidence": 0.963
+        },
+        {
+          "text": "got",
+          "start": 89.78,
+          "end": 89.8,
+          "confidence": 0.945
+        },
+        {
+          "text": "them,",
+          "start": 89.8,
+          "end": 89.82,
+          "confidence": 0.966
+        },
+        {
+          "text": "got",
+          "start": 89.82,
+          "end": 89.84,
+          "confidence": 0.948
+        },
+        {
+          "text": "them,",
+          "start": 89.84,
+          "end": 89.86,
+          "confidence": 0.968
+        },
+        {
+          "text": "got",
+          "start": 89.86,
+          "end": 89.88,
+          "confidence": 0.95
+        },
+        {
+          "text": "them,",
+          "start": 89.88,
+          "end": 89.9,
+          "confidence": 0.971
+        },
+        {
+          "text": "got",
+          "start": 89.9,
+          "end": 89.92,
+          "confidence": 0.951
+        },
+        {
+          "text": "them,",
+          "start": 89.92,
+          "end": 89.94,
+          "confidence": 0.975
+        },
+        {
+          "text": "got",
+          "start": 89.94,
+          "end": 89.96,
+          "confidence": 0.95
+        },
+        {
+          "text": "them,",
+          "start": 89.96,
+          "end": 89.98,
+          "confidence": 0.975
+        },
+        {
+          "text": "got",
+          "start": 89.98,
+          "end": 90.0,
+          "confidence": 0.951
+        },
+        {
+          "text": "them,",
+          "start": 90.0,
+          "end": 90.02,
+          "confidence": 0.977
+        },
+        {
+          "text": "got",
+          "start": 90.02,
+          "end": 90.04,
+          "confidence": 0.953
+        },
+        {
+          "text": "them,",
+          "start": 90.04,
+          "end": 90.06,
+          "confidence": 0.977
+        },
+        {
+          "text": "got",
+          "start": 90.06,
+          "end": 90.08,
+          "confidence": 0.954
+        },
+        {
+          "text": "them,",
+          "start": 90.08,
+          "end": 90.1,
+          "confidence": 0.979
+        },
+        {
+          "text": "got",
+          "start": 90.1,
+          "end": 90.12,
+          "confidence": 0.955
+        },
+        {
+          "text": "them,",
+          "start": 90.12,
+          "end": 90.14,
+          "confidence": 0.979
+        },
+        {
+          "text": "got",
+          "start": 90.14,
+          "end": 90.16,
+          "confidence": 0.956
+        },
+        {
+          "text": "them,",
+          "start": 90.16,
+          "end": 90.18,
+          "confidence": 0.981
+        },
+        {
+          "text": "got",
+          "start": 90.18,
+          "end": 90.2,
+          "confidence": 0.956
+        },
+        {
+          "text": "them,",
+          "start": 90.2,
+          "end": 90.22,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 90.22,
+          "end": 90.24,
+          "confidence": 0.958
+        },
+        {
+          "text": "them,",
+          "start": 90.24,
+          "end": 90.26,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 90.26,
+          "end": 90.28,
+          "confidence": 0.959
+        },
+        {
+          "text": "them,",
+          "start": 90.28,
+          "end": 90.3,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 90.3,
+          "end": 90.32,
+          "confidence": 0.961
+        },
+        {
+          "text": "them,",
+          "start": 90.32,
+          "end": 90.34,
+          "confidence": 0.982
+        },
+        {
+          "text": "got",
+          "start": 90.34,
+          "end": 90.36,
+          "confidence": 0.963
+        },
+        {
+          "text": "them,",
+          "start": 90.36,
+          "end": 90.38,
+          "confidence": 0.984
+        },
+        {
+          "text": "got",
+          "start": 90.38,
+          "end": 90.4,
+          "confidence": 0.964
+        },
+        {
+          "text": "them,",
+          "start": 90.4,
+          "end": 90.42,
+          "confidence": 0.984
+        },
+        {
+          "text": "got",
+          "start": 90.42,
+          "end": 90.44,
+          "confidence": 0.966
+        },
+        {
+          "text": "them,",
+          "start": 90.44,
+          "end": 90.46,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 90.46,
+          "end": 90.48,
+          "confidence": 0.968
+        },
+        {
+          "text": "them,",
+          "start": 90.48,
+          "end": 90.5,
+          "confidence": 0.985
+        },
+        {
+          "text": "got",
+          "start": 90.5,
+          "end": 90.52,
+          "confidence": 0.969
+        },
+        {
+          "text": "them,",
+          "start": 90.52,
+          "end": 90.54,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 90.54,
+          "end": 90.56,
+          "confidence": 0.971
+        },
+        {
+          "text": "them,",
+          "start": 90.56,
+          "end": 90.58,
+          "confidence": 0.986
+        },
+        {
+          "text": "got",
+          "start": 90.58,
+          "end": 90.6,
+          "confidence": 0.973
+        },
+        {
+          "text": "them,",
+          "start": 90.6,
+          "end": 90.62,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 90.62,
+          "end": 90.64,
+          "confidence": 0.974
+        },
+        {
+          "text": "them,",
+          "start": 90.64,
+          "end": 90.66,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 90.66,
+          "end": 90.68,
+          "confidence": 0.976
+        },
+        {
+          "text": "them,",
+          "start": 90.68,
+          "end": 90.7,
+          "confidence": 0.987
+        },
+        {
+          "text": "got",
+          "start": 90.7,
+          "end": 90.72,
+          "confidence": 0.979
+        },
+        {
+          "text": "them,",
+          "start": 90.72,
+          "end": 90.74,
+          "confidence": 0.988
+        },
+        {
+          "text": "got",
+          "start": 90.74,
+          "end": 90.76,
+          "confidence": 0.98
+        },
+        {
+          "text": "them,",
+          "start": 90.76,
+          "end": 90.78,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 90.78,
+          "end": 90.8,
+          "confidence": 0.981
+        },
+        {
+          "text": "them,",
+          "start": 90.8,
+          "end": 90.82,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 90.82,
+          "end": 90.84,
+          "confidence": 0.983
+        },
+        {
+          "text": "them,",
+          "start": 90.84,
+          "end": 90.86,
+          "confidence": 0.989
+        },
+        {
+          "text": "got",
+          "start": 90.86,
+          "end": 90.88,
+          "confidence": 0.985
+        },
+        {
+          "text": "them,",
+          "start": 90.88,
+          "end": 90.9,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 90.9,
+          "end": 90.92,
+          "confidence": 0.986
+        },
+        {
+          "text": "them,",
+          "start": 90.92,
+          "end": 90.94,
+          "confidence": 0.99
+        },
+        {
+          "text": "got",
+          "start": 90.94,
+          "end": 90.96,
+          "confidence": 0.987
+        },
+        {
+          "text": "them,",
+          "start": 90.96,
+          "end": 90.98,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 90.98,
+          "end": 91.0,
+          "confidence": 0.988
+        },
+        {
+          "text": "them,",
+          "start": 91.0,
+          "end": 91.02,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 91.02,
+          "end": 91.04,
+          "confidence": 0.989
+        },
+        {
+          "text": "them,",
+          "start": 91.04,
+          "end": 91.06,
+          "confidence": 0.991
+        },
+        {
+          "text": "got",
+          "start": 91.06,
+          "end": 91.08,
+          "confidence": 0.99
+        },
+        {
+          "text": "them,",
+          "start": 91.08,
+          "end": 91.1,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 91.1,
+          "end": 91.12,
+          "confidence": 0.99
+        },
+        {
+          "text": "them,",
+          "start": 91.12,
+          "end": 91.14,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 91.14,
+          "end": 91.16,
+          "confidence": 0.991
+        },
+        {
+          "text": "them,",
+          "start": 91.16,
+          "end": 91.18,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 91.18,
+          "end": 91.2,
+          "confidence": 0.992
+        },
+        {
+          "text": "them,",
+          "start": 91.2,
+          "end": 91.22,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 91.22,
+          "end": 91.24,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 91.24,
+          "end": 91.26,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 91.26,
+          "end": 91.28,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 91.28,
+          "end": 91.3,
+          "confidence": 0.992
+        },
+        {
+          "text": "got",
+          "start": 91.3,
+          "end": 91.32,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 91.32,
+          "end": 91.34,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 91.34,
+          "end": 91.36,
+          "confidence": 0.993
+        },
+        {
+          "text": "them,",
+          "start": 91.36,
+          "end": 91.38,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 91.38,
+          "end": 91.4,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 91.4,
+          "end": 91.42,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 91.42,
+          "end": 91.44,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 91.44,
+          "end": 91.46,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 91.46,
+          "end": 91.48,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 91.48,
+          "end": 91.5,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 91.5,
+          "end": 91.52,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 91.52,
+          "end": 91.54,
+          "confidence": 0.993
+        },
+        {
+          "text": "got",
+          "start": 91.54,
+          "end": 91.56,
+          "confidence": 0.994
+        },
+        {
+          "text": "them,",
+          "start": 91.56,
+          "end": 91.58,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 91.58,
+          "end": 91.6,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 91.6,
+          "end": 91.62,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 91.62,
+          "end": 91.64,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 91.64,
+          "end": 91.66,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 91.66,
+          "end": 91.68,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 91.68,
+          "end": 91.7,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 91.7,
+          "end": 91.72,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 91.72,
+          "end": 91.74,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 91.74,
+          "end": 91.76,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 91.76,
+          "end": 91.78,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 91.78,
+          "end": 91.8,
+          "confidence": 0.995
+        },
+        {
+          "text": "them,",
+          "start": 91.8,
+          "end": 91.82,
+          "confidence": 0.994
+        },
+        {
+          "text": "got",
+          "start": 91.82,
+          "end": 91.84,
+          "confidence": 0.995
+        },
+        {
+          "text": "them",
+          "start": 91.84,
+          "end": 91.86,
+          "confidence": 0.998
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/punctuations_no/bonjour.wav.csv b/tests/expected/punctuations_no/bonjour.wav.csv
new file mode 100644
index 0000000000000000000000000000000000000000..515648b4ee80e092404f6e79d04d7028cefdae78
--- /dev/null
+++ b/tests/expected/punctuations_no/bonjour.wav.csv
@@ -0,0 +1 @@
+Bonjour !,0.14,0.94
diff --git a/tests/expected/punctuations_no/bonjour.wav.srt b/tests/expected/punctuations_no/bonjour.wav.srt
new file mode 100644
index 0000000000000000000000000000000000000000..d8d205dc3daf944fcf8cbd38edc5f45287fb5510
--- /dev/null
+++ b/tests/expected/punctuations_no/bonjour.wav.srt
@@ -0,0 +1,4 @@
+1
+00:00:00,140 --> 00:00:00,940
+Bonjour !
+
diff --git a/tests/expected/punctuations_no/bonjour.wav.tsv b/tests/expected/punctuations_no/bonjour.wav.tsv
new file mode 100644
index 0000000000000000000000000000000000000000..4244f49ea0e650559f762b334550dd60e0a2f2a6
--- /dev/null
+++ b/tests/expected/punctuations_no/bonjour.wav.tsv
@@ -0,0 +1,2 @@
+start	end	text
+140	940	Bonjour !
diff --git a/tests/expected/punctuations_no/bonjour.wav.txt b/tests/expected/punctuations_no/bonjour.wav.txt
new file mode 100644
index 0000000000000000000000000000000000000000..6625d5f9893711f1c711cc5a3695219d1f4d9cc4
--- /dev/null
+++ b/tests/expected/punctuations_no/bonjour.wav.txt
@@ -0,0 +1 @@
+Bonjour !
diff --git a/tests/expected/punctuations_no/bonjour.wav.vtt b/tests/expected/punctuations_no/bonjour.wav.vtt
new file mode 100644
index 0000000000000000000000000000000000000000..ecc03120fcb44b8ed669288169bdae00ce0c79ec
--- /dev/null
+++ b/tests/expected/punctuations_no/bonjour.wav.vtt
@@ -0,0 +1,7 @@
+WEBVTT
+
+WEBVTT
+
+00:00.140 --> 00:00.940
+Bonjour !
+
diff --git a/tests/expected/punctuations_no/bonjour.wav.words.csv b/tests/expected/punctuations_no/bonjour.wav.words.csv
new file mode 100644
index 0000000000000000000000000000000000000000..c164f6417663f8765245f8e23022ad85080f7941
--- /dev/null
+++ b/tests/expected/punctuations_no/bonjour.wav.words.csv
@@ -0,0 +1 @@
+Bonjour,0.14,0.94
diff --git a/tests/expected/punctuations_no/bonjour.wav.words.json b/tests/expected/punctuations_no/bonjour.wav.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..16f8fddd1de9409ecc8426f5bd914f21d902393c
--- /dev/null
+++ b/tests/expected/punctuations_no/bonjour.wav.words.json
@@ -0,0 +1,32 @@
+{
+  "text": " Bonjour !",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.14,
+      "end": 0.94,
+      "text": " Bonjour !",
+      "tokens": [
+        50364,
+        25431,
+        2298,
+        50402
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7046648502349854,
+      "compression_ratio": 0.5294117647058824,
+      "no_speech_prob": 0.08610370755195618,
+      "confidence": 0.964,
+      "words": [
+        {
+          "text": "Bonjour",
+          "start": 0.14,
+          "end": 0.94,
+          "confidence": 0.964
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/punctuations_no/bonjour.wav.words.srt b/tests/expected/punctuations_no/bonjour.wav.words.srt
new file mode 100644
index 0000000000000000000000000000000000000000..cd14abb1f5b082f428f7e68574088414fa661db8
--- /dev/null
+++ b/tests/expected/punctuations_no/bonjour.wav.words.srt
@@ -0,0 +1,4 @@
+1
+00:00:00,140 --> 00:00:00,940
+Bonjour
+
diff --git a/tests/expected/punctuations_no/bonjour.wav.words.tsv b/tests/expected/punctuations_no/bonjour.wav.words.tsv
new file mode 100644
index 0000000000000000000000000000000000000000..2ddd00966ddffa056b18e3903294c7ef5795ffe1
--- /dev/null
+++ b/tests/expected/punctuations_no/bonjour.wav.words.tsv
@@ -0,0 +1,2 @@
+start	end	text
+140	940	Bonjour
diff --git a/tests/expected/punctuations_no/bonjour.wav.words.vtt b/tests/expected/punctuations_no/bonjour.wav.words.vtt
new file mode 100644
index 0000000000000000000000000000000000000000..a3ce34860a05ec1125085a02e60a5eac85458c72
--- /dev/null
+++ b/tests/expected/punctuations_no/bonjour.wav.words.vtt
@@ -0,0 +1,7 @@
+WEBVTT
+
+WEBVTT
+
+00:00.140 --> 00:00.940
+Bonjour
+
diff --git a/tests/expected/punctuations_no/punctuations.mp3.csv b/tests/expected/punctuations_no/punctuations.mp3.csv
new file mode 100644
index 0000000000000000000000000000000000000000..32a9d46e0d6565dc2b2aa8bc1bc5c2958fad26f9
--- /dev/null
+++ b/tests/expected/punctuations_no/punctuations.mp3.csv
@@ -0,0 +1 @@
+"Dis-moi, est-ce que l'avion vole ?",0.38,2.76
diff --git a/tests/expected/punctuations_no/punctuations.mp3.srt b/tests/expected/punctuations_no/punctuations.mp3.srt
new file mode 100644
index 0000000000000000000000000000000000000000..877851ff9664283f0877d16b24551fa2d7a88226
--- /dev/null
+++ b/tests/expected/punctuations_no/punctuations.mp3.srt
@@ -0,0 +1,4 @@
+1
+00:00:00,380 --> 00:00:02,760
+Dis-moi, est-ce que l'avion vole ?
+
diff --git a/tests/expected/punctuations_no/punctuations.mp3.tsv b/tests/expected/punctuations_no/punctuations.mp3.tsv
new file mode 100644
index 0000000000000000000000000000000000000000..58cf737627008302c822b962a66b0b7e46a3a1de
--- /dev/null
+++ b/tests/expected/punctuations_no/punctuations.mp3.tsv
@@ -0,0 +1,2 @@
+start	end	text
+380	2760	Dis-moi, est-ce que l'avion vole ?
diff --git a/tests/expected/punctuations_no/punctuations.mp3.txt b/tests/expected/punctuations_no/punctuations.mp3.txt
new file mode 100644
index 0000000000000000000000000000000000000000..6490b685ff0adf8d95873de48095732fd91c30fd
--- /dev/null
+++ b/tests/expected/punctuations_no/punctuations.mp3.txt
@@ -0,0 +1 @@
+Dis-moi, est-ce que l'avion vole ?
diff --git a/tests/expected/punctuations_no/punctuations.mp3.vtt b/tests/expected/punctuations_no/punctuations.mp3.vtt
new file mode 100644
index 0000000000000000000000000000000000000000..8397a28e233bce3dbd3ddbf7a4226bf3c210e870
--- /dev/null
+++ b/tests/expected/punctuations_no/punctuations.mp3.vtt
@@ -0,0 +1,7 @@
+WEBVTT
+
+WEBVTT
+
+00:00.380 --> 00:02.760
+Dis-moi, est-ce que l'avion vole ?
+
diff --git a/tests/expected/punctuations_no/punctuations.mp3.words.csv b/tests/expected/punctuations_no/punctuations.mp3.words.csv
new file mode 100644
index 0000000000000000000000000000000000000000..e5fbcbf2c422d3c24608bdcea9f55eb45171a093
--- /dev/null
+++ b/tests/expected/punctuations_no/punctuations.mp3.words.csv
@@ -0,0 +1,5 @@
+Dis-moi,0.38,1.1
+est-ce,1.28,1.5
+que,1.5,1.66
+l'avion,1.66,2.04
+vole,2.04,2.76
diff --git a/tests/expected/punctuations_no/punctuations.mp3.words.json b/tests/expected/punctuations_no/punctuations.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..e4ff96e3ad4a9ed767427d7c70a4e020f8bf667d
--- /dev/null
+++ b/tests/expected/punctuations_no/punctuations.mp3.words.json
@@ -0,0 +1,68 @@
+{
+  "text": " Dis-moi, est-ce que l'avion vole ?",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.38,
+      "end": 2.76,
+      "text": " Dis-moi, est-ce que l'avion vole ?",
+      "tokens": [
+        50364,
+        4208,
+        12,
+        29292,
+        11,
+        871,
+        12,
+        384,
+        631,
+        287,
+        6,
+        706,
+        313,
+        49877,
+        2506,
+        50496
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.26327380012063417,
+      "compression_ratio": 0.8095238095238095,
+      "no_speech_prob": 0.03882359713315964,
+      "confidence": 0.928,
+      "words": [
+        {
+          "text": "Dis-moi",
+          "start": 0.38,
+          "end": 1.1,
+          "confidence": 0.809
+        },
+        {
+          "text": "est-ce",
+          "start": 1.28,
+          "end": 1.5,
+          "confidence": 0.968
+        },
+        {
+          "text": "que",
+          "start": 1.5,
+          "end": 1.66,
+          "confidence": 0.978
+        },
+        {
+          "text": "l'avion",
+          "start": 1.66,
+          "end": 2.04,
+          "confidence": 0.993
+        },
+        {
+          "text": "vole",
+          "start": 2.04,
+          "end": 2.76,
+          "confidence": 0.898
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/punctuations_no/punctuations.mp3.words.srt b/tests/expected/punctuations_no/punctuations.mp3.words.srt
new file mode 100644
index 0000000000000000000000000000000000000000..9a0041e682bad02b37134d8a0d764cd07b64f608
--- /dev/null
+++ b/tests/expected/punctuations_no/punctuations.mp3.words.srt
@@ -0,0 +1,20 @@
+1
+00:00:00,380 --> 00:00:01,100
+Dis-moi
+
+2
+00:00:01,280 --> 00:00:01,500
+est-ce
+
+3
+00:00:01,500 --> 00:00:01,660
+que
+
+4
+00:00:01,660 --> 00:00:02,040
+l'avion
+
+5
+00:00:02,040 --> 00:00:02,760
+vole
+
diff --git a/tests/expected/punctuations_no/punctuations.mp3.words.tsv b/tests/expected/punctuations_no/punctuations.mp3.words.tsv
new file mode 100644
index 0000000000000000000000000000000000000000..a9613c4fe6697b2aa5ea56eecd09fb9c18d32210
--- /dev/null
+++ b/tests/expected/punctuations_no/punctuations.mp3.words.tsv
@@ -0,0 +1,6 @@
+start	end	text
+380	1100	Dis-moi
+1280	1500	est-ce
+1500	1660	que
+1660	2040	l'avion
+2040	2760	vole
diff --git a/tests/expected/punctuations_no/punctuations.mp3.words.vtt b/tests/expected/punctuations_no/punctuations.mp3.words.vtt
new file mode 100644
index 0000000000000000000000000000000000000000..fc6f8a3b6558650512d59fcdc3ce41735b03176d
--- /dev/null
+++ b/tests/expected/punctuations_no/punctuations.mp3.words.vtt
@@ -0,0 +1,19 @@
+WEBVTT
+
+WEBVTT
+
+00:00.380 --> 00:01.100
+Dis-moi
+
+00:01.280 --> 00:01.500
+est-ce
+
+00:01.500 --> 00:01.660
+que
+
+00:01.660 --> 00:02.040
+l'avion
+
+00:02.040 --> 00:02.760
+vole
+
diff --git a/tests/expected/punctuations_yes/bonjour.wav.csv b/tests/expected/punctuations_yes/bonjour.wav.csv
new file mode 100644
index 0000000000000000000000000000000000000000..515648b4ee80e092404f6e79d04d7028cefdae78
--- /dev/null
+++ b/tests/expected/punctuations_yes/bonjour.wav.csv
@@ -0,0 +1 @@
+Bonjour !,0.14,0.94
diff --git a/tests/expected/punctuations_yes/bonjour.wav.srt b/tests/expected/punctuations_yes/bonjour.wav.srt
new file mode 100644
index 0000000000000000000000000000000000000000..d8d205dc3daf944fcf8cbd38edc5f45287fb5510
--- /dev/null
+++ b/tests/expected/punctuations_yes/bonjour.wav.srt
@@ -0,0 +1,4 @@
+1
+00:00:00,140 --> 00:00:00,940
+Bonjour !
+
diff --git a/tests/expected/punctuations_yes/bonjour.wav.tsv b/tests/expected/punctuations_yes/bonjour.wav.tsv
new file mode 100644
index 0000000000000000000000000000000000000000..4244f49ea0e650559f762b334550dd60e0a2f2a6
--- /dev/null
+++ b/tests/expected/punctuations_yes/bonjour.wav.tsv
@@ -0,0 +1,2 @@
+start	end	text
+140	940	Bonjour !
diff --git a/tests/expected/punctuations_yes/bonjour.wav.txt b/tests/expected/punctuations_yes/bonjour.wav.txt
new file mode 100644
index 0000000000000000000000000000000000000000..6625d5f9893711f1c711cc5a3695219d1f4d9cc4
--- /dev/null
+++ b/tests/expected/punctuations_yes/bonjour.wav.txt
@@ -0,0 +1 @@
+Bonjour !
diff --git a/tests/expected/punctuations_yes/bonjour.wav.vtt b/tests/expected/punctuations_yes/bonjour.wav.vtt
new file mode 100644
index 0000000000000000000000000000000000000000..ecc03120fcb44b8ed669288169bdae00ce0c79ec
--- /dev/null
+++ b/tests/expected/punctuations_yes/bonjour.wav.vtt
@@ -0,0 +1,7 @@
+WEBVTT
+
+WEBVTT
+
+00:00.140 --> 00:00.940
+Bonjour !
+
diff --git a/tests/expected/punctuations_yes/bonjour.wav.words.csv b/tests/expected/punctuations_yes/bonjour.wav.words.csv
new file mode 100644
index 0000000000000000000000000000000000000000..515648b4ee80e092404f6e79d04d7028cefdae78
--- /dev/null
+++ b/tests/expected/punctuations_yes/bonjour.wav.words.csv
@@ -0,0 +1 @@
+Bonjour !,0.14,0.94
diff --git a/tests/expected/punctuations_yes/bonjour.wav.words.json b/tests/expected/punctuations_yes/bonjour.wav.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..1539b7c83897fb3c4c929768b3ef7782d28c3f37
--- /dev/null
+++ b/tests/expected/punctuations_yes/bonjour.wav.words.json
@@ -0,0 +1,32 @@
+{
+  "text": " Bonjour !",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.14,
+      "end": 0.94,
+      "text": " Bonjour !",
+      "tokens": [
+        50364,
+        25431,
+        2298,
+        50402
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7046648502349854,
+      "compression_ratio": 0.5294117647058824,
+      "no_speech_prob": 0.08610370755195618,
+      "confidence": 0.964,
+      "words": [
+        {
+          "text": "Bonjour !",
+          "start": 0.14,
+          "end": 0.94,
+          "confidence": 0.964
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/punctuations_yes/bonjour.wav.words.srt b/tests/expected/punctuations_yes/bonjour.wav.words.srt
new file mode 100644
index 0000000000000000000000000000000000000000..d8d205dc3daf944fcf8cbd38edc5f45287fb5510
--- /dev/null
+++ b/tests/expected/punctuations_yes/bonjour.wav.words.srt
@@ -0,0 +1,4 @@
+1
+00:00:00,140 --> 00:00:00,940
+Bonjour !
+
diff --git a/tests/expected/punctuations_yes/bonjour.wav.words.tsv b/tests/expected/punctuations_yes/bonjour.wav.words.tsv
new file mode 100644
index 0000000000000000000000000000000000000000..4244f49ea0e650559f762b334550dd60e0a2f2a6
--- /dev/null
+++ b/tests/expected/punctuations_yes/bonjour.wav.words.tsv
@@ -0,0 +1,2 @@
+start	end	text
+140	940	Bonjour !
diff --git a/tests/expected/punctuations_yes/bonjour.wav.words.vtt b/tests/expected/punctuations_yes/bonjour.wav.words.vtt
new file mode 100644
index 0000000000000000000000000000000000000000..ecc03120fcb44b8ed669288169bdae00ce0c79ec
--- /dev/null
+++ b/tests/expected/punctuations_yes/bonjour.wav.words.vtt
@@ -0,0 +1,7 @@
+WEBVTT
+
+WEBVTT
+
+00:00.140 --> 00:00.940
+Bonjour !
+
diff --git a/tests/expected/punctuations_yes/punctuations.mp3.csv b/tests/expected/punctuations_yes/punctuations.mp3.csv
new file mode 100644
index 0000000000000000000000000000000000000000..32a9d46e0d6565dc2b2aa8bc1bc5c2958fad26f9
--- /dev/null
+++ b/tests/expected/punctuations_yes/punctuations.mp3.csv
@@ -0,0 +1 @@
+"Dis-moi, est-ce que l'avion vole ?",0.38,2.76
diff --git a/tests/expected/punctuations_yes/punctuations.mp3.srt b/tests/expected/punctuations_yes/punctuations.mp3.srt
new file mode 100644
index 0000000000000000000000000000000000000000..877851ff9664283f0877d16b24551fa2d7a88226
--- /dev/null
+++ b/tests/expected/punctuations_yes/punctuations.mp3.srt
@@ -0,0 +1,4 @@
+1
+00:00:00,380 --> 00:00:02,760
+Dis-moi, est-ce que l'avion vole ?
+
diff --git a/tests/expected/punctuations_yes/punctuations.mp3.tsv b/tests/expected/punctuations_yes/punctuations.mp3.tsv
new file mode 100644
index 0000000000000000000000000000000000000000..58cf737627008302c822b962a66b0b7e46a3a1de
--- /dev/null
+++ b/tests/expected/punctuations_yes/punctuations.mp3.tsv
@@ -0,0 +1,2 @@
+start	end	text
+380	2760	Dis-moi, est-ce que l'avion vole ?
diff --git a/tests/expected/punctuations_yes/punctuations.mp3.txt b/tests/expected/punctuations_yes/punctuations.mp3.txt
new file mode 100644
index 0000000000000000000000000000000000000000..6490b685ff0adf8d95873de48095732fd91c30fd
--- /dev/null
+++ b/tests/expected/punctuations_yes/punctuations.mp3.txt
@@ -0,0 +1 @@
+Dis-moi, est-ce que l'avion vole ?
diff --git a/tests/expected/punctuations_yes/punctuations.mp3.vtt b/tests/expected/punctuations_yes/punctuations.mp3.vtt
new file mode 100644
index 0000000000000000000000000000000000000000..8397a28e233bce3dbd3ddbf7a4226bf3c210e870
--- /dev/null
+++ b/tests/expected/punctuations_yes/punctuations.mp3.vtt
@@ -0,0 +1,7 @@
+WEBVTT
+
+WEBVTT
+
+00:00.380 --> 00:02.760
+Dis-moi, est-ce que l'avion vole ?
+
diff --git a/tests/expected/punctuations_yes/punctuations.mp3.words.csv b/tests/expected/punctuations_yes/punctuations.mp3.words.csv
new file mode 100644
index 0000000000000000000000000000000000000000..6d6a4383de2f4c469a0fc0048edda5d5d3cfc3e9
--- /dev/null
+++ b/tests/expected/punctuations_yes/punctuations.mp3.words.csv
@@ -0,0 +1,5 @@
+"Dis-moi,",0.38,1.1
+est-ce,1.28,1.5
+que,1.5,1.66
+l'avion,1.66,2.04
+vole ?,2.04,2.76
diff --git a/tests/expected/punctuations_yes/punctuations.mp3.words.json b/tests/expected/punctuations_yes/punctuations.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..ea6d774cf345132b175fedfe5a717c4cd27cc3aa
--- /dev/null
+++ b/tests/expected/punctuations_yes/punctuations.mp3.words.json
@@ -0,0 +1,68 @@
+{
+  "text": " Dis-moi, est-ce que l'avion vole ?",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.38,
+      "end": 2.76,
+      "text": " Dis-moi, est-ce que l'avion vole ?",
+      "tokens": [
+        50364,
+        4208,
+        12,
+        29292,
+        11,
+        871,
+        12,
+        384,
+        631,
+        287,
+        6,
+        706,
+        313,
+        49877,
+        2506,
+        50496
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.26327380012063417,
+      "compression_ratio": 0.8095238095238095,
+      "no_speech_prob": 0.03882359713315964,
+      "confidence": 0.928,
+      "words": [
+        {
+          "text": "Dis-moi,",
+          "start": 0.38,
+          "end": 1.1,
+          "confidence": 0.809
+        },
+        {
+          "text": "est-ce",
+          "start": 1.28,
+          "end": 1.5,
+          "confidence": 0.968
+        },
+        {
+          "text": "que",
+          "start": 1.5,
+          "end": 1.66,
+          "confidence": 0.978
+        },
+        {
+          "text": "l'avion",
+          "start": 1.66,
+          "end": 2.04,
+          "confidence": 0.993
+        },
+        {
+          "text": "vole ?",
+          "start": 2.04,
+          "end": 2.76,
+          "confidence": 0.898
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/punctuations_yes/punctuations.mp3.words.srt b/tests/expected/punctuations_yes/punctuations.mp3.words.srt
new file mode 100644
index 0000000000000000000000000000000000000000..91c0fbf35dff3f5043392a4b6035510d073372d4
--- /dev/null
+++ b/tests/expected/punctuations_yes/punctuations.mp3.words.srt
@@ -0,0 +1,20 @@
+1
+00:00:00,380 --> 00:00:01,100
+Dis-moi,
+
+2
+00:00:01,280 --> 00:00:01,500
+est-ce
+
+3
+00:00:01,500 --> 00:00:01,660
+que
+
+4
+00:00:01,660 --> 00:00:02,040
+l'avion
+
+5
+00:00:02,040 --> 00:00:02,760
+vole ?
+
diff --git a/tests/expected/punctuations_yes/punctuations.mp3.words.tsv b/tests/expected/punctuations_yes/punctuations.mp3.words.tsv
new file mode 100644
index 0000000000000000000000000000000000000000..f267961f36fcab7036a58e7e979625d89df087e4
--- /dev/null
+++ b/tests/expected/punctuations_yes/punctuations.mp3.words.tsv
@@ -0,0 +1,6 @@
+start	end	text
+380	1100	Dis-moi,
+1280	1500	est-ce
+1500	1660	que
+1660	2040	l'avion
+2040	2760	vole ?
diff --git a/tests/expected/punctuations_yes/punctuations.mp3.words.vtt b/tests/expected/punctuations_yes/punctuations.mp3.words.vtt
new file mode 100644
index 0000000000000000000000000000000000000000..0a2cdcec1b994bb7512933594d72181013183838
--- /dev/null
+++ b/tests/expected/punctuations_yes/punctuations.mp3.words.vtt
@@ -0,0 +1,19 @@
+WEBVTT
+
+WEBVTT
+
+00:00.380 --> 00:01.100
+Dis-moi,
+
+00:01.280 --> 00:01.500
+est-ce
+
+00:01.500 --> 00:01.660
+que
+
+00:01.660 --> 00:02.040
+l'avion
+
+00:02.040 --> 00:02.760
+vole ?
+
diff --git a/tests/expected/small.en.cpu/arabic.mp3.words.json b/tests/expected/small.en.cpu/arabic.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..acb72a1674c019af75523e14dc77422914030a68
--- /dev/null
+++ b/tests/expected/small.en.cpu/arabic.mp3.words.json
@@ -0,0 +1,3346 @@
+{
+  "text": " I am the one who is the one who is the one who is the one who is the one who is the one I am the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 1.0,
+      "end": 7.72,
+      "text": " I am the one who is the one who is the one who is the one who is the one who is the one",
+      "tokens": [
+        314,
+        716,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23478534274631077,
+      "compression_ratio": 24.294117647058822,
+      "no_speech_prob": 0.6507940292358398,
+      "confidence": 0.358,
+      "words": [
+        {
+          "text": "I",
+          "start": 1.0,
+          "end": 3.16,
+          "confidence": 0.053
+        },
+        {
+          "text": "am",
+          "start": 3.16,
+          "end": 4.04,
+          "confidence": 0.152
+        },
+        {
+          "text": "the",
+          "start": 4.04,
+          "end": 4.08,
+          "confidence": 0.143
+        },
+        {
+          "text": "one",
+          "start": 4.08,
+          "end": 6.1,
+          "confidence": 0.085
+        },
+        {
+          "text": "who",
+          "start": 6.1,
+          "end": 6.28,
+          "confidence": 0.718
+        },
+        {
+          "text": "is",
+          "start": 6.28,
+          "end": 6.32,
+          "confidence": 0.12
+        },
+        {
+          "text": "the",
+          "start": 6.32,
+          "end": 6.36,
+          "confidence": 0.134
+        },
+        {
+          "text": "one",
+          "start": 6.36,
+          "end": 6.4,
+          "confidence": 0.204
+        },
+        {
+          "text": "who",
+          "start": 6.4,
+          "end": 6.44,
+          "confidence": 0.618
+        },
+        {
+          "text": "is",
+          "start": 6.44,
+          "end": 6.96,
+          "confidence": 0.319
+        },
+        {
+          "text": "the",
+          "start": 6.96,
+          "end": 7.0,
+          "confidence": 0.382
+        },
+        {
+          "text": "one",
+          "start": 7.0,
+          "end": 7.24,
+          "confidence": 0.443
+        },
+        {
+          "text": "who",
+          "start": 7.24,
+          "end": 7.28,
+          "confidence": 0.448
+        },
+        {
+          "text": "is",
+          "start": 7.28,
+          "end": 7.32,
+          "confidence": 0.518
+        },
+        {
+          "text": "the",
+          "start": 7.32,
+          "end": 7.36,
+          "confidence": 0.543
+        },
+        {
+          "text": "one",
+          "start": 7.36,
+          "end": 7.4,
+          "confidence": 0.723
+        },
+        {
+          "text": "who",
+          "start": 7.4,
+          "end": 7.44,
+          "confidence": 0.433
+        },
+        {
+          "text": "is",
+          "start": 7.44,
+          "end": 7.48,
+          "confidence": 0.678
+        },
+        {
+          "text": "the",
+          "start": 7.48,
+          "end": 7.52,
+          "confidence": 0.636
+        },
+        {
+          "text": "one",
+          "start": 7.52,
+          "end": 7.56,
+          "confidence": 0.817
+        },
+        {
+          "text": "who",
+          "start": 7.56,
+          "end": 7.6,
+          "confidence": 0.505
+        },
+        {
+          "text": "is",
+          "start": 7.6,
+          "end": 7.64,
+          "confidence": 0.74
+        },
+        {
+          "text": "the",
+          "start": 7.64,
+          "end": 7.68,
+          "confidence": 0.697
+        },
+        {
+          "text": "one",
+          "start": 7.68,
+          "end": 7.72,
+          "confidence": 0.698
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 700,
+      "start": 7.72,
+      "end": 37.02,
+      "text": " I am the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the",
+      "tokens": [
+        50363,
+        314,
+        716,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.06210707770453559,
+      "compression_ratio": 24.5,
+      "no_speech_prob": 3.115955405519344e-05,
+      "confidence": 0.939,
+      "words": [
+        {
+          "text": "I",
+          "start": 7.72,
+          "end": 9.42,
+          "confidence": 0.22
+        },
+        {
+          "text": "am",
+          "start": 9.42,
+          "end": 12.1,
+          "confidence": 0.81
+        },
+        {
+          "text": "the",
+          "start": 12.1,
+          "end": 12.48,
+          "confidence": 0.872
+        },
+        {
+          "text": "one",
+          "start": 12.48,
+          "end": 12.58,
+          "confidence": 0.927
+        },
+        {
+          "text": "who",
+          "start": 12.58,
+          "end": 13.4,
+          "confidence": 0.966
+        },
+        {
+          "text": "is",
+          "start": 13.4,
+          "end": 13.96,
+          "confidence": 0.934
+        },
+        {
+          "text": "the",
+          "start": 13.96,
+          "end": 14.56,
+          "confidence": 0.968
+        },
+        {
+          "text": "one",
+          "start": 14.56,
+          "end": 14.6,
+          "confidence": 0.989
+        },
+        {
+          "text": "who",
+          "start": 14.6,
+          "end": 14.64,
+          "confidence": 0.951
+        },
+        {
+          "text": "is",
+          "start": 14.64,
+          "end": 14.68,
+          "confidence": 0.965
+        },
+        {
+          "text": "the",
+          "start": 14.68,
+          "end": 15.04,
+          "confidence": 0.977
+        },
+        {
+          "text": "one",
+          "start": 15.04,
+          "end": 17.78,
+          "confidence": 0.993
+        },
+        {
+          "text": "who",
+          "start": 17.78,
+          "end": 17.82,
+          "confidence": 0.843
+        },
+        {
+          "text": "is",
+          "start": 17.82,
+          "end": 18.58,
+          "confidence": 0.977
+        },
+        {
+          "text": "the",
+          "start": 18.58,
+          "end": 18.62,
+          "confidence": 0.979
+        },
+        {
+          "text": "one",
+          "start": 18.62,
+          "end": 18.66,
+          "confidence": 0.991
+        },
+        {
+          "text": "who",
+          "start": 18.66,
+          "end": 19.46,
+          "confidence": 0.694
+        },
+        {
+          "text": "is",
+          "start": 19.46,
+          "end": 20.9,
+          "confidence": 0.979
+        },
+        {
+          "text": "the",
+          "start": 20.9,
+          "end": 20.94,
+          "confidence": 0.978
+        },
+        {
+          "text": "one",
+          "start": 20.94,
+          "end": 20.98,
+          "confidence": 0.99
+        },
+        {
+          "text": "who",
+          "start": 20.98,
+          "end": 21.02,
+          "confidence": 0.657
+        },
+        {
+          "text": "is",
+          "start": 21.02,
+          "end": 21.06,
+          "confidence": 0.977
+        },
+        {
+          "text": "the",
+          "start": 21.06,
+          "end": 21.52,
+          "confidence": 0.974
+        },
+        {
+          "text": "one",
+          "start": 21.52,
+          "end": 21.56,
+          "confidence": 0.983
+        },
+        {
+          "text": "who",
+          "start": 21.56,
+          "end": 21.6,
+          "confidence": 0.609
+        },
+        {
+          "text": "is",
+          "start": 21.6,
+          "end": 22.04,
+          "confidence": 0.978
+        },
+        {
+          "text": "the",
+          "start": 22.04,
+          "end": 22.5,
+          "confidence": 0.966
+        },
+        {
+          "text": "one",
+          "start": 22.5,
+          "end": 23.6,
+          "confidence": 0.986
+        },
+        {
+          "text": "who",
+          "start": 23.6,
+          "end": 24.76,
+          "confidence": 0.624
+        },
+        {
+          "text": "is",
+          "start": 24.76,
+          "end": 26.18,
+          "confidence": 0.978
+        },
+        {
+          "text": "the",
+          "start": 26.18,
+          "end": 26.8,
+          "confidence": 0.962
+        },
+        {
+          "text": "one",
+          "start": 26.8,
+          "end": 26.84,
+          "confidence": 0.984
+        },
+        {
+          "text": "who",
+          "start": 26.84,
+          "end": 26.88,
+          "confidence": 0.679
+        },
+        {
+          "text": "is",
+          "start": 26.88,
+          "end": 27.4,
+          "confidence": 0.978
+        },
+        {
+          "text": "the",
+          "start": 27.4,
+          "end": 28.14,
+          "confidence": 0.958
+        },
+        {
+          "text": "one",
+          "start": 28.14,
+          "end": 28.28,
+          "confidence": 0.98
+        },
+        {
+          "text": "who",
+          "start": 28.28,
+          "end": 28.32,
+          "confidence": 0.671
+        },
+        {
+          "text": "is",
+          "start": 28.32,
+          "end": 28.36,
+          "confidence": 0.979
+        },
+        {
+          "text": "the",
+          "start": 28.36,
+          "end": 28.4,
+          "confidence": 0.955
+        },
+        {
+          "text": "one",
+          "start": 28.4,
+          "end": 28.8,
+          "confidence": 0.975
+        },
+        {
+          "text": "who",
+          "start": 28.8,
+          "end": 29.14,
+          "confidence": 0.683
+        },
+        {
+          "text": "is",
+          "start": 29.14,
+          "end": 29.18,
+          "confidence": 0.978
+        },
+        {
+          "text": "the",
+          "start": 29.18,
+          "end": 29.22,
+          "confidence": 0.956
+        },
+        {
+          "text": "one",
+          "start": 29.22,
+          "end": 29.56,
+          "confidence": 0.972
+        },
+        {
+          "text": "who",
+          "start": 29.56,
+          "end": 29.74,
+          "confidence": 0.695
+        },
+        {
+          "text": "is",
+          "start": 29.74,
+          "end": 29.78,
+          "confidence": 0.978
+        },
+        {
+          "text": "the",
+          "start": 29.78,
+          "end": 29.82,
+          "confidence": 0.957
+        },
+        {
+          "text": "one",
+          "start": 29.82,
+          "end": 29.86,
+          "confidence": 0.971
+        },
+        {
+          "text": "who",
+          "start": 29.86,
+          "end": 29.9,
+          "confidence": 0.713
+        },
+        {
+          "text": "is",
+          "start": 29.9,
+          "end": 29.94,
+          "confidence": 0.98
+        },
+        {
+          "text": "the",
+          "start": 29.94,
+          "end": 29.98,
+          "confidence": 0.958
+        },
+        {
+          "text": "one",
+          "start": 29.98,
+          "end": 30.02,
+          "confidence": 0.971
+        },
+        {
+          "text": "who",
+          "start": 30.02,
+          "end": 30.06,
+          "confidence": 0.737
+        },
+        {
+          "text": "is",
+          "start": 30.06,
+          "end": 30.1,
+          "confidence": 0.982
+        },
+        {
+          "text": "the",
+          "start": 30.1,
+          "end": 30.14,
+          "confidence": 0.96
+        },
+        {
+          "text": "one",
+          "start": 30.14,
+          "end": 30.18,
+          "confidence": 0.971
+        },
+        {
+          "text": "who",
+          "start": 30.18,
+          "end": 30.22,
+          "confidence": 0.754
+        },
+        {
+          "text": "is",
+          "start": 30.22,
+          "end": 30.26,
+          "confidence": 0.984
+        },
+        {
+          "text": "the",
+          "start": 30.26,
+          "end": 30.3,
+          "confidence": 0.962
+        },
+        {
+          "text": "one",
+          "start": 30.3,
+          "end": 30.34,
+          "confidence": 0.973
+        },
+        {
+          "text": "who",
+          "start": 30.34,
+          "end": 30.38,
+          "confidence": 0.759
+        },
+        {
+          "text": "is",
+          "start": 30.38,
+          "end": 30.42,
+          "confidence": 0.986
+        },
+        {
+          "text": "the",
+          "start": 30.42,
+          "end": 30.46,
+          "confidence": 0.964
+        },
+        {
+          "text": "one",
+          "start": 30.46,
+          "end": 30.5,
+          "confidence": 0.974
+        },
+        {
+          "text": "who",
+          "start": 30.5,
+          "end": 30.54,
+          "confidence": 0.765
+        },
+        {
+          "text": "is",
+          "start": 30.54,
+          "end": 30.58,
+          "confidence": 0.987
+        },
+        {
+          "text": "the",
+          "start": 30.58,
+          "end": 30.62,
+          "confidence": 0.966
+        },
+        {
+          "text": "one",
+          "start": 30.62,
+          "end": 30.66,
+          "confidence": 0.975
+        },
+        {
+          "text": "who",
+          "start": 30.66,
+          "end": 30.7,
+          "confidence": 0.774
+        },
+        {
+          "text": "is",
+          "start": 30.7,
+          "end": 30.74,
+          "confidence": 0.988
+        },
+        {
+          "text": "the",
+          "start": 30.74,
+          "end": 30.78,
+          "confidence": 0.969
+        },
+        {
+          "text": "one",
+          "start": 30.78,
+          "end": 30.82,
+          "confidence": 0.975
+        },
+        {
+          "text": "who",
+          "start": 30.82,
+          "end": 30.86,
+          "confidence": 0.801
+        },
+        {
+          "text": "is",
+          "start": 30.86,
+          "end": 30.9,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 30.9,
+          "end": 30.94,
+          "confidence": 0.97
+        },
+        {
+          "text": "one",
+          "start": 30.94,
+          "end": 30.98,
+          "confidence": 0.976
+        },
+        {
+          "text": "who",
+          "start": 30.98,
+          "end": 31.02,
+          "confidence": 0.818
+        },
+        {
+          "text": "is",
+          "start": 31.02,
+          "end": 31.06,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 31.06,
+          "end": 31.1,
+          "confidence": 0.972
+        },
+        {
+          "text": "one",
+          "start": 31.1,
+          "end": 31.14,
+          "confidence": 0.977
+        },
+        {
+          "text": "who",
+          "start": 31.14,
+          "end": 31.18,
+          "confidence": 0.838
+        },
+        {
+          "text": "is",
+          "start": 31.18,
+          "end": 31.22,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 31.22,
+          "end": 31.26,
+          "confidence": 0.973
+        },
+        {
+          "text": "one",
+          "start": 31.26,
+          "end": 31.3,
+          "confidence": 0.977
+        },
+        {
+          "text": "who",
+          "start": 31.3,
+          "end": 31.34,
+          "confidence": 0.862
+        },
+        {
+          "text": "is",
+          "start": 31.34,
+          "end": 31.38,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 31.38,
+          "end": 31.42,
+          "confidence": 0.974
+        },
+        {
+          "text": "one",
+          "start": 31.42,
+          "end": 31.46,
+          "confidence": 0.977
+        },
+        {
+          "text": "who",
+          "start": 31.46,
+          "end": 31.5,
+          "confidence": 0.882
+        },
+        {
+          "text": "is",
+          "start": 31.5,
+          "end": 31.54,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 31.54,
+          "end": 31.58,
+          "confidence": 0.974
+        },
+        {
+          "text": "one",
+          "start": 31.58,
+          "end": 31.62,
+          "confidence": 0.977
+        },
+        {
+          "text": "who",
+          "start": 31.62,
+          "end": 31.66,
+          "confidence": 0.895
+        },
+        {
+          "text": "is",
+          "start": 31.66,
+          "end": 31.7,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 31.7,
+          "end": 31.74,
+          "confidence": 0.975
+        },
+        {
+          "text": "one",
+          "start": 31.74,
+          "end": 31.78,
+          "confidence": 0.977
+        },
+        {
+          "text": "who",
+          "start": 31.78,
+          "end": 31.82,
+          "confidence": 0.905
+        },
+        {
+          "text": "is",
+          "start": 31.82,
+          "end": 31.86,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 31.86,
+          "end": 31.9,
+          "confidence": 0.975
+        },
+        {
+          "text": "one",
+          "start": 31.9,
+          "end": 31.94,
+          "confidence": 0.977
+        },
+        {
+          "text": "who",
+          "start": 31.94,
+          "end": 31.98,
+          "confidence": 0.92
+        },
+        {
+          "text": "is",
+          "start": 31.98,
+          "end": 32.02,
+          "confidence": 0.99
+        },
+        {
+          "text": "the",
+          "start": 32.02,
+          "end": 32.06,
+          "confidence": 0.976
+        },
+        {
+          "text": "one",
+          "start": 32.06,
+          "end": 32.1,
+          "confidence": 0.978
+        },
+        {
+          "text": "who",
+          "start": 32.1,
+          "end": 32.14,
+          "confidence": 0.924
+        },
+        {
+          "text": "is",
+          "start": 32.14,
+          "end": 32.18,
+          "confidence": 0.99
+        },
+        {
+          "text": "the",
+          "start": 32.18,
+          "end": 32.22,
+          "confidence": 0.977
+        },
+        {
+          "text": "one",
+          "start": 32.22,
+          "end": 32.26,
+          "confidence": 0.978
+        },
+        {
+          "text": "who",
+          "start": 32.26,
+          "end": 32.3,
+          "confidence": 0.932
+        },
+        {
+          "text": "is",
+          "start": 32.3,
+          "end": 32.34,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 32.34,
+          "end": 32.38,
+          "confidence": 0.976
+        },
+        {
+          "text": "one",
+          "start": 32.38,
+          "end": 32.42,
+          "confidence": 0.977
+        },
+        {
+          "text": "who",
+          "start": 32.42,
+          "end": 32.46,
+          "confidence": 0.936
+        },
+        {
+          "text": "is",
+          "start": 32.46,
+          "end": 32.5,
+          "confidence": 0.99
+        },
+        {
+          "text": "the",
+          "start": 32.5,
+          "end": 32.54,
+          "confidence": 0.977
+        },
+        {
+          "text": "one",
+          "start": 32.54,
+          "end": 32.58,
+          "confidence": 0.978
+        },
+        {
+          "text": "who",
+          "start": 32.58,
+          "end": 32.62,
+          "confidence": 0.94
+        },
+        {
+          "text": "is",
+          "start": 32.62,
+          "end": 32.66,
+          "confidence": 0.99
+        },
+        {
+          "text": "the",
+          "start": 32.66,
+          "end": 32.7,
+          "confidence": 0.977
+        },
+        {
+          "text": "one",
+          "start": 32.7,
+          "end": 32.74,
+          "confidence": 0.978
+        },
+        {
+          "text": "who",
+          "start": 32.74,
+          "end": 32.78,
+          "confidence": 0.942
+        },
+        {
+          "text": "is",
+          "start": 32.78,
+          "end": 32.82,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 32.82,
+          "end": 32.86,
+          "confidence": 0.977
+        },
+        {
+          "text": "one",
+          "start": 32.86,
+          "end": 32.9,
+          "confidence": 0.978
+        },
+        {
+          "text": "who",
+          "start": 32.9,
+          "end": 32.94,
+          "confidence": 0.941
+        },
+        {
+          "text": "is",
+          "start": 32.94,
+          "end": 32.98,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 32.98,
+          "end": 33.02,
+          "confidence": 0.978
+        },
+        {
+          "text": "one",
+          "start": 33.02,
+          "end": 33.06,
+          "confidence": 0.978
+        },
+        {
+          "text": "who",
+          "start": 33.06,
+          "end": 33.1,
+          "confidence": 0.942
+        },
+        {
+          "text": "is",
+          "start": 33.1,
+          "end": 33.14,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 33.14,
+          "end": 33.18,
+          "confidence": 0.978
+        },
+        {
+          "text": "one",
+          "start": 33.18,
+          "end": 33.22,
+          "confidence": 0.978
+        },
+        {
+          "text": "who",
+          "start": 33.22,
+          "end": 33.26,
+          "confidence": 0.942
+        },
+        {
+          "text": "is",
+          "start": 33.26,
+          "end": 33.3,
+          "confidence": 0.99
+        },
+        {
+          "text": "the",
+          "start": 33.3,
+          "end": 33.34,
+          "confidence": 0.978
+        },
+        {
+          "text": "one",
+          "start": 33.34,
+          "end": 33.38,
+          "confidence": 0.978
+        },
+        {
+          "text": "who",
+          "start": 33.38,
+          "end": 33.42,
+          "confidence": 0.941
+        },
+        {
+          "text": "is",
+          "start": 33.42,
+          "end": 33.46,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 33.46,
+          "end": 33.5,
+          "confidence": 0.979
+        },
+        {
+          "text": "one",
+          "start": 33.5,
+          "end": 33.54,
+          "confidence": 0.977
+        },
+        {
+          "text": "who",
+          "start": 33.54,
+          "end": 33.58,
+          "confidence": 0.941
+        },
+        {
+          "text": "is",
+          "start": 33.58,
+          "end": 33.62,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 33.62,
+          "end": 33.66,
+          "confidence": 0.978
+        },
+        {
+          "text": "one",
+          "start": 33.66,
+          "end": 33.7,
+          "confidence": 0.977
+        },
+        {
+          "text": "who",
+          "start": 33.7,
+          "end": 33.74,
+          "confidence": 0.939
+        },
+        {
+          "text": "is",
+          "start": 33.74,
+          "end": 33.78,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 33.78,
+          "end": 33.82,
+          "confidence": 0.979
+        },
+        {
+          "text": "one",
+          "start": 33.82,
+          "end": 33.86,
+          "confidence": 0.977
+        },
+        {
+          "text": "who",
+          "start": 33.86,
+          "end": 33.9,
+          "confidence": 0.939
+        },
+        {
+          "text": "is",
+          "start": 33.9,
+          "end": 33.94,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 33.94,
+          "end": 33.98,
+          "confidence": 0.979
+        },
+        {
+          "text": "one",
+          "start": 33.98,
+          "end": 34.02,
+          "confidence": 0.977
+        },
+        {
+          "text": "who",
+          "start": 34.02,
+          "end": 34.06,
+          "confidence": 0.938
+        },
+        {
+          "text": "is",
+          "start": 34.06,
+          "end": 34.1,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 34.1,
+          "end": 34.14,
+          "confidence": 0.978
+        },
+        {
+          "text": "one",
+          "start": 34.14,
+          "end": 34.18,
+          "confidence": 0.977
+        },
+        {
+          "text": "who",
+          "start": 34.18,
+          "end": 34.22,
+          "confidence": 0.936
+        },
+        {
+          "text": "is",
+          "start": 34.22,
+          "end": 34.26,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 34.26,
+          "end": 34.3,
+          "confidence": 0.978
+        },
+        {
+          "text": "one",
+          "start": 34.3,
+          "end": 34.34,
+          "confidence": 0.977
+        },
+        {
+          "text": "who",
+          "start": 34.34,
+          "end": 34.38,
+          "confidence": 0.936
+        },
+        {
+          "text": "is",
+          "start": 34.38,
+          "end": 34.42,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 34.42,
+          "end": 34.46,
+          "confidence": 0.979
+        },
+        {
+          "text": "one",
+          "start": 34.46,
+          "end": 34.5,
+          "confidence": 0.976
+        },
+        {
+          "text": "who",
+          "start": 34.5,
+          "end": 34.54,
+          "confidence": 0.936
+        },
+        {
+          "text": "is",
+          "start": 34.54,
+          "end": 34.58,
+          "confidence": 0.988
+        },
+        {
+          "text": "the",
+          "start": 34.58,
+          "end": 34.62,
+          "confidence": 0.978
+        },
+        {
+          "text": "one",
+          "start": 34.62,
+          "end": 34.66,
+          "confidence": 0.977
+        },
+        {
+          "text": "who",
+          "start": 34.66,
+          "end": 34.7,
+          "confidence": 0.936
+        },
+        {
+          "text": "is",
+          "start": 34.7,
+          "end": 34.74,
+          "confidence": 0.988
+        },
+        {
+          "text": "the",
+          "start": 34.74,
+          "end": 34.78,
+          "confidence": 0.978
+        },
+        {
+          "text": "one",
+          "start": 34.78,
+          "end": 34.82,
+          "confidence": 0.976
+        },
+        {
+          "text": "who",
+          "start": 34.82,
+          "end": 34.86,
+          "confidence": 0.935
+        },
+        {
+          "text": "is",
+          "start": 34.86,
+          "end": 34.9,
+          "confidence": 0.988
+        },
+        {
+          "text": "the",
+          "start": 34.9,
+          "end": 34.94,
+          "confidence": 0.979
+        },
+        {
+          "text": "one",
+          "start": 34.94,
+          "end": 34.98,
+          "confidence": 0.976
+        },
+        {
+          "text": "who",
+          "start": 34.98,
+          "end": 35.02,
+          "confidence": 0.936
+        },
+        {
+          "text": "is",
+          "start": 35.02,
+          "end": 35.06,
+          "confidence": 0.987
+        },
+        {
+          "text": "the",
+          "start": 35.06,
+          "end": 35.1,
+          "confidence": 0.978
+        },
+        {
+          "text": "one",
+          "start": 35.1,
+          "end": 35.14,
+          "confidence": 0.976
+        },
+        {
+          "text": "who",
+          "start": 35.14,
+          "end": 35.18,
+          "confidence": 0.936
+        },
+        {
+          "text": "is",
+          "start": 35.18,
+          "end": 35.22,
+          "confidence": 0.987
+        },
+        {
+          "text": "the",
+          "start": 35.22,
+          "end": 35.26,
+          "confidence": 0.978
+        },
+        {
+          "text": "one",
+          "start": 35.26,
+          "end": 35.3,
+          "confidence": 0.976
+        },
+        {
+          "text": "who",
+          "start": 35.3,
+          "end": 35.34,
+          "confidence": 0.935
+        },
+        {
+          "text": "is",
+          "start": 35.34,
+          "end": 35.38,
+          "confidence": 0.987
+        },
+        {
+          "text": "the",
+          "start": 35.38,
+          "end": 35.42,
+          "confidence": 0.977
+        },
+        {
+          "text": "one",
+          "start": 35.42,
+          "end": 35.46,
+          "confidence": 0.976
+        },
+        {
+          "text": "who",
+          "start": 35.46,
+          "end": 35.5,
+          "confidence": 0.934
+        },
+        {
+          "text": "is",
+          "start": 35.5,
+          "end": 35.54,
+          "confidence": 0.986
+        },
+        {
+          "text": "the",
+          "start": 35.54,
+          "end": 35.58,
+          "confidence": 0.977
+        },
+        {
+          "text": "one",
+          "start": 35.58,
+          "end": 35.62,
+          "confidence": 0.976
+        },
+        {
+          "text": "who",
+          "start": 35.62,
+          "end": 35.66,
+          "confidence": 0.933
+        },
+        {
+          "text": "is",
+          "start": 35.66,
+          "end": 35.7,
+          "confidence": 0.985
+        },
+        {
+          "text": "the",
+          "start": 35.7,
+          "end": 35.74,
+          "confidence": 0.977
+        },
+        {
+          "text": "one",
+          "start": 35.74,
+          "end": 35.78,
+          "confidence": 0.974
+        },
+        {
+          "text": "who",
+          "start": 35.78,
+          "end": 35.82,
+          "confidence": 0.939
+        },
+        {
+          "text": "is",
+          "start": 35.82,
+          "end": 35.86,
+          "confidence": 0.986
+        },
+        {
+          "text": "the",
+          "start": 35.86,
+          "end": 35.9,
+          "confidence": 0.977
+        },
+        {
+          "text": "one",
+          "start": 35.9,
+          "end": 35.94,
+          "confidence": 0.975
+        },
+        {
+          "text": "who",
+          "start": 35.94,
+          "end": 35.98,
+          "confidence": 0.932
+        },
+        {
+          "text": "is",
+          "start": 35.98,
+          "end": 36.02,
+          "confidence": 0.984
+        },
+        {
+          "text": "the",
+          "start": 36.02,
+          "end": 36.06,
+          "confidence": 0.976
+        },
+        {
+          "text": "one",
+          "start": 36.06,
+          "end": 36.1,
+          "confidence": 0.975
+        },
+        {
+          "text": "who",
+          "start": 36.1,
+          "end": 36.14,
+          "confidence": 0.931
+        },
+        {
+          "text": "is",
+          "start": 36.14,
+          "end": 36.18,
+          "confidence": 0.984
+        },
+        {
+          "text": "the",
+          "start": 36.18,
+          "end": 36.22,
+          "confidence": 0.976
+        },
+        {
+          "text": "one",
+          "start": 36.22,
+          "end": 36.26,
+          "confidence": 0.975
+        },
+        {
+          "text": "who",
+          "start": 36.26,
+          "end": 36.3,
+          "confidence": 0.929
+        },
+        {
+          "text": "is",
+          "start": 36.3,
+          "end": 36.34,
+          "confidence": 0.983
+        },
+        {
+          "text": "the",
+          "start": 36.34,
+          "end": 36.38,
+          "confidence": 0.975
+        },
+        {
+          "text": "one",
+          "start": 36.38,
+          "end": 36.42,
+          "confidence": 0.975
+        },
+        {
+          "text": "who",
+          "start": 36.42,
+          "end": 36.46,
+          "confidence": 0.929
+        },
+        {
+          "text": "is",
+          "start": 36.46,
+          "end": 36.5,
+          "confidence": 0.982
+        },
+        {
+          "text": "the",
+          "start": 36.5,
+          "end": 36.54,
+          "confidence": 0.974
+        },
+        {
+          "text": "one",
+          "start": 36.54,
+          "end": 36.58,
+          "confidence": 0.975
+        },
+        {
+          "text": "who",
+          "start": 36.58,
+          "end": 36.62,
+          "confidence": 0.928
+        },
+        {
+          "text": "is",
+          "start": 36.62,
+          "end": 36.66,
+          "confidence": 0.982
+        },
+        {
+          "text": "the",
+          "start": 36.66,
+          "end": 36.7,
+          "confidence": 0.974
+        },
+        {
+          "text": "one",
+          "start": 36.7,
+          "end": 36.74,
+          "confidence": 0.975
+        },
+        {
+          "text": "who",
+          "start": 36.74,
+          "end": 36.92,
+          "confidence": 0.928
+        },
+        {
+          "text": "is",
+          "start": 36.92,
+          "end": 36.98,
+          "confidence": 0.981
+        },
+        {
+          "text": "the",
+          "start": 36.98,
+          "end": 37.02,
+          "confidence": 0.973
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 3700,
+      "start": 37.02,
+      "end": 67.0,
+      "text": " one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is",
+      "tokens": [
+        50363,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.017284017139010958,
+      "compression_ratio": 26.93548387096774,
+      "no_speech_prob": 0.09498446434736252,
+      "confidence": 0.983,
+      "words": [
+        {
+          "text": "one",
+          "start": 37.02,
+          "end": 37.4,
+          "confidence": 0.964
+        },
+        {
+          "text": "who",
+          "start": 37.4,
+          "end": 39.86,
+          "confidence": 0.961
+        },
+        {
+          "text": "is",
+          "start": 39.86,
+          "end": 39.9,
+          "confidence": 0.977
+        },
+        {
+          "text": "the",
+          "start": 39.9,
+          "end": 39.94,
+          "confidence": 0.975
+        },
+        {
+          "text": "one",
+          "start": 39.94,
+          "end": 39.98,
+          "confidence": 0.964
+        },
+        {
+          "text": "who",
+          "start": 39.98,
+          "end": 40.02,
+          "confidence": 0.982
+        },
+        {
+          "text": "is",
+          "start": 40.02,
+          "end": 40.06,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 40.06,
+          "end": 40.1,
+          "confidence": 0.978
+        },
+        {
+          "text": "one",
+          "start": 40.1,
+          "end": 40.14,
+          "confidence": 0.98
+        },
+        {
+          "text": "who",
+          "start": 40.14,
+          "end": 40.18,
+          "confidence": 0.989
+        },
+        {
+          "text": "is",
+          "start": 40.18,
+          "end": 40.22,
+          "confidence": 0.992
+        },
+        {
+          "text": "the",
+          "start": 40.22,
+          "end": 40.26,
+          "confidence": 0.97
+        },
+        {
+          "text": "one",
+          "start": 40.26,
+          "end": 40.3,
+          "confidence": 0.982
+        },
+        {
+          "text": "who",
+          "start": 40.3,
+          "end": 40.34,
+          "confidence": 0.989
+        },
+        {
+          "text": "is",
+          "start": 40.34,
+          "end": 40.38,
+          "confidence": 0.993
+        },
+        {
+          "text": "the",
+          "start": 40.38,
+          "end": 40.42,
+          "confidence": 0.971
+        },
+        {
+          "text": "one",
+          "start": 40.42,
+          "end": 40.46,
+          "confidence": 0.984
+        },
+        {
+          "text": "who",
+          "start": 40.46,
+          "end": 40.5,
+          "confidence": 0.99
+        },
+        {
+          "text": "is",
+          "start": 40.5,
+          "end": 40.54,
+          "confidence": 0.994
+        },
+        {
+          "text": "the",
+          "start": 40.54,
+          "end": 40.58,
+          "confidence": 0.969
+        },
+        {
+          "text": "one",
+          "start": 40.58,
+          "end": 40.62,
+          "confidence": 0.985
+        },
+        {
+          "text": "who",
+          "start": 40.62,
+          "end": 40.66,
+          "confidence": 0.989
+        },
+        {
+          "text": "is",
+          "start": 40.66,
+          "end": 40.7,
+          "confidence": 0.991
+        },
+        {
+          "text": "the",
+          "start": 40.7,
+          "end": 40.74,
+          "confidence": 0.625
+        },
+        {
+          "text": "one",
+          "start": 40.74,
+          "end": 40.78,
+          "confidence": 0.947
+        },
+        {
+          "text": "who",
+          "start": 40.78,
+          "end": 40.82,
+          "confidence": 0.985
+        },
+        {
+          "text": "is",
+          "start": 40.82,
+          "end": 40.86,
+          "confidence": 0.99
+        },
+        {
+          "text": "the",
+          "start": 40.86,
+          "end": 40.9,
+          "confidence": 0.91
+        },
+        {
+          "text": "one",
+          "start": 40.9,
+          "end": 40.94,
+          "confidence": 0.984
+        },
+        {
+          "text": "who",
+          "start": 40.94,
+          "end": 40.98,
+          "confidence": 0.986
+        },
+        {
+          "text": "is",
+          "start": 40.98,
+          "end": 41.02,
+          "confidence": 0.994
+        },
+        {
+          "text": "the",
+          "start": 41.02,
+          "end": 41.06,
+          "confidence": 0.933
+        },
+        {
+          "text": "one",
+          "start": 41.06,
+          "end": 41.1,
+          "confidence": 0.985
+        },
+        {
+          "text": "who",
+          "start": 41.1,
+          "end": 41.14,
+          "confidence": 0.988
+        },
+        {
+          "text": "is",
+          "start": 41.14,
+          "end": 41.18,
+          "confidence": 0.996
+        },
+        {
+          "text": "the",
+          "start": 41.18,
+          "end": 41.22,
+          "confidence": 0.948
+        },
+        {
+          "text": "one",
+          "start": 41.22,
+          "end": 41.26,
+          "confidence": 0.987
+        },
+        {
+          "text": "who",
+          "start": 41.26,
+          "end": 41.3,
+          "confidence": 0.989
+        },
+        {
+          "text": "is",
+          "start": 41.3,
+          "end": 41.34,
+          "confidence": 0.997
+        },
+        {
+          "text": "the",
+          "start": 41.34,
+          "end": 41.38,
+          "confidence": 0.961
+        },
+        {
+          "text": "one",
+          "start": 41.38,
+          "end": 41.42,
+          "confidence": 0.988
+        },
+        {
+          "text": "who",
+          "start": 41.42,
+          "end": 41.46,
+          "confidence": 0.99
+        },
+        {
+          "text": "is",
+          "start": 41.46,
+          "end": 41.5,
+          "confidence": 0.997
+        },
+        {
+          "text": "the",
+          "start": 41.5,
+          "end": 41.54,
+          "confidence": 0.969
+        },
+        {
+          "text": "one",
+          "start": 41.54,
+          "end": 41.58,
+          "confidence": 0.989
+        },
+        {
+          "text": "who",
+          "start": 41.58,
+          "end": 41.62,
+          "confidence": 0.99
+        },
+        {
+          "text": "is",
+          "start": 41.62,
+          "end": 41.66,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 41.66,
+          "end": 41.7,
+          "confidence": 0.976
+        },
+        {
+          "text": "one",
+          "start": 41.7,
+          "end": 41.74,
+          "confidence": 0.99
+        },
+        {
+          "text": "who",
+          "start": 41.74,
+          "end": 41.78,
+          "confidence": 0.99
+        },
+        {
+          "text": "is",
+          "start": 41.78,
+          "end": 41.82,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 41.82,
+          "end": 41.86,
+          "confidence": 0.981
+        },
+        {
+          "text": "one",
+          "start": 41.86,
+          "end": 41.9,
+          "confidence": 0.99
+        },
+        {
+          "text": "who",
+          "start": 41.9,
+          "end": 41.94,
+          "confidence": 0.99
+        },
+        {
+          "text": "is",
+          "start": 41.94,
+          "end": 41.98,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 41.98,
+          "end": 42.02,
+          "confidence": 0.984
+        },
+        {
+          "text": "one",
+          "start": 42.02,
+          "end": 42.06,
+          "confidence": 0.991
+        },
+        {
+          "text": "who",
+          "start": 42.06,
+          "end": 42.1,
+          "confidence": 0.99
+        },
+        {
+          "text": "is",
+          "start": 42.1,
+          "end": 42.14,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 42.14,
+          "end": 42.18,
+          "confidence": 0.987
+        },
+        {
+          "text": "one",
+          "start": 42.18,
+          "end": 42.22,
+          "confidence": 0.991
+        },
+        {
+          "text": "who",
+          "start": 42.22,
+          "end": 42.26,
+          "confidence": 0.99
+        },
+        {
+          "text": "is",
+          "start": 42.26,
+          "end": 42.3,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 42.3,
+          "end": 42.34,
+          "confidence": 0.988
+        },
+        {
+          "text": "one",
+          "start": 42.34,
+          "end": 42.38,
+          "confidence": 0.991
+        },
+        {
+          "text": "who",
+          "start": 42.38,
+          "end": 42.42,
+          "confidence": 0.989
+        },
+        {
+          "text": "is",
+          "start": 42.42,
+          "end": 42.46,
+          "confidence": 0.999
+        },
+        {
+          "text": "the",
+          "start": 42.46,
+          "end": 42.5,
+          "confidence": 0.989
+        },
+        {
+          "text": "one",
+          "start": 42.5,
+          "end": 42.54,
+          "confidence": 0.991
+        },
+        {
+          "text": "who",
+          "start": 42.54,
+          "end": 42.58,
+          "confidence": 0.989
+        },
+        {
+          "text": "is",
+          "start": 42.58,
+          "end": 42.62,
+          "confidence": 0.999
+        },
+        {
+          "text": "the",
+          "start": 42.62,
+          "end": 42.66,
+          "confidence": 0.99
+        },
+        {
+          "text": "one",
+          "start": 42.66,
+          "end": 42.7,
+          "confidence": 0.991
+        },
+        {
+          "text": "who",
+          "start": 42.7,
+          "end": 42.74,
+          "confidence": 0.989
+        },
+        {
+          "text": "is",
+          "start": 42.74,
+          "end": 42.78,
+          "confidence": 0.999
+        },
+        {
+          "text": "the",
+          "start": 42.78,
+          "end": 42.82,
+          "confidence": 0.99
+        },
+        {
+          "text": "one",
+          "start": 42.82,
+          "end": 42.86,
+          "confidence": 0.992
+        },
+        {
+          "text": "who",
+          "start": 42.86,
+          "end": 42.9,
+          "confidence": 0.988
+        },
+        {
+          "text": "is",
+          "start": 42.9,
+          "end": 42.94,
+          "confidence": 0.999
+        },
+        {
+          "text": "the",
+          "start": 42.94,
+          "end": 42.98,
+          "confidence": 0.991
+        },
+        {
+          "text": "one",
+          "start": 42.98,
+          "end": 43.02,
+          "confidence": 0.991
+        },
+        {
+          "text": "who",
+          "start": 43.02,
+          "end": 43.06,
+          "confidence": 0.988
+        },
+        {
+          "text": "is",
+          "start": 43.06,
+          "end": 43.1,
+          "confidence": 0.999
+        },
+        {
+          "text": "the",
+          "start": 43.1,
+          "end": 43.14,
+          "confidence": 0.991
+        },
+        {
+          "text": "one",
+          "start": 43.14,
+          "end": 43.18,
+          "confidence": 0.991
+        },
+        {
+          "text": "who",
+          "start": 43.18,
+          "end": 43.22,
+          "confidence": 0.988
+        },
+        {
+          "text": "is",
+          "start": 43.22,
+          "end": 43.26,
+          "confidence": 0.999
+        },
+        {
+          "text": "the",
+          "start": 43.26,
+          "end": 43.3,
+          "confidence": 0.991
+        },
+        {
+          "text": "one",
+          "start": 43.3,
+          "end": 43.34,
+          "confidence": 0.991
+        },
+        {
+          "text": "who",
+          "start": 43.34,
+          "end": 43.38,
+          "confidence": 0.988
+        },
+        {
+          "text": "is",
+          "start": 43.38,
+          "end": 43.42,
+          "confidence": 0.999
+        },
+        {
+          "text": "the",
+          "start": 43.42,
+          "end": 43.46,
+          "confidence": 0.991
+        },
+        {
+          "text": "one",
+          "start": 43.46,
+          "end": 43.5,
+          "confidence": 0.991
+        },
+        {
+          "text": "who",
+          "start": 43.5,
+          "end": 43.54,
+          "confidence": 0.987
+        },
+        {
+          "text": "is",
+          "start": 43.54,
+          "end": 43.58,
+          "confidence": 0.999
+        },
+        {
+          "text": "the",
+          "start": 43.58,
+          "end": 43.62,
+          "confidence": 0.991
+        },
+        {
+          "text": "one",
+          "start": 43.62,
+          "end": 43.66,
+          "confidence": 0.991
+        },
+        {
+          "text": "who",
+          "start": 43.66,
+          "end": 43.7,
+          "confidence": 0.987
+        },
+        {
+          "text": "is",
+          "start": 43.7,
+          "end": 43.74,
+          "confidence": 0.999
+        },
+        {
+          "text": "the",
+          "start": 43.74,
+          "end": 43.78,
+          "confidence": 0.991
+        },
+        {
+          "text": "one",
+          "start": 43.78,
+          "end": 43.82,
+          "confidence": 0.991
+        },
+        {
+          "text": "who",
+          "start": 43.82,
+          "end": 43.86,
+          "confidence": 0.987
+        },
+        {
+          "text": "is",
+          "start": 43.86,
+          "end": 43.9,
+          "confidence": 0.999
+        },
+        {
+          "text": "the",
+          "start": 43.9,
+          "end": 43.94,
+          "confidence": 0.991
+        },
+        {
+          "text": "one",
+          "start": 43.94,
+          "end": 43.98,
+          "confidence": 0.99
+        },
+        {
+          "text": "who",
+          "start": 43.98,
+          "end": 44.02,
+          "confidence": 0.986
+        },
+        {
+          "text": "is",
+          "start": 44.02,
+          "end": 44.06,
+          "confidence": 0.999
+        },
+        {
+          "text": "the",
+          "start": 44.06,
+          "end": 44.1,
+          "confidence": 0.991
+        },
+        {
+          "text": "one",
+          "start": 44.1,
+          "end": 44.14,
+          "confidence": 0.99
+        },
+        {
+          "text": "who",
+          "start": 44.14,
+          "end": 44.18,
+          "confidence": 0.986
+        },
+        {
+          "text": "is",
+          "start": 44.18,
+          "end": 44.22,
+          "confidence": 0.999
+        },
+        {
+          "text": "the",
+          "start": 44.22,
+          "end": 44.26,
+          "confidence": 0.991
+        },
+        {
+          "text": "one",
+          "start": 44.26,
+          "end": 44.3,
+          "confidence": 0.99
+        },
+        {
+          "text": "who",
+          "start": 44.3,
+          "end": 44.34,
+          "confidence": 0.985
+        },
+        {
+          "text": "is",
+          "start": 44.34,
+          "end": 44.38,
+          "confidence": 0.999
+        },
+        {
+          "text": "the",
+          "start": 44.38,
+          "end": 44.42,
+          "confidence": 0.991
+        },
+        {
+          "text": "one",
+          "start": 44.42,
+          "end": 44.46,
+          "confidence": 0.99
+        },
+        {
+          "text": "who",
+          "start": 44.46,
+          "end": 44.5,
+          "confidence": 0.985
+        },
+        {
+          "text": "is",
+          "start": 44.5,
+          "end": 44.54,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 44.54,
+          "end": 44.58,
+          "confidence": 0.991
+        },
+        {
+          "text": "one",
+          "start": 44.58,
+          "end": 44.62,
+          "confidence": 0.989
+        },
+        {
+          "text": "who",
+          "start": 44.62,
+          "end": 44.66,
+          "confidence": 0.984
+        },
+        {
+          "text": "is",
+          "start": 44.66,
+          "end": 44.7,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 44.7,
+          "end": 44.74,
+          "confidence": 0.991
+        },
+        {
+          "text": "one",
+          "start": 44.74,
+          "end": 44.78,
+          "confidence": 0.989
+        },
+        {
+          "text": "who",
+          "start": 44.78,
+          "end": 44.82,
+          "confidence": 0.983
+        },
+        {
+          "text": "is",
+          "start": 44.82,
+          "end": 44.86,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 44.86,
+          "end": 44.9,
+          "confidence": 0.991
+        },
+        {
+          "text": "one",
+          "start": 44.9,
+          "end": 44.94,
+          "confidence": 0.989
+        },
+        {
+          "text": "who",
+          "start": 44.94,
+          "end": 44.98,
+          "confidence": 0.983
+        },
+        {
+          "text": "is",
+          "start": 44.98,
+          "end": 45.02,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 45.02,
+          "end": 45.06,
+          "confidence": 0.991
+        },
+        {
+          "text": "one",
+          "start": 45.06,
+          "end": 45.1,
+          "confidence": 0.988
+        },
+        {
+          "text": "who",
+          "start": 45.1,
+          "end": 45.14,
+          "confidence": 0.982
+        },
+        {
+          "text": "is",
+          "start": 45.14,
+          "end": 45.18,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 45.18,
+          "end": 45.22,
+          "confidence": 0.99
+        },
+        {
+          "text": "one",
+          "start": 45.22,
+          "end": 45.26,
+          "confidence": 0.988
+        },
+        {
+          "text": "who",
+          "start": 45.26,
+          "end": 45.3,
+          "confidence": 0.98
+        },
+        {
+          "text": "is",
+          "start": 45.3,
+          "end": 45.34,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 45.34,
+          "end": 45.38,
+          "confidence": 0.99
+        },
+        {
+          "text": "one",
+          "start": 45.38,
+          "end": 45.42,
+          "confidence": 0.987
+        },
+        {
+          "text": "who",
+          "start": 45.42,
+          "end": 45.46,
+          "confidence": 0.979
+        },
+        {
+          "text": "is",
+          "start": 45.46,
+          "end": 45.5,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 45.5,
+          "end": 45.54,
+          "confidence": 0.99
+        },
+        {
+          "text": "one",
+          "start": 45.54,
+          "end": 45.58,
+          "confidence": 0.987
+        },
+        {
+          "text": "who",
+          "start": 45.58,
+          "end": 45.62,
+          "confidence": 0.978
+        },
+        {
+          "text": "is",
+          "start": 45.62,
+          "end": 45.66,
+          "confidence": 0.997
+        },
+        {
+          "text": "the",
+          "start": 45.66,
+          "end": 45.7,
+          "confidence": 0.99
+        },
+        {
+          "text": "one",
+          "start": 45.7,
+          "end": 45.74,
+          "confidence": 0.986
+        },
+        {
+          "text": "who",
+          "start": 45.74,
+          "end": 45.78,
+          "confidence": 0.976
+        },
+        {
+          "text": "is",
+          "start": 45.78,
+          "end": 45.82,
+          "confidence": 0.997
+        },
+        {
+          "text": "the",
+          "start": 45.82,
+          "end": 45.86,
+          "confidence": 0.989
+        },
+        {
+          "text": "one",
+          "start": 45.86,
+          "end": 45.9,
+          "confidence": 0.986
+        },
+        {
+          "text": "who",
+          "start": 45.9,
+          "end": 45.94,
+          "confidence": 0.976
+        },
+        {
+          "text": "is",
+          "start": 45.94,
+          "end": 45.98,
+          "confidence": 0.997
+        },
+        {
+          "text": "the",
+          "start": 45.98,
+          "end": 46.02,
+          "confidence": 0.989
+        },
+        {
+          "text": "one",
+          "start": 46.02,
+          "end": 46.06,
+          "confidence": 0.986
+        },
+        {
+          "text": "who",
+          "start": 46.06,
+          "end": 46.1,
+          "confidence": 0.974
+        },
+        {
+          "text": "is",
+          "start": 46.1,
+          "end": 46.14,
+          "confidence": 0.997
+        },
+        {
+          "text": "the",
+          "start": 46.14,
+          "end": 46.18,
+          "confidence": 0.989
+        },
+        {
+          "text": "one",
+          "start": 46.18,
+          "end": 46.22,
+          "confidence": 0.985
+        },
+        {
+          "text": "who",
+          "start": 46.22,
+          "end": 46.26,
+          "confidence": 0.972
+        },
+        {
+          "text": "is",
+          "start": 46.26,
+          "end": 46.3,
+          "confidence": 0.996
+        },
+        {
+          "text": "the",
+          "start": 46.3,
+          "end": 46.34,
+          "confidence": 0.988
+        },
+        {
+          "text": "one",
+          "start": 46.34,
+          "end": 46.38,
+          "confidence": 0.984
+        },
+        {
+          "text": "who",
+          "start": 46.38,
+          "end": 46.42,
+          "confidence": 0.971
+        },
+        {
+          "text": "is",
+          "start": 46.42,
+          "end": 46.46,
+          "confidence": 0.996
+        },
+        {
+          "text": "the",
+          "start": 46.46,
+          "end": 46.5,
+          "confidence": 0.988
+        },
+        {
+          "text": "one",
+          "start": 46.5,
+          "end": 46.54,
+          "confidence": 0.984
+        },
+        {
+          "text": "who",
+          "start": 46.54,
+          "end": 46.58,
+          "confidence": 0.97
+        },
+        {
+          "text": "is",
+          "start": 46.58,
+          "end": 46.62,
+          "confidence": 0.996
+        },
+        {
+          "text": "the",
+          "start": 46.62,
+          "end": 46.66,
+          "confidence": 0.987
+        },
+        {
+          "text": "one",
+          "start": 46.66,
+          "end": 46.7,
+          "confidence": 0.984
+        },
+        {
+          "text": "who",
+          "start": 46.7,
+          "end": 46.74,
+          "confidence": 0.968
+        },
+        {
+          "text": "is",
+          "start": 46.74,
+          "end": 46.78,
+          "confidence": 0.995
+        },
+        {
+          "text": "the",
+          "start": 46.78,
+          "end": 46.82,
+          "confidence": 0.987
+        },
+        {
+          "text": "one",
+          "start": 46.82,
+          "end": 46.86,
+          "confidence": 0.983
+        },
+        {
+          "text": "who",
+          "start": 46.86,
+          "end": 46.9,
+          "confidence": 0.966
+        },
+        {
+          "text": "is",
+          "start": 46.9,
+          "end": 46.94,
+          "confidence": 0.995
+        },
+        {
+          "text": "the",
+          "start": 46.94,
+          "end": 46.98,
+          "confidence": 0.986
+        },
+        {
+          "text": "one",
+          "start": 46.98,
+          "end": 47.02,
+          "confidence": 0.982
+        },
+        {
+          "text": "who",
+          "start": 47.02,
+          "end": 47.06,
+          "confidence": 0.964
+        },
+        {
+          "text": "is",
+          "start": 47.06,
+          "end": 47.1,
+          "confidence": 0.995
+        },
+        {
+          "text": "the",
+          "start": 47.1,
+          "end": 47.14,
+          "confidence": 0.986
+        },
+        {
+          "text": "one",
+          "start": 47.14,
+          "end": 47.18,
+          "confidence": 0.982
+        },
+        {
+          "text": "who",
+          "start": 47.18,
+          "end": 47.22,
+          "confidence": 0.963
+        },
+        {
+          "text": "is",
+          "start": 47.22,
+          "end": 47.26,
+          "confidence": 0.994
+        },
+        {
+          "text": "the",
+          "start": 47.26,
+          "end": 47.3,
+          "confidence": 0.985
+        },
+        {
+          "text": "one",
+          "start": 47.3,
+          "end": 47.34,
+          "confidence": 0.981
+        },
+        {
+          "text": "who",
+          "start": 47.34,
+          "end": 47.38,
+          "confidence": 0.959
+        },
+        {
+          "text": "is",
+          "start": 47.38,
+          "end": 47.42,
+          "confidence": 0.993
+        },
+        {
+          "text": "the",
+          "start": 47.42,
+          "end": 47.46,
+          "confidence": 0.984
+        },
+        {
+          "text": "one",
+          "start": 47.46,
+          "end": 47.5,
+          "confidence": 0.98
+        },
+        {
+          "text": "who",
+          "start": 47.5,
+          "end": 47.54,
+          "confidence": 0.958
+        },
+        {
+          "text": "is",
+          "start": 47.54,
+          "end": 47.58,
+          "confidence": 0.993
+        },
+        {
+          "text": "the",
+          "start": 47.58,
+          "end": 47.62,
+          "confidence": 0.983
+        },
+        {
+          "text": "one",
+          "start": 47.62,
+          "end": 47.66,
+          "confidence": 0.979
+        },
+        {
+          "text": "who",
+          "start": 47.66,
+          "end": 47.7,
+          "confidence": 0.955
+        },
+        {
+          "text": "is",
+          "start": 47.7,
+          "end": 47.74,
+          "confidence": 0.993
+        },
+        {
+          "text": "the",
+          "start": 47.74,
+          "end": 47.78,
+          "confidence": 0.982
+        },
+        {
+          "text": "one",
+          "start": 47.78,
+          "end": 47.82,
+          "confidence": 0.979
+        },
+        {
+          "text": "who",
+          "start": 47.82,
+          "end": 47.86,
+          "confidence": 0.953
+        },
+        {
+          "text": "is",
+          "start": 47.86,
+          "end": 47.9,
+          "confidence": 0.992
+        },
+        {
+          "text": "the",
+          "start": 47.9,
+          "end": 47.94,
+          "confidence": 0.982
+        },
+        {
+          "text": "one",
+          "start": 47.94,
+          "end": 47.98,
+          "confidence": 0.978
+        },
+        {
+          "text": "who",
+          "start": 47.98,
+          "end": 48.02,
+          "confidence": 0.952
+        },
+        {
+          "text": "is",
+          "start": 48.02,
+          "end": 48.06,
+          "confidence": 0.992
+        },
+        {
+          "text": "the",
+          "start": 48.06,
+          "end": 48.1,
+          "confidence": 0.981
+        },
+        {
+          "text": "one",
+          "start": 48.1,
+          "end": 48.14,
+          "confidence": 0.976
+        },
+        {
+          "text": "who",
+          "start": 48.14,
+          "end": 48.18,
+          "confidence": 0.95
+        },
+        {
+          "text": "is",
+          "start": 48.18,
+          "end": 48.22,
+          "confidence": 0.991
+        },
+        {
+          "text": "the",
+          "start": 48.22,
+          "end": 48.26,
+          "confidence": 0.98
+        },
+        {
+          "text": "one",
+          "start": 48.26,
+          "end": 48.3,
+          "confidence": 0.976
+        },
+        {
+          "text": "who",
+          "start": 48.3,
+          "end": 48.34,
+          "confidence": 0.949
+        },
+        {
+          "text": "is",
+          "start": 48.34,
+          "end": 48.38,
+          "confidence": 0.991
+        },
+        {
+          "text": "the",
+          "start": 48.38,
+          "end": 48.42,
+          "confidence": 0.979
+        },
+        {
+          "text": "one",
+          "start": 48.42,
+          "end": 48.46,
+          "confidence": 0.976
+        },
+        {
+          "text": "who",
+          "start": 48.46,
+          "end": 48.5,
+          "confidence": 0.944
+        },
+        {
+          "text": "is",
+          "start": 48.5,
+          "end": 48.54,
+          "confidence": 0.99
+        },
+        {
+          "text": "the",
+          "start": 48.54,
+          "end": 48.58,
+          "confidence": 0.979
+        },
+        {
+          "text": "one",
+          "start": 48.58,
+          "end": 48.62,
+          "confidence": 0.975
+        },
+        {
+          "text": "who",
+          "start": 48.62,
+          "end": 48.66,
+          "confidence": 0.945
+        },
+        {
+          "text": "is",
+          "start": 48.66,
+          "end": 67.0,
+          "confidence": 0.99
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/small.en/arabic.mp3.words.json b/tests/expected/small.en/arabic.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..190e702c32876986132ac46515c9177cad2b5b22
--- /dev/null
+++ b/tests/expected/small.en/arabic.mp3.words.json
@@ -0,0 +1,3348 @@
+{
+  "text": " I am the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 2.92,
+      "end": 7.72,
+      "text": " I am the one who is the one who is the one who is the one who is the one who is the one",
+      "tokens": [
+        50363,
+        314,
+        716,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        50713
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.2332169426812066,
+      "compression_ratio": 24.294117647058822,
+      "no_speech_prob": 0.6509259939193726,
+      "confidence": 0.358,
+      "words": [
+        {
+          "text": "I",
+          "start": 2.92,
+          "end": 3.16,
+          "confidence": 0.053
+        },
+        {
+          "text": "am",
+          "start": 3.16,
+          "end": 4.04,
+          "confidence": 0.152
+        },
+        {
+          "text": "the",
+          "start": 4.04,
+          "end": 5.44,
+          "confidence": 0.144
+        },
+        {
+          "text": "one",
+          "start": 5.44,
+          "end": 6.1,
+          "confidence": 0.086
+        },
+        {
+          "text": "who",
+          "start": 6.1,
+          "end": 6.18,
+          "confidence": 0.718
+        },
+        {
+          "text": "is",
+          "start": 6.18,
+          "end": 6.22,
+          "confidence": 0.119
+        },
+        {
+          "text": "the",
+          "start": 6.22,
+          "end": 6.24,
+          "confidence": 0.134
+        },
+        {
+          "text": "one",
+          "start": 6.24,
+          "end": 6.72,
+          "confidence": 0.203
+        },
+        {
+          "text": "who",
+          "start": 6.72,
+          "end": 6.74,
+          "confidence": 0.618
+        },
+        {
+          "text": "is",
+          "start": 6.74,
+          "end": 7.18,
+          "confidence": 0.319
+        },
+        {
+          "text": "the",
+          "start": 7.18,
+          "end": 7.2,
+          "confidence": 0.38
+        },
+        {
+          "text": "one",
+          "start": 7.2,
+          "end": 7.48,
+          "confidence": 0.443
+        },
+        {
+          "text": "who",
+          "start": 7.48,
+          "end": 7.5,
+          "confidence": 0.447
+        },
+        {
+          "text": "is",
+          "start": 7.5,
+          "end": 7.52,
+          "confidence": 0.518
+        },
+        {
+          "text": "the",
+          "start": 7.52,
+          "end": 7.54,
+          "confidence": 0.542
+        },
+        {
+          "text": "one",
+          "start": 7.54,
+          "end": 7.56,
+          "confidence": 0.724
+        },
+        {
+          "text": "who",
+          "start": 7.56,
+          "end": 7.58,
+          "confidence": 0.433
+        },
+        {
+          "text": "is",
+          "start": 7.58,
+          "end": 7.6,
+          "confidence": 0.677
+        },
+        {
+          "text": "the",
+          "start": 7.6,
+          "end": 7.62,
+          "confidence": 0.638
+        },
+        {
+          "text": "one",
+          "start": 7.62,
+          "end": 7.64,
+          "confidence": 0.817
+        },
+        {
+          "text": "who",
+          "start": 7.64,
+          "end": 7.66,
+          "confidence": 0.504
+        },
+        {
+          "text": "is",
+          "start": 7.66,
+          "end": 7.68,
+          "confidence": 0.74
+        },
+        {
+          "text": "the",
+          "start": 7.68,
+          "end": 7.7,
+          "confidence": 0.696
+        },
+        {
+          "text": "one",
+          "start": 7.7,
+          "end": 7.72,
+          "confidence": 0.697
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 700,
+      "start": 7.72,
+      "end": 37.18,
+      "text": " who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the",
+      "tokens": [
+        50363,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.07849001566569011,
+      "compression_ratio": 26.93548387096774,
+      "no_speech_prob": 0.6889318823814392,
+      "confidence": 0.925,
+      "words": [
+        {
+          "text": "who",
+          "start": 7.72,
+          "end": 7.74,
+          "confidence": 0.214
+        },
+        {
+          "text": "is",
+          "start": 7.74,
+          "end": 7.76,
+          "confidence": 0.892
+        },
+        {
+          "text": "the",
+          "start": 7.76,
+          "end": 7.78,
+          "confidence": 0.918
+        },
+        {
+          "text": "one",
+          "start": 7.78,
+          "end": 9.96,
+          "confidence": 0.955
+        },
+        {
+          "text": "who",
+          "start": 9.96,
+          "end": 13.46,
+          "confidence": 0.905
+        },
+        {
+          "text": "is",
+          "start": 13.46,
+          "end": 14.0,
+          "confidence": 0.908
+        },
+        {
+          "text": "the",
+          "start": 14.0,
+          "end": 14.38,
+          "confidence": 0.942
+        },
+        {
+          "text": "one",
+          "start": 14.38,
+          "end": 14.4,
+          "confidence": 0.977
+        },
+        {
+          "text": "who",
+          "start": 14.4,
+          "end": 14.42,
+          "confidence": 0.759
+        },
+        {
+          "text": "is",
+          "start": 14.42,
+          "end": 14.44,
+          "confidence": 0.932
+        },
+        {
+          "text": "the",
+          "start": 14.44,
+          "end": 15.24,
+          "confidence": 0.957
+        },
+        {
+          "text": "one",
+          "start": 15.24,
+          "end": 18.0,
+          "confidence": 0.982
+        },
+        {
+          "text": "who",
+          "start": 18.0,
+          "end": 18.02,
+          "confidence": 0.582
+        },
+        {
+          "text": "is",
+          "start": 18.02,
+          "end": 18.04,
+          "confidence": 0.944
+        },
+        {
+          "text": "the",
+          "start": 18.04,
+          "end": 18.06,
+          "confidence": 0.953
+        },
+        {
+          "text": "one",
+          "start": 18.06,
+          "end": 18.08,
+          "confidence": 0.98
+        },
+        {
+          "text": "who",
+          "start": 18.08,
+          "end": 19.38,
+          "confidence": 0.578
+        },
+        {
+          "text": "is",
+          "start": 19.38,
+          "end": 19.9,
+          "confidence": 0.953
+        },
+        {
+          "text": "the",
+          "start": 19.9,
+          "end": 19.92,
+          "confidence": 0.95
+        },
+        {
+          "text": "one",
+          "start": 19.92,
+          "end": 19.94,
+          "confidence": 0.98
+        },
+        {
+          "text": "who",
+          "start": 19.94,
+          "end": 19.96,
+          "confidence": 0.592
+        },
+        {
+          "text": "is",
+          "start": 19.96,
+          "end": 20.88,
+          "confidence": 0.95
+        },
+        {
+          "text": "the",
+          "start": 20.88,
+          "end": 21.28,
+          "confidence": 0.872
+        },
+        {
+          "text": "one",
+          "start": 21.28,
+          "end": 21.52,
+          "confidence": 0.902
+        },
+        {
+          "text": "who",
+          "start": 21.52,
+          "end": 21.54,
+          "confidence": 0.5
+        },
+        {
+          "text": "is",
+          "start": 21.54,
+          "end": 22.04,
+          "confidence": 0.943
+        },
+        {
+          "text": "the",
+          "start": 22.04,
+          "end": 22.24,
+          "confidence": 0.898
+        },
+        {
+          "text": "one",
+          "start": 22.24,
+          "end": 25.3,
+          "confidence": 0.98
+        },
+        {
+          "text": "who",
+          "start": 25.3,
+          "end": 25.32,
+          "confidence": 0.542
+        },
+        {
+          "text": "is",
+          "start": 25.32,
+          "end": 26.18,
+          "confidence": 0.953
+        },
+        {
+          "text": "the",
+          "start": 26.18,
+          "end": 26.64,
+          "confidence": 0.904
+        },
+        {
+          "text": "one",
+          "start": 26.64,
+          "end": 26.92,
+          "confidence": 0.976
+        },
+        {
+          "text": "who",
+          "start": 26.92,
+          "end": 26.94,
+          "confidence": 0.587
+        },
+        {
+          "text": "is",
+          "start": 26.94,
+          "end": 27.42,
+          "confidence": 0.953
+        },
+        {
+          "text": "the",
+          "start": 27.42,
+          "end": 28.08,
+          "confidence": 0.903
+        },
+        {
+          "text": "one",
+          "start": 28.08,
+          "end": 28.1,
+          "confidence": 0.968
+        },
+        {
+          "text": "who",
+          "start": 28.1,
+          "end": 28.12,
+          "confidence": 0.604
+        },
+        {
+          "text": "is",
+          "start": 28.12,
+          "end": 28.14,
+          "confidence": 0.956
+        },
+        {
+          "text": "the",
+          "start": 28.14,
+          "end": 28.16,
+          "confidence": 0.91
+        },
+        {
+          "text": "one",
+          "start": 28.16,
+          "end": 28.46,
+          "confidence": 0.963
+        },
+        {
+          "text": "who",
+          "start": 28.46,
+          "end": 28.48,
+          "confidence": 0.623
+        },
+        {
+          "text": "is",
+          "start": 28.48,
+          "end": 28.5,
+          "confidence": 0.96
+        },
+        {
+          "text": "the",
+          "start": 28.5,
+          "end": 28.52,
+          "confidence": 0.92
+        },
+        {
+          "text": "one",
+          "start": 28.52,
+          "end": 30.08,
+          "confidence": 0.961
+        },
+        {
+          "text": "who",
+          "start": 30.08,
+          "end": 30.1,
+          "confidence": 0.65
+        },
+        {
+          "text": "is",
+          "start": 30.1,
+          "end": 30.12,
+          "confidence": 0.965
+        },
+        {
+          "text": "the",
+          "start": 30.12,
+          "end": 30.3,
+          "confidence": 0.93
+        },
+        {
+          "text": "one",
+          "start": 30.3,
+          "end": 30.32,
+          "confidence": 0.961
+        },
+        {
+          "text": "who",
+          "start": 30.32,
+          "end": 31.0,
+          "confidence": 0.672
+        },
+        {
+          "text": "is",
+          "start": 31.0,
+          "end": 31.52,
+          "confidence": 0.971
+        },
+        {
+          "text": "the",
+          "start": 31.52,
+          "end": 31.54,
+          "confidence": 0.94
+        },
+        {
+          "text": "one",
+          "start": 31.54,
+          "end": 32.26,
+          "confidence": 0.962
+        },
+        {
+          "text": "who",
+          "start": 32.26,
+          "end": 32.48,
+          "confidence": 0.704
+        },
+        {
+          "text": "is",
+          "start": 32.48,
+          "end": 33.26,
+          "confidence": 0.976
+        },
+        {
+          "text": "the",
+          "start": 33.26,
+          "end": 33.28,
+          "confidence": 0.946
+        },
+        {
+          "text": "one",
+          "start": 33.28,
+          "end": 33.56,
+          "confidence": 0.964
+        },
+        {
+          "text": "who",
+          "start": 33.56,
+          "end": 33.86,
+          "confidence": 0.723
+        },
+        {
+          "text": "is",
+          "start": 33.86,
+          "end": 33.88,
+          "confidence": 0.979
+        },
+        {
+          "text": "the",
+          "start": 33.88,
+          "end": 33.9,
+          "confidence": 0.951
+        },
+        {
+          "text": "one",
+          "start": 33.9,
+          "end": 33.92,
+          "confidence": 0.966
+        },
+        {
+          "text": "who",
+          "start": 33.92,
+          "end": 33.94,
+          "confidence": 0.747
+        },
+        {
+          "text": "is",
+          "start": 33.94,
+          "end": 33.96,
+          "confidence": 0.982
+        },
+        {
+          "text": "the",
+          "start": 33.96,
+          "end": 33.98,
+          "confidence": 0.956
+        },
+        {
+          "text": "one",
+          "start": 33.98,
+          "end": 34.0,
+          "confidence": 0.967
+        },
+        {
+          "text": "who",
+          "start": 34.0,
+          "end": 34.02,
+          "confidence": 0.757
+        },
+        {
+          "text": "is",
+          "start": 34.02,
+          "end": 34.04,
+          "confidence": 0.984
+        },
+        {
+          "text": "the",
+          "start": 34.04,
+          "end": 34.06,
+          "confidence": 0.961
+        },
+        {
+          "text": "one",
+          "start": 34.06,
+          "end": 34.08,
+          "confidence": 0.969
+        },
+        {
+          "text": "who",
+          "start": 34.08,
+          "end": 34.1,
+          "confidence": 0.776
+        },
+        {
+          "text": "is",
+          "start": 34.1,
+          "end": 34.12,
+          "confidence": 0.986
+        },
+        {
+          "text": "the",
+          "start": 34.12,
+          "end": 34.14,
+          "confidence": 0.965
+        },
+        {
+          "text": "one",
+          "start": 34.14,
+          "end": 34.16,
+          "confidence": 0.97
+        },
+        {
+          "text": "who",
+          "start": 34.16,
+          "end": 34.18,
+          "confidence": 0.8
+        },
+        {
+          "text": "is",
+          "start": 34.18,
+          "end": 34.2,
+          "confidence": 0.987
+        },
+        {
+          "text": "the",
+          "start": 34.2,
+          "end": 34.22,
+          "confidence": 0.968
+        },
+        {
+          "text": "one",
+          "start": 34.22,
+          "end": 34.24,
+          "confidence": 0.971
+        },
+        {
+          "text": "who",
+          "start": 34.24,
+          "end": 34.26,
+          "confidence": 0.82
+        },
+        {
+          "text": "is",
+          "start": 34.26,
+          "end": 34.28,
+          "confidence": 0.987
+        },
+        {
+          "text": "the",
+          "start": 34.28,
+          "end": 34.3,
+          "confidence": 0.969
+        },
+        {
+          "text": "one",
+          "start": 34.3,
+          "end": 34.32,
+          "confidence": 0.972
+        },
+        {
+          "text": "who",
+          "start": 34.32,
+          "end": 34.34,
+          "confidence": 0.836
+        },
+        {
+          "text": "is",
+          "start": 34.34,
+          "end": 34.36,
+          "confidence": 0.988
+        },
+        {
+          "text": "the",
+          "start": 34.36,
+          "end": 34.38,
+          "confidence": 0.971
+        },
+        {
+          "text": "one",
+          "start": 34.38,
+          "end": 34.4,
+          "confidence": 0.972
+        },
+        {
+          "text": "who",
+          "start": 34.4,
+          "end": 34.42,
+          "confidence": 0.872
+        },
+        {
+          "text": "is",
+          "start": 34.42,
+          "end": 34.44,
+          "confidence": 0.988
+        },
+        {
+          "text": "the",
+          "start": 34.44,
+          "end": 34.46,
+          "confidence": 0.972
+        },
+        {
+          "text": "one",
+          "start": 34.46,
+          "end": 34.48,
+          "confidence": 0.973
+        },
+        {
+          "text": "who",
+          "start": 34.48,
+          "end": 34.5,
+          "confidence": 0.889
+        },
+        {
+          "text": "is",
+          "start": 34.5,
+          "end": 34.52,
+          "confidence": 0.988
+        },
+        {
+          "text": "the",
+          "start": 34.52,
+          "end": 34.54,
+          "confidence": 0.973
+        },
+        {
+          "text": "one",
+          "start": 34.54,
+          "end": 34.56,
+          "confidence": 0.973
+        },
+        {
+          "text": "who",
+          "start": 34.56,
+          "end": 34.58,
+          "confidence": 0.899
+        },
+        {
+          "text": "is",
+          "start": 34.58,
+          "end": 34.6,
+          "confidence": 0.988
+        },
+        {
+          "text": "the",
+          "start": 34.6,
+          "end": 34.62,
+          "confidence": 0.973
+        },
+        {
+          "text": "one",
+          "start": 34.62,
+          "end": 34.64,
+          "confidence": 0.973
+        },
+        {
+          "text": "who",
+          "start": 34.64,
+          "end": 34.66,
+          "confidence": 0.912
+        },
+        {
+          "text": "is",
+          "start": 34.66,
+          "end": 34.68,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 34.68,
+          "end": 34.7,
+          "confidence": 0.973
+        },
+        {
+          "text": "one",
+          "start": 34.7,
+          "end": 34.72,
+          "confidence": 0.973
+        },
+        {
+          "text": "who",
+          "start": 34.72,
+          "end": 34.74,
+          "confidence": 0.921
+        },
+        {
+          "text": "is",
+          "start": 34.74,
+          "end": 34.76,
+          "confidence": 0.988
+        },
+        {
+          "text": "the",
+          "start": 34.76,
+          "end": 34.78,
+          "confidence": 0.974
+        },
+        {
+          "text": "one",
+          "start": 34.78,
+          "end": 34.8,
+          "confidence": 0.974
+        },
+        {
+          "text": "who",
+          "start": 34.8,
+          "end": 34.82,
+          "confidence": 0.927
+        },
+        {
+          "text": "is",
+          "start": 34.82,
+          "end": 34.84,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 34.84,
+          "end": 34.86,
+          "confidence": 0.974
+        },
+        {
+          "text": "one",
+          "start": 34.86,
+          "end": 34.88,
+          "confidence": 0.974
+        },
+        {
+          "text": "who",
+          "start": 34.88,
+          "end": 34.9,
+          "confidence": 0.935
+        },
+        {
+          "text": "is",
+          "start": 34.9,
+          "end": 34.92,
+          "confidence": 0.988
+        },
+        {
+          "text": "the",
+          "start": 34.92,
+          "end": 34.94,
+          "confidence": 0.974
+        },
+        {
+          "text": "one",
+          "start": 34.94,
+          "end": 34.96,
+          "confidence": 0.974
+        },
+        {
+          "text": "who",
+          "start": 34.96,
+          "end": 34.98,
+          "confidence": 0.934
+        },
+        {
+          "text": "is",
+          "start": 34.98,
+          "end": 35.0,
+          "confidence": 0.988
+        },
+        {
+          "text": "the",
+          "start": 35.0,
+          "end": 35.02,
+          "confidence": 0.975
+        },
+        {
+          "text": "one",
+          "start": 35.02,
+          "end": 35.04,
+          "confidence": 0.974
+        },
+        {
+          "text": "who",
+          "start": 35.04,
+          "end": 35.06,
+          "confidence": 0.937
+        },
+        {
+          "text": "is",
+          "start": 35.06,
+          "end": 35.08,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 35.08,
+          "end": 35.1,
+          "confidence": 0.976
+        },
+        {
+          "text": "one",
+          "start": 35.1,
+          "end": 35.12,
+          "confidence": 0.974
+        },
+        {
+          "text": "who",
+          "start": 35.12,
+          "end": 35.14,
+          "confidence": 0.937
+        },
+        {
+          "text": "is",
+          "start": 35.14,
+          "end": 35.16,
+          "confidence": 0.988
+        },
+        {
+          "text": "the",
+          "start": 35.16,
+          "end": 35.18,
+          "confidence": 0.976
+        },
+        {
+          "text": "one",
+          "start": 35.18,
+          "end": 35.2,
+          "confidence": 0.974
+        },
+        {
+          "text": "who",
+          "start": 35.2,
+          "end": 35.22,
+          "confidence": 0.934
+        },
+        {
+          "text": "is",
+          "start": 35.22,
+          "end": 35.24,
+          "confidence": 0.988
+        },
+        {
+          "text": "the",
+          "start": 35.24,
+          "end": 35.26,
+          "confidence": 0.976
+        },
+        {
+          "text": "one",
+          "start": 35.26,
+          "end": 35.28,
+          "confidence": 0.975
+        },
+        {
+          "text": "who",
+          "start": 35.28,
+          "end": 35.3,
+          "confidence": 0.933
+        },
+        {
+          "text": "is",
+          "start": 35.3,
+          "end": 35.32,
+          "confidence": 0.988
+        },
+        {
+          "text": "the",
+          "start": 35.32,
+          "end": 35.34,
+          "confidence": 0.977
+        },
+        {
+          "text": "one",
+          "start": 35.34,
+          "end": 35.36,
+          "confidence": 0.975
+        },
+        {
+          "text": "who",
+          "start": 35.36,
+          "end": 35.38,
+          "confidence": 0.93
+        },
+        {
+          "text": "is",
+          "start": 35.38,
+          "end": 35.4,
+          "confidence": 0.988
+        },
+        {
+          "text": "the",
+          "start": 35.4,
+          "end": 35.42,
+          "confidence": 0.977
+        },
+        {
+          "text": "one",
+          "start": 35.42,
+          "end": 35.44,
+          "confidence": 0.974
+        },
+        {
+          "text": "who",
+          "start": 35.44,
+          "end": 35.46,
+          "confidence": 0.928
+        },
+        {
+          "text": "is",
+          "start": 35.46,
+          "end": 35.48,
+          "confidence": 0.988
+        },
+        {
+          "text": "the",
+          "start": 35.48,
+          "end": 35.5,
+          "confidence": 0.977
+        },
+        {
+          "text": "one",
+          "start": 35.5,
+          "end": 35.52,
+          "confidence": 0.974
+        },
+        {
+          "text": "who",
+          "start": 35.52,
+          "end": 35.54,
+          "confidence": 0.926
+        },
+        {
+          "text": "is",
+          "start": 35.54,
+          "end": 35.56,
+          "confidence": 0.988
+        },
+        {
+          "text": "the",
+          "start": 35.56,
+          "end": 35.58,
+          "confidence": 0.977
+        },
+        {
+          "text": "one",
+          "start": 35.58,
+          "end": 35.6,
+          "confidence": 0.974
+        },
+        {
+          "text": "who",
+          "start": 35.6,
+          "end": 35.62,
+          "confidence": 0.928
+        },
+        {
+          "text": "is",
+          "start": 35.62,
+          "end": 35.64,
+          "confidence": 0.988
+        },
+        {
+          "text": "the",
+          "start": 35.64,
+          "end": 35.66,
+          "confidence": 0.977
+        },
+        {
+          "text": "one",
+          "start": 35.66,
+          "end": 35.68,
+          "confidence": 0.974
+        },
+        {
+          "text": "who",
+          "start": 35.68,
+          "end": 35.7,
+          "confidence": 0.926
+        },
+        {
+          "text": "is",
+          "start": 35.7,
+          "end": 35.72,
+          "confidence": 0.988
+        },
+        {
+          "text": "the",
+          "start": 35.72,
+          "end": 35.74,
+          "confidence": 0.978
+        },
+        {
+          "text": "one",
+          "start": 35.74,
+          "end": 35.76,
+          "confidence": 0.974
+        },
+        {
+          "text": "who",
+          "start": 35.76,
+          "end": 35.78,
+          "confidence": 0.928
+        },
+        {
+          "text": "is",
+          "start": 35.78,
+          "end": 35.8,
+          "confidence": 0.988
+        },
+        {
+          "text": "the",
+          "start": 35.8,
+          "end": 35.82,
+          "confidence": 0.978
+        },
+        {
+          "text": "one",
+          "start": 35.82,
+          "end": 35.84,
+          "confidence": 0.973
+        },
+        {
+          "text": "who",
+          "start": 35.84,
+          "end": 35.86,
+          "confidence": 0.926
+        },
+        {
+          "text": "is",
+          "start": 35.86,
+          "end": 35.88,
+          "confidence": 0.988
+        },
+        {
+          "text": "the",
+          "start": 35.88,
+          "end": 35.9,
+          "confidence": 0.977
+        },
+        {
+          "text": "one",
+          "start": 35.9,
+          "end": 35.92,
+          "confidence": 0.974
+        },
+        {
+          "text": "who",
+          "start": 35.92,
+          "end": 35.94,
+          "confidence": 0.928
+        },
+        {
+          "text": "is",
+          "start": 35.94,
+          "end": 35.96,
+          "confidence": 0.987
+        },
+        {
+          "text": "the",
+          "start": 35.96,
+          "end": 35.98,
+          "confidence": 0.977
+        },
+        {
+          "text": "one",
+          "start": 35.98,
+          "end": 36.0,
+          "confidence": 0.973
+        },
+        {
+          "text": "who",
+          "start": 36.0,
+          "end": 36.02,
+          "confidence": 0.925
+        },
+        {
+          "text": "is",
+          "start": 36.02,
+          "end": 36.04,
+          "confidence": 0.987
+        },
+        {
+          "text": "the",
+          "start": 36.04,
+          "end": 36.06,
+          "confidence": 0.977
+        },
+        {
+          "text": "one",
+          "start": 36.06,
+          "end": 36.08,
+          "confidence": 0.973
+        },
+        {
+          "text": "who",
+          "start": 36.08,
+          "end": 36.1,
+          "confidence": 0.925
+        },
+        {
+          "text": "is",
+          "start": 36.1,
+          "end": 36.12,
+          "confidence": 0.987
+        },
+        {
+          "text": "the",
+          "start": 36.12,
+          "end": 36.14,
+          "confidence": 0.977
+        },
+        {
+          "text": "one",
+          "start": 36.14,
+          "end": 36.16,
+          "confidence": 0.974
+        },
+        {
+          "text": "who",
+          "start": 36.16,
+          "end": 36.18,
+          "confidence": 0.927
+        },
+        {
+          "text": "is",
+          "start": 36.18,
+          "end": 36.2,
+          "confidence": 0.987
+        },
+        {
+          "text": "the",
+          "start": 36.2,
+          "end": 36.22,
+          "confidence": 0.977
+        },
+        {
+          "text": "one",
+          "start": 36.22,
+          "end": 36.24,
+          "confidence": 0.973
+        },
+        {
+          "text": "who",
+          "start": 36.24,
+          "end": 36.26,
+          "confidence": 0.923
+        },
+        {
+          "text": "is",
+          "start": 36.26,
+          "end": 36.28,
+          "confidence": 0.987
+        },
+        {
+          "text": "the",
+          "start": 36.28,
+          "end": 36.3,
+          "confidence": 0.977
+        },
+        {
+          "text": "one",
+          "start": 36.3,
+          "end": 36.32,
+          "confidence": 0.972
+        },
+        {
+          "text": "who",
+          "start": 36.32,
+          "end": 36.34,
+          "confidence": 0.924
+        },
+        {
+          "text": "is",
+          "start": 36.34,
+          "end": 36.36,
+          "confidence": 0.986
+        },
+        {
+          "text": "the",
+          "start": 36.36,
+          "end": 36.38,
+          "confidence": 0.976
+        },
+        {
+          "text": "one",
+          "start": 36.38,
+          "end": 36.4,
+          "confidence": 0.972
+        },
+        {
+          "text": "who",
+          "start": 36.4,
+          "end": 36.42,
+          "confidence": 0.922
+        },
+        {
+          "text": "is",
+          "start": 36.42,
+          "end": 36.44,
+          "confidence": 0.985
+        },
+        {
+          "text": "the",
+          "start": 36.44,
+          "end": 36.46,
+          "confidence": 0.976
+        },
+        {
+          "text": "one",
+          "start": 36.46,
+          "end": 36.48,
+          "confidence": 0.973
+        },
+        {
+          "text": "who",
+          "start": 36.48,
+          "end": 36.5,
+          "confidence": 0.924
+        },
+        {
+          "text": "is",
+          "start": 36.5,
+          "end": 36.52,
+          "confidence": 0.985
+        },
+        {
+          "text": "the",
+          "start": 36.52,
+          "end": 36.54,
+          "confidence": 0.975
+        },
+        {
+          "text": "one",
+          "start": 36.54,
+          "end": 36.56,
+          "confidence": 0.973
+        },
+        {
+          "text": "who",
+          "start": 36.56,
+          "end": 36.58,
+          "confidence": 0.92
+        },
+        {
+          "text": "is",
+          "start": 36.58,
+          "end": 36.6,
+          "confidence": 0.983
+        },
+        {
+          "text": "the",
+          "start": 36.6,
+          "end": 36.62,
+          "confidence": 0.975
+        },
+        {
+          "text": "one",
+          "start": 36.62,
+          "end": 36.64,
+          "confidence": 0.971
+        },
+        {
+          "text": "who",
+          "start": 36.64,
+          "end": 36.66,
+          "confidence": 0.921
+        },
+        {
+          "text": "is",
+          "start": 36.66,
+          "end": 36.68,
+          "confidence": 0.983
+        },
+        {
+          "text": "the",
+          "start": 36.68,
+          "end": 36.7,
+          "confidence": 0.974
+        },
+        {
+          "text": "one",
+          "start": 36.7,
+          "end": 36.72,
+          "confidence": 0.973
+        },
+        {
+          "text": "who",
+          "start": 36.72,
+          "end": 36.74,
+          "confidence": 0.918
+        },
+        {
+          "text": "is",
+          "start": 36.74,
+          "end": 36.76,
+          "confidence": 0.982
+        },
+        {
+          "text": "the",
+          "start": 36.76,
+          "end": 36.78,
+          "confidence": 0.974
+        },
+        {
+          "text": "one",
+          "start": 36.78,
+          "end": 36.8,
+          "confidence": 0.973
+        },
+        {
+          "text": "who",
+          "start": 36.8,
+          "end": 36.82,
+          "confidence": 0.919
+        },
+        {
+          "text": "is",
+          "start": 36.82,
+          "end": 36.84,
+          "confidence": 0.982
+        },
+        {
+          "text": "the",
+          "start": 36.84,
+          "end": 36.86,
+          "confidence": 0.973
+        },
+        {
+          "text": "one",
+          "start": 36.86,
+          "end": 36.88,
+          "confidence": 0.973
+        },
+        {
+          "text": "who",
+          "start": 36.88,
+          "end": 36.9,
+          "confidence": 0.917
+        },
+        {
+          "text": "is",
+          "start": 36.9,
+          "end": 36.92,
+          "confidence": 0.981
+        },
+        {
+          "text": "the",
+          "start": 36.92,
+          "end": 36.94,
+          "confidence": 0.973
+        },
+        {
+          "text": "one",
+          "start": 36.94,
+          "end": 36.96,
+          "confidence": 0.972
+        },
+        {
+          "text": "who",
+          "start": 36.96,
+          "end": 36.98,
+          "confidence": 0.919
+        },
+        {
+          "text": "is",
+          "start": 36.98,
+          "end": 37.0,
+          "confidence": 0.98
+        },
+        {
+          "text": "the",
+          "start": 37.0,
+          "end": 37.02,
+          "confidence": 0.972
+        },
+        {
+          "text": "one",
+          "start": 37.02,
+          "end": 37.04,
+          "confidence": 0.972
+        },
+        {
+          "text": "who",
+          "start": 37.04,
+          "end": 37.06,
+          "confidence": 0.918
+        },
+        {
+          "text": "is",
+          "start": 37.06,
+          "end": 37.08,
+          "confidence": 0.979
+        },
+        {
+          "text": "the",
+          "start": 37.08,
+          "end": 37.1,
+          "confidence": 0.972
+        },
+        {
+          "text": "one",
+          "start": 37.1,
+          "end": 37.12,
+          "confidence": 0.972
+        },
+        {
+          "text": "who",
+          "start": 37.12,
+          "end": 37.14,
+          "confidence": 0.917
+        },
+        {
+          "text": "is",
+          "start": 37.14,
+          "end": 37.16,
+          "confidence": 0.978
+        },
+        {
+          "text": "the",
+          "start": 37.16,
+          "end": 37.18,
+          "confidence": 0.971
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 3700,
+      "start": 37.18,
+      "end": 66.98,
+      "text": " one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is the one who is",
+      "tokens": [
+        50363,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318,
+        262,
+        530,
+        508,
+        318
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.024528507656521266,
+      "compression_ratio": 26.93548387096774,
+      "no_speech_prob": 0.09981618076562881,
+      "confidence": 0.976,
+      "words": [
+        {
+          "text": "one",
+          "start": 37.18,
+          "end": 37.32,
+          "confidence": 0.959
+        },
+        {
+          "text": "who",
+          "start": 37.32,
+          "end": 37.9,
+          "confidence": 0.954
+        },
+        {
+          "text": "is",
+          "start": 37.9,
+          "end": 37.92,
+          "confidence": 0.968
+        },
+        {
+          "text": "the",
+          "start": 37.92,
+          "end": 38.1,
+          "confidence": 0.962
+        },
+        {
+          "text": "one",
+          "start": 38.1,
+          "end": 38.6,
+          "confidence": 0.965
+        },
+        {
+          "text": "who",
+          "start": 38.6,
+          "end": 39.36,
+          "confidence": 0.979
+        },
+        {
+          "text": "is",
+          "start": 39.36,
+          "end": 39.58,
+          "confidence": 0.986
+        },
+        {
+          "text": "the",
+          "start": 39.58,
+          "end": 39.6,
+          "confidence": 0.969
+        },
+        {
+          "text": "one",
+          "start": 39.6,
+          "end": 39.62,
+          "confidence": 0.981
+        },
+        {
+          "text": "who",
+          "start": 39.62,
+          "end": 39.82,
+          "confidence": 0.985
+        },
+        {
+          "text": "is",
+          "start": 39.82,
+          "end": 40.12,
+          "confidence": 0.99
+        },
+        {
+          "text": "the",
+          "start": 40.12,
+          "end": 40.32,
+          "confidence": 0.957
+        },
+        {
+          "text": "one",
+          "start": 40.32,
+          "end": 40.62,
+          "confidence": 0.983
+        },
+        {
+          "text": "who",
+          "start": 40.62,
+          "end": 40.64,
+          "confidence": 0.984
+        },
+        {
+          "text": "is",
+          "start": 40.64,
+          "end": 40.66,
+          "confidence": 0.99
+        },
+        {
+          "text": "the",
+          "start": 40.66,
+          "end": 40.68,
+          "confidence": 0.956
+        },
+        {
+          "text": "one",
+          "start": 40.68,
+          "end": 40.74,
+          "confidence": 0.984
+        },
+        {
+          "text": "who",
+          "start": 40.74,
+          "end": 40.76,
+          "confidence": 0.984
+        },
+        {
+          "text": "is",
+          "start": 40.76,
+          "end": 40.78,
+          "confidence": 0.991
+        },
+        {
+          "text": "the",
+          "start": 40.78,
+          "end": 40.8,
+          "confidence": 0.953
+        },
+        {
+          "text": "one",
+          "start": 40.8,
+          "end": 40.82,
+          "confidence": 0.985
+        },
+        {
+          "text": "who",
+          "start": 40.82,
+          "end": 40.84,
+          "confidence": 0.979
+        },
+        {
+          "text": "is",
+          "start": 40.84,
+          "end": 40.86,
+          "confidence": 0.987
+        },
+        {
+          "text": "the",
+          "start": 40.86,
+          "end": 40.88,
+          "confidence": 0.495
+        },
+        {
+          "text": "one",
+          "start": 40.88,
+          "end": 41.5,
+          "confidence": 0.951
+        },
+        {
+          "text": "who",
+          "start": 41.5,
+          "end": 41.52,
+          "confidence": 0.968
+        },
+        {
+          "text": "is",
+          "start": 41.52,
+          "end": 41.54,
+          "confidence": 0.983
+        },
+        {
+          "text": "the",
+          "start": 41.54,
+          "end": 41.56,
+          "confidence": 0.844
+        },
+        {
+          "text": "one",
+          "start": 41.56,
+          "end": 41.58,
+          "confidence": 0.982
+        },
+        {
+          "text": "who",
+          "start": 41.58,
+          "end": 41.6,
+          "confidence": 0.973
+        },
+        {
+          "text": "is",
+          "start": 41.6,
+          "end": 41.62,
+          "confidence": 0.991
+        },
+        {
+          "text": "the",
+          "start": 41.62,
+          "end": 41.64,
+          "confidence": 0.888
+        },
+        {
+          "text": "one",
+          "start": 41.64,
+          "end": 41.66,
+          "confidence": 0.984
+        },
+        {
+          "text": "who",
+          "start": 41.66,
+          "end": 41.68,
+          "confidence": 0.978
+        },
+        {
+          "text": "is",
+          "start": 41.68,
+          "end": 41.7,
+          "confidence": 0.994
+        },
+        {
+          "text": "the",
+          "start": 41.7,
+          "end": 41.72,
+          "confidence": 0.915
+        },
+        {
+          "text": "one",
+          "start": 41.72,
+          "end": 41.74,
+          "confidence": 0.985
+        },
+        {
+          "text": "who",
+          "start": 41.74,
+          "end": 41.76,
+          "confidence": 0.981
+        },
+        {
+          "text": "is",
+          "start": 41.76,
+          "end": 41.78,
+          "confidence": 0.995
+        },
+        {
+          "text": "the",
+          "start": 41.78,
+          "end": 41.8,
+          "confidence": 0.937
+        },
+        {
+          "text": "one",
+          "start": 41.8,
+          "end": 41.82,
+          "confidence": 0.986
+        },
+        {
+          "text": "who",
+          "start": 41.82,
+          "end": 41.84,
+          "confidence": 0.983
+        },
+        {
+          "text": "is",
+          "start": 41.84,
+          "end": 41.86,
+          "confidence": 0.996
+        },
+        {
+          "text": "the",
+          "start": 41.86,
+          "end": 41.88,
+          "confidence": 0.95
+        },
+        {
+          "text": "one",
+          "start": 41.88,
+          "end": 41.9,
+          "confidence": 0.987
+        },
+        {
+          "text": "who",
+          "start": 41.9,
+          "end": 41.92,
+          "confidence": 0.983
+        },
+        {
+          "text": "is",
+          "start": 41.92,
+          "end": 41.94,
+          "confidence": 0.996
+        },
+        {
+          "text": "the",
+          "start": 41.94,
+          "end": 41.96,
+          "confidence": 0.961
+        },
+        {
+          "text": "one",
+          "start": 41.96,
+          "end": 41.98,
+          "confidence": 0.987
+        },
+        {
+          "text": "who",
+          "start": 41.98,
+          "end": 42.0,
+          "confidence": 0.984
+        },
+        {
+          "text": "is",
+          "start": 42.0,
+          "end": 42.02,
+          "confidence": 0.997
+        },
+        {
+          "text": "the",
+          "start": 42.02,
+          "end": 42.04,
+          "confidence": 0.969
+        },
+        {
+          "text": "one",
+          "start": 42.04,
+          "end": 42.06,
+          "confidence": 0.987
+        },
+        {
+          "text": "who",
+          "start": 42.06,
+          "end": 42.08,
+          "confidence": 0.983
+        },
+        {
+          "text": "is",
+          "start": 42.08,
+          "end": 42.1,
+          "confidence": 0.997
+        },
+        {
+          "text": "the",
+          "start": 42.1,
+          "end": 42.12,
+          "confidence": 0.975
+        },
+        {
+          "text": "one",
+          "start": 42.12,
+          "end": 42.14,
+          "confidence": 0.988
+        },
+        {
+          "text": "who",
+          "start": 42.14,
+          "end": 42.16,
+          "confidence": 0.983
+        },
+        {
+          "text": "is",
+          "start": 42.16,
+          "end": 42.18,
+          "confidence": 0.997
+        },
+        {
+          "text": "the",
+          "start": 42.18,
+          "end": 42.2,
+          "confidence": 0.979
+        },
+        {
+          "text": "one",
+          "start": 42.2,
+          "end": 42.22,
+          "confidence": 0.989
+        },
+        {
+          "text": "who",
+          "start": 42.22,
+          "end": 42.24,
+          "confidence": 0.983
+        },
+        {
+          "text": "is",
+          "start": 42.24,
+          "end": 42.26,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 42.26,
+          "end": 42.28,
+          "confidence": 0.982
+        },
+        {
+          "text": "one",
+          "start": 42.28,
+          "end": 42.3,
+          "confidence": 0.989
+        },
+        {
+          "text": "who",
+          "start": 42.3,
+          "end": 42.32,
+          "confidence": 0.982
+        },
+        {
+          "text": "is",
+          "start": 42.32,
+          "end": 42.34,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 42.34,
+          "end": 42.4,
+          "confidence": 0.983
+        },
+        {
+          "text": "one",
+          "start": 42.4,
+          "end": 42.56,
+          "confidence": 0.989
+        },
+        {
+          "text": "who",
+          "start": 42.56,
+          "end": 42.58,
+          "confidence": 0.982
+        },
+        {
+          "text": "is",
+          "start": 42.58,
+          "end": 42.62,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 42.62,
+          "end": 42.64,
+          "confidence": 0.985
+        },
+        {
+          "text": "one",
+          "start": 42.64,
+          "end": 43.62,
+          "confidence": 0.989
+        },
+        {
+          "text": "who",
+          "start": 43.62,
+          "end": 43.64,
+          "confidence": 0.981
+        },
+        {
+          "text": "is",
+          "start": 43.64,
+          "end": 43.66,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 43.66,
+          "end": 43.68,
+          "confidence": 0.986
+        },
+        {
+          "text": "one",
+          "start": 43.68,
+          "end": 43.7,
+          "confidence": 0.989
+        },
+        {
+          "text": "who",
+          "start": 43.7,
+          "end": 43.72,
+          "confidence": 0.981
+        },
+        {
+          "text": "is",
+          "start": 43.72,
+          "end": 43.74,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 43.74,
+          "end": 43.76,
+          "confidence": 0.987
+        },
+        {
+          "text": "one",
+          "start": 43.76,
+          "end": 44.02,
+          "confidence": 0.989
+        },
+        {
+          "text": "who",
+          "start": 44.02,
+          "end": 44.04,
+          "confidence": 0.981
+        },
+        {
+          "text": "is",
+          "start": 44.04,
+          "end": 44.06,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 44.06,
+          "end": 44.08,
+          "confidence": 0.988
+        },
+        {
+          "text": "one",
+          "start": 44.08,
+          "end": 44.1,
+          "confidence": 0.989
+        },
+        {
+          "text": "who",
+          "start": 44.1,
+          "end": 44.12,
+          "confidence": 0.981
+        },
+        {
+          "text": "is",
+          "start": 44.12,
+          "end": 44.14,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 44.14,
+          "end": 44.16,
+          "confidence": 0.988
+        },
+        {
+          "text": "one",
+          "start": 44.16,
+          "end": 44.18,
+          "confidence": 0.989
+        },
+        {
+          "text": "who",
+          "start": 44.18,
+          "end": 44.2,
+          "confidence": 0.981
+        },
+        {
+          "text": "is",
+          "start": 44.2,
+          "end": 44.22,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 44.22,
+          "end": 44.24,
+          "confidence": 0.988
+        },
+        {
+          "text": "one",
+          "start": 44.24,
+          "end": 44.26,
+          "confidence": 0.989
+        },
+        {
+          "text": "who",
+          "start": 44.26,
+          "end": 44.28,
+          "confidence": 0.98
+        },
+        {
+          "text": "is",
+          "start": 44.28,
+          "end": 44.3,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 44.3,
+          "end": 44.32,
+          "confidence": 0.988
+        },
+        {
+          "text": "one",
+          "start": 44.32,
+          "end": 44.34,
+          "confidence": 0.988
+        },
+        {
+          "text": "who",
+          "start": 44.34,
+          "end": 44.36,
+          "confidence": 0.98
+        },
+        {
+          "text": "is",
+          "start": 44.36,
+          "end": 44.38,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 44.38,
+          "end": 44.4,
+          "confidence": 0.988
+        },
+        {
+          "text": "one",
+          "start": 44.4,
+          "end": 44.42,
+          "confidence": 0.988
+        },
+        {
+          "text": "who",
+          "start": 44.42,
+          "end": 44.44,
+          "confidence": 0.98
+        },
+        {
+          "text": "is",
+          "start": 44.44,
+          "end": 44.46,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 44.46,
+          "end": 44.48,
+          "confidence": 0.988
+        },
+        {
+          "text": "one",
+          "start": 44.48,
+          "end": 44.54,
+          "confidence": 0.988
+        },
+        {
+          "text": "who",
+          "start": 44.54,
+          "end": 44.56,
+          "confidence": 0.98
+        },
+        {
+          "text": "is",
+          "start": 44.56,
+          "end": 44.58,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 44.58,
+          "end": 44.6,
+          "confidence": 0.988
+        },
+        {
+          "text": "one",
+          "start": 44.6,
+          "end": 45.16,
+          "confidence": 0.987
+        },
+        {
+          "text": "who",
+          "start": 45.16,
+          "end": 45.18,
+          "confidence": 0.98
+        },
+        {
+          "text": "is",
+          "start": 45.18,
+          "end": 45.2,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 45.2,
+          "end": 45.22,
+          "confidence": 0.988
+        },
+        {
+          "text": "one",
+          "start": 45.22,
+          "end": 45.24,
+          "confidence": 0.987
+        },
+        {
+          "text": "who",
+          "start": 45.24,
+          "end": 45.26,
+          "confidence": 0.979
+        },
+        {
+          "text": "is",
+          "start": 45.26,
+          "end": 45.28,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 45.28,
+          "end": 45.3,
+          "confidence": 0.988
+        },
+        {
+          "text": "one",
+          "start": 45.3,
+          "end": 45.32,
+          "confidence": 0.986
+        },
+        {
+          "text": "who",
+          "start": 45.32,
+          "end": 45.34,
+          "confidence": 0.978
+        },
+        {
+          "text": "is",
+          "start": 45.34,
+          "end": 45.36,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 45.36,
+          "end": 45.38,
+          "confidence": 0.988
+        },
+        {
+          "text": "one",
+          "start": 45.38,
+          "end": 45.4,
+          "confidence": 0.986
+        },
+        {
+          "text": "who",
+          "start": 45.4,
+          "end": 45.42,
+          "confidence": 0.977
+        },
+        {
+          "text": "is",
+          "start": 45.42,
+          "end": 45.44,
+          "confidence": 0.998
+        },
+        {
+          "text": "the",
+          "start": 45.44,
+          "end": 45.46,
+          "confidence": 0.988
+        },
+        {
+          "text": "one",
+          "start": 45.46,
+          "end": 45.94,
+          "confidence": 0.985
+        },
+        {
+          "text": "who",
+          "start": 45.94,
+          "end": 45.96,
+          "confidence": 0.975
+        },
+        {
+          "text": "is",
+          "start": 45.96,
+          "end": 45.98,
+          "confidence": 0.997
+        },
+        {
+          "text": "the",
+          "start": 45.98,
+          "end": 46.0,
+          "confidence": 0.988
+        },
+        {
+          "text": "one",
+          "start": 46.0,
+          "end": 46.02,
+          "confidence": 0.985
+        },
+        {
+          "text": "who",
+          "start": 46.02,
+          "end": 46.04,
+          "confidence": 0.976
+        },
+        {
+          "text": "is",
+          "start": 46.04,
+          "end": 46.06,
+          "confidence": 0.997
+        },
+        {
+          "text": "the",
+          "start": 46.06,
+          "end": 46.08,
+          "confidence": 0.988
+        },
+        {
+          "text": "one",
+          "start": 46.08,
+          "end": 46.1,
+          "confidence": 0.984
+        },
+        {
+          "text": "who",
+          "start": 46.1,
+          "end": 46.12,
+          "confidence": 0.975
+        },
+        {
+          "text": "is",
+          "start": 46.12,
+          "end": 46.14,
+          "confidence": 0.997
+        },
+        {
+          "text": "the",
+          "start": 46.14,
+          "end": 46.16,
+          "confidence": 0.987
+        },
+        {
+          "text": "one",
+          "start": 46.16,
+          "end": 46.18,
+          "confidence": 0.984
+        },
+        {
+          "text": "who",
+          "start": 46.18,
+          "end": 46.2,
+          "confidence": 0.971
+        },
+        {
+          "text": "is",
+          "start": 46.2,
+          "end": 46.22,
+          "confidence": 0.997
+        },
+        {
+          "text": "the",
+          "start": 46.22,
+          "end": 46.24,
+          "confidence": 0.986
+        },
+        {
+          "text": "one",
+          "start": 46.24,
+          "end": 46.26,
+          "confidence": 0.983
+        },
+        {
+          "text": "who",
+          "start": 46.26,
+          "end": 46.28,
+          "confidence": 0.971
+        },
+        {
+          "text": "is",
+          "start": 46.28,
+          "end": 46.3,
+          "confidence": 0.996
+        },
+        {
+          "text": "the",
+          "start": 46.3,
+          "end": 46.32,
+          "confidence": 0.986
+        },
+        {
+          "text": "one",
+          "start": 46.32,
+          "end": 46.84,
+          "confidence": 0.982
+        },
+        {
+          "text": "who",
+          "start": 46.84,
+          "end": 46.86,
+          "confidence": 0.969
+        },
+        {
+          "text": "is",
+          "start": 46.86,
+          "end": 46.88,
+          "confidence": 0.996
+        },
+        {
+          "text": "the",
+          "start": 46.88,
+          "end": 46.9,
+          "confidence": 0.986
+        },
+        {
+          "text": "one",
+          "start": 46.9,
+          "end": 46.92,
+          "confidence": 0.982
+        },
+        {
+          "text": "who",
+          "start": 46.92,
+          "end": 46.94,
+          "confidence": 0.966
+        },
+        {
+          "text": "is",
+          "start": 46.94,
+          "end": 46.96,
+          "confidence": 0.996
+        },
+        {
+          "text": "the",
+          "start": 46.96,
+          "end": 46.98,
+          "confidence": 0.985
+        },
+        {
+          "text": "one",
+          "start": 46.98,
+          "end": 47.1,
+          "confidence": 0.982
+        },
+        {
+          "text": "who",
+          "start": 47.1,
+          "end": 47.12,
+          "confidence": 0.966
+        },
+        {
+          "text": "is",
+          "start": 47.12,
+          "end": 47.14,
+          "confidence": 0.995
+        },
+        {
+          "text": "the",
+          "start": 47.14,
+          "end": 47.16,
+          "confidence": 0.985
+        },
+        {
+          "text": "one",
+          "start": 47.16,
+          "end": 47.18,
+          "confidence": 0.982
+        },
+        {
+          "text": "who",
+          "start": 47.18,
+          "end": 47.2,
+          "confidence": 0.963
+        },
+        {
+          "text": "is",
+          "start": 47.2,
+          "end": 47.22,
+          "confidence": 0.995
+        },
+        {
+          "text": "the",
+          "start": 47.22,
+          "end": 47.24,
+          "confidence": 0.984
+        },
+        {
+          "text": "one",
+          "start": 47.24,
+          "end": 47.26,
+          "confidence": 0.98
+        },
+        {
+          "text": "who",
+          "start": 47.26,
+          "end": 47.28,
+          "confidence": 0.959
+        },
+        {
+          "text": "is",
+          "start": 47.28,
+          "end": 47.3,
+          "confidence": 0.994
+        },
+        {
+          "text": "the",
+          "start": 47.3,
+          "end": 47.32,
+          "confidence": 0.983
+        },
+        {
+          "text": "one",
+          "start": 47.32,
+          "end": 47.34,
+          "confidence": 0.98
+        },
+        {
+          "text": "who",
+          "start": 47.34,
+          "end": 47.36,
+          "confidence": 0.958
+        },
+        {
+          "text": "is",
+          "start": 47.36,
+          "end": 47.38,
+          "confidence": 0.994
+        },
+        {
+          "text": "the",
+          "start": 47.38,
+          "end": 47.4,
+          "confidence": 0.983
+        },
+        {
+          "text": "one",
+          "start": 47.4,
+          "end": 47.6,
+          "confidence": 0.979
+        },
+        {
+          "text": "who",
+          "start": 47.6,
+          "end": 47.62,
+          "confidence": 0.955
+        },
+        {
+          "text": "is",
+          "start": 47.62,
+          "end": 47.64,
+          "confidence": 0.993
+        },
+        {
+          "text": "the",
+          "start": 47.64,
+          "end": 47.66,
+          "confidence": 0.982
+        },
+        {
+          "text": "one",
+          "start": 47.66,
+          "end": 47.68,
+          "confidence": 0.98
+        },
+        {
+          "text": "who",
+          "start": 47.68,
+          "end": 47.7,
+          "confidence": 0.956
+        },
+        {
+          "text": "is",
+          "start": 47.7,
+          "end": 47.72,
+          "confidence": 0.993
+        },
+        {
+          "text": "the",
+          "start": 47.72,
+          "end": 47.74,
+          "confidence": 0.981
+        },
+        {
+          "text": "one",
+          "start": 47.74,
+          "end": 47.76,
+          "confidence": 0.978
+        },
+        {
+          "text": "who",
+          "start": 47.76,
+          "end": 47.78,
+          "confidence": 0.949
+        },
+        {
+          "text": "is",
+          "start": 47.78,
+          "end": 47.8,
+          "confidence": 0.992
+        },
+        {
+          "text": "the",
+          "start": 47.8,
+          "end": 47.82,
+          "confidence": 0.98
+        },
+        {
+          "text": "one",
+          "start": 47.82,
+          "end": 49.1,
+          "confidence": 0.978
+        },
+        {
+          "text": "who",
+          "start": 49.1,
+          "end": 49.12,
+          "confidence": 0.948
+        },
+        {
+          "text": "is",
+          "start": 49.12,
+          "end": 49.14,
+          "confidence": 0.991
+        },
+        {
+          "text": "the",
+          "start": 49.14,
+          "end": 49.16,
+          "confidence": 0.98
+        },
+        {
+          "text": "one",
+          "start": 49.16,
+          "end": 49.26,
+          "confidence": 0.978
+        },
+        {
+          "text": "who",
+          "start": 49.26,
+          "end": 49.28,
+          "confidence": 0.949
+        },
+        {
+          "text": "is",
+          "start": 49.28,
+          "end": 49.3,
+          "confidence": 0.991
+        },
+        {
+          "text": "the",
+          "start": 49.3,
+          "end": 49.32,
+          "confidence": 0.979
+        },
+        {
+          "text": "one",
+          "start": 49.32,
+          "end": 49.34,
+          "confidence": 0.977
+        },
+        {
+          "text": "who",
+          "start": 49.34,
+          "end": 49.36,
+          "confidence": 0.944
+        },
+        {
+          "text": "is",
+          "start": 49.36,
+          "end": 49.38,
+          "confidence": 0.99
+        },
+        {
+          "text": "the",
+          "start": 49.38,
+          "end": 49.4,
+          "confidence": 0.977
+        },
+        {
+          "text": "one",
+          "start": 49.4,
+          "end": 49.42,
+          "confidence": 0.976
+        },
+        {
+          "text": "who",
+          "start": 49.42,
+          "end": 49.44,
+          "confidence": 0.94
+        },
+        {
+          "text": "is",
+          "start": 49.44,
+          "end": 49.46,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 49.46,
+          "end": 49.48,
+          "confidence": 0.977
+        },
+        {
+          "text": "one",
+          "start": 49.48,
+          "end": 49.5,
+          "confidence": 0.975
+        },
+        {
+          "text": "who",
+          "start": 49.5,
+          "end": 49.52,
+          "confidence": 0.94
+        },
+        {
+          "text": "is",
+          "start": 49.52,
+          "end": 49.54,
+          "confidence": 0.989
+        },
+        {
+          "text": "the",
+          "start": 49.54,
+          "end": 49.56,
+          "confidence": 0.975
+        },
+        {
+          "text": "one",
+          "start": 49.56,
+          "end": 49.58,
+          "confidence": 0.975
+        },
+        {
+          "text": "who",
+          "start": 49.58,
+          "end": 49.6,
+          "confidence": 0.935
+        },
+        {
+          "text": "is",
+          "start": 49.6,
+          "end": 49.62,
+          "confidence": 0.987
+        },
+        {
+          "text": "the",
+          "start": 49.62,
+          "end": 49.64,
+          "confidence": 0.974
+        },
+        {
+          "text": "one",
+          "start": 49.64,
+          "end": 49.66,
+          "confidence": 0.975
+        },
+        {
+          "text": "who",
+          "start": 49.66,
+          "end": 49.68,
+          "confidence": 0.936
+        },
+        {
+          "text": "is",
+          "start": 49.68,
+          "end": 49.7,
+          "confidence": 0.988
+        },
+        {
+          "text": "the",
+          "start": 49.7,
+          "end": 49.72,
+          "confidence": 0.974
+        },
+        {
+          "text": "one",
+          "start": 49.72,
+          "end": 49.74,
+          "confidence": 0.971
+        },
+        {
+          "text": "who",
+          "start": 49.74,
+          "end": 49.76,
+          "confidence": 0.932
+        },
+        {
+          "text": "is",
+          "start": 49.76,
+          "end": 49.78,
+          "confidence": 0.986
+        },
+        {
+          "text": "the",
+          "start": 49.78,
+          "end": 49.8,
+          "confidence": 0.971
+        },
+        {
+          "text": "one",
+          "start": 49.8,
+          "end": 49.82,
+          "confidence": 0.971
+        },
+        {
+          "text": "who",
+          "start": 49.82,
+          "end": 49.84,
+          "confidence": 0.928
+        },
+        {
+          "text": "is",
+          "start": 49.84,
+          "end": 49.86,
+          "confidence": 0.986
+        },
+        {
+          "text": "the",
+          "start": 49.86,
+          "end": 49.88,
+          "confidence": 0.971
+        },
+        {
+          "text": "one",
+          "start": 49.88,
+          "end": 49.9,
+          "confidence": 0.971
+        },
+        {
+          "text": "who",
+          "start": 49.9,
+          "end": 49.92,
+          "confidence": 0.923
+        },
+        {
+          "text": "is",
+          "start": 49.92,
+          "end": 49.94,
+          "confidence": 0.985
+        },
+        {
+          "text": "the",
+          "start": 49.94,
+          "end": 49.96,
+          "confidence": 0.97
+        },
+        {
+          "text": "one",
+          "start": 49.96,
+          "end": 66.64,
+          "confidence": 0.969
+        },
+        {
+          "text": "who",
+          "start": 66.64,
+          "end": 66.66,
+          "confidence": 0.925
+        },
+        {
+          "text": "is",
+          "start": 66.66,
+          "end": 66.98,
+          "confidence": 0.985
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/split_subtitles/punctuations.mp3_20.srt b/tests/expected/split_subtitles/punctuations.mp3_20.srt
new file mode 100644
index 0000000000000000000000000000000000000000..607f0125cf1df1d150f8432a5ce5ad72669143df
--- /dev/null
+++ b/tests/expected/split_subtitles/punctuations.mp3_20.srt
@@ -0,0 +1,12 @@
+1
+00:00:00,400 --> 00:00:01,360
+Dis-moi,
+
+2
+00:00:01,360 --> 00:00:02,020
+est-ce que l'avion
+
+3
+00:00:02,020 --> 00:00:02,340
+vole?
+
diff --git a/tests/expected/split_subtitles/punctuations.mp3_20.vtt b/tests/expected/split_subtitles/punctuations.mp3_20.vtt
new file mode 100644
index 0000000000000000000000000000000000000000..d06e85098725e851017bd86f94fa529b5c66d030
--- /dev/null
+++ b/tests/expected/split_subtitles/punctuations.mp3_20.vtt
@@ -0,0 +1,11 @@
+WEBVTT
+
+00:00.400 --> 00:01.360
+Dis-moi,
+
+00:01.360 --> 00:02.020
+est-ce que l'avion
+
+00:02.020 --> 00:02.340
+vole?
+
diff --git a/tests/expected/split_subtitles/punctuations.mp3_50.srt b/tests/expected/split_subtitles/punctuations.mp3_50.srt
new file mode 100644
index 0000000000000000000000000000000000000000..ffc9a2b42b2c510691ec27b303df2c88825c0aa4
--- /dev/null
+++ b/tests/expected/split_subtitles/punctuations.mp3_50.srt
@@ -0,0 +1,4 @@
+1
+00:00:00,400 --> 00:00:02,340
+Dis-moi, est-ce que l'avion vole?
+
diff --git a/tests/expected/split_subtitles/punctuations.mp3_50.vtt b/tests/expected/split_subtitles/punctuations.mp3_50.vtt
new file mode 100644
index 0000000000000000000000000000000000000000..83c7bd9a0253ca6a8d117803fac3a2bdc3b9e525
--- /dev/null
+++ b/tests/expected/split_subtitles/punctuations.mp3_50.vtt
@@ -0,0 +1,5 @@
+WEBVTT
+
+00:00.400 --> 00:02.340
+Dis-moi, est-ce que l'avion vole?
+
diff --git a/tests/expected/split_subtitles/punctuations.mp3_6.srt b/tests/expected/split_subtitles/punctuations.mp3_6.srt
new file mode 100644
index 0000000000000000000000000000000000000000..0caea3d7e82a647c78c154e2d1879292e5442c9d
--- /dev/null
+++ b/tests/expected/split_subtitles/punctuations.mp3_6.srt
@@ -0,0 +1,20 @@
+1
+00:00:00,400 --> 00:00:01,360
+Dis-moi,
+
+2
+00:00:01,360 --> 00:00:01,520
+est-ce
+
+3
+00:00:01,520 --> 00:00:01,640
+que
+
+4
+00:00:01,640 --> 00:00:02,020
+l'avion
+
+5
+00:00:02,020 --> 00:00:02,340
+vole?
+
diff --git a/tests/expected/split_subtitles/punctuations.mp3_6.vtt b/tests/expected/split_subtitles/punctuations.mp3_6.vtt
new file mode 100644
index 0000000000000000000000000000000000000000..f255e42075a222812432fc82fe6622c86de71015
--- /dev/null
+++ b/tests/expected/split_subtitles/punctuations.mp3_6.vtt
@@ -0,0 +1,17 @@
+WEBVTT
+
+00:00.400 --> 00:01.360
+Dis-moi,
+
+00:01.360 --> 00:01.520
+est-ce
+
+00:01.520 --> 00:01.640
+que
+
+00:01.640 --> 00:02.020
+l'avion
+
+00:02.020 --> 00:02.340
+vole?
+
diff --git a/tests/expected/split_subtitles/smartphone.mp3_20.srt b/tests/expected/split_subtitles/smartphone.mp3_20.srt
new file mode 100644
index 0000000000000000000000000000000000000000..22c039440f6cb0beda8f9ccf043d766a717ac78a
--- /dev/null
+++ b/tests/expected/split_subtitles/smartphone.mp3_20.srt
@@ -0,0 +1,812 @@
+1
+00:00:00,380 --> 00:00:01,080
+C'est évident ce que
+
+2
+00:00:01,080 --> 00:00:01,780
+dit Nicolas,
+
+3
+00:00:01,780 --> 00:00:02,380
+mais je ne me
+
+4
+00:00:02,380 --> 00:00:02,840
+l'étais jamais
+
+5
+00:00:02,840 --> 00:00:03,620
+formulé comme ça.
+
+6
+00:00:04,080 --> 00:00:05,000
+Ce qui fait la force
+
+7
+00:00:05,000 --> 00:00:05,880
+du smartphone,
+
+8
+00:00:05,880 --> 00:00:06,520
+c'est pas seulement
+
+9
+00:00:06,520 --> 00:00:07,560
+l'accumulation des
+
+10
+00:00:07,560 --> 00:00:07,920
+fonctions,
+
+11
+00:00:08,320 --> 00:00:09,100
+mais la manière dont
+
+12
+00:00:09,100 --> 00:00:10,320
+elles interagissent
+
+13
+00:00:10,320 --> 00:00:10,880
+entre elles.
+
+14
+00:00:10,960 --> 00:00:11,400
+Ce qui dit
+
+15
+00:00:11,400 --> 00:00:11,780
+d'ailleurs sur la
+
+16
+00:00:11,780 --> 00:00:12,120
+photo,
+
+17
+00:00:12,120 --> 00:00:13,000
+c'est hyper convaincant.
+
+18
+00:00:13,340 --> 00:00:14,340
+Alors évidemment,
+
+19
+00:00:14,340 --> 00:00:15,160
+il faudrait ajouter
+
+20
+00:00:15,160 --> 00:00:16,020
+les interfaces.
+
+21
+00:00:16,220 --> 00:00:17,260
+L'écran tactile a
+
+22
+00:00:17,260 --> 00:00:18,620
+été beaucoup très
+
+23
+00:00:18,620 --> 00:00:19,360
+souvent mentionné.
+
+24
+00:00:19,840 --> 00:00:20,520
+Mais bon,
+
+25
+00:00:20,520 --> 00:00:20,960
+il faut dire qu'il
+
+26
+00:00:20,960 --> 00:00:22,100
+profite aussi de 20
+
+27
+00:00:22,100 --> 00:00:22,920
+ans pendant lesquels
+
+28
+00:00:22,920 --> 00:00:23,720
+les ordinateurs nous
+
+29
+00:00:23,720 --> 00:00:24,500
+ont appris à cliquer
+
+30
+00:00:24,500 --> 00:00:25,260
+sur des icônes.
+
+31
+00:00:25,420 --> 00:00:26,660
+Sauf que le
+
+32
+00:00:26,660 --> 00:00:27,620
+smartphone ajoute le
+
+33
+00:00:27,620 --> 00:00:28,180
+toucher,
+
+34
+00:00:28,180 --> 00:00:28,680
+ce qui rend le
+
+35
+00:00:28,680 --> 00:00:30,220
+contact plus direct,
+
+36
+00:00:30,220 --> 00:00:30,640
+plus sensible.
+
+37
+00:00:31,040 --> 00:00:31,700
+Et puis évidemment,
+
+38
+00:00:31,700 --> 00:00:32,120
+il faudrait parler
+
+39
+00:00:32,120 --> 00:00:32,480
+aussi des
+
+40
+00:00:32,480 --> 00:00:33,180
+applications qui
+
+41
+00:00:33,180 --> 00:00:33,960
+permettent de
+
+42
+00:00:33,960 --> 00:00:34,800
+contourner le côté
+
+43
+00:00:34,800 --> 00:00:35,780
+touffu de la
+
+44
+00:00:35,780 --> 00:00:36,780
+navigation web pour
+
+45
+00:00:36,780 --> 00:00:37,680
+aller directement au
+
+46
+00:00:37,680 --> 00:00:37,820
+but.
+
+47
+00:00:37,820 --> 00:00:39,420
+Bref, tout ça,
+
+48
+00:00:39,420 --> 00:00:40,160
+ce sont les
+
+49
+00:00:40,160 --> 00:00:40,960
+conditions qui
+
+50
+00:00:40,960 --> 00:00:42,060
+permettent de créer
+
+51
+00:00:42,060 --> 00:00:42,800
+cet objet dont
+
+52
+00:00:42,800 --> 00:00:43,700
+Nicolas dit qu'il
+
+53
+00:00:43,700 --> 00:00:43,880
+est
+
+54
+00:00:43,880 --> 00:00:44,980
+vraisemblablement
+
+55
+00:00:44,980 --> 00:00:45,700
+inédit dans
+
+56
+00:00:45,700 --> 00:00:46,180
+l'histoire de
+
+57
+00:00:46,180 --> 00:00:46,580
+l'humanité.
+
+58
+00:00:46,600 --> 00:00:47,720
+Mais ça,
+
+59
+00:00:47,720 --> 00:00:48,260
+ça soulève une autre
+
+60
+00:00:48,260 --> 00:00:48,820
+interrogation.
+
+61
+00:00:49,220 --> 00:00:49,980
+Est-ce que le fait
+
+62
+00:00:49,980 --> 00:00:51,120
+que cet objet soit
+
+63
+00:00:51,120 --> 00:00:52,420
+inédit induit que
+
+64
+00:00:52,420 --> 00:00:53,660
+notre rapport à lui
+
+65
+00:00:53,660 --> 00:00:55,000
+est aussi un rapport
+
+66
+00:00:55,000 --> 00:00:55,460
+inédit?
+
+67
+00:00:55,460 --> 00:00:56,240
+Je veux dire,
+
+68
+00:00:56,240 --> 00:00:56,580
+est-ce que le
+
+69
+00:00:56,580 --> 00:00:57,280
+rapport qu'on a au
+
+70
+00:00:57,280 --> 00:00:57,920
+smartphone est
+
+71
+00:00:57,920 --> 00:00:58,660
+comparable à celui
+
+72
+00:00:58,660 --> 00:00:59,460
+qu'on entretenait à
+
+73
+00:00:59,460 --> 00:00:59,960
+d'autres objets
+
+74
+00:00:59,960 --> 00:01:01,500
+techniques comme la
+
+75
+00:01:01,500 --> 00:01:02,680
+voiture ou le
+
+76
+00:01:02,680 --> 00:01:03,120
+téléphone?
+
+77
+00:01:03,360 --> 00:01:05,660
+Il n'y a pas
+
+78
+00:01:05,660 --> 00:01:06,420
+d'équivalent en
+
+79
+00:01:06,420 --> 00:01:06,660
+fait.
+
+80
+00:01:06,880 --> 00:01:07,540
+Et donc cette espèce
+
+81
+00:01:07,540 --> 00:01:08,940
+de nouveauté dans la
+
+82
+00:01:08,940 --> 00:01:10,240
+relation à l'objet,
+
+83
+00:01:10,240 --> 00:01:10,760
+c'est fascinant et
+
+84
+00:01:10,760 --> 00:01:11,520
+terrifiant.
+
+85
+00:01:11,620 --> 00:01:12,440
+Parce qu'on a
+
+86
+00:01:12,440 --> 00:01:13,560
+l'impression,
+
+87
+00:01:13,560 --> 00:01:14,400
+comme le disent les
+
+88
+00:01:14,400 --> 00:01:15,000
+utilisateurs et les
+
+89
+00:01:15,000 --> 00:01:15,220
+services,
+
+90
+00:01:15,220 --> 00:01:16,080
+d'être dépendants de
+
+91
+00:01:16,080 --> 00:01:16,480
+cet objet,
+
+92
+00:01:16,860 --> 00:01:17,340
+d'induire en fait
+
+93
+00:01:17,340 --> 00:01:18,480
+une espèce de
+
+94
+00:01:18,480 --> 00:01:18,600
+relation,
+
+95
+00:01:18,600 --> 00:01:19,920
+de médiation avec le
+
+96
+00:01:19,920 --> 00:01:21,780
+monde qui rend de
+
+97
+00:01:21,780 --> 00:01:22,240
+l'ampleur et qui
+
+98
+00:01:22,240 --> 00:01:22,720
+amène aussi à des
+
+99
+00:01:22,720 --> 00:01:23,260
+formes de rejet.
+
+100
+00:01:23,940 --> 00:01:24,940
+Donc,
+
+101
+00:01:24,940 --> 00:01:26,560
+à objet inédit,
+
+102
+00:01:26,560 --> 00:01:27,800
+rapport inédit.
+
+103
+00:01:28,020 --> 00:01:29,280
+Et ce rapport,
+
+104
+00:01:29,280 --> 00:01:29,880
+si j'en crois
+
+105
+00:01:29,880 --> 00:01:30,540
+Nicolas,
+
+106
+00:01:30,540 --> 00:01:31,800
+serait caractérisé
+
+107
+00:01:31,800 --> 00:01:33,400
+par un mélange de
+
+108
+00:01:33,400 --> 00:01:34,680
+dépendance et de
+
+109
+00:01:34,680 --> 00:01:35,140
+rejet.
+
+110
+00:01:35,780 --> 00:01:37,140
+Bon, en vrai,
+
+111
+00:01:37,140 --> 00:01:38,080
+il faudrait remonter
+
+112
+00:01:38,080 --> 00:01:39,320
+très très finement
+
+113
+00:01:39,320 --> 00:01:40,240
+toute l'histoire des
+
+114
+00:01:40,240 --> 00:01:41,480
+objets techniques et
+
+115
+00:01:41,480 --> 00:01:42,320
+de leur insertion
+
+116
+00:01:42,320 --> 00:01:42,860
+dans nos vies
+
+117
+00:01:42,900 --> 00:01:43,760
+pour déterminer si
+
+118
+00:01:43,760 --> 00:01:44,740
+ce rapport est
+
+119
+00:01:44,740 --> 00:01:45,740
+totalement inédit.
+
+120
+00:01:46,100 --> 00:01:46,920
+Mais j'ai
+
+121
+00:01:46,920 --> 00:01:47,560
+l'impression comme
+
+122
+00:01:47,560 --> 00:01:48,700
+ça que Nicolas ne se
+
+123
+00:01:48,700 --> 00:01:49,340
+trompe pas vraiment.
+
+124
+00:01:49,880 --> 00:01:50,520
+Pour autant que je
+
+125
+00:01:50,520 --> 00:01:51,140
+sache,
+
+126
+00:01:51,140 --> 00:01:52,060
+il y a eu plein de
+
+127
+00:01:52,060 --> 00:01:52,940
+discussions autour
+
+128
+00:01:52,940 --> 00:01:54,060
+de la voiture ou
+
+129
+00:01:54,060 --> 00:01:54,980
+même du téléphone.
+
+130
+00:01:55,340 --> 00:01:56,400
+Mais la dépendance
+
+131
+00:01:56,400 --> 00:01:57,460
+n'était pas du même
+
+132
+00:01:57,460 --> 00:01:57,780
+ordre.
+
+133
+00:01:57,780 --> 00:01:58,780
+Donc le rejet non
+
+134
+00:01:58,780 --> 00:01:59,380
+plus n'était pas du
+
+135
+00:01:59,380 --> 00:01:59,840
+même ordre.
+
+136
+00:01:59,980 --> 00:02:00,880
+On peut adorer sa
+
+137
+00:02:00,880 --> 00:02:01,460
+bagnole,
+
+138
+00:02:01,460 --> 00:02:02,340
+en avoir besoin pour
+
+139
+00:02:02,340 --> 00:02:03,020
+plein de choses.
+
+140
+00:02:03,280 --> 00:02:04,680
+Et bien, le soir,
+
+141
+00:02:04,680 --> 00:02:05,380
+quand on va se
+
+142
+00:02:05,380 --> 00:02:05,800
+coucher,
+
+143
+00:02:05,800 --> 00:02:06,360
+on la laisse.
+
+144
+00:02:06,980 --> 00:02:07,800
+On ne l'a pas dans
+
+145
+00:02:07,800 --> 00:02:08,680
+la main quand on est
+
+146
+00:02:08,680 --> 00:02:09,140
+au lit,
+
+147
+00:02:09,140 --> 00:02:09,680
+on ne l'emmène pas
+
+148
+00:02:09,680 --> 00:02:10,480
+au chiottes.
+
+149
+00:02:10,860 --> 00:02:11,480
+On pouvait être
+
+150
+00:02:11,480 --> 00:02:13,100
+énervé par son môme
+
+151
+00:02:13,100 --> 00:02:13,800
+qui occupait la
+
+152
+00:02:13,800 --> 00:02:14,600
+ligne de téléphone
+
+153
+00:02:14,600 --> 00:02:15,360
+pendant une heure
+
+154
+00:02:15,360 --> 00:02:15,960
+chaque soir pour
+
+155
+00:02:15,960 --> 00:02:16,600
+discuter avec un
+
+156
+00:02:16,600 --> 00:02:16,900
+copain.
+
+157
+00:02:17,280 --> 00:02:17,940
+Mais ça ne
+
+158
+00:02:17,940 --> 00:02:18,980
+ressemblait pas à ce
+
+159
+00:02:18,980 --> 00:02:20,120
+qu'on peut ressentir
+
+160
+00:02:20,120 --> 00:02:21,340
+à voir ce même môme
+
+161
+00:02:21,340 --> 00:02:21,880
+aujourd'hui,
+
+162
+00:02:22,140 --> 00:02:23,180
+continuellement avec
+
+163
+00:02:23,180 --> 00:02:23,940
+son smartphone dans
+
+164
+00:02:23,940 --> 00:02:24,360
+la main,
+
+165
+00:02:24,360 --> 00:02:25,060
+comme si c'était une
+
+166
+00:02:25,060 --> 00:02:25,820
+sorte de pacemaker
+
+167
+00:02:25,820 --> 00:02:26,300
+externe,
+
+168
+00:02:26,340 --> 00:02:27,360
+comme si le lâcher
+
+169
+00:02:27,360 --> 00:02:28,000
+allait entraîner sa
+
+170
+00:02:28,000 --> 00:02:28,840
+mort immédiate.
+
+171
+00:02:29,040 --> 00:02:29,280
+Bon,
+
+172
+00:02:29,280 --> 00:02:29,880
+je dis ça pour le
+
+173
+00:02:29,880 --> 00:02:30,320
+môme,
+
+174
+00:02:30,320 --> 00:02:31,140
+mais c'est évidemment
+
+175
+00:02:31,140 --> 00:02:31,760
+valable pour nous
+
+176
+00:02:31,760 --> 00:02:31,960
+aussi.
+
+177
+00:02:32,340 --> 00:02:33,460
+Donc,
+
+178
+00:02:33,460 --> 00:02:34,240
+rapport inédit.
+
+179
+00:02:34,240 --> 00:02:35,480
+D'accord.
+
+180
+00:02:35,480 --> 00:02:36,680
+Mais pourquoi a-t-on
+
+181
+00:02:36,680 --> 00:02:37,260
+l'impression qu'on
+
+182
+00:02:37,260 --> 00:02:38,220
+n'en sortira jamais?
+
+183
+00:02:38,860 --> 00:02:39,780
+Est-ce qu'il faut en
+
+184
+00:02:39,780 --> 00:02:40,660
+remettre la faute
+
+185
+00:02:40,660 --> 00:02:41,720
+sur les gens qui ont
+
+186
+00:02:41,720 --> 00:02:42,780
+créé cet outil
+
+187
+00:02:42,780 --> 00:02:43,500
+merveilleux et
+
+188
+00:02:43,500 --> 00:02:43,860
+diabolique,
+
+189
+00:02:43,860 --> 00:02:44,660
+et diabolique parce
+
+190
+00:02:44,660 --> 00:02:45,320
+que merveilleux?
+
+191
+00:02:46,340 --> 00:02:47,480
+Les économistes
+
+192
+00:02:47,480 --> 00:02:47,820
+parlent de
+
+193
+00:02:47,820 --> 00:02:48,500
+dépendance du
+
+194
+00:02:48,500 --> 00:02:48,820
+sentier.
+
+195
+00:02:48,860 --> 00:02:49,700
+C'est l'idée qu'on
+
+196
+00:02:49,700 --> 00:02:50,780
+est sur un sentier
+
+197
+00:02:50,780 --> 00:02:51,900
+qui a été établi,
+
+198
+00:02:51,900 --> 00:02:52,720
+soit volontairement
+
+199
+00:02:52,720 --> 00:02:54,240
+en marchant dessus,
+
+200
+00:02:54,240 --> 00:02:55,500
+soit en définissant
+
+201
+00:02:55,500 --> 00:02:56,040
+des bornes,
+
+202
+00:02:56,040 --> 00:02:56,820
+en définissant une
+
+203
+00:02:56,820 --> 00:02:57,420
+signalétique.
+
diff --git a/tests/expected/split_subtitles/smartphone.mp3_20.vtt b/tests/expected/split_subtitles/smartphone.mp3_20.vtt
new file mode 100644
index 0000000000000000000000000000000000000000..b880a5ca949532022a422bc316c7efd245866555
--- /dev/null
+++ b/tests/expected/split_subtitles/smartphone.mp3_20.vtt
@@ -0,0 +1,611 @@
+WEBVTT
+
+00:00.380 --> 00:01.080
+C'est évident ce que
+
+00:01.080 --> 00:01.780
+dit Nicolas,
+
+00:01.780 --> 00:02.380
+mais je ne me
+
+00:02.380 --> 00:02.840
+l'étais jamais
+
+00:02.840 --> 00:03.620
+formulé comme ça.
+
+00:04.080 --> 00:05.000
+Ce qui fait la force
+
+00:05.000 --> 00:05.880
+du smartphone,
+
+00:05.880 --> 00:06.520
+c'est pas seulement
+
+00:06.520 --> 00:07.560
+l'accumulation des
+
+00:07.560 --> 00:07.920
+fonctions,
+
+00:08.320 --> 00:09.100
+mais la manière dont
+
+00:09.100 --> 00:10.320
+elles interagissent
+
+00:10.320 --> 00:10.880
+entre elles.
+
+00:10.960 --> 00:11.400
+Ce qui dit
+
+00:11.400 --> 00:11.780
+d'ailleurs sur la
+
+00:11.780 --> 00:12.120
+photo,
+
+00:12.120 --> 00:13.000
+c'est hyper convaincant.
+
+00:13.340 --> 00:14.340
+Alors évidemment,
+
+00:14.340 --> 00:15.160
+il faudrait ajouter
+
+00:15.160 --> 00:16.020
+les interfaces.
+
+00:16.220 --> 00:17.260
+L'écran tactile a
+
+00:17.260 --> 00:18.620
+été beaucoup très
+
+00:18.620 --> 00:19.360
+souvent mentionné.
+
+00:19.840 --> 00:20.520
+Mais bon,
+
+00:20.520 --> 00:20.960
+il faut dire qu'il
+
+00:20.960 --> 00:22.100
+profite aussi de 20
+
+00:22.100 --> 00:22.920
+ans pendant lesquels
+
+00:22.920 --> 00:23.720
+les ordinateurs nous
+
+00:23.720 --> 00:24.500
+ont appris à cliquer
+
+00:24.500 --> 00:25.260
+sur des icônes.
+
+00:25.420 --> 00:26.660
+Sauf que le
+
+00:26.660 --> 00:27.620
+smartphone ajoute le
+
+00:27.620 --> 00:28.180
+toucher,
+
+00:28.180 --> 00:28.680
+ce qui rend le
+
+00:28.680 --> 00:30.220
+contact plus direct,
+
+00:30.220 --> 00:30.640
+plus sensible.
+
+00:31.040 --> 00:31.700
+Et puis évidemment,
+
+00:31.700 --> 00:32.120
+il faudrait parler
+
+00:32.120 --> 00:32.480
+aussi des
+
+00:32.480 --> 00:33.180
+applications qui
+
+00:33.180 --> 00:33.960
+permettent de
+
+00:33.960 --> 00:34.800
+contourner le côté
+
+00:34.800 --> 00:35.780
+touffu de la
+
+00:35.780 --> 00:36.780
+navigation web pour
+
+00:36.780 --> 00:37.680
+aller directement au
+
+00:37.680 --> 00:37.820
+but.
+
+00:37.820 --> 00:39.420
+Bref, tout ça,
+
+00:39.420 --> 00:40.160
+ce sont les
+
+00:40.160 --> 00:40.960
+conditions qui
+
+00:40.960 --> 00:42.060
+permettent de créer
+
+00:42.060 --> 00:42.800
+cet objet dont
+
+00:42.800 --> 00:43.700
+Nicolas dit qu'il
+
+00:43.700 --> 00:43.880
+est
+
+00:43.880 --> 00:44.980
+vraisemblablement
+
+00:44.980 --> 00:45.700
+inédit dans
+
+00:45.700 --> 00:46.180
+l'histoire de
+
+00:46.180 --> 00:46.580
+l'humanité.
+
+00:46.600 --> 00:47.720
+Mais ça,
+
+00:47.720 --> 00:48.260
+ça soulève une autre
+
+00:48.260 --> 00:48.820
+interrogation.
+
+00:49.220 --> 00:49.980
+Est-ce que le fait
+
+00:49.980 --> 00:51.120
+que cet objet soit
+
+00:51.120 --> 00:52.420
+inédit induit que
+
+00:52.420 --> 00:53.660
+notre rapport à lui
+
+00:53.660 --> 00:55.000
+est aussi un rapport
+
+00:55.000 --> 00:55.460
+inédit?
+
+00:55.460 --> 00:56.240
+Je veux dire,
+
+00:56.240 --> 00:56.580
+est-ce que le
+
+00:56.580 --> 00:57.280
+rapport qu'on a au
+
+00:57.280 --> 00:57.920
+smartphone est
+
+00:57.920 --> 00:58.660
+comparable à celui
+
+00:58.660 --> 00:59.460
+qu'on entretenait à
+
+00:59.460 --> 00:59.960
+d'autres objets
+
+00:59.960 --> 01:01.500
+techniques comme la
+
+01:01.500 --> 01:02.680
+voiture ou le
+
+01:02.680 --> 01:03.120
+téléphone?
+
+01:03.360 --> 01:05.660
+Il n'y a pas
+
+01:05.660 --> 01:06.420
+d'équivalent en
+
+01:06.420 --> 01:06.660
+fait.
+
+01:06.880 --> 01:07.540
+Et donc cette espèce
+
+01:07.540 --> 01:08.940
+de nouveauté dans la
+
+01:08.940 --> 01:10.240
+relation à l'objet,
+
+01:10.240 --> 01:10.760
+c'est fascinant et
+
+01:10.760 --> 01:11.520
+terrifiant.
+
+01:11.620 --> 01:12.440
+Parce qu'on a
+
+01:12.440 --> 01:13.560
+l'impression,
+
+01:13.560 --> 01:14.400
+comme le disent les
+
+01:14.400 --> 01:15.000
+utilisateurs et les
+
+01:15.000 --> 01:15.220
+services,
+
+01:15.220 --> 01:16.080
+d'être dépendants de
+
+01:16.080 --> 01:16.480
+cet objet,
+
+01:16.860 --> 01:17.340
+d'induire en fait
+
+01:17.340 --> 01:18.480
+une espèce de
+
+01:18.480 --> 01:18.600
+relation,
+
+01:18.600 --> 01:19.920
+de médiation avec le
+
+01:19.920 --> 01:21.780
+monde qui rend de
+
+01:21.780 --> 01:22.240
+l'ampleur et qui
+
+01:22.240 --> 01:22.720
+amène aussi à des
+
+01:22.720 --> 01:23.260
+formes de rejet.
+
+01:23.940 --> 01:24.940
+Donc,
+
+01:24.940 --> 01:26.560
+à objet inédit,
+
+01:26.560 --> 01:27.800
+rapport inédit.
+
+01:28.020 --> 01:29.280
+Et ce rapport,
+
+01:29.280 --> 01:29.880
+si j'en crois
+
+01:29.880 --> 01:30.540
+Nicolas,
+
+01:30.540 --> 01:31.800
+serait caractérisé
+
+01:31.800 --> 01:33.400
+par un mélange de
+
+01:33.400 --> 01:34.680
+dépendance et de
+
+01:34.680 --> 01:35.140
+rejet.
+
+01:35.780 --> 01:37.140
+Bon, en vrai,
+
+01:37.140 --> 01:38.080
+il faudrait remonter
+
+01:38.080 --> 01:39.320
+très très finement
+
+01:39.320 --> 01:40.240
+toute l'histoire des
+
+01:40.240 --> 01:41.480
+objets techniques et
+
+01:41.480 --> 01:42.320
+de leur insertion
+
+01:42.320 --> 01:42.860
+dans nos vies
+
+01:42.900 --> 01:43.760
+pour déterminer si
+
+01:43.760 --> 01:44.740
+ce rapport est
+
+01:44.740 --> 01:45.740
+totalement inédit.
+
+01:46.100 --> 01:46.920
+Mais j'ai
+
+01:46.920 --> 01:47.560
+l'impression comme
+
+01:47.560 --> 01:48.700
+ça que Nicolas ne se
+
+01:48.700 --> 01:49.340
+trompe pas vraiment.
+
+01:49.880 --> 01:50.520
+Pour autant que je
+
+01:50.520 --> 01:51.140
+sache,
+
+01:51.140 --> 01:52.060
+il y a eu plein de
+
+01:52.060 --> 01:52.940
+discussions autour
+
+01:52.940 --> 01:54.060
+de la voiture ou
+
+01:54.060 --> 01:54.980
+même du téléphone.
+
+01:55.340 --> 01:56.400
+Mais la dépendance
+
+01:56.400 --> 01:57.460
+n'était pas du même
+
+01:57.460 --> 01:57.780
+ordre.
+
+01:57.780 --> 01:58.780
+Donc le rejet non
+
+01:58.780 --> 01:59.380
+plus n'était pas du
+
+01:59.380 --> 01:59.840
+même ordre.
+
+01:59.980 --> 02:00.880
+On peut adorer sa
+
+02:00.880 --> 02:01.460
+bagnole,
+
+02:01.460 --> 02:02.340
+en avoir besoin pour
+
+02:02.340 --> 02:03.020
+plein de choses.
+
+02:03.280 --> 02:04.680
+Et bien, le soir,
+
+02:04.680 --> 02:05.380
+quand on va se
+
+02:05.380 --> 02:05.800
+coucher,
+
+02:05.800 --> 02:06.360
+on la laisse.
+
+02:06.980 --> 02:07.800
+On ne l'a pas dans
+
+02:07.800 --> 02:08.680
+la main quand on est
+
+02:08.680 --> 02:09.140
+au lit,
+
+02:09.140 --> 02:09.680
+on ne l'emmène pas
+
+02:09.680 --> 02:10.480
+au chiottes.
+
+02:10.860 --> 02:11.480
+On pouvait être
+
+02:11.480 --> 02:13.100
+énervé par son môme
+
+02:13.100 --> 02:13.800
+qui occupait la
+
+02:13.800 --> 02:14.600
+ligne de téléphone
+
+02:14.600 --> 02:15.360
+pendant une heure
+
+02:15.360 --> 02:15.960
+chaque soir pour
+
+02:15.960 --> 02:16.600
+discuter avec un
+
+02:16.600 --> 02:16.900
+copain.
+
+02:17.280 --> 02:17.940
+Mais ça ne
+
+02:17.940 --> 02:18.980
+ressemblait pas à ce
+
+02:18.980 --> 02:20.120
+qu'on peut ressentir
+
+02:20.120 --> 02:21.340
+à voir ce même môme
+
+02:21.340 --> 02:21.880
+aujourd'hui,
+
+02:22.140 --> 02:23.180
+continuellement avec
+
+02:23.180 --> 02:23.940
+son smartphone dans
+
+02:23.940 --> 02:24.360
+la main,
+
+02:24.360 --> 02:25.060
+comme si c'était une
+
+02:25.060 --> 02:25.820
+sorte de pacemaker
+
+02:25.820 --> 02:26.300
+externe,
+
+02:26.340 --> 02:27.360
+comme si le lâcher
+
+02:27.360 --> 02:28.000
+allait entraîner sa
+
+02:28.000 --> 02:28.840
+mort immédiate.
+
+02:29.040 --> 02:29.280
+Bon,
+
+02:29.280 --> 02:29.880
+je dis ça pour le
+
+02:29.880 --> 02:30.320
+môme,
+
+02:30.320 --> 02:31.140
+mais c'est évidemment
+
+02:31.140 --> 02:31.760
+valable pour nous
+
+02:31.760 --> 02:31.960
+aussi.
+
+02:32.340 --> 02:33.460
+Donc,
+
+02:33.460 --> 02:34.240
+rapport inédit.
+
+02:34.240 --> 02:35.480
+D'accord.
+
+02:35.480 --> 02:36.680
+Mais pourquoi a-t-on
+
+02:36.680 --> 02:37.260
+l'impression qu'on
+
+02:37.260 --> 02:38.220
+n'en sortira jamais?
+
+02:38.860 --> 02:39.780
+Est-ce qu'il faut en
+
+02:39.780 --> 02:40.660
+remettre la faute
+
+02:40.660 --> 02:41.720
+sur les gens qui ont
+
+02:41.720 --> 02:42.780
+créé cet outil
+
+02:42.780 --> 02:43.500
+merveilleux et
+
+02:43.500 --> 02:43.860
+diabolique,
+
+02:43.860 --> 02:44.660
+et diabolique parce
+
+02:44.660 --> 02:45.320
+que merveilleux?
+
+02:46.340 --> 02:47.480
+Les économistes
+
+02:47.480 --> 02:47.820
+parlent de
+
+02:47.820 --> 02:48.500
+dépendance du
+
+02:48.500 --> 02:48.820
+sentier.
+
+02:48.860 --> 02:49.700
+C'est l'idée qu'on
+
+02:49.700 --> 02:50.780
+est sur un sentier
+
+02:50.780 --> 02:51.900
+qui a été établi,
+
+02:51.900 --> 02:52.720
+soit volontairement
+
+02:52.720 --> 02:54.240
+en marchant dessus,
+
+02:54.240 --> 02:55.500
+soit en définissant
+
+02:55.500 --> 02:56.040
+des bornes,
+
+02:56.040 --> 02:56.820
+en définissant une
+
+02:56.820 --> 02:57.420
+signalétique.
+
diff --git a/tests/expected/split_subtitles/smartphone.mp3_50.srt b/tests/expected/split_subtitles/smartphone.mp3_50.srt
new file mode 100644
index 0000000000000000000000000000000000000000..5a9cbd960d9a7073f91c8d0412e7daf0f797d25c
--- /dev/null
+++ b/tests/expected/split_subtitles/smartphone.mp3_50.srt
@@ -0,0 +1,356 @@
+1
+00:00:00,380 --> 00:00:01,780
+C'est évident ce que dit Nicolas,
+
+2
+00:00:01,780 --> 00:00:03,620
+mais je ne me l'étais jamais formulé comme ça.
+
+3
+00:00:04,080 --> 00:00:05,880
+Ce qui fait la force du smartphone,
+
+4
+00:00:05,880 --> 00:00:07,920
+c'est pas seulement l'accumulation des fonctions,
+
+5
+00:00:08,320 --> 00:00:10,580
+mais la manière dont elles interagissent entre
+
+6
+00:00:10,580 --> 00:00:10,880
+elles.
+
+7
+00:00:10,960 --> 00:00:12,120
+Ce qui dit d'ailleurs sur la photo,
+
+8
+00:00:12,120 --> 00:00:13,000
+c'est hyper convaincant.
+
+9
+00:00:13,340 --> 00:00:14,340
+Alors évidemment,
+
+10
+00:00:14,340 --> 00:00:16,020
+il faudrait ajouter les interfaces.
+
+11
+00:00:16,220 --> 00:00:18,900
+L'écran tactile a été beaucoup très souvent
+
+12
+00:00:18,900 --> 00:00:19,360
+mentionné.
+
+13
+00:00:19,840 --> 00:00:20,520
+Mais bon,
+
+14
+00:00:20,520 --> 00:00:22,480
+il faut dire qu'il profite aussi de 20 ans pendant
+
+15
+00:00:22,480 --> 00:00:24,500
+lesquels les ordinateurs nous ont appris à cliquer
+
+16
+00:00:24,500 --> 00:00:25,260
+sur des icônes.
+
+17
+00:00:25,420 --> 00:00:28,180
+Sauf que le smartphone ajoute le toucher,
+
+18
+00:00:28,180 --> 00:00:30,640
+ce qui rend le contact plus direct, plus sensible.
+
+19
+00:00:31,040 --> 00:00:31,700
+Et puis évidemment,
+
+20
+00:00:31,700 --> 00:00:33,180
+il faudrait parler aussi des applications qui
+
+21
+00:00:33,180 --> 00:00:35,780
+permettent de contourner le côté touffu de la
+
+22
+00:00:35,780 --> 00:00:37,820
+navigation web pour aller directement au but.
+
+23
+00:00:37,820 --> 00:00:39,420
+Bref, tout ça,
+
+24
+00:00:39,420 --> 00:00:42,380
+ce sont les conditions qui permettent de créer cet
+
+25
+00:00:42,380 --> 00:00:44,980
+objet dont Nicolas dit qu'il est vraisemblablement
+
+26
+00:00:44,980 --> 00:00:46,580
+inédit dans l'histoire de l'humanité.
+
+27
+00:00:46,600 --> 00:00:48,820
+Mais ça, ça soulève une autre interrogation.
+
+28
+00:00:49,220 --> 00:00:51,800
+Est-ce que le fait que cet objet soit inédit
+
+29
+00:00:51,800 --> 00:00:54,700
+induit que notre rapport à lui est aussi un
+
+30
+00:00:54,700 --> 00:00:55,460
+rapport inédit?
+
+31
+00:00:55,460 --> 00:00:56,240
+Je veux dire,
+
+32
+00:00:56,240 --> 00:00:57,920
+est-ce que le rapport qu'on a au smartphone est
+
+33
+00:00:57,920 --> 00:00:59,700
+comparable à celui qu'on entretenait à d'autres
+
+34
+00:00:59,700 --> 00:01:02,680
+objets techniques comme la voiture ou le
+
+35
+00:01:02,680 --> 00:01:03,120
+téléphone?
+
+36
+00:01:03,360 --> 00:01:06,660
+Il n'y a pas d'équivalent en fait.
+
+37
+00:01:06,880 --> 00:01:09,220
+Et donc cette espèce de nouveauté dans la relation
+
+38
+00:01:09,220 --> 00:01:11,520
+à l'objet, c'est fascinant et terrifiant.
+
+39
+00:01:11,620 --> 00:01:13,560
+Parce qu'on a l'impression,
+
+40
+00:01:13,560 --> 00:01:15,220
+comme le disent les utilisateurs et les services,
+
+41
+00:01:15,220 --> 00:01:16,480
+d'être dépendants de cet objet,
+
+42
+00:01:16,860 --> 00:01:18,600
+d'induire en fait une espèce de relation,
+
+43
+00:01:18,600 --> 00:01:22,020
+de médiation avec le monde qui rend de l'ampleur
+
+44
+00:01:22,020 --> 00:01:23,260
+et qui amène aussi à des formes de rejet.
+
+45
+00:01:23,940 --> 00:01:27,800
+Donc, à objet inédit, rapport inédit.
+
+46
+00:01:28,020 --> 00:01:30,540
+Et ce rapport, si j'en crois Nicolas,
+
+47
+00:01:30,540 --> 00:01:34,540
+serait caractérisé par un mélange de dépendance et
+
+48
+00:01:34,540 --> 00:01:35,140
+de rejet.
+
+49
+00:01:35,780 --> 00:01:37,140
+Bon, en vrai,
+
+50
+00:01:37,140 --> 00:01:39,700
+il faudrait remonter très très finement toute
+
+51
+00:01:39,700 --> 00:01:41,840
+l'histoire des objets techniques et de leur
+
+52
+00:01:41,840 --> 00:01:42,860
+insertion dans nos vies
+
+53
+00:01:42,900 --> 00:01:45,300
+pour déterminer si ce rapport est totalement
+
+54
+00:01:45,300 --> 00:01:45,740
+inédit.
+
+55
+00:01:46,100 --> 00:01:48,700
+Mais j'ai l'impression comme ça que Nicolas ne se
+
+56
+00:01:48,700 --> 00:01:49,340
+trompe pas vraiment.
+
+57
+00:01:49,880 --> 00:01:51,140
+Pour autant que je sache,
+
+58
+00:01:51,140 --> 00:01:53,520
+il y a eu plein de discussions autour de la
+
+59
+00:01:53,520 --> 00:01:54,980
+voiture ou même du téléphone.
+
+60
+00:01:55,340 --> 00:01:57,780
+Mais la dépendance n'était pas du même ordre.
+
+61
+00:01:57,780 --> 00:01:59,840
+Donc le rejet non plus n'était pas du même ordre.
+
+62
+00:01:59,980 --> 00:02:01,460
+On peut adorer sa bagnole,
+
+63
+00:02:01,460 --> 00:02:03,020
+en avoir besoin pour plein de choses.
+
+64
+00:02:03,280 --> 00:02:05,800
+Et bien, le soir, quand on va se coucher,
+
+65
+00:02:05,800 --> 00:02:06,360
+on la laisse.
+
+66
+00:02:06,980 --> 00:02:09,140
+On ne l'a pas dans la main quand on est au lit,
+
+67
+00:02:09,140 --> 00:02:10,480
+on ne l'emmène pas au chiottes.
+
+68
+00:02:10,860 --> 00:02:13,760
+On pouvait être énervé par son môme qui occupait
+
+69
+00:02:13,760 --> 00:02:15,540
+la ligne de téléphone pendant une heure chaque
+
+70
+00:02:15,540 --> 00:02:16,900
+soir pour discuter avec un copain.
+
+71
+00:02:17,280 --> 00:02:19,480
+Mais ça ne ressemblait pas à ce qu'on peut
+
+72
+00:02:19,480 --> 00:02:21,880
+ressentir à voir ce même môme aujourd'hui,
+
+73
+00:02:22,140 --> 00:02:24,360
+continuellement avec son smartphone dans la main,
+
+74
+00:02:24,360 --> 00:02:26,300
+comme si c'était une sorte de pacemaker externe,
+
+75
+00:02:26,340 --> 00:02:28,220
+comme si le lâcher allait entraîner sa mort
+
+76
+00:02:28,220 --> 00:02:28,840
+immédiate.
+
+77
+00:02:29,040 --> 00:02:30,320
+Bon, je dis ça pour le môme,
+
+78
+00:02:30,320 --> 00:02:31,960
+mais c'est évidemment valable pour nous aussi.
+
+79
+00:02:32,340 --> 00:02:35,480
+Donc, rapport inédit. D'accord.
+
+80
+00:02:35,480 --> 00:02:37,440
+Mais pourquoi a-t-on l'impression qu'on n'en
+
+81
+00:02:37,440 --> 00:02:38,220
+sortira jamais?
+
+82
+00:02:38,860 --> 00:02:41,280
+Est-ce qu'il faut en remettre la faute sur les
+
+83
+00:02:41,280 --> 00:02:43,500
+gens qui ont créé cet outil merveilleux et
+
+84
+00:02:43,500 --> 00:02:45,320
+diabolique, et diabolique parce que merveilleux?
+
+85
+00:02:46,340 --> 00:02:48,820
+Les économistes parlent de dépendance du sentier.
+
+86
+00:02:48,860 --> 00:02:51,120
+C'est l'idée qu'on est sur un sentier qui a été
+
+87
+00:02:51,120 --> 00:02:54,240
+établi, soit volontairement en marchant dessus,
+
+88
+00:02:54,240 --> 00:02:56,040
+soit en définissant des bornes,
+
+89
+00:02:56,040 --> 00:02:57,420
+en définissant une signalétique.
+
diff --git a/tests/expected/split_subtitles/smartphone.mp3_50.vtt b/tests/expected/split_subtitles/smartphone.mp3_50.vtt
new file mode 100644
index 0000000000000000000000000000000000000000..68d9b01306781ba2fcb81166b675053824255222
--- /dev/null
+++ b/tests/expected/split_subtitles/smartphone.mp3_50.vtt
@@ -0,0 +1,269 @@
+WEBVTT
+
+00:00.380 --> 00:01.780
+C'est évident ce que dit Nicolas,
+
+00:01.780 --> 00:03.620
+mais je ne me l'étais jamais formulé comme ça.
+
+00:04.080 --> 00:05.880
+Ce qui fait la force du smartphone,
+
+00:05.880 --> 00:07.920
+c'est pas seulement l'accumulation des fonctions,
+
+00:08.320 --> 00:10.580
+mais la manière dont elles interagissent entre
+
+00:10.580 --> 00:10.880
+elles.
+
+00:10.960 --> 00:12.120
+Ce qui dit d'ailleurs sur la photo,
+
+00:12.120 --> 00:13.000
+c'est hyper convaincant.
+
+00:13.340 --> 00:14.340
+Alors évidemment,
+
+00:14.340 --> 00:16.020
+il faudrait ajouter les interfaces.
+
+00:16.220 --> 00:18.900
+L'écran tactile a été beaucoup très souvent
+
+00:18.900 --> 00:19.360
+mentionné.
+
+00:19.840 --> 00:20.520
+Mais bon,
+
+00:20.520 --> 00:22.480
+il faut dire qu'il profite aussi de 20 ans pendant
+
+00:22.480 --> 00:24.500
+lesquels les ordinateurs nous ont appris à cliquer
+
+00:24.500 --> 00:25.260
+sur des icônes.
+
+00:25.420 --> 00:28.180
+Sauf que le smartphone ajoute le toucher,
+
+00:28.180 --> 00:30.640
+ce qui rend le contact plus direct, plus sensible.
+
+00:31.040 --> 00:31.700
+Et puis évidemment,
+
+00:31.700 --> 00:33.180
+il faudrait parler aussi des applications qui
+
+00:33.180 --> 00:35.780
+permettent de contourner le côté touffu de la
+
+00:35.780 --> 00:37.820
+navigation web pour aller directement au but.
+
+00:37.820 --> 00:39.420
+Bref, tout ça,
+
+00:39.420 --> 00:42.380
+ce sont les conditions qui permettent de créer cet
+
+00:42.380 --> 00:44.980
+objet dont Nicolas dit qu'il est vraisemblablement
+
+00:44.980 --> 00:46.580
+inédit dans l'histoire de l'humanité.
+
+00:46.600 --> 00:48.820
+Mais ça, ça soulève une autre interrogation.
+
+00:49.220 --> 00:51.800
+Est-ce que le fait que cet objet soit inédit
+
+00:51.800 --> 00:54.700
+induit que notre rapport à lui est aussi un
+
+00:54.700 --> 00:55.460
+rapport inédit?
+
+00:55.460 --> 00:56.240
+Je veux dire,
+
+00:56.240 --> 00:57.920
+est-ce que le rapport qu'on a au smartphone est
+
+00:57.920 --> 00:59.700
+comparable à celui qu'on entretenait à d'autres
+
+00:59.700 --> 01:02.680
+objets techniques comme la voiture ou le
+
+01:02.680 --> 01:03.120
+téléphone?
+
+01:03.360 --> 01:06.660
+Il n'y a pas d'équivalent en fait.
+
+01:06.880 --> 01:09.220
+Et donc cette espèce de nouveauté dans la relation
+
+01:09.220 --> 01:11.520
+à l'objet, c'est fascinant et terrifiant.
+
+01:11.620 --> 01:13.560
+Parce qu'on a l'impression,
+
+01:13.560 --> 01:15.220
+comme le disent les utilisateurs et les services,
+
+01:15.220 --> 01:16.480
+d'être dépendants de cet objet,
+
+01:16.860 --> 01:18.600
+d'induire en fait une espèce de relation,
+
+01:18.600 --> 01:22.020
+de médiation avec le monde qui rend de l'ampleur
+
+01:22.020 --> 01:23.260
+et qui amène aussi à des formes de rejet.
+
+01:23.940 --> 01:27.800
+Donc, à objet inédit, rapport inédit.
+
+01:28.020 --> 01:30.540
+Et ce rapport, si j'en crois Nicolas,
+
+01:30.540 --> 01:34.540
+serait caractérisé par un mélange de dépendance et
+
+01:34.540 --> 01:35.140
+de rejet.
+
+01:35.780 --> 01:37.140
+Bon, en vrai,
+
+01:37.140 --> 01:39.700
+il faudrait remonter très très finement toute
+
+01:39.700 --> 01:41.840
+l'histoire des objets techniques et de leur
+
+01:41.840 --> 01:42.860
+insertion dans nos vies
+
+01:42.900 --> 01:45.300
+pour déterminer si ce rapport est totalement
+
+01:45.300 --> 01:45.740
+inédit.
+
+01:46.100 --> 01:48.700
+Mais j'ai l'impression comme ça que Nicolas ne se
+
+01:48.700 --> 01:49.340
+trompe pas vraiment.
+
+01:49.880 --> 01:51.140
+Pour autant que je sache,
+
+01:51.140 --> 01:53.520
+il y a eu plein de discussions autour de la
+
+01:53.520 --> 01:54.980
+voiture ou même du téléphone.
+
+01:55.340 --> 01:57.780
+Mais la dépendance n'était pas du même ordre.
+
+01:57.780 --> 01:59.840
+Donc le rejet non plus n'était pas du même ordre.
+
+01:59.980 --> 02:01.460
+On peut adorer sa bagnole,
+
+02:01.460 --> 02:03.020
+en avoir besoin pour plein de choses.
+
+02:03.280 --> 02:05.800
+Et bien, le soir, quand on va se coucher,
+
+02:05.800 --> 02:06.360
+on la laisse.
+
+02:06.980 --> 02:09.140
+On ne l'a pas dans la main quand on est au lit,
+
+02:09.140 --> 02:10.480
+on ne l'emmène pas au chiottes.
+
+02:10.860 --> 02:13.760
+On pouvait être énervé par son môme qui occupait
+
+02:13.760 --> 02:15.540
+la ligne de téléphone pendant une heure chaque
+
+02:15.540 --> 02:16.900
+soir pour discuter avec un copain.
+
+02:17.280 --> 02:19.480
+Mais ça ne ressemblait pas à ce qu'on peut
+
+02:19.480 --> 02:21.880
+ressentir à voir ce même môme aujourd'hui,
+
+02:22.140 --> 02:24.360
+continuellement avec son smartphone dans la main,
+
+02:24.360 --> 02:26.300
+comme si c'était une sorte de pacemaker externe,
+
+02:26.340 --> 02:28.220
+comme si le lâcher allait entraîner sa mort
+
+02:28.220 --> 02:28.840
+immédiate.
+
+02:29.040 --> 02:30.320
+Bon, je dis ça pour le môme,
+
+02:30.320 --> 02:31.960
+mais c'est évidemment valable pour nous aussi.
+
+02:32.340 --> 02:35.480
+Donc, rapport inédit. D'accord.
+
+02:35.480 --> 02:37.440
+Mais pourquoi a-t-on l'impression qu'on n'en
+
+02:37.440 --> 02:38.220
+sortira jamais?
+
+02:38.860 --> 02:41.280
+Est-ce qu'il faut en remettre la faute sur les
+
+02:41.280 --> 02:43.500
+gens qui ont créé cet outil merveilleux et
+
+02:43.500 --> 02:45.320
+diabolique, et diabolique parce que merveilleux?
+
+02:46.340 --> 02:48.820
+Les économistes parlent de dépendance du sentier.
+
+02:48.860 --> 02:51.120
+C'est l'idée qu'on est sur un sentier qui a été
+
+02:51.120 --> 02:54.240
+établi, soit volontairement en marchant dessus,
+
+02:54.240 --> 02:56.040
+soit en définissant des bornes,
+
+02:56.040 --> 02:57.420
+en définissant une signalétique.
+
diff --git a/tests/expected/split_subtitles/smartphone.mp3_6.srt b/tests/expected/split_subtitles/smartphone.mp3_6.srt
new file mode 100644
index 0000000000000000000000000000000000000000..e03246f80d846a479b5404c598c34d50b8266e96
--- /dev/null
+++ b/tests/expected/split_subtitles/smartphone.mp3_6.srt
@@ -0,0 +1,2024 @@
+1
+00:00:00,380 --> 00:00:00,580
+C'est
+
+2
+00:00:00,580 --> 00:00:00,880
+évident
+
+3
+00:00:00,880 --> 00:00:01,080
+ce que
+
+4
+00:00:01,080 --> 00:00:01,200
+dit
+
+5
+00:00:01,200 --> 00:00:01,780
+Nicolas,
+
+6
+00:00:01,780 --> 00:00:01,900
+mais
+
+7
+00:00:01,900 --> 00:00:02,340
+je ne
+
+8
+00:00:02,340 --> 00:00:02,380
+me
+
+9
+00:00:02,380 --> 00:00:02,580
+l'étais
+
+10
+00:00:02,580 --> 00:00:02,840
+jamais
+
+11
+00:00:02,840 --> 00:00:03,260
+formulé
+
+12
+00:00:03,260 --> 00:00:03,420
+comme
+
+13
+00:00:03,420 --> 00:00:03,620
+ça.
+
+14
+00:00:04,080 --> 00:00:04,340
+Ce qui
+
+15
+00:00:04,340 --> 00:00:04,480
+fait
+
+16
+00:00:04,480 --> 00:00:04,660
+la
+
+17
+00:00:04,660 --> 00:00:05,000
+force
+
+18
+00:00:05,000 --> 00:00:05,200
+du
+
+19
+00:00:05,200 --> 00:00:05,880
+smartphone,
+
+20
+00:00:05,880 --> 00:00:06,120
+c'est
+
+21
+00:00:06,120 --> 00:00:06,260
+pas
+
+22
+00:00:06,260 --> 00:00:06,520
+seulement
+
+23
+00:00:06,520 --> 00:00:07,380
+l'accumulation
+
+24
+00:00:07,380 --> 00:00:07,560
+des
+
+25
+00:00:07,560 --> 00:00:07,920
+fonctions,
+
+26
+00:00:08,320 --> 00:00:08,440
+mais
+
+27
+00:00:08,440 --> 00:00:08,600
+la
+
+28
+00:00:08,600 --> 00:00:08,900
+manière
+
+29
+00:00:08,900 --> 00:00:09,100
+dont
+
+30
+00:00:09,100 --> 00:00:09,480
+elles
+
+31
+00:00:09,480 --> 00:00:10,320
+interagissent
+
+32
+00:00:10,320 --> 00:00:10,580
+entre
+
+33
+00:00:10,580 --> 00:00:10,880
+elles.
+
+34
+00:00:10,960 --> 00:00:11,220
+Ce qui
+
+35
+00:00:11,220 --> 00:00:11,400
+dit
+
+36
+00:00:11,400 --> 00:00:11,560
+d'ailleurs
+
+37
+00:00:11,560 --> 00:00:11,780
+sur la
+
+38
+00:00:11,780 --> 00:00:12,120
+photo,
+
+39
+00:00:12,120 --> 00:00:12,200
+c'est
+
+40
+00:00:12,200 --> 00:00:12,420
+hyper
+
+41
+00:00:12,420 --> 00:00:13,000
+convaincant.
+
+42
+00:00:13,340 --> 00:00:13,620
+Alors
+
+43
+00:00:13,620 --> 00:00:14,340
+évidemment,
+
+44
+00:00:14,340 --> 00:00:14,380
+il
+
+45
+00:00:14,380 --> 00:00:14,740
+faudrait
+
+46
+00:00:14,740 --> 00:00:15,160
+ajouter
+
+47
+00:00:15,160 --> 00:00:15,520
+les
+
+48
+00:00:15,520 --> 00:00:16,020
+interfaces.
+
+49
+00:00:16,220 --> 00:00:16,700
+L'écran
+
+50
+00:00:16,700 --> 00:00:17,060
+tactile
+
+51
+00:00:17,060 --> 00:00:17,880
+a été
+
+52
+00:00:17,880 --> 00:00:18,280
+beaucoup
+
+53
+00:00:18,280 --> 00:00:18,620
+très
+
+54
+00:00:18,620 --> 00:00:18,900
+souvent
+
+55
+00:00:18,900 --> 00:00:19,360
+mentionné.
+
+56
+00:00:19,840 --> 00:00:20,220
+Mais
+
+57
+00:00:20,220 --> 00:00:20,520
+bon,
+
+58
+00:00:20,520 --> 00:00:20,600
+il
+
+59
+00:00:20,600 --> 00:00:20,700
+faut
+
+60
+00:00:20,700 --> 00:00:20,840
+dire
+
+61
+00:00:20,840 --> 00:00:20,960
+qu'il
+
+62
+00:00:20,960 --> 00:00:21,260
+profite
+
+63
+00:00:21,260 --> 00:00:21,680
+aussi
+
+64
+00:00:21,680 --> 00:00:22,100
+de 20
+
+65
+00:00:22,100 --> 00:00:22,320
+ans
+
+66
+00:00:22,320 --> 00:00:22,480
+pendant
+
+67
+00:00:22,480 --> 00:00:22,920
+lesquels
+
+68
+00:00:22,920 --> 00:00:23,040
+les
+
+69
+00:00:23,040 --> 00:00:23,540
+ordinateurs
+
+70
+00:00:23,540 --> 00:00:23,720
+nous
+
+71
+00:00:23,720 --> 00:00:23,820
+ont
+
+72
+00:00:23,820 --> 00:00:24,100
+appris
+
+73
+00:00:24,100 --> 00:00:24,240
+à
+
+74
+00:00:24,240 --> 00:00:24,500
+cliquer
+
+75
+00:00:24,500 --> 00:00:24,660
+sur
+
+76
+00:00:24,660 --> 00:00:24,940
+des
+
+77
+00:00:24,940 --> 00:00:25,260
+icônes.
+
+78
+00:00:25,420 --> 00:00:25,760
+Sauf
+
+79
+00:00:25,760 --> 00:00:26,660
+que le
+
+80
+00:00:26,660 --> 00:00:27,060
+smartphone
+
+81
+00:00:27,060 --> 00:00:27,440
+ajoute
+
+82
+00:00:27,440 --> 00:00:27,620
+le
+
+83
+00:00:27,620 --> 00:00:28,180
+toucher,
+
+84
+00:00:28,180 --> 00:00:28,280
+ce qui
+
+85
+00:00:28,280 --> 00:00:28,480
+rend
+
+86
+00:00:28,480 --> 00:00:28,680
+le
+
+87
+00:00:28,680 --> 00:00:29,100
+contact
+
+88
+00:00:29,100 --> 00:00:29,460
+plus
+
+89
+00:00:29,460 --> 00:00:30,220
+direct,
+
+90
+00:00:30,220 --> 00:00:30,260
+plus
+
+91
+00:00:30,260 --> 00:00:30,640
+sensible.
+
+92
+00:00:31,040 --> 00:00:31,220
+Et
+
+93
+00:00:31,220 --> 00:00:31,360
+puis
+
+94
+00:00:31,360 --> 00:00:31,700
+évidemment,
+
+95
+00:00:31,700 --> 00:00:31,740
+il
+
+96
+00:00:31,740 --> 00:00:31,940
+faudrait
+
+97
+00:00:31,940 --> 00:00:32,120
+parler
+
+98
+00:00:32,120 --> 00:00:32,340
+aussi
+
+99
+00:00:32,340 --> 00:00:32,480
+des
+
+100
+00:00:32,480 --> 00:00:32,900
+applications
+
+101
+00:00:32,900 --> 00:00:33,180
+qui
+
+102
+00:00:33,180 --> 00:00:33,740
+permettent
+
+103
+00:00:33,740 --> 00:00:33,960
+de
+
+104
+00:00:33,960 --> 00:00:34,420
+contourner
+
+105
+00:00:34,420 --> 00:00:34,520
+le
+
+106
+00:00:34,520 --> 00:00:34,800
+côté
+
+107
+00:00:34,800 --> 00:00:35,320
+touffu
+
+108
+00:00:35,320 --> 00:00:35,780
+de la
+
+109
+00:00:35,780 --> 00:00:36,240
+navigation
+
+110
+00:00:36,240 --> 00:00:36,600
+web
+
+111
+00:00:36,600 --> 00:00:36,780
+pour
+
+112
+00:00:36,780 --> 00:00:36,980
+aller
+
+113
+00:00:36,980 --> 00:00:37,520
+directement
+
+114
+00:00:37,520 --> 00:00:37,680
+au
+
+115
+00:00:37,680 --> 00:00:37,820
+but.
+
+116
+00:00:37,820 --> 00:00:38,760
+Bref,
+
+117
+00:00:38,760 --> 00:00:38,980
+tout
+
+118
+00:00:38,980 --> 00:00:39,420
+ça,
+
+119
+00:00:39,420 --> 00:00:39,880
+ce sont
+
+120
+00:00:39,880 --> 00:00:40,160
+les
+
+121
+00:00:40,160 --> 00:00:40,680
+conditions
+
+122
+00:00:40,680 --> 00:00:40,960
+qui
+
+123
+00:00:40,960 --> 00:00:41,460
+permettent
+
+124
+00:00:41,460 --> 00:00:41,600
+de
+
+125
+00:00:41,600 --> 00:00:42,060
+créer
+
+126
+00:00:42,060 --> 00:00:42,380
+cet
+
+127
+00:00:42,380 --> 00:00:42,600
+objet
+
+128
+00:00:42,600 --> 00:00:42,800
+dont
+
+129
+00:00:42,800 --> 00:00:43,260
+Nicolas
+
+130
+00:00:43,260 --> 00:00:43,500
+dit
+
+131
+00:00:43,500 --> 00:00:43,700
+qu'il
+
+132
+00:00:43,700 --> 00:00:43,880
+est
+
+133
+00:00:43,880 --> 00:00:44,980
+vraisemblablement
+
+134
+00:00:44,980 --> 00:00:45,380
+inédit
+
+135
+00:00:45,380 --> 00:00:45,700
+dans
+
+136
+00:00:45,700 --> 00:00:45,980
+l'histoire
+
+137
+00:00:45,980 --> 00:00:46,180
+de
+
+138
+00:00:46,180 --> 00:00:46,580
+l'humanité.
+
+139
+00:00:46,600 --> 00:00:47,240
+Mais
+
+140
+00:00:47,240 --> 00:00:47,720
+ça,
+
+141
+00:00:47,720 --> 00:00:47,840
+ça soulève
+
+142
+00:00:47,840 --> 00:00:48,020
+une
+
+143
+00:00:48,020 --> 00:00:48,260
+autre
+
+144
+00:00:48,260 --> 00:00:48,820
+interrogation.
+
+145
+00:00:49,220 --> 00:00:49,620
+Est-ce
+
+146
+00:00:49,620 --> 00:00:49,820
+que le
+
+147
+00:00:49,820 --> 00:00:49,980
+fait
+
+148
+00:00:49,980 --> 00:00:50,140
+que
+
+149
+00:00:50,140 --> 00:00:50,320
+cet
+
+150
+00:00:50,320 --> 00:00:50,660
+objet
+
+151
+00:00:50,660 --> 00:00:51,120
+soit
+
+152
+00:00:51,120 --> 00:00:51,800
+inédit
+
+153
+00:00:51,800 --> 00:00:52,320
+induit
+
+154
+00:00:52,320 --> 00:00:52,420
+que
+
+155
+00:00:52,420 --> 00:00:52,720
+notre
+
+156
+00:00:52,720 --> 00:00:53,280
+rapport
+
+157
+00:00:53,280 --> 00:00:53,660
+à lui
+
+158
+00:00:53,660 --> 00:00:54,020
+est
+
+159
+00:00:54,020 --> 00:00:54,540
+aussi
+
+160
+00:00:54,540 --> 00:00:54,700
+un
+
+161
+00:00:54,700 --> 00:00:55,000
+rapport
+
+162
+00:00:55,000 --> 00:00:55,460
+inédit?
+
+163
+00:00:55,460 --> 00:00:55,900
+Je
+
+164
+00:00:55,900 --> 00:00:56,000
+veux
+
+165
+00:00:56,000 --> 00:00:56,240
+dire,
+
+166
+00:00:56,240 --> 00:00:56,360
+est-ce
+
+167
+00:00:56,360 --> 00:00:56,580
+que le
+
+168
+00:00:56,580 --> 00:00:56,880
+rapport
+
+169
+00:00:56,880 --> 00:00:57,040
+qu'on
+
+170
+00:00:57,040 --> 00:00:57,280
+a au
+
+171
+00:00:57,280 --> 00:00:57,600
+smartphone
+
+172
+00:00:57,600 --> 00:00:57,920
+est
+
+173
+00:00:57,920 --> 00:00:58,240
+comparable
+
+174
+00:00:58,240 --> 00:00:58,480
+à
+
+175
+00:00:58,480 --> 00:00:58,660
+celui
+
+176
+00:00:58,660 --> 00:00:58,900
+qu'on
+
+177
+00:00:58,900 --> 00:00:59,320
+entretenait
+
+178
+00:00:59,320 --> 00:00:59,460
+à
+
+179
+00:00:59,460 --> 00:00:59,700
+d'autres
+
+180
+00:00:59,700 --> 00:00:59,960
+objets
+
+181
+00:00:59,960 --> 00:01:00,460
+techniques
+
+182
+00:01:00,460 --> 00:01:00,880
+comme
+
+183
+00:01:00,880 --> 00:01:01,500
+la
+
+184
+00:01:01,500 --> 00:01:02,060
+voiture
+
+185
+00:01:02,060 --> 00:01:02,680
+ou le
+
+186
+00:01:02,680 --> 00:01:03,120
+téléphone?
+
+187
+00:01:03,360 --> 00:01:05,480
+Il n'y
+
+188
+00:01:05,480 --> 00:01:05,660
+a pas
+
+189
+00:01:05,660 --> 00:01:06,220
+d'équivalent
+
+190
+00:01:06,220 --> 00:01:06,420
+en
+
+191
+00:01:06,420 --> 00:01:06,660
+fait.
+
+192
+00:01:06,880 --> 00:01:06,980
+Et
+
+193
+00:01:06,980 --> 00:01:07,080
+donc
+
+194
+00:01:07,080 --> 00:01:07,280
+cette
+
+195
+00:01:07,280 --> 00:01:07,540
+espèce
+
+196
+00:01:07,540 --> 00:01:07,680
+de
+
+197
+00:01:07,680 --> 00:01:08,480
+nouveauté
+
+198
+00:01:08,480 --> 00:01:08,660
+dans
+
+199
+00:01:08,660 --> 00:01:08,940
+la
+
+200
+00:01:08,940 --> 00:01:09,220
+relation
+
+201
+00:01:09,220 --> 00:01:09,380
+à
+
+202
+00:01:09,380 --> 00:01:10,240
+l'objet,
+
+203
+00:01:10,240 --> 00:01:10,380
+c'est
+
+204
+00:01:10,380 --> 00:01:10,640
+fascinant
+
+205
+00:01:10,640 --> 00:01:10,760
+et
+
+206
+00:01:10,760 --> 00:01:11,520
+terrifiant.
+
+207
+00:01:11,620 --> 00:01:11,860
+Parce
+
+208
+00:01:11,860 --> 00:01:12,120
+qu'on
+
+209
+00:01:12,120 --> 00:01:12,440
+a
+
+210
+00:01:12,440 --> 00:01:13,560
+l'impression,
+
+211
+00:01:13,560 --> 00:01:13,840
+comme
+
+212
+00:01:13,840 --> 00:01:14,000
+le
+
+213
+00:01:14,000 --> 00:01:14,200
+disent
+
+214
+00:01:14,200 --> 00:01:14,400
+les
+
+215
+00:01:14,400 --> 00:01:14,840
+utilisateurs
+
+216
+00:01:14,840 --> 00:01:15,000
+et les
+
+217
+00:01:15,000 --> 00:01:15,220
+services,
+
+218
+00:01:15,220 --> 00:01:15,420
+d'être
+
+219
+00:01:15,420 --> 00:01:15,960
+dépendants
+
+220
+00:01:15,960 --> 00:01:16,260
+de cet
+
+221
+00:01:16,260 --> 00:01:16,480
+objet,
+
+222
+00:01:16,860 --> 00:01:17,080
+d'induire
+
+223
+00:01:17,080 --> 00:01:17,240
+en
+
+224
+00:01:17,240 --> 00:01:17,340
+fait
+
+225
+00:01:17,340 --> 00:01:17,520
+une
+
+226
+00:01:17,520 --> 00:01:17,880
+espèce
+
+227
+00:01:17,880 --> 00:01:18,480
+de
+
+228
+00:01:18,480 --> 00:01:18,600
+relation,
+
+229
+00:01:18,600 --> 00:01:18,940
+de
+
+230
+00:01:18,940 --> 00:01:19,520
+médiation
+
+231
+00:01:19,520 --> 00:01:19,740
+avec
+
+232
+00:01:19,740 --> 00:01:19,920
+le
+
+233
+00:01:19,920 --> 00:01:20,640
+monde
+
+234
+00:01:20,640 --> 00:01:21,100
+qui
+
+235
+00:01:21,100 --> 00:01:21,640
+rend
+
+236
+00:01:21,640 --> 00:01:21,780
+de
+
+237
+00:01:21,780 --> 00:01:22,020
+l'ampleur
+
+238
+00:01:22,020 --> 00:01:22,240
+et qui
+
+239
+00:01:22,240 --> 00:01:22,360
+amène
+
+240
+00:01:22,360 --> 00:01:22,560
+aussi
+
+241
+00:01:22,560 --> 00:01:22,720
+à des
+
+242
+00:01:22,720 --> 00:01:22,900
+formes
+
+243
+00:01:22,900 --> 00:01:23,020
+de
+
+244
+00:01:23,020 --> 00:01:23,260
+rejet.
+
+245
+00:01:23,940 --> 00:01:24,940
+Donc,
+
+246
+00:01:24,940 --> 00:01:24,980
+à
+
+247
+00:01:24,980 --> 00:01:25,360
+objet
+
+248
+00:01:25,360 --> 00:01:26,560
+inédit,
+
+249
+00:01:26,560 --> 00:01:27,000
+rapport
+
+250
+00:01:27,000 --> 00:01:27,800
+inédit.
+
+251
+00:01:28,020 --> 00:01:28,860
+Et ce
+
+252
+00:01:28,860 --> 00:01:29,280
+rapport,
+
+253
+00:01:29,280 --> 00:01:29,560
+si
+
+254
+00:01:29,560 --> 00:01:29,840
+j'en
+
+255
+00:01:29,840 --> 00:01:29,880
+crois
+
+256
+00:01:29,880 --> 00:01:30,540
+Nicolas,
+
+257
+00:01:30,540 --> 00:01:30,940
+serait
+
+258
+00:01:30,940 --> 00:01:31,800
+caractérisé
+
+259
+00:01:31,800 --> 00:01:32,440
+par un
+
+260
+00:01:32,440 --> 00:01:32,980
+mélange
+
+261
+00:01:32,980 --> 00:01:33,400
+de
+
+262
+00:01:33,400 --> 00:01:34,240
+dépendance
+
+263
+00:01:34,240 --> 00:01:34,680
+et de
+
+264
+00:01:34,680 --> 00:01:35,140
+rejet.
+
+265
+00:01:35,780 --> 00:01:36,380
+Bon,
+
+266
+00:01:36,380 --> 00:01:36,520
+en
+
+267
+00:01:36,520 --> 00:01:37,140
+vrai,
+
+268
+00:01:37,140 --> 00:01:37,180
+il
+
+269
+00:01:37,180 --> 00:01:37,580
+faudrait
+
+270
+00:01:37,580 --> 00:01:38,080
+remonter
+
+271
+00:01:38,080 --> 00:01:38,580
+très
+
+272
+00:01:38,580 --> 00:01:38,700
+très
+
+273
+00:01:38,700 --> 00:01:39,320
+finement
+
+274
+00:01:39,320 --> 00:01:39,700
+toute
+
+275
+00:01:39,700 --> 00:01:40,060
+l'histoire
+
+276
+00:01:40,060 --> 00:01:40,240
+des
+
+277
+00:01:40,240 --> 00:01:40,480
+objets
+
+278
+00:01:40,480 --> 00:01:41,020
+techniques
+
+279
+00:01:41,020 --> 00:01:41,680
+et de
+
+280
+00:01:41,680 --> 00:01:41,840
+leur
+
+281
+00:01:41,840 --> 00:01:42,320
+insertion
+
+282
+00:01:42,320 --> 00:01:42,480
+dans
+
+283
+00:01:42,480 --> 00:01:42,660
+nos
+
+284
+00:01:42,660 --> 00:01:42,860
+vies
+
+285
+00:01:42,900 --> 00:01:43,060
+pour
+
+286
+00:01:43,060 --> 00:01:43,660
+déterminer
+
+287
+00:01:43,660 --> 00:01:43,940
+si ce
+
+288
+00:01:43,940 --> 00:01:44,260
+rapport
+
+289
+00:01:44,260 --> 00:01:44,740
+est
+
+290
+00:01:44,740 --> 00:01:45,300
+totalement
+
+291
+00:01:45,300 --> 00:01:45,740
+inédit.
+
+292
+00:01:46,100 --> 00:01:46,360
+Mais
+
+293
+00:01:46,360 --> 00:01:46,920
+j'ai
+
+294
+00:01:46,920 --> 00:01:47,360
+l'impression
+
+295
+00:01:47,360 --> 00:01:47,560
+comme
+
+296
+00:01:47,560 --> 00:01:47,960
+ça que
+
+297
+00:01:47,960 --> 00:01:48,460
+Nicolas
+
+298
+00:01:48,460 --> 00:01:48,700
+ne se
+
+299
+00:01:48,700 --> 00:01:48,880
+trompe
+
+300
+00:01:48,880 --> 00:01:49,080
+pas
+
+301
+00:01:49,080 --> 00:01:49,340
+vraiment.
+
+302
+00:01:49,880 --> 00:01:50,080
+Pour
+
+303
+00:01:50,080 --> 00:01:50,240
+autant
+
+304
+00:01:50,240 --> 00:01:50,520
+que je
+
+305
+00:01:50,520 --> 00:01:51,140
+sache,
+
+306
+00:01:51,140 --> 00:01:51,360
+il y a
+
+307
+00:01:51,360 --> 00:01:51,680
+eu
+
+308
+00:01:51,680 --> 00:01:51,880
+plein
+
+309
+00:01:51,880 --> 00:01:52,060
+de
+
+310
+00:01:52,060 --> 00:01:52,600
+discussions
+
+311
+00:01:52,600 --> 00:01:52,940
+autour
+
+312
+00:01:52,940 --> 00:01:53,520
+de la
+
+313
+00:01:53,520 --> 00:01:53,860
+voiture
+
+314
+00:01:53,860 --> 00:01:54,060
+ou
+
+315
+00:01:54,060 --> 00:01:54,440
+même
+
+316
+00:01:54,440 --> 00:01:54,600
+du
+
+317
+00:01:54,600 --> 00:01:54,980
+téléphone.
+
+318
+00:01:55,340 --> 00:01:55,720
+Mais
+
+319
+00:01:55,720 --> 00:01:56,020
+la
+
+320
+00:01:56,020 --> 00:01:56,400
+dépendance
+
+321
+00:01:56,400 --> 00:01:56,620
+n'était
+
+322
+00:01:56,620 --> 00:01:57,160
+pas du
+
+323
+00:01:57,160 --> 00:01:57,460
+même
+
+324
+00:01:57,460 --> 00:01:57,780
+ordre.
+
+325
+00:01:57,780 --> 00:01:57,980
+Donc
+
+326
+00:01:57,980 --> 00:01:58,340
+le
+
+327
+00:01:58,340 --> 00:01:58,620
+rejet
+
+328
+00:01:58,620 --> 00:01:58,780
+non
+
+329
+00:01:58,780 --> 00:01:58,940
+plus
+
+330
+00:01:58,940 --> 00:01:59,120
+n'était
+
+331
+00:01:59,120 --> 00:01:59,380
+pas du
+
+332
+00:01:59,380 --> 00:01:59,560
+même
+
+333
+00:01:59,560 --> 00:01:59,840
+ordre.
+
+334
+00:01:59,980 --> 00:02:00,180
+On
+
+335
+00:02:00,180 --> 00:02:00,380
+peut
+
+336
+00:02:00,380 --> 00:02:00,660
+adorer
+
+337
+00:02:00,660 --> 00:02:00,880
+sa
+
+338
+00:02:00,880 --> 00:02:01,460
+bagnole,
+
+339
+00:02:01,460 --> 00:02:01,560
+en
+
+340
+00:02:01,560 --> 00:02:01,740
+avoir
+
+341
+00:02:01,740 --> 00:02:02,100
+besoin
+
+342
+00:02:02,100 --> 00:02:02,340
+pour
+
+343
+00:02:02,340 --> 00:02:02,680
+plein
+
+344
+00:02:02,680 --> 00:02:02,800
+de
+
+345
+00:02:02,800 --> 00:02:03,020
+choses.
+
+346
+00:02:03,280 --> 00:02:03,460
+Et
+
+347
+00:02:03,460 --> 00:02:03,860
+bien,
+
+348
+00:02:03,860 --> 00:02:03,980
+le
+
+349
+00:02:03,980 --> 00:02:04,680
+soir,
+
+350
+00:02:04,680 --> 00:02:04,900
+quand
+
+351
+00:02:04,900 --> 00:02:05,140
+on va
+
+352
+00:02:05,140 --> 00:02:05,380
+se
+
+353
+00:02:05,380 --> 00:02:05,800
+coucher,
+
+354
+00:02:05,800 --> 00:02:06,220
+on la
+
+355
+00:02:06,220 --> 00:02:06,360
+laisse.
+
+356
+00:02:06,980 --> 00:02:07,360
+On ne
+
+357
+00:02:07,360 --> 00:02:07,480
+l'a
+
+358
+00:02:07,480 --> 00:02:07,680
+pas
+
+359
+00:02:07,680 --> 00:02:07,800
+dans
+
+360
+00:02:07,800 --> 00:02:08,060
+la
+
+361
+00:02:08,060 --> 00:02:08,260
+main
+
+362
+00:02:08,260 --> 00:02:08,440
+quand
+
+363
+00:02:08,440 --> 00:02:08,680
+on est
+
+364
+00:02:08,680 --> 00:02:09,040
+au
+
+365
+00:02:09,040 --> 00:02:09,140
+lit,
+
+366
+00:02:09,140 --> 00:02:09,300
+on ne
+
+367
+00:02:09,300 --> 00:02:09,500
+l'emmène
+
+368
+00:02:09,500 --> 00:02:09,860
+pas au
+
+369
+00:02:09,860 --> 00:02:10,480
+chiottes.
+
+370
+00:02:10,860 --> 00:02:11,040
+On
+
+371
+00:02:11,040 --> 00:02:11,280
+pouvait
+
+372
+00:02:11,280 --> 00:02:11,480
+être
+
+373
+00:02:11,480 --> 00:02:12,220
+énervé
+
+374
+00:02:12,220 --> 00:02:12,440
+par
+
+375
+00:02:12,440 --> 00:02:12,700
+son
+
+376
+00:02:12,700 --> 00:02:13,100
+môme
+
+377
+00:02:13,100 --> 00:02:13,340
+qui
+
+378
+00:02:13,340 --> 00:02:13,760
+occupait
+
+379
+00:02:13,760 --> 00:02:13,800
+la
+
+380
+00:02:13,800 --> 00:02:14,080
+ligne
+
+381
+00:02:14,080 --> 00:02:14,140
+de
+
+382
+00:02:14,140 --> 00:02:14,600
+téléphone
+
+383
+00:02:14,600 --> 00:02:14,820
+pendant
+
+384
+00:02:14,820 --> 00:02:15,200
+une
+
+385
+00:02:15,200 --> 00:02:15,360
+heure
+
+386
+00:02:15,360 --> 00:02:15,540
+chaque
+
+387
+00:02:15,540 --> 00:02:15,800
+soir
+
+388
+00:02:15,800 --> 00:02:15,960
+pour
+
+389
+00:02:15,960 --> 00:02:16,280
+discuter
+
+390
+00:02:16,280 --> 00:02:16,480
+avec
+
+391
+00:02:16,480 --> 00:02:16,600
+un
+
+392
+00:02:16,600 --> 00:02:16,900
+copain.
+
+393
+00:02:17,280 --> 00:02:17,460
+Mais
+
+394
+00:02:17,460 --> 00:02:17,940
+ça ne
+
+395
+00:02:17,940 --> 00:02:18,400
+ressemblait
+
+396
+00:02:18,400 --> 00:02:18,940
+pas à
+
+397
+00:02:18,940 --> 00:02:18,980
+ce
+
+398
+00:02:18,980 --> 00:02:19,100
+qu'on
+
+399
+00:02:19,100 --> 00:02:19,480
+peut
+
+400
+00:02:19,480 --> 00:02:20,120
+ressentir
+
+401
+00:02:20,120 --> 00:02:20,460
+à voir
+
+402
+00:02:20,460 --> 00:02:20,680
+ce
+
+403
+00:02:20,680 --> 00:02:20,920
+même
+
+404
+00:02:20,920 --> 00:02:21,340
+môme
+
+405
+00:02:21,340 --> 00:02:21,880
+aujourd'hui,
+
+406
+00:02:22,140 --> 00:02:22,940
+continuellement
+
+407
+00:02:22,940 --> 00:02:23,180
+avec
+
+408
+00:02:23,180 --> 00:02:23,380
+son
+
+409
+00:02:23,380 --> 00:02:23,760
+smartphone
+
+410
+00:02:23,760 --> 00:02:23,940
+dans
+
+411
+00:02:23,940 --> 00:02:24,000
+la
+
+412
+00:02:24,000 --> 00:02:24,360
+main,
+
+413
+00:02:24,360 --> 00:02:24,520
+comme
+
+414
+00:02:24,520 --> 00:02:24,640
+si
+
+415
+00:02:24,640 --> 00:02:24,820
+c'était
+
+416
+00:02:24,820 --> 00:02:25,060
+une
+
+417
+00:02:25,060 --> 00:02:25,220
+sorte
+
+418
+00:02:25,220 --> 00:02:25,300
+de
+
+419
+00:02:25,300 --> 00:02:25,820
+pacemaker
+
+420
+00:02:25,820 --> 00:02:26,300
+externe,
+
+421
+00:02:26,340 --> 00:02:26,580
+comme
+
+422
+00:02:26,580 --> 00:02:26,860
+si le
+
+423
+00:02:26,860 --> 00:02:27,360
+lâcher
+
+424
+00:02:27,360 --> 00:02:27,560
+allait
+
+425
+00:02:27,560 --> 00:02:27,860
+entraîner
+
+426
+00:02:27,860 --> 00:02:28,000
+sa
+
+427
+00:02:28,000 --> 00:02:28,220
+mort
+
+428
+00:02:28,220 --> 00:02:28,840
+immédiate.
+
+429
+00:02:29,040 --> 00:02:29,280
+Bon,
+
+430
+00:02:29,280 --> 00:02:29,460
+je dis
+
+431
+00:02:29,460 --> 00:02:29,640
+ça
+
+432
+00:02:29,640 --> 00:02:29,740
+pour
+
+433
+00:02:29,740 --> 00:02:29,880
+le
+
+434
+00:02:29,880 --> 00:02:30,320
+môme,
+
+435
+00:02:30,320 --> 00:02:30,520
+mais
+
+436
+00:02:30,520 --> 00:02:30,820
+c'est
+
+437
+00:02:30,820 --> 00:02:31,140
+évidemment
+
+438
+00:02:31,140 --> 00:02:31,480
+valable
+
+439
+00:02:31,480 --> 00:02:31,620
+pour
+
+440
+00:02:31,620 --> 00:02:31,760
+nous
+
+441
+00:02:31,760 --> 00:02:31,960
+aussi.
+
+442
+00:02:32,340 --> 00:02:33,460
+Donc,
+
+443
+00:02:33,460 --> 00:02:33,660
+rapport
+
+444
+00:02:33,660 --> 00:02:34,240
+inédit.
+
+445
+00:02:34,240 --> 00:02:35,480
+D'accord.
+
+446
+00:02:35,480 --> 00:02:35,820
+Mais
+
+447
+00:02:35,820 --> 00:02:36,320
+pourquoi
+
+448
+00:02:36,320 --> 00:02:36,680
+a-t-on
+
+449
+00:02:36,680 --> 00:02:37,060
+l'impression
+
+450
+00:02:37,060 --> 00:02:37,260
+qu'on
+
+451
+00:02:37,260 --> 00:02:37,440
+n'en
+
+452
+00:02:37,440 --> 00:02:37,900
+sortira
+
+453
+00:02:37,900 --> 00:02:38,220
+jamais?
+
+454
+00:02:38,860 --> 00:02:39,340
+Est-ce
+
+455
+00:02:39,340 --> 00:02:39,460
+qu'il
+
+456
+00:02:39,460 --> 00:02:39,620
+faut
+
+457
+00:02:39,620 --> 00:02:39,780
+en
+
+458
+00:02:39,780 --> 00:02:40,120
+remettre
+
+459
+00:02:40,120 --> 00:02:40,340
+la
+
+460
+00:02:40,340 --> 00:02:40,660
+faute
+
+461
+00:02:40,660 --> 00:02:40,940
+sur
+
+462
+00:02:40,940 --> 00:02:41,280
+les
+
+463
+00:02:41,280 --> 00:02:41,440
+gens
+
+464
+00:02:41,440 --> 00:02:41,580
+qui
+
+465
+00:02:41,580 --> 00:02:41,720
+ont
+
+466
+00:02:41,720 --> 00:02:42,300
+créé
+
+467
+00:02:42,300 --> 00:02:42,460
+cet
+
+468
+00:02:42,460 --> 00:02:42,780
+outil
+
+469
+00:02:42,780 --> 00:02:43,340
+merveilleux
+
+470
+00:02:43,340 --> 00:02:43,500
+et
+
+471
+00:02:43,500 --> 00:02:43,860
+diabolique,
+
+472
+00:02:43,860 --> 00:02:43,920
+et
+
+473
+00:02:43,920 --> 00:02:44,400
+diabolique
+
+474
+00:02:44,400 --> 00:02:44,660
+parce
+
+475
+00:02:44,660 --> 00:02:44,840
+que
+
+476
+00:02:44,840 --> 00:02:45,320
+merveilleux?
+
+477
+00:02:46,340 --> 00:02:47,040
+Les
+
+478
+00:02:47,040 --> 00:02:47,480
+économistes
+
+479
+00:02:47,480 --> 00:02:47,680
+parlent
+
+480
+00:02:47,680 --> 00:02:47,820
+de
+
+481
+00:02:47,820 --> 00:02:48,360
+dépendance
+
+482
+00:02:48,360 --> 00:02:48,500
+du
+
+483
+00:02:48,500 --> 00:02:48,820
+sentier.
+
+484
+00:02:48,860 --> 00:02:49,100
+C'est
+
+485
+00:02:49,100 --> 00:02:49,340
+l'idée
+
+486
+00:02:49,340 --> 00:02:49,700
+qu'on
+
+487
+00:02:49,700 --> 00:02:49,880
+est
+
+488
+00:02:49,880 --> 00:02:50,540
+sur un
+
+489
+00:02:50,540 --> 00:02:50,780
+sentier
+
+490
+00:02:50,780 --> 00:02:50,940
+qui a
+
+491
+00:02:50,940 --> 00:02:51,120
+été
+
+492
+00:02:51,120 --> 00:02:51,900
+établi,
+
+493
+00:02:51,900 --> 00:02:52,120
+soit
+
+494
+00:02:52,120 --> 00:02:52,720
+volontairement
+
+495
+00:02:52,720 --> 00:02:52,800
+en
+
+496
+00:02:52,800 --> 00:02:53,060
+marchant
+
+497
+00:02:53,060 --> 00:02:54,240
+dessus,
+
+498
+00:02:54,240 --> 00:02:54,920
+soit
+
+499
+00:02:54,920 --> 00:02:55,360
+en
+
+500
+00:02:55,360 --> 00:02:55,500
+définissant
+
+501
+00:02:55,500 --> 00:02:55,760
+des
+
+502
+00:02:55,760 --> 00:02:56,040
+bornes,
+
+503
+00:02:56,040 --> 00:02:56,080
+en
+
+504
+00:02:56,080 --> 00:02:56,580
+définissant
+
+505
+00:02:56,580 --> 00:02:56,820
+une
+
+506
+00:02:56,820 --> 00:02:57,420
+signalétique.
+
diff --git a/tests/expected/split_subtitles/smartphone.mp3_6.vtt b/tests/expected/split_subtitles/smartphone.mp3_6.vtt
new file mode 100644
index 0000000000000000000000000000000000000000..61871c111372405e0b3331b5d11e0e1cbd3f450e
--- /dev/null
+++ b/tests/expected/split_subtitles/smartphone.mp3_6.vtt
@@ -0,0 +1,1520 @@
+WEBVTT
+
+00:00.380 --> 00:00.580
+C'est
+
+00:00.580 --> 00:00.880
+évident
+
+00:00.880 --> 00:01.080
+ce que
+
+00:01.080 --> 00:01.200
+dit
+
+00:01.200 --> 00:01.780
+Nicolas,
+
+00:01.780 --> 00:01.900
+mais
+
+00:01.900 --> 00:02.340
+je ne
+
+00:02.340 --> 00:02.380
+me
+
+00:02.380 --> 00:02.580
+l'étais
+
+00:02.580 --> 00:02.840
+jamais
+
+00:02.840 --> 00:03.260
+formulé
+
+00:03.260 --> 00:03.420
+comme
+
+00:03.420 --> 00:03.620
+ça.
+
+00:04.080 --> 00:04.340
+Ce qui
+
+00:04.340 --> 00:04.480
+fait
+
+00:04.480 --> 00:04.660
+la
+
+00:04.660 --> 00:05.000
+force
+
+00:05.000 --> 00:05.200
+du
+
+00:05.200 --> 00:05.880
+smartphone,
+
+00:05.880 --> 00:06.120
+c'est
+
+00:06.120 --> 00:06.260
+pas
+
+00:06.260 --> 00:06.520
+seulement
+
+00:06.520 --> 00:07.380
+l'accumulation
+
+00:07.380 --> 00:07.560
+des
+
+00:07.560 --> 00:07.920
+fonctions,
+
+00:08.320 --> 00:08.440
+mais
+
+00:08.440 --> 00:08.600
+la
+
+00:08.600 --> 00:08.900
+manière
+
+00:08.900 --> 00:09.100
+dont
+
+00:09.100 --> 00:09.480
+elles
+
+00:09.480 --> 00:10.320
+interagissent
+
+00:10.320 --> 00:10.580
+entre
+
+00:10.580 --> 00:10.880
+elles.
+
+00:10.960 --> 00:11.220
+Ce qui
+
+00:11.220 --> 00:11.400
+dit
+
+00:11.400 --> 00:11.560
+d'ailleurs
+
+00:11.560 --> 00:11.780
+sur la
+
+00:11.780 --> 00:12.120
+photo,
+
+00:12.120 --> 00:12.200
+c'est
+
+00:12.200 --> 00:12.420
+hyper
+
+00:12.420 --> 00:13.000
+convaincant.
+
+00:13.340 --> 00:13.620
+Alors
+
+00:13.620 --> 00:14.340
+évidemment,
+
+00:14.340 --> 00:14.380
+il
+
+00:14.380 --> 00:14.740
+faudrait
+
+00:14.740 --> 00:15.160
+ajouter
+
+00:15.160 --> 00:15.520
+les
+
+00:15.520 --> 00:16.020
+interfaces.
+
+00:16.220 --> 00:16.700
+L'écran
+
+00:16.700 --> 00:17.060
+tactile
+
+00:17.060 --> 00:17.880
+a été
+
+00:17.880 --> 00:18.280
+beaucoup
+
+00:18.280 --> 00:18.620
+très
+
+00:18.620 --> 00:18.900
+souvent
+
+00:18.900 --> 00:19.360
+mentionné.
+
+00:19.840 --> 00:20.220
+Mais
+
+00:20.220 --> 00:20.520
+bon,
+
+00:20.520 --> 00:20.600
+il
+
+00:20.600 --> 00:20.700
+faut
+
+00:20.700 --> 00:20.840
+dire
+
+00:20.840 --> 00:20.960
+qu'il
+
+00:20.960 --> 00:21.260
+profite
+
+00:21.260 --> 00:21.680
+aussi
+
+00:21.680 --> 00:22.100
+de 20
+
+00:22.100 --> 00:22.320
+ans
+
+00:22.320 --> 00:22.480
+pendant
+
+00:22.480 --> 00:22.920
+lesquels
+
+00:22.920 --> 00:23.040
+les
+
+00:23.040 --> 00:23.540
+ordinateurs
+
+00:23.540 --> 00:23.720
+nous
+
+00:23.720 --> 00:23.820
+ont
+
+00:23.820 --> 00:24.100
+appris
+
+00:24.100 --> 00:24.240
+à
+
+00:24.240 --> 00:24.500
+cliquer
+
+00:24.500 --> 00:24.660
+sur
+
+00:24.660 --> 00:24.940
+des
+
+00:24.940 --> 00:25.260
+icônes.
+
+00:25.420 --> 00:25.760
+Sauf
+
+00:25.760 --> 00:26.660
+que le
+
+00:26.660 --> 00:27.060
+smartphone
+
+00:27.060 --> 00:27.440
+ajoute
+
+00:27.440 --> 00:27.620
+le
+
+00:27.620 --> 00:28.180
+toucher,
+
+00:28.180 --> 00:28.280
+ce qui
+
+00:28.280 --> 00:28.480
+rend
+
+00:28.480 --> 00:28.680
+le
+
+00:28.680 --> 00:29.100
+contact
+
+00:29.100 --> 00:29.460
+plus
+
+00:29.460 --> 00:30.220
+direct,
+
+00:30.220 --> 00:30.260
+plus
+
+00:30.260 --> 00:30.640
+sensible.
+
+00:31.040 --> 00:31.220
+Et
+
+00:31.220 --> 00:31.360
+puis
+
+00:31.360 --> 00:31.700
+évidemment,
+
+00:31.700 --> 00:31.740
+il
+
+00:31.740 --> 00:31.940
+faudrait
+
+00:31.940 --> 00:32.120
+parler
+
+00:32.120 --> 00:32.340
+aussi
+
+00:32.340 --> 00:32.480
+des
+
+00:32.480 --> 00:32.900
+applications
+
+00:32.900 --> 00:33.180
+qui
+
+00:33.180 --> 00:33.740
+permettent
+
+00:33.740 --> 00:33.960
+de
+
+00:33.960 --> 00:34.420
+contourner
+
+00:34.420 --> 00:34.520
+le
+
+00:34.520 --> 00:34.800
+côté
+
+00:34.800 --> 00:35.320
+touffu
+
+00:35.320 --> 00:35.780
+de la
+
+00:35.780 --> 00:36.240
+navigation
+
+00:36.240 --> 00:36.600
+web
+
+00:36.600 --> 00:36.780
+pour
+
+00:36.780 --> 00:36.980
+aller
+
+00:36.980 --> 00:37.520
+directement
+
+00:37.520 --> 00:37.680
+au
+
+00:37.680 --> 00:37.820
+but.
+
+00:37.820 --> 00:38.760
+Bref,
+
+00:38.760 --> 00:38.980
+tout
+
+00:38.980 --> 00:39.420
+ça,
+
+00:39.420 --> 00:39.880
+ce sont
+
+00:39.880 --> 00:40.160
+les
+
+00:40.160 --> 00:40.680
+conditions
+
+00:40.680 --> 00:40.960
+qui
+
+00:40.960 --> 00:41.460
+permettent
+
+00:41.460 --> 00:41.600
+de
+
+00:41.600 --> 00:42.060
+créer
+
+00:42.060 --> 00:42.380
+cet
+
+00:42.380 --> 00:42.600
+objet
+
+00:42.600 --> 00:42.800
+dont
+
+00:42.800 --> 00:43.260
+Nicolas
+
+00:43.260 --> 00:43.500
+dit
+
+00:43.500 --> 00:43.700
+qu'il
+
+00:43.700 --> 00:43.880
+est
+
+00:43.880 --> 00:44.980
+vraisemblablement
+
+00:44.980 --> 00:45.380
+inédit
+
+00:45.380 --> 00:45.700
+dans
+
+00:45.700 --> 00:45.980
+l'histoire
+
+00:45.980 --> 00:46.180
+de
+
+00:46.180 --> 00:46.580
+l'humanité.
+
+00:46.600 --> 00:47.240
+Mais
+
+00:47.240 --> 00:47.720
+ça,
+
+00:47.720 --> 00:47.840
+ça soulève
+
+00:47.840 --> 00:48.020
+une
+
+00:48.020 --> 00:48.260
+autre
+
+00:48.260 --> 00:48.820
+interrogation.
+
+00:49.220 --> 00:49.620
+Est-ce
+
+00:49.620 --> 00:49.820
+que le
+
+00:49.820 --> 00:49.980
+fait
+
+00:49.980 --> 00:50.140
+que
+
+00:50.140 --> 00:50.320
+cet
+
+00:50.320 --> 00:50.660
+objet
+
+00:50.660 --> 00:51.120
+soit
+
+00:51.120 --> 00:51.800
+inédit
+
+00:51.800 --> 00:52.320
+induit
+
+00:52.320 --> 00:52.420
+que
+
+00:52.420 --> 00:52.720
+notre
+
+00:52.720 --> 00:53.280
+rapport
+
+00:53.280 --> 00:53.660
+à lui
+
+00:53.660 --> 00:54.020
+est
+
+00:54.020 --> 00:54.540
+aussi
+
+00:54.540 --> 00:54.700
+un
+
+00:54.700 --> 00:55.000
+rapport
+
+00:55.000 --> 00:55.460
+inédit?
+
+00:55.460 --> 00:55.900
+Je
+
+00:55.900 --> 00:56.000
+veux
+
+00:56.000 --> 00:56.240
+dire,
+
+00:56.240 --> 00:56.360
+est-ce
+
+00:56.360 --> 00:56.580
+que le
+
+00:56.580 --> 00:56.880
+rapport
+
+00:56.880 --> 00:57.040
+qu'on
+
+00:57.040 --> 00:57.280
+a au
+
+00:57.280 --> 00:57.600
+smartphone
+
+00:57.600 --> 00:57.920
+est
+
+00:57.920 --> 00:58.240
+comparable
+
+00:58.240 --> 00:58.480
+à
+
+00:58.480 --> 00:58.660
+celui
+
+00:58.660 --> 00:58.900
+qu'on
+
+00:58.900 --> 00:59.320
+entretenait
+
+00:59.320 --> 00:59.460
+à
+
+00:59.460 --> 00:59.700
+d'autres
+
+00:59.700 --> 00:59.960
+objets
+
+00:59.960 --> 01:00.460
+techniques
+
+01:00.460 --> 01:00.880
+comme
+
+01:00.880 --> 01:01.500
+la
+
+01:01.500 --> 01:02.060
+voiture
+
+01:02.060 --> 01:02.680
+ou le
+
+01:02.680 --> 01:03.120
+téléphone?
+
+01:03.360 --> 01:05.480
+Il n'y
+
+01:05.480 --> 01:05.660
+a pas
+
+01:05.660 --> 01:06.220
+d'équivalent
+
+01:06.220 --> 01:06.420
+en
+
+01:06.420 --> 01:06.660
+fait.
+
+01:06.880 --> 01:06.980
+Et
+
+01:06.980 --> 01:07.080
+donc
+
+01:07.080 --> 01:07.280
+cette
+
+01:07.280 --> 01:07.540
+espèce
+
+01:07.540 --> 01:07.680
+de
+
+01:07.680 --> 01:08.480
+nouveauté
+
+01:08.480 --> 01:08.660
+dans
+
+01:08.660 --> 01:08.940
+la
+
+01:08.940 --> 01:09.220
+relation
+
+01:09.220 --> 01:09.380
+à
+
+01:09.380 --> 01:10.240
+l'objet,
+
+01:10.240 --> 01:10.380
+c'est
+
+01:10.380 --> 01:10.640
+fascinant
+
+01:10.640 --> 01:10.760
+et
+
+01:10.760 --> 01:11.520
+terrifiant.
+
+01:11.620 --> 01:11.860
+Parce
+
+01:11.860 --> 01:12.120
+qu'on
+
+01:12.120 --> 01:12.440
+a
+
+01:12.440 --> 01:13.560
+l'impression,
+
+01:13.560 --> 01:13.840
+comme
+
+01:13.840 --> 01:14.000
+le
+
+01:14.000 --> 01:14.200
+disent
+
+01:14.200 --> 01:14.400
+les
+
+01:14.400 --> 01:14.840
+utilisateurs
+
+01:14.840 --> 01:15.000
+et les
+
+01:15.000 --> 01:15.220
+services,
+
+01:15.220 --> 01:15.420
+d'être
+
+01:15.420 --> 01:15.960
+dépendants
+
+01:15.960 --> 01:16.260
+de cet
+
+01:16.260 --> 01:16.480
+objet,
+
+01:16.860 --> 01:17.080
+d'induire
+
+01:17.080 --> 01:17.240
+en
+
+01:17.240 --> 01:17.340
+fait
+
+01:17.340 --> 01:17.520
+une
+
+01:17.520 --> 01:17.880
+espèce
+
+01:17.880 --> 01:18.480
+de
+
+01:18.480 --> 01:18.600
+relation,
+
+01:18.600 --> 01:18.940
+de
+
+01:18.940 --> 01:19.520
+médiation
+
+01:19.520 --> 01:19.740
+avec
+
+01:19.740 --> 01:19.920
+le
+
+01:19.920 --> 01:20.640
+monde
+
+01:20.640 --> 01:21.100
+qui
+
+01:21.100 --> 01:21.640
+rend
+
+01:21.640 --> 01:21.780
+de
+
+01:21.780 --> 01:22.020
+l'ampleur
+
+01:22.020 --> 01:22.240
+et qui
+
+01:22.240 --> 01:22.360
+amène
+
+01:22.360 --> 01:22.560
+aussi
+
+01:22.560 --> 01:22.720
+à des
+
+01:22.720 --> 01:22.900
+formes
+
+01:22.900 --> 01:23.020
+de
+
+01:23.020 --> 01:23.260
+rejet.
+
+01:23.940 --> 01:24.940
+Donc,
+
+01:24.940 --> 01:24.980
+à
+
+01:24.980 --> 01:25.360
+objet
+
+01:25.360 --> 01:26.560
+inédit,
+
+01:26.560 --> 01:27.000
+rapport
+
+01:27.000 --> 01:27.800
+inédit.
+
+01:28.020 --> 01:28.860
+Et ce
+
+01:28.860 --> 01:29.280
+rapport,
+
+01:29.280 --> 01:29.560
+si
+
+01:29.560 --> 01:29.840
+j'en
+
+01:29.840 --> 01:29.880
+crois
+
+01:29.880 --> 01:30.540
+Nicolas,
+
+01:30.540 --> 01:30.940
+serait
+
+01:30.940 --> 01:31.800
+caractérisé
+
+01:31.800 --> 01:32.440
+par un
+
+01:32.440 --> 01:32.980
+mélange
+
+01:32.980 --> 01:33.400
+de
+
+01:33.400 --> 01:34.240
+dépendance
+
+01:34.240 --> 01:34.680
+et de
+
+01:34.680 --> 01:35.140
+rejet.
+
+01:35.780 --> 01:36.380
+Bon,
+
+01:36.380 --> 01:36.520
+en
+
+01:36.520 --> 01:37.140
+vrai,
+
+01:37.140 --> 01:37.180
+il
+
+01:37.180 --> 01:37.580
+faudrait
+
+01:37.580 --> 01:38.080
+remonter
+
+01:38.080 --> 01:38.580
+très
+
+01:38.580 --> 01:38.700
+très
+
+01:38.700 --> 01:39.320
+finement
+
+01:39.320 --> 01:39.700
+toute
+
+01:39.700 --> 01:40.060
+l'histoire
+
+01:40.060 --> 01:40.240
+des
+
+01:40.240 --> 01:40.480
+objets
+
+01:40.480 --> 01:41.020
+techniques
+
+01:41.020 --> 01:41.680
+et de
+
+01:41.680 --> 01:41.840
+leur
+
+01:41.840 --> 01:42.320
+insertion
+
+01:42.320 --> 01:42.480
+dans
+
+01:42.480 --> 01:42.660
+nos
+
+01:42.660 --> 01:42.860
+vies
+
+01:42.900 --> 01:43.060
+pour
+
+01:43.060 --> 01:43.660
+déterminer
+
+01:43.660 --> 01:43.940
+si ce
+
+01:43.940 --> 01:44.260
+rapport
+
+01:44.260 --> 01:44.740
+est
+
+01:44.740 --> 01:45.300
+totalement
+
+01:45.300 --> 01:45.740
+inédit.
+
+01:46.100 --> 01:46.360
+Mais
+
+01:46.360 --> 01:46.920
+j'ai
+
+01:46.920 --> 01:47.360
+l'impression
+
+01:47.360 --> 01:47.560
+comme
+
+01:47.560 --> 01:47.960
+ça que
+
+01:47.960 --> 01:48.460
+Nicolas
+
+01:48.460 --> 01:48.700
+ne se
+
+01:48.700 --> 01:48.880
+trompe
+
+01:48.880 --> 01:49.080
+pas
+
+01:49.080 --> 01:49.340
+vraiment.
+
+01:49.880 --> 01:50.080
+Pour
+
+01:50.080 --> 01:50.240
+autant
+
+01:50.240 --> 01:50.520
+que je
+
+01:50.520 --> 01:51.140
+sache,
+
+01:51.140 --> 01:51.360
+il y a
+
+01:51.360 --> 01:51.680
+eu
+
+01:51.680 --> 01:51.880
+plein
+
+01:51.880 --> 01:52.060
+de
+
+01:52.060 --> 01:52.600
+discussions
+
+01:52.600 --> 01:52.940
+autour
+
+01:52.940 --> 01:53.520
+de la
+
+01:53.520 --> 01:53.860
+voiture
+
+01:53.860 --> 01:54.060
+ou
+
+01:54.060 --> 01:54.440
+même
+
+01:54.440 --> 01:54.600
+du
+
+01:54.600 --> 01:54.980
+téléphone.
+
+01:55.340 --> 01:55.720
+Mais
+
+01:55.720 --> 01:56.020
+la
+
+01:56.020 --> 01:56.400
+dépendance
+
+01:56.400 --> 01:56.620
+n'était
+
+01:56.620 --> 01:57.160
+pas du
+
+01:57.160 --> 01:57.460
+même
+
+01:57.460 --> 01:57.780
+ordre.
+
+01:57.780 --> 01:57.980
+Donc
+
+01:57.980 --> 01:58.340
+le
+
+01:58.340 --> 01:58.620
+rejet
+
+01:58.620 --> 01:58.780
+non
+
+01:58.780 --> 01:58.940
+plus
+
+01:58.940 --> 01:59.120
+n'était
+
+01:59.120 --> 01:59.380
+pas du
+
+01:59.380 --> 01:59.560
+même
+
+01:59.560 --> 01:59.840
+ordre.
+
+01:59.980 --> 02:00.180
+On
+
+02:00.180 --> 02:00.380
+peut
+
+02:00.380 --> 02:00.660
+adorer
+
+02:00.660 --> 02:00.880
+sa
+
+02:00.880 --> 02:01.460
+bagnole,
+
+02:01.460 --> 02:01.560
+en
+
+02:01.560 --> 02:01.740
+avoir
+
+02:01.740 --> 02:02.100
+besoin
+
+02:02.100 --> 02:02.340
+pour
+
+02:02.340 --> 02:02.680
+plein
+
+02:02.680 --> 02:02.800
+de
+
+02:02.800 --> 02:03.020
+choses.
+
+02:03.280 --> 02:03.460
+Et
+
+02:03.460 --> 02:03.860
+bien,
+
+02:03.860 --> 02:03.980
+le
+
+02:03.980 --> 02:04.680
+soir,
+
+02:04.680 --> 02:04.900
+quand
+
+02:04.900 --> 02:05.140
+on va
+
+02:05.140 --> 02:05.380
+se
+
+02:05.380 --> 02:05.800
+coucher,
+
+02:05.800 --> 02:06.220
+on la
+
+02:06.220 --> 02:06.360
+laisse.
+
+02:06.980 --> 02:07.360
+On ne
+
+02:07.360 --> 02:07.480
+l'a
+
+02:07.480 --> 02:07.680
+pas
+
+02:07.680 --> 02:07.800
+dans
+
+02:07.800 --> 02:08.060
+la
+
+02:08.060 --> 02:08.260
+main
+
+02:08.260 --> 02:08.440
+quand
+
+02:08.440 --> 02:08.680
+on est
+
+02:08.680 --> 02:09.040
+au
+
+02:09.040 --> 02:09.140
+lit,
+
+02:09.140 --> 02:09.300
+on ne
+
+02:09.300 --> 02:09.500
+l'emmène
+
+02:09.500 --> 02:09.860
+pas au
+
+02:09.860 --> 02:10.480
+chiottes.
+
+02:10.860 --> 02:11.040
+On
+
+02:11.040 --> 02:11.280
+pouvait
+
+02:11.280 --> 02:11.480
+être
+
+02:11.480 --> 02:12.220
+énervé
+
+02:12.220 --> 02:12.440
+par
+
+02:12.440 --> 02:12.700
+son
+
+02:12.700 --> 02:13.100
+môme
+
+02:13.100 --> 02:13.340
+qui
+
+02:13.340 --> 02:13.760
+occupait
+
+02:13.760 --> 02:13.800
+la
+
+02:13.800 --> 02:14.080
+ligne
+
+02:14.080 --> 02:14.140
+de
+
+02:14.140 --> 02:14.600
+téléphone
+
+02:14.600 --> 02:14.820
+pendant
+
+02:14.820 --> 02:15.200
+une
+
+02:15.200 --> 02:15.360
+heure
+
+02:15.360 --> 02:15.540
+chaque
+
+02:15.540 --> 02:15.800
+soir
+
+02:15.800 --> 02:15.960
+pour
+
+02:15.960 --> 02:16.280
+discuter
+
+02:16.280 --> 02:16.480
+avec
+
+02:16.480 --> 02:16.600
+un
+
+02:16.600 --> 02:16.900
+copain.
+
+02:17.280 --> 02:17.460
+Mais
+
+02:17.460 --> 02:17.940
+ça ne
+
+02:17.940 --> 02:18.400
+ressemblait
+
+02:18.400 --> 02:18.940
+pas à
+
+02:18.940 --> 02:18.980
+ce
+
+02:18.980 --> 02:19.100
+qu'on
+
+02:19.100 --> 02:19.480
+peut
+
+02:19.480 --> 02:20.120
+ressentir
+
+02:20.120 --> 02:20.460
+à voir
+
+02:20.460 --> 02:20.680
+ce
+
+02:20.680 --> 02:20.920
+même
+
+02:20.920 --> 02:21.340
+môme
+
+02:21.340 --> 02:21.880
+aujourd'hui,
+
+02:22.140 --> 02:22.940
+continuellement
+
+02:22.940 --> 02:23.180
+avec
+
+02:23.180 --> 02:23.380
+son
+
+02:23.380 --> 02:23.760
+smartphone
+
+02:23.760 --> 02:23.940
+dans
+
+02:23.940 --> 02:24.000
+la
+
+02:24.000 --> 02:24.360
+main,
+
+02:24.360 --> 02:24.520
+comme
+
+02:24.520 --> 02:24.640
+si
+
+02:24.640 --> 02:24.820
+c'était
+
+02:24.820 --> 02:25.060
+une
+
+02:25.060 --> 02:25.220
+sorte
+
+02:25.220 --> 02:25.300
+de
+
+02:25.300 --> 02:25.820
+pacemaker
+
+02:25.820 --> 02:26.300
+externe,
+
+02:26.340 --> 02:26.580
+comme
+
+02:26.580 --> 02:26.860
+si le
+
+02:26.860 --> 02:27.360
+lâcher
+
+02:27.360 --> 02:27.560
+allait
+
+02:27.560 --> 02:27.860
+entraîner
+
+02:27.860 --> 02:28.000
+sa
+
+02:28.000 --> 02:28.220
+mort
+
+02:28.220 --> 02:28.840
+immédiate.
+
+02:29.040 --> 02:29.280
+Bon,
+
+02:29.280 --> 02:29.460
+je dis
+
+02:29.460 --> 02:29.640
+ça
+
+02:29.640 --> 02:29.740
+pour
+
+02:29.740 --> 02:29.880
+le
+
+02:29.880 --> 02:30.320
+môme,
+
+02:30.320 --> 02:30.520
+mais
+
+02:30.520 --> 02:30.820
+c'est
+
+02:30.820 --> 02:31.140
+évidemment
+
+02:31.140 --> 02:31.480
+valable
+
+02:31.480 --> 02:31.620
+pour
+
+02:31.620 --> 02:31.760
+nous
+
+02:31.760 --> 02:31.960
+aussi.
+
+02:32.340 --> 02:33.460
+Donc,
+
+02:33.460 --> 02:33.660
+rapport
+
+02:33.660 --> 02:34.240
+inédit.
+
+02:34.240 --> 02:35.480
+D'accord.
+
+02:35.480 --> 02:35.820
+Mais
+
+02:35.820 --> 02:36.320
+pourquoi
+
+02:36.320 --> 02:36.680
+a-t-on
+
+02:36.680 --> 02:37.060
+l'impression
+
+02:37.060 --> 02:37.260
+qu'on
+
+02:37.260 --> 02:37.440
+n'en
+
+02:37.440 --> 02:37.900
+sortira
+
+02:37.900 --> 02:38.220
+jamais?
+
+02:38.860 --> 02:39.340
+Est-ce
+
+02:39.340 --> 02:39.460
+qu'il
+
+02:39.460 --> 02:39.620
+faut
+
+02:39.620 --> 02:39.780
+en
+
+02:39.780 --> 02:40.120
+remettre
+
+02:40.120 --> 02:40.340
+la
+
+02:40.340 --> 02:40.660
+faute
+
+02:40.660 --> 02:40.940
+sur
+
+02:40.940 --> 02:41.280
+les
+
+02:41.280 --> 02:41.440
+gens
+
+02:41.440 --> 02:41.580
+qui
+
+02:41.580 --> 02:41.720
+ont
+
+02:41.720 --> 02:42.300
+créé
+
+02:42.300 --> 02:42.460
+cet
+
+02:42.460 --> 02:42.780
+outil
+
+02:42.780 --> 02:43.340
+merveilleux
+
+02:43.340 --> 02:43.500
+et
+
+02:43.500 --> 02:43.860
+diabolique,
+
+02:43.860 --> 02:43.920
+et
+
+02:43.920 --> 02:44.400
+diabolique
+
+02:44.400 --> 02:44.660
+parce
+
+02:44.660 --> 02:44.840
+que
+
+02:44.840 --> 02:45.320
+merveilleux?
+
+02:46.340 --> 02:47.040
+Les
+
+02:47.040 --> 02:47.480
+économistes
+
+02:47.480 --> 02:47.680
+parlent
+
+02:47.680 --> 02:47.820
+de
+
+02:47.820 --> 02:48.360
+dépendance
+
+02:48.360 --> 02:48.500
+du
+
+02:48.500 --> 02:48.820
+sentier.
+
+02:48.860 --> 02:49.100
+C'est
+
+02:49.100 --> 02:49.340
+l'idée
+
+02:49.340 --> 02:49.700
+qu'on
+
+02:49.700 --> 02:49.880
+est
+
+02:49.880 --> 02:50.540
+sur un
+
+02:50.540 --> 02:50.780
+sentier
+
+02:50.780 --> 02:50.940
+qui a
+
+02:50.940 --> 02:51.120
+été
+
+02:51.120 --> 02:51.900
+établi,
+
+02:51.900 --> 02:52.120
+soit
+
+02:52.120 --> 02:52.720
+volontairement
+
+02:52.720 --> 02:52.800
+en
+
+02:52.800 --> 02:53.060
+marchant
+
+02:53.060 --> 02:54.240
+dessus,
+
+02:54.240 --> 02:54.920
+soit
+
+02:54.920 --> 02:55.360
+en
+
+02:55.360 --> 02:55.500
+définissant
+
+02:55.500 --> 02:55.760
+des
+
+02:55.760 --> 02:56.040
+bornes,
+
+02:56.040 --> 02:56.080
+en
+
+02:56.080 --> 02:56.580
+définissant
+
+02:56.580 --> 02:56.820
+une
+
+02:56.820 --> 02:57.420
+signalétique.
+
diff --git a/tests/expected/tiny.en.cpu/nocond_bonjour_vous_allez_bien.mp3.words.json b/tests/expected/tiny.en.cpu/nocond_bonjour_vous_allez_bien.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..be3e848ef767849ee49d451215e9eb018ec0f049
--- /dev/null
+++ b/tests/expected/tiny.en.cpu/nocond_bonjour_vous_allez_bien.mp3.words.json
@@ -0,0 +1,204 @@
+{
+  "text": " Mohoo! Let's go with it again! Mohoo! Mohoo! Mohoo! Let's go with it again!",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.44,
+      "end": 2.98,
+      "text": " Mohoo! Let's go with it again!",
+      "tokens": [
+        50363,
+        337,
+        1219,
+        2238,
+        0,
+        3914,
+        338,
+        467,
+        351,
+        340,
+        757,
+        0,
+        50513
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.8020243644714355,
+      "compression_ratio": 0.7894736842105263,
+      "no_speech_prob": 0.11818066984415054,
+      "confidence": 0.496,
+      "words": [
+        {
+          "text": "Mohoo!",
+          "start": 0.44,
+          "end": 1.72,
+          "confidence": 0.271
+        },
+        {
+          "text": "Let's",
+          "start": 1.72,
+          "end": 2.04,
+          "confidence": 0.678
+        },
+        {
+          "text": "go",
+          "start": 2.04,
+          "end": 2.18,
+          "confidence": 0.914
+        },
+        {
+          "text": "with",
+          "start": 2.18,
+          "end": 2.38,
+          "confidence": 0.234
+        },
+        {
+          "text": "it",
+          "start": 2.38,
+          "end": 2.44,
+          "confidence": 0.933
+        },
+        {
+          "text": "again!",
+          "start": 2.44,
+          "end": 2.98,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 3000,
+      "start": 30.06,
+      "end": 31.25,
+      "text": " Mohoo!",
+      "tokens": [
+        337,
+        1219,
+        2238,
+        0
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.8320662379264832,
+      "compression_ratio": 0.7894736842105263,
+      "no_speech_prob": 0.15341022610664368,
+      "confidence": 0.308,
+      "words": [
+        {
+          "text": "Mohoo!",
+          "start": 30.06,
+          "end": 31.25,
+          "confidence": 0.308
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 3100,
+      "start": 31.25,
+      "end": 32.48,
+      "text": " Mohoo!",
+      "tokens": [
+        337,
+        1219,
+        2238,
+        0
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.767271101474762,
+      "compression_ratio": 0.7894736842105263,
+      "no_speech_prob": 0.1705959141254425,
+      "confidence": 0.329,
+      "words": [
+        {
+          "text": "Mohoo!",
+          "start": 31.25,
+          "end": 32.48,
+          "confidence": 0.329
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 3200,
+      "start": 32.98,
+      "end": 33.8,
+      "text": " Mohoo!",
+      "tokens": [
+        337,
+        1219,
+        2238,
+        0
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5514491200447083,
+      "compression_ratio": 0.7894736842105263,
+      "no_speech_prob": 0.1296440064907074,
+      "confidence": 0.338,
+      "words": [
+        {
+          "text": "Mohoo!",
+          "start": 32.98,
+          "end": 33.8,
+          "confidence": 0.338
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 3400,
+      "start": 34.4,
+      "end": 35.48,
+      "text": " Let's go with it again!",
+      "tokens": [
+        50363,
+        3914,
+        338,
+        467,
+        351,
+        340,
+        757,
+        0,
+        50463
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3764993667602539,
+      "compression_ratio": 0.7419354838709677,
+      "no_speech_prob": 0.05320969223976135,
+      "confidence": 0.815,
+      "words": [
+        {
+          "text": "Let's",
+          "start": 34.4,
+          "end": 34.58,
+          "confidence": 0.862
+        },
+        {
+          "text": "go",
+          "start": 34.58,
+          "end": 34.76,
+          "confidence": 0.923
+        },
+        {
+          "text": "with",
+          "start": 34.76,
+          "end": 34.96,
+          "confidence": 0.627
+        },
+        {
+          "text": "it",
+          "start": 34.96,
+          "end": 35.0,
+          "confidence": 0.686
+        },
+        {
+          "text": "again!",
+          "start": 35.0,
+          "end": 35.48,
+          "confidence": 0.992
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/tiny.en/accurate_bonjour_vous_allez_bien.mp3.words.json b/tests/expected/tiny.en/accurate_bonjour_vous_allez_bien.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..2e3ab6c3b9044538fc203c07d609c9cd0936f351
--- /dev/null
+++ b/tests/expected/tiny.en/accurate_bonjour_vous_allez_bien.mp3.words.json
@@ -0,0 +1,134 @@
+{
+  "text": " Mohoo, let's go with it again Mohoo, let's go with it again",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.42,
+      "end": 2.84,
+      "text": " Mohoo, let's go with it again",
+      "tokens": [
+        50363,
+        337,
+        1219,
+        2238,
+        11,
+        1309,
+        338,
+        467,
+        351,
+        340,
+        757,
+        50501
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7695202460655799,
+      "compression_ratio": 0.7837837837837838,
+      "no_speech_prob": 0.11803863942623138,
+      "confidence": 0.485,
+      "words": [
+        {
+          "text": "Mohoo,",
+          "start": 0.42,
+          "end": 1.38,
+          "confidence": 0.245
+        },
+        {
+          "text": "let's",
+          "start": 1.92,
+          "end": 2.2,
+          "confidence": 0.91
+        },
+        {
+          "text": "go",
+          "start": 2.2,
+          "end": 2.3,
+          "confidence": 0.908
+        },
+        {
+          "text": "with",
+          "start": 2.3,
+          "end": 2.46,
+          "confidence": 0.286
+        },
+        {
+          "text": "it",
+          "start": 2.46,
+          "end": 2.56,
+          "confidence": 0.939
+        },
+        {
+          "text": "again",
+          "start": 2.56,
+          "end": 2.84,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 3000,
+      "start": 32.86,
+      "end": 35.42,
+      "text": " Mohoo, let's go with it again",
+      "tokens": [
+        50363,
+        337,
+        1219,
+        2238,
+        11,
+        1309,
+        338,
+        467,
+        351,
+        340,
+        757,
+        50627
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4126271101144644,
+      "compression_ratio": 0.7837837837837838,
+      "no_speech_prob": 0.34721481800079346,
+      "confidence": 0.544,
+      "words": [
+        {
+          "text": "Mohoo,",
+          "start": 32.86,
+          "end": 34.02,
+          "confidence": 0.277
+        },
+        {
+          "text": "let's",
+          "start": 34.46,
+          "end": 34.74,
+          "confidence": 0.89
+        },
+        {
+          "text": "go",
+          "start": 34.74,
+          "end": 34.86,
+          "confidence": 0.935
+        },
+        {
+          "text": "with",
+          "start": 34.86,
+          "end": 34.98,
+          "confidence": 0.658
+        },
+        {
+          "text": "it",
+          "start": 34.98,
+          "end": 35.1,
+          "confidence": 0.79
+        },
+        {
+          "text": "again",
+          "start": 35.1,
+          "end": 35.42,
+          "confidence": 0.997
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/tiny.en/efficient_bonjour_vous_allez_bien.mp3.words.json b/tests/expected/tiny.en/efficient_bonjour_vous_allez_bien.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..fd22690c94ca48ebf75bd0ad7159776ca30f8161
--- /dev/null
+++ b/tests/expected/tiny.en/efficient_bonjour_vous_allez_bien.mp3.words.json
@@ -0,0 +1,136 @@
+{
+  "text": " Mohoo! Let's go with it again! Mohoo! Let's go with it again!",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.42,
+      "end": 2.8,
+      "text": " Mohoo! Let's go with it again!",
+      "tokens": [
+        50363,
+        337,
+        1219,
+        2238,
+        0,
+        3914,
+        338,
+        467,
+        351,
+        340,
+        757,
+        0,
+        50513
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.8020311764308384,
+      "compression_ratio": 0.7894736842105263,
+      "no_speech_prob": 0.11798259615898132,
+      "confidence": 0.496,
+      "words": [
+        {
+          "text": "Mohoo!",
+          "start": 0.42,
+          "end": 1.36,
+          "confidence": 0.271
+        },
+        {
+          "text": "Let's",
+          "start": 1.9,
+          "end": 2.18,
+          "confidence": 0.677
+        },
+        {
+          "text": "go",
+          "start": 2.18,
+          "end": 2.32,
+          "confidence": 0.914
+        },
+        {
+          "text": "with",
+          "start": 2.32,
+          "end": 2.46,
+          "confidence": 0.233
+        },
+        {
+          "text": "it",
+          "start": 2.46,
+          "end": 2.56,
+          "confidence": 0.933
+        },
+        {
+          "text": "again!",
+          "start": 2.56,
+          "end": 2.8,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 3000,
+      "start": 32.98,
+      "end": 35.44,
+      "text": " Mohoo! Let's go with it again!",
+      "tokens": [
+        50363,
+        337,
+        1219,
+        2238,
+        0,
+        3914,
+        338,
+        467,
+        351,
+        340,
+        757,
+        0,
+        50663
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1937453576496669,
+      "compression_ratio": 0.7894736842105263,
+      "no_speech_prob": 0.45197251439094543,
+      "confidence": 0.952,
+      "words": [
+        {
+          "text": "Mohoo!",
+          "start": 32.98,
+          "end": 34.02,
+          "confidence": 0.896
+        },
+        {
+          "text": "Let's",
+          "start": 34.44,
+          "end": 34.72,
+          "confidence": 0.96
+        },
+        {
+          "text": "go",
+          "start": 34.72,
+          "end": 34.84,
+          "confidence": 0.99
+        },
+        {
+          "text": "with",
+          "start": 34.84,
+          "end": 35.0,
+          "confidence": 0.985
+        },
+        {
+          "text": "it",
+          "start": 35.0,
+          "end": 35.1,
+          "confidence": 0.991
+        },
+        {
+          "text": "again!",
+          "start": 35.1,
+          "end": 35.44,
+          "confidence": 0.998
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/tiny.en/nocond_bonjour_vous_allez_bien.mp3.words.json b/tests/expected/tiny.en/nocond_bonjour_vous_allez_bien.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..7e5c247abd49416c05ae5573819ef3e295747932
--- /dev/null
+++ b/tests/expected/tiny.en/nocond_bonjour_vous_allez_bien.mp3.words.json
@@ -0,0 +1,154 @@
+{
+  "text": " Mohoo! Let's go with it again! Mohoo! Let's go with it again!",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.42,
+      "end": 2.8,
+      "text": " Mohoo! Let's go with it again!",
+      "tokens": [
+        50363,
+        337,
+        1219,
+        2238,
+        0,
+        3914,
+        338,
+        467,
+        351,
+        340,
+        757,
+        0,
+        50513
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.8020311764308384,
+      "compression_ratio": 0.7894736842105263,
+      "no_speech_prob": 0.11798259615898132,
+      "confidence": 0.496,
+      "words": [
+        {
+          "text": "Mohoo!",
+          "start": 0.42,
+          "end": 1.36,
+          "confidence": 0.271
+        },
+        {
+          "text": "Let's",
+          "start": 1.9,
+          "end": 2.18,
+          "confidence": 0.677
+        },
+        {
+          "text": "go",
+          "start": 2.18,
+          "end": 2.32,
+          "confidence": 0.914
+        },
+        {
+          "text": "with",
+          "start": 2.32,
+          "end": 2.46,
+          "confidence": 0.233
+        },
+        {
+          "text": "it",
+          "start": 2.46,
+          "end": 2.56,
+          "confidence": 0.933
+        },
+        {
+          "text": "again!",
+          "start": 2.56,
+          "end": 2.8,
+          "confidence": 0.996
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 3000,
+      "start": 30.0,
+      "end": 30.06,
+      "text": " Mohoo!",
+      "tokens": [
+        50363,
+        337,
+        1219,
+        2238,
+        0,
+        50413
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.8368260264396667,
+      "compression_ratio": 0.7894736842105263,
+      "no_speech_prob": 0.13588112592697144,
+      "confidence": 0.306,
+      "words": [
+        {
+          "text": "Mohoo!",
+          "start": 30.0,
+          "end": 30.06,
+          "confidence": 0.306
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 3000,
+      "start": 34.38,
+      "end": 35.36,
+      "text": " Let's go with it again!",
+      "tokens": [
+        50413,
+        3914,
+        338,
+        467,
+        351,
+        340,
+        757,
+        0,
+        50613
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.8368260264396667,
+      "compression_ratio": 0.7894736842105263,
+      "no_speech_prob": 0.13588112592697144,
+      "confidence": 0.847,
+      "words": [
+        {
+          "text": "Let's",
+          "start": 34.38,
+          "end": 34.74,
+          "confidence": 0.876
+        },
+        {
+          "text": "go",
+          "start": 34.74,
+          "end": 34.86,
+          "confidence": 0.96
+        },
+        {
+          "text": "with",
+          "start": 34.86,
+          "end": 34.98,
+          "confidence": 0.619
+        },
+        {
+          "text": "it",
+          "start": 34.98,
+          "end": 35.1,
+          "confidence": 0.811
+        },
+        {
+          "text": "again!",
+          "start": 35.1,
+          "end": 35.36,
+          "confidence": 0.997
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_auto.cpu/gaenswein15.mp3.words.json b/tests/expected/tiny_auto.cpu/gaenswein15.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..2fa1b2d83ea55923062a1564d4750ee40a08e1b9
--- /dev/null
+++ b/tests/expected/tiny_auto.cpu/gaenswein15.mp3.words.json
@@ -0,0 +1,318 @@
+{
+  "text": " Wie wieder zu dazu ist Meshfuchs von 1962 als Meshale für die außerordentliche Form des grullischen Rätos ist dann nicht so weitergegangen wie sich Papsbelle dick das gewünscht hatte. Das hat er als Meshale im Rätos.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.9,
+      "end": 12.76,
+      "text": " Wie wieder zu dazu ist Meshfuchs von 1962 als Meshale für die außerordentliche Form des grullischen Rätos ist dann nicht so weitergegangen wie sich Papsbelle dick das gewünscht hatte.",
+      "tokens": [
+        9233,
+        6216,
+        2164,
+        13034,
+        1418,
+        376,
+        14935,
+        69,
+        37503,
+        2957,
+        39498,
+        3907,
+        376,
+        14935,
+        1220,
+        2959,
+        978,
+        39428,
+        765,
+        7698,
+        68,
+        10126,
+        730,
+        677,
+        858,
+        6282,
+        497,
+        3628,
+        329,
+        1418,
+        3594,
+        1979,
+        370,
+        8988,
+        432,
+        47152,
+        3355,
+        3041,
+        430,
+        2382,
+        65,
+        4434,
+        18659,
+        1482,
+        6906,
+        3412,
+        82,
+        4701,
+        13299,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6555103008563702,
+      "compression_ratio": 1.2619047619047619,
+      "no_speech_prob": 0.11051499098539352,
+      "confidence": 0.541,
+      "words": [
+        {
+          "text": "Wie",
+          "start": 0.9,
+          "end": 1.06,
+          "confidence": 0.478
+        },
+        {
+          "text": "wieder",
+          "start": 1.06,
+          "end": 1.32,
+          "confidence": 0.901
+        },
+        {
+          "text": "zu",
+          "start": 1.32,
+          "end": 1.54,
+          "confidence": 0.249
+        },
+        {
+          "text": "dazu",
+          "start": 1.54,
+          "end": 1.86,
+          "confidence": 0.131
+        },
+        {
+          "text": "ist",
+          "start": 1.86,
+          "end": 2.12,
+          "confidence": 0.586
+        },
+        {
+          "text": "Meshfuchs",
+          "start": 2.12,
+          "end": 2.72,
+          "confidence": 0.332
+        },
+        {
+          "text": "von",
+          "start": 2.72,
+          "end": 2.94,
+          "confidence": 0.626
+        },
+        {
+          "text": "1962",
+          "start": 2.94,
+          "end": 4.72,
+          "confidence": 0.208
+        },
+        {
+          "text": "als",
+          "start": 4.72,
+          "end": 5.22,
+          "confidence": 0.885
+        },
+        {
+          "text": "Meshale",
+          "start": 5.22,
+          "end": 5.7,
+          "confidence": 0.385
+        },
+        {
+          "text": "für",
+          "start": 5.7,
+          "end": 5.9,
+          "confidence": 0.933
+        },
+        {
+          "text": "die",
+          "start": 5.9,
+          "end": 6.08,
+          "confidence": 0.972
+        },
+        {
+          "text": "außerordentliche",
+          "start": 6.08,
+          "end": 6.98,
+          "confidence": 0.899
+        },
+        {
+          "text": "Form",
+          "start": 6.98,
+          "end": 7.22,
+          "confidence": 0.655
+        },
+        {
+          "text": "des",
+          "start": 7.22,
+          "end": 7.58,
+          "confidence": 0.971
+        },
+        {
+          "text": "grullischen",
+          "start": 7.58,
+          "end": 8.04,
+          "confidence": 0.384
+        },
+        {
+          "text": "Rätos",
+          "start": 8.04,
+          "end": 8.58,
+          "confidence": 0.368
+        },
+        {
+          "text": "ist",
+          "start": 8.58,
+          "end": 9.6,
+          "confidence": 0.549
+        },
+        {
+          "text": "dann",
+          "start": 9.6,
+          "end": 9.74,
+          "confidence": 0.5
+        },
+        {
+          "text": "nicht",
+          "start": 9.74,
+          "end": 9.92,
+          "confidence": 0.936
+        },
+        {
+          "text": "so",
+          "start": 9.92,
+          "end": 10.08,
+          "confidence": 0.953
+        },
+        {
+          "text": "weitergegangen",
+          "start": 10.08,
+          "end": 10.86,
+          "confidence": 0.74
+        },
+        {
+          "text": "wie",
+          "start": 10.86,
+          "end": 11.04,
+          "confidence": 0.703
+        },
+        {
+          "text": "sich",
+          "start": 11.04,
+          "end": 11.22,
+          "confidence": 0.939
+        },
+        {
+          "text": "Papsbelle",
+          "start": 11.22,
+          "end": 11.62,
+          "confidence": 0.356
+        },
+        {
+          "text": "dick",
+          "start": 11.62,
+          "end": 11.84,
+          "confidence": 0.319
+        },
+        {
+          "text": "das",
+          "start": 11.84,
+          "end": 12.08,
+          "confidence": 0.844
+        },
+        {
+          "text": "gewünscht",
+          "start": 12.08,
+          "end": 12.48,
+          "confidence": 0.818
+        },
+        {
+          "text": "hatte.",
+          "start": 12.48,
+          "end": 12.76,
+          "confidence": 0.922
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 1300,
+      "start": 13.98,
+      "end": 15.22,
+      "text": " Das hat er als Meshale im Rätos.",
+      "tokens": [
+        50364,
+        2846,
+        2385,
+        1189,
+        3907,
+        376,
+        14935,
+        1220,
+        566,
+        497,
+        3628,
+        329,
+        13,
+        51314
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9505692799886067,
+      "compression_ratio": 0.8048780487804879,
+      "no_speech_prob": 0.044665463268756866,
+      "confidence": 0.381,
+      "words": [
+        {
+          "text": "Das",
+          "start": 13.98,
+          "end": 14.2,
+          "confidence": 0.841
+        },
+        {
+          "text": "hat",
+          "start": 14.2,
+          "end": 14.32,
+          "confidence": 0.878
+        },
+        {
+          "text": "er",
+          "start": 14.32,
+          "end": 14.46,
+          "confidence": 0.606
+        },
+        {
+          "text": "als",
+          "start": 14.46,
+          "end": 14.7,
+          "confidence": 0.626
+        },
+        {
+          "text": "Meshale",
+          "start": 14.7,
+          "end": 15.0,
+          "confidence": 0.206
+        },
+        {
+          "text": "im",
+          "start": 15.0,
+          "end": 15.04,
+          "confidence": 0.101
+        },
+        {
+          "text": "Rätos.",
+          "start": 15.04,
+          "end": 15.22,
+          "confidence": 0.464
+        }
+      ]
+    }
+  ],
+  "language": "de"
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_auto.cpu/radio_short.mp3.words.json b/tests/expected/tiny_auto.cpu/radio_short.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..f2388cb2c74572247a52a55a46815f03a82a84a0
--- /dev/null
+++ b/tests/expected/tiny_auto.cpu/radio_short.mp3.words.json
@@ -0,0 +1,3786 @@
+{
+  "text": " What are you telling me, guys? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, guys? What are you telling me, guys? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude?",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.06,
+      "end": 5.92,
+      "text": " What are you telling me, guys?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        1074,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4002814409209461,
+      "compression_ratio": 4.660377358490566,
+      "no_speech_prob": 0.5112143754959106,
+      "confidence": 0.343,
+      "words": [
+        {
+          "text": "What",
+          "start": 0.06,
+          "end": 4.9,
+          "confidence": 0.041
+        },
+        {
+          "text": "are",
+          "start": 4.9,
+          "end": 5.18,
+          "confidence": 0.603
+        },
+        {
+          "text": "you",
+          "start": 5.18,
+          "end": 5.42,
+          "confidence": 0.97
+        },
+        {
+          "text": "telling",
+          "start": 5.42,
+          "end": 5.64,
+          "confidence": 0.354
+        },
+        {
+          "text": "me,",
+          "start": 5.64,
+          "end": 5.88,
+          "confidence": 0.622
+        },
+        {
+          "text": "guys?",
+          "start": 5.88,
+          "end": 5.92,
+          "confidence": 0.307
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 6.5,
+      "end": 7.5,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4002814409209461,
+      "compression_ratio": 4.660377358490566,
+      "no_speech_prob": 0.5112143754959106,
+      "confidence": 0.677,
+      "words": [
+        {
+          "text": "What",
+          "start": 6.5,
+          "end": 6.92,
+          "confidence": 0.885
+        },
+        {
+          "text": "are",
+          "start": 6.92,
+          "end": 6.96,
+          "confidence": 0.936
+        },
+        {
+          "text": "you",
+          "start": 6.96,
+          "end": 7.02,
+          "confidence": 0.993
+        },
+        {
+          "text": "telling",
+          "start": 7.02,
+          "end": 7.24,
+          "confidence": 0.904
+        },
+        {
+          "text": "me,",
+          "start": 7.24,
+          "end": 7.46,
+          "confidence": 0.984
+        },
+        {
+          "text": "dude?",
+          "start": 7.46,
+          "end": 7.5,
+          "confidence": 0.131
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 7.52,
+      "end": 8.28,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4002814409209461,
+      "compression_ratio": 4.660377358490566,
+      "no_speech_prob": 0.5112143754959106,
+      "confidence": 0.827,
+      "words": [
+        {
+          "text": "What",
+          "start": 7.52,
+          "end": 7.56,
+          "confidence": 0.545
+        },
+        {
+          "text": "are",
+          "start": 7.56,
+          "end": 7.6,
+          "confidence": 0.851
+        },
+        {
+          "text": "you",
+          "start": 7.6,
+          "end": 7.64,
+          "confidence": 0.994
+        },
+        {
+          "text": "telling",
+          "start": 7.64,
+          "end": 7.68,
+          "confidence": 0.849
+        },
+        {
+          "text": "me,",
+          "start": 7.68,
+          "end": 8.16,
+          "confidence": 0.951
+        },
+        {
+          "text": "dude?",
+          "start": 8.16,
+          "end": 8.28,
+          "confidence": 0.857
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 10.46,
+      "end": 12.48,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4002814409209461,
+      "compression_ratio": 4.660377358490566,
+      "no_speech_prob": 0.5112143754959106,
+      "confidence": 0.774,
+      "words": [
+        {
+          "text": "What",
+          "start": 10.46,
+          "end": 10.54,
+          "confidence": 0.422
+        },
+        {
+          "text": "are",
+          "start": 10.54,
+          "end": 10.6,
+          "confidence": 0.79
+        },
+        {
+          "text": "you",
+          "start": 10.6,
+          "end": 11.38,
+          "confidence": 0.994
+        },
+        {
+          "text": "telling",
+          "start": 11.38,
+          "end": 11.66,
+          "confidence": 0.809
+        },
+        {
+          "text": "me,",
+          "start": 11.66,
+          "end": 12.44,
+          "confidence": 0.956
+        },
+        {
+          "text": "dude?",
+          "start": 12.44,
+          "end": 12.48,
+          "confidence": 0.837
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 12.48,
+      "end": 14.46,
+      "text": " What are you telling me, guys?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        1074,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4002814409209461,
+      "compression_ratio": 4.660377358490566,
+      "no_speech_prob": 0.5112143754959106,
+      "confidence": 0.762,
+      "words": [
+        {
+          "text": "What",
+          "start": 12.48,
+          "end": 12.52,
+          "confidence": 0.504
+        },
+        {
+          "text": "are",
+          "start": 12.52,
+          "end": 12.56,
+          "confidence": 0.845
+        },
+        {
+          "text": "you",
+          "start": 12.56,
+          "end": 12.6,
+          "confidence": 0.994
+        },
+        {
+          "text": "telling",
+          "start": 12.6,
+          "end": 12.64,
+          "confidence": 0.844
+        },
+        {
+          "text": "me,",
+          "start": 12.64,
+          "end": 13.18,
+          "confidence": 0.962
+        },
+        {
+          "text": "guys?",
+          "start": 13.18,
+          "end": 14.46,
+          "confidence": 0.57
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 0,
+      "start": 16.5,
+      "end": 21.3,
+      "text": " What are you telling me, guys?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        1074,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4002814409209461,
+      "compression_ratio": 4.660377358490566,
+      "no_speech_prob": 0.5112143754959106,
+      "confidence": 0.936,
+      "words": [
+        {
+          "text": "What",
+          "start": 16.5,
+          "end": 20.42,
+          "confidence": 0.887
+        },
+        {
+          "text": "are",
+          "start": 20.42,
+          "end": 20.54,
+          "confidence": 0.936
+        },
+        {
+          "text": "you",
+          "start": 20.54,
+          "end": 20.7,
+          "confidence": 0.996
+        },
+        {
+          "text": "telling",
+          "start": 20.7,
+          "end": 20.94,
+          "confidence": 0.934
+        },
+        {
+          "text": "me,",
+          "start": 20.94,
+          "end": 21.26,
+          "confidence": 0.897
+        },
+        {
+          "text": "guys?",
+          "start": 21.26,
+          "end": 21.3,
+          "confidence": 0.969
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 0,
+      "start": 21.5,
+      "end": 22.78,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4002814409209461,
+      "compression_ratio": 4.660377358490566,
+      "no_speech_prob": 0.5112143754959106,
+      "confidence": 0.953,
+      "words": [
+        {
+          "text": "What",
+          "start": 21.5,
+          "end": 22.2,
+          "confidence": 0.951
+        },
+        {
+          "text": "are",
+          "start": 22.2,
+          "end": 22.24,
+          "confidence": 0.966
+        },
+        {
+          "text": "you",
+          "start": 22.24,
+          "end": 22.36,
+          "confidence": 0.997
+        },
+        {
+          "text": "telling",
+          "start": 22.36,
+          "end": 22.5,
+          "confidence": 0.862
+        },
+        {
+          "text": "me,",
+          "start": 22.5,
+          "end": 22.7,
+          "confidence": 0.984
+        },
+        {
+          "text": "dude?",
+          "start": 22.7,
+          "end": 22.78,
+          "confidence": 0.967
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 0,
+      "start": 22.78,
+      "end": 23.02,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4002814409209461,
+      "compression_ratio": 4.660377358490566,
+      "no_speech_prob": 0.5112143754959106,
+      "confidence": 0.856,
+      "words": [
+        {
+          "text": "What",
+          "start": 22.78,
+          "end": 22.82,
+          "confidence": 0.54
+        },
+        {
+          "text": "are",
+          "start": 22.82,
+          "end": 22.86,
+          "confidence": 0.888
+        },
+        {
+          "text": "you",
+          "start": 22.86,
+          "end": 22.9,
+          "confidence": 0.996
+        },
+        {
+          "text": "telling",
+          "start": 22.9,
+          "end": 22.94,
+          "confidence": 0.882
+        },
+        {
+          "text": "me,",
+          "start": 22.94,
+          "end": 22.98,
+          "confidence": 0.975
+        },
+        {
+          "text": "dude?",
+          "start": 22.98,
+          "end": 23.02,
+          "confidence": 0.955
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 2600,
+      "start": 26.02,
+      "end": 28.74,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.26995800480698096,
+      "compression_ratio": 9.136363636363637,
+      "no_speech_prob": 0.0041488660499453545,
+      "confidence": 0.523,
+      "words": [
+        {
+          "text": "What",
+          "start": 26.02,
+          "end": 26.06,
+          "confidence": 0.145
+        },
+        {
+          "text": "are",
+          "start": 26.06,
+          "end": 27.16,
+          "confidence": 0.442
+        },
+        {
+          "text": "you",
+          "start": 27.16,
+          "end": 28.24,
+          "confidence": 0.944
+        },
+        {
+          "text": "telling",
+          "start": 28.24,
+          "end": 28.28,
+          "confidence": 0.536
+        },
+        {
+          "text": "me,",
+          "start": 28.28,
+          "end": 28.7,
+          "confidence": 0.926
+        },
+        {
+          "text": "dude?",
+          "start": 28.7,
+          "end": 28.74,
+          "confidence": 0.683
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 2600,
+      "start": 30.5,
+      "end": 31.8,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.26995800480698096,
+      "compression_ratio": 9.136363636363637,
+      "no_speech_prob": 0.0041488660499453545,
+      "confidence": 0.586,
+      "words": [
+        {
+          "text": "What",
+          "start": 30.5,
+          "end": 31.1,
+          "confidence": 0.193
+        },
+        {
+          "text": "are",
+          "start": 31.1,
+          "end": 31.14,
+          "confidence": 0.532
+        },
+        {
+          "text": "you",
+          "start": 31.14,
+          "end": 31.46,
+          "confidence": 0.966
+        },
+        {
+          "text": "telling",
+          "start": 31.46,
+          "end": 31.5,
+          "confidence": 0.588
+        },
+        {
+          "text": "me,",
+          "start": 31.5,
+          "end": 31.68,
+          "confidence": 0.895
+        },
+        {
+          "text": "dude?",
+          "start": 31.68,
+          "end": 31.8,
+          "confidence": 0.776
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 2600,
+      "start": 31.8,
+      "end": 32.58,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.26995800480698096,
+      "compression_ratio": 9.136363636363637,
+      "no_speech_prob": 0.0041488660499453545,
+      "confidence": 0.664,
+      "words": [
+        {
+          "text": "What",
+          "start": 31.8,
+          "end": 32.26,
+          "confidence": 0.321
+        },
+        {
+          "text": "are",
+          "start": 32.26,
+          "end": 32.3,
+          "confidence": 0.594
+        },
+        {
+          "text": "you",
+          "start": 32.3,
+          "end": 32.4,
+          "confidence": 0.972
+        },
+        {
+          "text": "telling",
+          "start": 32.4,
+          "end": 32.44,
+          "confidence": 0.609
+        },
+        {
+          "text": "me,",
+          "start": 32.44,
+          "end": 32.48,
+          "confidence": 0.891
+        },
+        {
+          "text": "dude?",
+          "start": 32.48,
+          "end": 32.58,
+          "confidence": 0.85
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 2600,
+      "start": 33.52,
+      "end": 35.4,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.26995800480698096,
+      "compression_ratio": 9.136363636363637,
+      "no_speech_prob": 0.0041488660499453545,
+      "confidence": 0.711,
+      "words": [
+        {
+          "text": "What",
+          "start": 33.52,
+          "end": 33.56,
+          "confidence": 0.44
+        },
+        {
+          "text": "are",
+          "start": 33.56,
+          "end": 33.66,
+          "confidence": 0.602
+        },
+        {
+          "text": "you",
+          "start": 33.66,
+          "end": 33.74,
+          "confidence": 0.972
+        },
+        {
+          "text": "telling",
+          "start": 33.74,
+          "end": 34.84,
+          "confidence": 0.635
+        },
+        {
+          "text": "me,",
+          "start": 34.84,
+          "end": 35.36,
+          "confidence": 0.901
+        },
+        {
+          "text": "dude?",
+          "start": 35.36,
+          "end": 35.4,
+          "confidence": 0.88
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 2600,
+      "start": 36.24,
+      "end": 38.1,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.26995800480698096,
+      "compression_ratio": 9.136363636363637,
+      "no_speech_prob": 0.0041488660499453545,
+      "confidence": 0.745,
+      "words": [
+        {
+          "text": "What",
+          "start": 36.24,
+          "end": 36.34,
+          "confidence": 0.474
+        },
+        {
+          "text": "are",
+          "start": 36.34,
+          "end": 36.38,
+          "confidence": 0.621
+        },
+        {
+          "text": "you",
+          "start": 36.38,
+          "end": 37.34,
+          "confidence": 0.973
+        },
+        {
+          "text": "telling",
+          "start": 37.34,
+          "end": 37.42,
+          "confidence": 0.715
+        },
+        {
+          "text": "me,",
+          "start": 37.42,
+          "end": 38.06,
+          "confidence": 0.929
+        },
+        {
+          "text": "dude?",
+          "start": 38.06,
+          "end": 38.1,
+          "confidence": 0.9
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 2600,
+      "start": 38.1,
+      "end": 38.62,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.26995800480698096,
+      "compression_ratio": 9.136363636363637,
+      "no_speech_prob": 0.0041488660499453545,
+      "confidence": 0.787,
+      "words": [
+        {
+          "text": "What",
+          "start": 38.1,
+          "end": 38.14,
+          "confidence": 0.555
+        },
+        {
+          "text": "are",
+          "start": 38.14,
+          "end": 38.18,
+          "confidence": 0.674
+        },
+        {
+          "text": "you",
+          "start": 38.18,
+          "end": 38.22,
+          "confidence": 0.978
+        },
+        {
+          "text": "telling",
+          "start": 38.22,
+          "end": 38.26,
+          "confidence": 0.751
+        },
+        {
+          "text": "me,",
+          "start": 38.26,
+          "end": 38.3,
+          "confidence": 0.936
+        },
+        {
+          "text": "dude?",
+          "start": 38.3,
+          "end": 38.62,
+          "confidence": 0.921
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 2600,
+      "start": 39.52,
+      "end": 41.92,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.26995800480698096,
+      "compression_ratio": 9.136363636363637,
+      "no_speech_prob": 0.0041488660499453545,
+      "confidence": 0.813,
+      "words": [
+        {
+          "text": "What",
+          "start": 39.52,
+          "end": 40.78,
+          "confidence": 0.577
+        },
+        {
+          "text": "are",
+          "start": 40.78,
+          "end": 41.06,
+          "confidence": 0.737
+        },
+        {
+          "text": "you",
+          "start": 41.06,
+          "end": 41.14,
+          "confidence": 0.982
+        },
+        {
+          "text": "telling",
+          "start": 41.14,
+          "end": 41.18,
+          "confidence": 0.785
+        },
+        {
+          "text": "me,",
+          "start": 41.18,
+          "end": 41.86,
+          "confidence": 0.941
+        },
+        {
+          "text": "dude?",
+          "start": 41.86,
+          "end": 41.92,
+          "confidence": 0.936
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 2600,
+      "start": 41.92,
+      "end": 42.86,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.26995800480698096,
+      "compression_ratio": 9.136363636363637,
+      "no_speech_prob": 0.0041488660499453545,
+      "confidence": 0.834,
+      "words": [
+        {
+          "text": "What",
+          "start": 41.92,
+          "end": 41.96,
+          "confidence": 0.644
+        },
+        {
+          "text": "are",
+          "start": 41.96,
+          "end": 42.0,
+          "confidence": 0.752
+        },
+        {
+          "text": "you",
+          "start": 42.0,
+          "end": 42.08,
+          "confidence": 0.985
+        },
+        {
+          "text": "telling",
+          "start": 42.08,
+          "end": 42.3,
+          "confidence": 0.788
+        },
+        {
+          "text": "me,",
+          "start": 42.3,
+          "end": 42.82,
+          "confidence": 0.953
+        },
+        {
+          "text": "dude?",
+          "start": 42.82,
+          "end": 42.86,
+          "confidence": 0.938
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 2600,
+      "start": 44.5,
+      "end": 46.46,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.26995800480698096,
+      "compression_ratio": 9.136363636363637,
+      "no_speech_prob": 0.0041488660499453545,
+      "confidence": 0.795,
+      "words": [
+        {
+          "text": "What",
+          "start": 44.5,
+          "end": 45.0,
+          "confidence": 0.502
+        },
+        {
+          "text": "are",
+          "start": 45.0,
+          "end": 45.64,
+          "confidence": 0.732
+        },
+        {
+          "text": "you",
+          "start": 45.64,
+          "end": 45.72,
+          "confidence": 0.985
+        },
+        {
+          "text": "telling",
+          "start": 45.72,
+          "end": 45.92,
+          "confidence": 0.789
+        },
+        {
+          "text": "me,",
+          "start": 45.92,
+          "end": 46.38,
+          "confidence": 0.952
+        },
+        {
+          "text": "dude?",
+          "start": 46.38,
+          "end": 46.46,
+          "confidence": 0.932
+        }
+      ]
+    },
+    {
+      "id": 17,
+      "seek": 2600,
+      "start": 46.46,
+      "end": 46.94,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.26995800480698096,
+      "compression_ratio": 9.136363636363637,
+      "no_speech_prob": 0.0041488660499453545,
+      "confidence": 0.789,
+      "words": [
+        {
+          "text": "What",
+          "start": 46.46,
+          "end": 46.5,
+          "confidence": 0.481
+        },
+        {
+          "text": "are",
+          "start": 46.5,
+          "end": 46.54,
+          "confidence": 0.742
+        },
+        {
+          "text": "you",
+          "start": 46.54,
+          "end": 46.58,
+          "confidence": 0.987
+        },
+        {
+          "text": "telling",
+          "start": 46.58,
+          "end": 46.62,
+          "confidence": 0.779
+        },
+        {
+          "text": "me,",
+          "start": 46.62,
+          "end": 46.66,
+          "confidence": 0.948
+        },
+        {
+          "text": "dude?",
+          "start": 46.66,
+          "end": 46.94,
+          "confidence": 0.932
+        }
+      ]
+    },
+    {
+      "id": 18,
+      "seek": 2600,
+      "start": 47.52,
+      "end": 48.46,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.26995800480698096,
+      "compression_ratio": 9.136363636363637,
+      "no_speech_prob": 0.0041488660499453545,
+      "confidence": 0.792,
+      "words": [
+        {
+          "text": "What",
+          "start": 47.52,
+          "end": 47.56,
+          "confidence": 0.479
+        },
+        {
+          "text": "are",
+          "start": 47.56,
+          "end": 48.04,
+          "confidence": 0.746
+        },
+        {
+          "text": "you",
+          "start": 48.04,
+          "end": 48.1,
+          "confidence": 0.987
+        },
+        {
+          "text": "telling",
+          "start": 48.1,
+          "end": 48.28,
+          "confidence": 0.785
+        },
+        {
+          "text": "me,",
+          "start": 48.28,
+          "end": 48.42,
+          "confidence": 0.95
+        },
+        {
+          "text": "dude?",
+          "start": 48.42,
+          "end": 48.46,
+          "confidence": 0.936
+        }
+      ]
+    },
+    {
+      "id": 19,
+      "seek": 2600,
+      "start": 49.52,
+      "end": 51.38,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.26995800480698096,
+      "compression_ratio": 9.136363636363637,
+      "no_speech_prob": 0.0041488660499453545,
+      "confidence": 0.838,
+      "words": [
+        {
+          "text": "What",
+          "start": 49.52,
+          "end": 50.24,
+          "confidence": 0.651
+        },
+        {
+          "text": "are",
+          "start": 50.24,
+          "end": 50.48,
+          "confidence": 0.757
+        },
+        {
+          "text": "you",
+          "start": 50.48,
+          "end": 50.56,
+          "confidence": 0.989
+        },
+        {
+          "text": "telling",
+          "start": 50.56,
+          "end": 50.6,
+          "confidence": 0.793
+        },
+        {
+          "text": "me,",
+          "start": 50.6,
+          "end": 51.32,
+          "confidence": 0.95
+        },
+        {
+          "text": "dude?",
+          "start": 51.32,
+          "end": 51.38,
+          "confidence": 0.943
+        }
+      ]
+    },
+    {
+      "id": 20,
+      "seek": 2600,
+      "start": 51.98,
+      "end": 54.06,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.26995800480698096,
+      "compression_ratio": 9.136363636363637,
+      "no_speech_prob": 0.0041488660499453545,
+      "confidence": 0.78,
+      "words": [
+        {
+          "text": "What",
+          "start": 51.98,
+          "end": 52.14,
+          "confidence": 0.43
+        },
+        {
+          "text": "are",
+          "start": 52.14,
+          "end": 52.62,
+          "confidence": 0.737
+        },
+        {
+          "text": "you",
+          "start": 52.62,
+          "end": 52.72,
+          "confidence": 0.988
+        },
+        {
+          "text": "telling",
+          "start": 52.72,
+          "end": 52.88,
+          "confidence": 0.81
+        },
+        {
+          "text": "me,",
+          "start": 52.88,
+          "end": 54.02,
+          "confidence": 0.943
+        },
+        {
+          "text": "dude?",
+          "start": 54.02,
+          "end": 54.06,
+          "confidence": 0.944
+        }
+      ]
+    },
+    {
+      "id": 21,
+      "seek": 5400,
+      "start": 54.06,
+      "end": 55.0,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.17690415449545416,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0238738264888525,
+      "confidence": 0.7,
+      "words": [
+        {
+          "text": "What",
+          "start": 54.06,
+          "end": 54.1,
+          "confidence": 0.506
+        },
+        {
+          "text": "are",
+          "start": 54.1,
+          "end": 54.2,
+          "confidence": 0.588
+        },
+        {
+          "text": "you",
+          "start": 54.2,
+          "end": 54.46,
+          "confidence": 0.876
+        },
+        {
+          "text": "telling",
+          "start": 54.46,
+          "end": 54.5,
+          "confidence": 0.747
+        },
+        {
+          "text": "me,",
+          "start": 54.5,
+          "end": 54.96,
+          "confidence": 0.71
+        },
+        {
+          "text": "dude?",
+          "start": 54.96,
+          "end": 55.0,
+          "confidence": 0.848
+        }
+      ]
+    },
+    {
+      "id": 22,
+      "seek": 5400,
+      "start": 56.5,
+      "end": 58.0,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.17690415449545416,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0238738264888525,
+      "confidence": 0.739,
+      "words": [
+        {
+          "text": "What",
+          "start": 56.5,
+          "end": 56.82,
+          "confidence": 0.512
+        },
+        {
+          "text": "are",
+          "start": 56.82,
+          "end": 56.92,
+          "confidence": 0.568
+        },
+        {
+          "text": "you",
+          "start": 56.92,
+          "end": 57.12,
+          "confidence": 0.964
+        },
+        {
+          "text": "telling",
+          "start": 57.12,
+          "end": 57.16,
+          "confidence": 0.808
+        },
+        {
+          "text": "me,",
+          "start": 57.16,
+          "end": 57.96,
+          "confidence": 0.803
+        },
+        {
+          "text": "dude?",
+          "start": 57.96,
+          "end": 58.0,
+          "confidence": 0.897
+        }
+      ]
+    },
+    {
+      "id": 23,
+      "seek": 5400,
+      "start": 58.0,
+      "end": 58.9,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.17690415449545416,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0238738264888525,
+      "confidence": 0.741,
+      "words": [
+        {
+          "text": "What",
+          "start": 58.0,
+          "end": 58.64,
+          "confidence": 0.48
+        },
+        {
+          "text": "are",
+          "start": 58.64,
+          "end": 58.68,
+          "confidence": 0.584
+        },
+        {
+          "text": "you",
+          "start": 58.68,
+          "end": 58.78,
+          "confidence": 0.954
+        },
+        {
+          "text": "telling",
+          "start": 58.78,
+          "end": 58.82,
+          "confidence": 0.816
+        },
+        {
+          "text": "me,",
+          "start": 58.82,
+          "end": 58.86,
+          "confidence": 0.837
+        },
+        {
+          "text": "dude?",
+          "start": 58.86,
+          "end": 58.9,
+          "confidence": 0.908
+        }
+      ]
+    },
+    {
+      "id": 24,
+      "seek": 5400,
+      "start": 59.52,
+      "end": 60.5,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.17690415449545416,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0238738264888525,
+      "confidence": 0.783,
+      "words": [
+        {
+          "text": "What",
+          "start": 59.52,
+          "end": 60.02,
+          "confidence": 0.58
+        },
+        {
+          "text": "are",
+          "start": 60.02,
+          "end": 60.18,
+          "confidence": 0.641
+        },
+        {
+          "text": "you",
+          "start": 60.18,
+          "end": 60.22,
+          "confidence": 0.967
+        },
+        {
+          "text": "telling",
+          "start": 60.22,
+          "end": 60.26,
+          "confidence": 0.826
+        },
+        {
+          "text": "me,",
+          "start": 60.26,
+          "end": 60.38,
+          "confidence": 0.853
+        },
+        {
+          "text": "dude?",
+          "start": 60.38,
+          "end": 60.5,
+          "confidence": 0.911
+        }
+      ]
+    },
+    {
+      "id": 25,
+      "seek": 5400,
+      "start": 61.52,
+      "end": 62.82,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.17690415449545416,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0238738264888525,
+      "confidence": 0.803,
+      "words": [
+        {
+          "text": "What",
+          "start": 61.52,
+          "end": 62.34,
+          "confidence": 0.613
+        },
+        {
+          "text": "are",
+          "start": 62.34,
+          "end": 62.38,
+          "confidence": 0.66
+        },
+        {
+          "text": "you",
+          "start": 62.38,
+          "end": 62.42,
+          "confidence": 0.967
+        },
+        {
+          "text": "telling",
+          "start": 62.42,
+          "end": 62.74,
+          "confidence": 0.835
+        },
+        {
+          "text": "me,",
+          "start": 62.74,
+          "end": 62.78,
+          "confidence": 0.892
+        },
+        {
+          "text": "dude?",
+          "start": 62.78,
+          "end": 62.82,
+          "confidence": 0.918
+        }
+      ]
+    },
+    {
+      "id": 26,
+      "seek": 5400,
+      "start": 63.52,
+      "end": 65.59,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.17690415449545416,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0238738264888525,
+      "confidence": 0.835,
+      "words": [
+        {
+          "text": "What",
+          "start": 63.52,
+          "end": 64.12,
+          "confidence": 0.731
+        },
+        {
+          "text": "are",
+          "start": 64.12,
+          "end": 64.26,
+          "confidence": 0.666
+        },
+        {
+          "text": "you",
+          "start": 64.26,
+          "end": 64.3,
+          "confidence": 0.971
+        },
+        {
+          "text": "telling",
+          "start": 64.3,
+          "end": 64.6,
+          "confidence": 0.864
+        },
+        {
+          "text": "me,",
+          "start": 64.6,
+          "end": 65.02,
+          "confidence": 0.902
+        },
+        {
+          "text": "dude?",
+          "start": 65.02,
+          "end": 65.59,
+          "confidence": 0.92
+        }
+      ]
+    },
+    {
+      "id": 27,
+      "seek": 5400,
+      "start": 65.59,
+      "end": 66.94,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.17690415449545416,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0238738264888525,
+      "confidence": 0.825,
+      "words": [
+        {
+          "text": "What",
+          "start": 65.59,
+          "end": 65.84,
+          "confidence": 0.635
+        },
+        {
+          "text": "are",
+          "start": 65.84,
+          "end": 65.88,
+          "confidence": 0.691
+        },
+        {
+          "text": "you",
+          "start": 65.88,
+          "end": 65.92,
+          "confidence": 0.975
+        },
+        {
+          "text": "telling",
+          "start": 65.92,
+          "end": 65.96,
+          "confidence": 0.866
+        },
+        {
+          "text": "me,",
+          "start": 65.96,
+          "end": 66.86,
+          "confidence": 0.918
+        },
+        {
+          "text": "dude?",
+          "start": 66.86,
+          "end": 66.94,
+          "confidence": 0.927
+        }
+      ]
+    },
+    {
+      "id": 28,
+      "seek": 5400,
+      "start": 67.52,
+      "end": 69.18,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.17690415449545416,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0238738264888525,
+      "confidence": 0.821,
+      "words": [
+        {
+          "text": "What",
+          "start": 67.52,
+          "end": 67.76,
+          "confidence": 0.572
+        },
+        {
+          "text": "are",
+          "start": 67.76,
+          "end": 67.9,
+          "confidence": 0.721
+        },
+        {
+          "text": "you",
+          "start": 67.9,
+          "end": 67.98,
+          "confidence": 0.979
+        },
+        {
+          "text": "telling",
+          "start": 67.98,
+          "end": 68.06,
+          "confidence": 0.88
+        },
+        {
+          "text": "me,",
+          "start": 68.06,
+          "end": 68.74,
+          "confidence": 0.923
+        },
+        {
+          "text": "dude?",
+          "start": 68.74,
+          "end": 69.18,
+          "confidence": 0.931
+        }
+      ]
+    },
+    {
+      "id": 29,
+      "seek": 5400,
+      "start": 69.86,
+      "end": 72.14,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.17690415449545416,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0238738264888525,
+      "confidence": 0.831,
+      "words": [
+        {
+          "text": "What",
+          "start": 69.86,
+          "end": 69.9,
+          "confidence": 0.61
+        },
+        {
+          "text": "are",
+          "start": 69.9,
+          "end": 70.14,
+          "confidence": 0.724
+        },
+        {
+          "text": "you",
+          "start": 70.14,
+          "end": 70.54,
+          "confidence": 0.98
+        },
+        {
+          "text": "telling",
+          "start": 70.54,
+          "end": 71.0,
+          "confidence": 0.876
+        },
+        {
+          "text": "me,",
+          "start": 71.0,
+          "end": 71.9,
+          "confidence": 0.928
+        },
+        {
+          "text": "dude?",
+          "start": 71.9,
+          "end": 72.14,
+          "confidence": 0.932
+        }
+      ]
+    },
+    {
+      "id": 30,
+      "seek": 5400,
+      "start": 72.14,
+      "end": 72.76,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.17690415449545416,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0238738264888525,
+      "confidence": 0.813,
+      "words": [
+        {
+          "text": "What",
+          "start": 72.14,
+          "end": 72.4,
+          "confidence": 0.516
+        },
+        {
+          "text": "are",
+          "start": 72.4,
+          "end": 72.44,
+          "confidence": 0.736
+        },
+        {
+          "text": "you",
+          "start": 72.44,
+          "end": 72.52,
+          "confidence": 0.982
+        },
+        {
+          "text": "telling",
+          "start": 72.52,
+          "end": 72.6,
+          "confidence": 0.88
+        },
+        {
+          "text": "me,",
+          "start": 72.6,
+          "end": 72.72,
+          "confidence": 0.943
+        },
+        {
+          "text": "dude?",
+          "start": 72.72,
+          "end": 72.76,
+          "confidence": 0.937
+        }
+      ]
+    },
+    {
+      "id": 31,
+      "seek": 5400,
+      "start": 74.08,
+      "end": 76.34,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.17690415449545416,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0238738264888525,
+      "confidence": 0.85,
+      "words": [
+        {
+          "text": "What",
+          "start": 74.08,
+          "end": 74.32,
+          "confidence": 0.651
+        },
+        {
+          "text": "are",
+          "start": 74.32,
+          "end": 74.36,
+          "confidence": 0.755
+        },
+        {
+          "text": "you",
+          "start": 74.36,
+          "end": 74.94,
+          "confidence": 0.984
+        },
+        {
+          "text": "telling",
+          "start": 74.94,
+          "end": 75.56,
+          "confidence": 0.88
+        },
+        {
+          "text": "me,",
+          "start": 75.56,
+          "end": 76.3,
+          "confidence": 0.943
+        },
+        {
+          "text": "dude?",
+          "start": 76.3,
+          "end": 76.34,
+          "confidence": 0.937
+        }
+      ]
+    },
+    {
+      "id": 32,
+      "seek": 5400,
+      "start": 76.34,
+      "end": 77.98,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.17690415449545416,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0238738264888525,
+      "confidence": 0.839,
+      "words": [
+        {
+          "text": "What",
+          "start": 76.34,
+          "end": 77.38,
+          "confidence": 0.607
+        },
+        {
+          "text": "are",
+          "start": 77.38,
+          "end": 77.42,
+          "confidence": 0.759
+        },
+        {
+          "text": "you",
+          "start": 77.42,
+          "end": 77.46,
+          "confidence": 0.985
+        },
+        {
+          "text": "telling",
+          "start": 77.46,
+          "end": 77.54,
+          "confidence": 0.879
+        },
+        {
+          "text": "me,",
+          "start": 77.54,
+          "end": 77.94,
+          "confidence": 0.938
+        },
+        {
+          "text": "dude?",
+          "start": 77.94,
+          "end": 77.98,
+          "confidence": 0.936
+        }
+      ]
+    },
+    {
+      "id": 33,
+      "seek": 5400,
+      "start": 77.98,
+      "end": 79.08,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.17690415449545416,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0238738264888525,
+      "confidence": 0.85,
+      "words": [
+        {
+          "text": "What",
+          "start": 77.98,
+          "end": 78.02,
+          "confidence": 0.636
+        },
+        {
+          "text": "are",
+          "start": 78.02,
+          "end": 78.06,
+          "confidence": 0.75
+        },
+        {
+          "text": "you",
+          "start": 78.06,
+          "end": 78.92,
+          "confidence": 0.985
+        },
+        {
+          "text": "telling",
+          "start": 78.92,
+          "end": 78.96,
+          "confidence": 0.894
+        },
+        {
+          "text": "me,",
+          "start": 78.96,
+          "end": 79.04,
+          "confidence": 0.954
+        },
+        {
+          "text": "dude?",
+          "start": 79.04,
+          "end": 79.08,
+          "confidence": 0.939
+        }
+      ]
+    },
+    {
+      "id": 34,
+      "seek": 5400,
+      "start": 80.22,
+      "end": 81.66,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.17690415449545416,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0238738264888525,
+      "confidence": 0.813,
+      "words": [
+        {
+          "text": "What",
+          "start": 80.22,
+          "end": 80.26,
+          "confidence": 0.484
+        },
+        {
+          "text": "are",
+          "start": 80.26,
+          "end": 80.6,
+          "confidence": 0.745
+        },
+        {
+          "text": "you",
+          "start": 80.6,
+          "end": 80.68,
+          "confidence": 0.985
+        },
+        {
+          "text": "telling",
+          "start": 80.68,
+          "end": 80.96,
+          "confidence": 0.899
+        },
+        {
+          "text": "me,",
+          "start": 80.96,
+          "end": 81.62,
+          "confidence": 0.96
+        },
+        {
+          "text": "dude?",
+          "start": 81.62,
+          "end": 81.66,
+          "confidence": 0.942
+        }
+      ]
+    },
+    {
+      "id": 35,
+      "seek": 8200,
+      "start": 82.02,
+      "end": 83.08,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1252204868155466,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0009642249788157642,
+      "confidence": 0.772,
+      "words": [
+        {
+          "text": "What",
+          "start": 82.02,
+          "end": 82.06,
+          "confidence": 0.701
+        },
+        {
+          "text": "are",
+          "start": 82.06,
+          "end": 82.28,
+          "confidence": 0.488
+        },
+        {
+          "text": "you",
+          "start": 82.28,
+          "end": 82.38,
+          "confidence": 0.934
+        },
+        {
+          "text": "telling",
+          "start": 82.38,
+          "end": 82.42,
+          "confidence": 0.755
+        },
+        {
+          "text": "me,",
+          "start": 82.42,
+          "end": 82.86,
+          "confidence": 0.92
+        },
+        {
+          "text": "dude?",
+          "start": 82.86,
+          "end": 83.08,
+          "confidence": 0.956
+        }
+      ]
+    },
+    {
+      "id": 36,
+      "seek": 8200,
+      "start": 84.34,
+      "end": 85.3,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1252204868155466,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0009642249788157642,
+      "confidence": 0.786,
+      "words": [
+        {
+          "text": "What",
+          "start": 84.34,
+          "end": 84.38,
+          "confidence": 0.529
+        },
+        {
+          "text": "are",
+          "start": 84.38,
+          "end": 84.64,
+          "confidence": 0.637
+        },
+        {
+          "text": "you",
+          "start": 84.64,
+          "end": 85.12,
+          "confidence": 0.969
+        },
+        {
+          "text": "telling",
+          "start": 85.12,
+          "end": 85.16,
+          "confidence": 0.815
+        },
+        {
+          "text": "me,",
+          "start": 85.16,
+          "end": 85.26,
+          "confidence": 0.932
+        },
+        {
+          "text": "dude?",
+          "start": 85.26,
+          "end": 85.3,
+          "confidence": 0.952
+        }
+      ]
+    },
+    {
+      "id": 37,
+      "seek": 8200,
+      "start": 85.52,
+      "end": 87.94,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1252204868155466,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0009642249788157642,
+      "confidence": 0.836,
+      "words": [
+        {
+          "text": "What",
+          "start": 85.52,
+          "end": 86.82,
+          "confidence": 0.676
+        },
+        {
+          "text": "are",
+          "start": 86.82,
+          "end": 86.86,
+          "confidence": 0.703
+        },
+        {
+          "text": "you",
+          "start": 86.86,
+          "end": 86.98,
+          "confidence": 0.97
+        },
+        {
+          "text": "telling",
+          "start": 86.98,
+          "end": 87.02,
+          "confidence": 0.826
+        },
+        {
+          "text": "me,",
+          "start": 87.02,
+          "end": 87.9,
+          "confidence": 0.942
+        },
+        {
+          "text": "dude?",
+          "start": 87.9,
+          "end": 87.94,
+          "confidence": 0.955
+        }
+      ]
+    },
+    {
+      "id": 38,
+      "seek": 8200,
+      "start": 87.94,
+      "end": 89.56,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1252204868155466,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0009642249788157642,
+      "confidence": 0.849,
+      "words": [
+        {
+          "text": "What",
+          "start": 87.94,
+          "end": 88.34,
+          "confidence": 0.7
+        },
+        {
+          "text": "are",
+          "start": 88.34,
+          "end": 89.16,
+          "confidence": 0.717
+        },
+        {
+          "text": "you",
+          "start": 89.16,
+          "end": 89.44,
+          "confidence": 0.976
+        },
+        {
+          "text": "telling",
+          "start": 89.44,
+          "end": 89.48,
+          "confidence": 0.84
+        },
+        {
+          "text": "me,",
+          "start": 89.48,
+          "end": 89.52,
+          "confidence": 0.954
+        },
+        {
+          "text": "dude?",
+          "start": 89.52,
+          "end": 89.56,
+          "confidence": 0.954
+        }
+      ]
+    },
+    {
+      "id": 39,
+      "seek": 8200,
+      "start": 89.94,
+      "end": 90.9,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1252204868155466,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0009642249788157642,
+      "confidence": 0.859,
+      "words": [
+        {
+          "text": "What",
+          "start": 89.94,
+          "end": 90.1,
+          "confidence": 0.747
+        },
+        {
+          "text": "are",
+          "start": 90.1,
+          "end": 90.14,
+          "confidence": 0.718
+        },
+        {
+          "text": "you",
+          "start": 90.14,
+          "end": 90.28,
+          "confidence": 0.976
+        },
+        {
+          "text": "telling",
+          "start": 90.28,
+          "end": 90.5,
+          "confidence": 0.847
+        },
+        {
+          "text": "me,",
+          "start": 90.5,
+          "end": 90.86,
+          "confidence": 0.944
+        },
+        {
+          "text": "dude?",
+          "start": 90.86,
+          "end": 90.9,
+          "confidence": 0.959
+        }
+      ]
+    },
+    {
+      "id": 40,
+      "seek": 8200,
+      "start": 91.52,
+      "end": 92.2,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1252204868155466,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0009642249788157642,
+      "confidence": 0.851,
+      "words": [
+        {
+          "text": "What",
+          "start": 91.52,
+          "end": 91.6,
+          "confidence": 0.723
+        },
+        {
+          "text": "are",
+          "start": 91.6,
+          "end": 91.64,
+          "confidence": 0.718
+        },
+        {
+          "text": "you",
+          "start": 91.64,
+          "end": 91.68,
+          "confidence": 0.978
+        },
+        {
+          "text": "telling",
+          "start": 91.68,
+          "end": 91.72,
+          "confidence": 0.83
+        },
+        {
+          "text": "me,",
+          "start": 91.72,
+          "end": 92.16,
+          "confidence": 0.944
+        },
+        {
+          "text": "dude?",
+          "start": 92.16,
+          "end": 92.2,
+          "confidence": 0.958
+        }
+      ]
+    },
+    {
+      "id": 41,
+      "seek": 8200,
+      "start": 93.52,
+      "end": 94.66,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1252204868155466,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0009642249788157642,
+      "confidence": 0.862,
+      "words": [
+        {
+          "text": "What",
+          "start": 93.52,
+          "end": 94.04,
+          "confidence": 0.743
+        },
+        {
+          "text": "are",
+          "start": 94.04,
+          "end": 94.08,
+          "confidence": 0.73
+        },
+        {
+          "text": "you",
+          "start": 94.08,
+          "end": 94.24,
+          "confidence": 0.981
+        },
+        {
+          "text": "telling",
+          "start": 94.24,
+          "end": 94.28,
+          "confidence": 0.848
+        },
+        {
+          "text": "me,",
+          "start": 94.28,
+          "end": 94.36,
+          "confidence": 0.949
+        },
+        {
+          "text": "dude?",
+          "start": 94.36,
+          "end": 94.66,
+          "confidence": 0.962
+        }
+      ]
+    },
+    {
+      "id": 42,
+      "seek": 8200,
+      "start": 95.52,
+      "end": 98.44,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1252204868155466,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0009642249788157642,
+      "confidence": 0.867,
+      "words": [
+        {
+          "text": "What",
+          "start": 95.52,
+          "end": 97.08,
+          "confidence": 0.72
+        },
+        {
+          "text": "are",
+          "start": 97.08,
+          "end": 97.16,
+          "confidence": 0.762
+        },
+        {
+          "text": "you",
+          "start": 97.16,
+          "end": 97.28,
+          "confidence": 0.984
+        },
+        {
+          "text": "telling",
+          "start": 97.28,
+          "end": 97.72,
+          "confidence": 0.862
+        },
+        {
+          "text": "me,",
+          "start": 97.72,
+          "end": 98.4,
+          "confidence": 0.951
+        },
+        {
+          "text": "dude?",
+          "start": 98.4,
+          "end": 98.44,
+          "confidence": 0.962
+        }
+      ]
+    },
+    {
+      "id": 43,
+      "seek": 8200,
+      "start": 98.44,
+      "end": 98.9,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1252204868155466,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0009642249788157642,
+      "confidence": 0.885,
+      "words": [
+        {
+          "text": "What",
+          "start": 98.44,
+          "end": 98.48,
+          "confidence": 0.77
+        },
+        {
+          "text": "are",
+          "start": 98.48,
+          "end": 98.52,
+          "confidence": 0.781
+        },
+        {
+          "text": "you",
+          "start": 98.52,
+          "end": 98.78,
+          "confidence": 0.986
+        },
+        {
+          "text": "telling",
+          "start": 98.78,
+          "end": 98.82,
+          "confidence": 0.867
+        },
+        {
+          "text": "me,",
+          "start": 98.82,
+          "end": 98.86,
+          "confidence": 0.965
+        },
+        {
+          "text": "dude?",
+          "start": 98.86,
+          "end": 98.9,
+          "confidence": 0.965
+        }
+      ]
+    },
+    {
+      "id": 44,
+      "seek": 8200,
+      "start": 99.52,
+      "end": 101.8,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1252204868155466,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0009642249788157642,
+      "confidence": 0.887,
+      "words": [
+        {
+          "text": "What",
+          "start": 99.52,
+          "end": 101.06,
+          "confidence": 0.741
+        },
+        {
+          "text": "are",
+          "start": 101.06,
+          "end": 101.1,
+          "confidence": 0.806
+        },
+        {
+          "text": "you",
+          "start": 101.1,
+          "end": 101.14,
+          "confidence": 0.989
+        },
+        {
+          "text": "telling",
+          "start": 101.14,
+          "end": 101.44,
+          "confidence": 0.88
+        },
+        {
+          "text": "me,",
+          "start": 101.44,
+          "end": 101.76,
+          "confidence": 0.972
+        },
+        {
+          "text": "dude?",
+          "start": 101.76,
+          "end": 101.8,
+          "confidence": 0.966
+        }
+      ]
+    },
+    {
+      "id": 45,
+      "seek": 8200,
+      "start": 101.8,
+      "end": 103.02,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1252204868155466,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0009642249788157642,
+      "confidence": 0.881,
+      "words": [
+        {
+          "text": "What",
+          "start": 101.8,
+          "end": 102.82,
+          "confidence": 0.731
+        },
+        {
+          "text": "are",
+          "start": 102.82,
+          "end": 102.86,
+          "confidence": 0.796
+        },
+        {
+          "text": "you",
+          "start": 102.86,
+          "end": 102.9,
+          "confidence": 0.988
+        },
+        {
+          "text": "telling",
+          "start": 102.9,
+          "end": 102.94,
+          "confidence": 0.868
+        },
+        {
+          "text": "me,",
+          "start": 102.94,
+          "end": 102.98,
+          "confidence": 0.971
+        },
+        {
+          "text": "dude?",
+          "start": 102.98,
+          "end": 103.02,
+          "confidence": 0.966
+        }
+      ]
+    },
+    {
+      "id": 46,
+      "seek": 8200,
+      "start": 104.5,
+      "end": 105.34,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1252204868155466,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0009642249788157642,
+      "confidence": 0.888,
+      "words": [
+        {
+          "text": "What",
+          "start": 104.5,
+          "end": 104.82,
+          "confidence": 0.737
+        },
+        {
+          "text": "are",
+          "start": 104.82,
+          "end": 105.16,
+          "confidence": 0.806
+        },
+        {
+          "text": "you",
+          "start": 105.16,
+          "end": 105.2,
+          "confidence": 0.99
+        },
+        {
+          "text": "telling",
+          "start": 105.2,
+          "end": 105.24,
+          "confidence": 0.885
+        },
+        {
+          "text": "me,",
+          "start": 105.24,
+          "end": 105.3,
+          "confidence": 0.974
+        },
+        {
+          "text": "dude?",
+          "start": 105.3,
+          "end": 105.34,
+          "confidence": 0.967
+        }
+      ]
+    },
+    {
+      "id": 47,
+      "seek": 8200,
+      "start": 106.5,
+      "end": 108.02,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1252204868155466,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0009642249788157642,
+      "confidence": 0.874,
+      "words": [
+        {
+          "text": "What",
+          "start": 106.5,
+          "end": 106.92,
+          "confidence": 0.697
+        },
+        {
+          "text": "are",
+          "start": 106.92,
+          "end": 107.1,
+          "confidence": 0.786
+        },
+        {
+          "text": "you",
+          "start": 107.1,
+          "end": 107.14,
+          "confidence": 0.99
+        },
+        {
+          "text": "telling",
+          "start": 107.14,
+          "end": 107.18,
+          "confidence": 0.876
+        },
+        {
+          "text": "me,",
+          "start": 107.18,
+          "end": 107.76,
+          "confidence": 0.971
+        },
+        {
+          "text": "dude?",
+          "start": 107.76,
+          "end": 108.02,
+          "confidence": 0.968
+        }
+      ]
+    },
+    {
+      "id": 48,
+      "seek": 8200,
+      "start": 108.02,
+      "end": 109.54,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1252204868155466,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0009642249788157642,
+      "confidence": 0.82,
+      "words": [
+        {
+          "text": "What",
+          "start": 108.02,
+          "end": 108.06,
+          "confidence": 0.48
+        },
+        {
+          "text": "are",
+          "start": 108.06,
+          "end": 108.2,
+          "confidence": 0.773
+        },
+        {
+          "text": "you",
+          "start": 108.2,
+          "end": 108.24,
+          "confidence": 0.99
+        },
+        {
+          "text": "telling",
+          "start": 108.24,
+          "end": 108.34,
+          "confidence": 0.878
+        },
+        {
+          "text": "me,",
+          "start": 108.34,
+          "end": 109.48,
+          "confidence": 0.97
+        },
+        {
+          "text": "dude?",
+          "start": 109.48,
+          "end": 109.54,
+          "confidence": 0.97
+        }
+      ]
+    },
+    {
+      "id": 49,
+      "seek": 11000,
+      "start": 110.02,
+      "end": 110.56,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1162933564521897,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0005178684368729591,
+      "confidence": 0.719,
+      "words": [
+        {
+          "text": "What",
+          "start": 110.02,
+          "end": 110.16,
+          "confidence": 0.419
+        },
+        {
+          "text": "are",
+          "start": 110.16,
+          "end": 110.2,
+          "confidence": 0.523
+        },
+        {
+          "text": "you",
+          "start": 110.2,
+          "end": 110.24,
+          "confidence": 0.913
+        },
+        {
+          "text": "telling",
+          "start": 110.24,
+          "end": 110.48,
+          "confidence": 0.79
+        },
+        {
+          "text": "me,",
+          "start": 110.48,
+          "end": 110.52,
+          "confidence": 0.904
+        },
+        {
+          "text": "dude?",
+          "start": 110.52,
+          "end": 110.56,
+          "confidence": 0.964
+        }
+      ]
+    },
+    {
+      "id": 50,
+      "seek": 11000,
+      "start": 112.14,
+      "end": 113.52,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1162933564521897,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0005178684368729591,
+      "confidence": 0.835,
+      "words": [
+        {
+          "text": "What",
+          "start": 112.14,
+          "end": 112.3,
+          "confidence": 0.644
+        },
+        {
+          "text": "are",
+          "start": 112.3,
+          "end": 113.22,
+          "confidence": 0.734
+        },
+        {
+          "text": "you",
+          "start": 113.22,
+          "end": 113.4,
+          "confidence": 0.978
+        },
+        {
+          "text": "telling",
+          "start": 113.4,
+          "end": 113.44,
+          "confidence": 0.821
+        },
+        {
+          "text": "me,",
+          "start": 113.44,
+          "end": 113.48,
+          "confidence": 0.933
+        },
+        {
+          "text": "dude?",
+          "start": 113.48,
+          "end": 113.52,
+          "confidence": 0.962
+        }
+      ]
+    },
+    {
+      "id": 51,
+      "seek": 11000,
+      "start": 113.9,
+      "end": 114.9,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1162933564521897,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0005178684368729591,
+      "confidence": 0.832,
+      "words": [
+        {
+          "text": "What",
+          "start": 113.9,
+          "end": 114.06,
+          "confidence": 0.615
+        },
+        {
+          "text": "are",
+          "start": 114.06,
+          "end": 114.16,
+          "confidence": 0.733
+        },
+        {
+          "text": "you",
+          "start": 114.16,
+          "end": 114.36,
+          "confidence": 0.978
+        },
+        {
+          "text": "telling",
+          "start": 114.36,
+          "end": 114.4,
+          "confidence": 0.832
+        },
+        {
+          "text": "me,",
+          "start": 114.4,
+          "end": 114.86,
+          "confidence": 0.934
+        },
+        {
+          "text": "dude?",
+          "start": 114.86,
+          "end": 114.9,
+          "confidence": 0.967
+        }
+      ]
+    },
+    {
+      "id": 52,
+      "seek": 11000,
+      "start": 115.52,
+      "end": 117.54,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1162933564521897,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0005178684368729591,
+      "confidence": 0.86,
+      "words": [
+        {
+          "text": "What",
+          "start": 115.52,
+          "end": 116.54,
+          "confidence": 0.67
+        },
+        {
+          "text": "are",
+          "start": 116.54,
+          "end": 116.58,
+          "confidence": 0.788
+        },
+        {
+          "text": "you",
+          "start": 116.58,
+          "end": 116.64,
+          "confidence": 0.984
+        },
+        {
+          "text": "telling",
+          "start": 116.64,
+          "end": 116.68,
+          "confidence": 0.852
+        },
+        {
+          "text": "me,",
+          "start": 116.68,
+          "end": 117.44,
+          "confidence": 0.947
+        },
+        {
+          "text": "dude?",
+          "start": 117.44,
+          "end": 117.54,
+          "confidence": 0.966
+        }
+      ]
+    },
+    {
+      "id": 53,
+      "seek": 11000,
+      "start": 118.18,
+      "end": 120.14,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1162933564521897,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0005178684368729591,
+      "confidence": 0.88,
+      "words": [
+        {
+          "text": "What",
+          "start": 118.18,
+          "end": 118.36,
+          "confidence": 0.758
+        },
+        {
+          "text": "are",
+          "start": 118.36,
+          "end": 118.4,
+          "confidence": 0.789
+        },
+        {
+          "text": "you",
+          "start": 118.4,
+          "end": 118.74,
+          "confidence": 0.985
+        },
+        {
+          "text": "telling",
+          "start": 118.74,
+          "end": 118.82,
+          "confidence": 0.858
+        },
+        {
+          "text": "me,",
+          "start": 118.82,
+          "end": 120.1,
+          "confidence": 0.948
+        },
+        {
+          "text": "dude?",
+          "start": 120.1,
+          "end": 120.14,
+          "confidence": 0.968
+        }
+      ]
+    },
+    {
+      "id": 54,
+      "seek": 11000,
+      "start": 120.14,
+      "end": 120.38,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1162933564521897,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0005178684368729591,
+      "confidence": 0.884,
+      "words": [
+        {
+          "text": "What",
+          "start": 120.14,
+          "end": 120.18,
+          "confidence": 0.757
+        },
+        {
+          "text": "are",
+          "start": 120.18,
+          "end": 120.22,
+          "confidence": 0.808
+        },
+        {
+          "text": "you",
+          "start": 120.22,
+          "end": 120.26,
+          "confidence": 0.986
+        },
+        {
+          "text": "telling",
+          "start": 120.26,
+          "end": 120.3,
+          "confidence": 0.857
+        },
+        {
+          "text": "me,",
+          "start": 120.3,
+          "end": 120.34,
+          "confidence": 0.954
+        },
+        {
+          "text": "dude?",
+          "start": 120.34,
+          "end": 120.38,
+          "confidence": 0.966
+        }
+      ]
+    },
+    {
+      "id": 55,
+      "seek": 11000,
+      "start": 121.52,
+      "end": 123.36,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1162933564521897,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0005178684368729591,
+      "confidence": 0.874,
+      "words": [
+        {
+          "text": "What",
+          "start": 121.52,
+          "end": 122.72,
+          "confidence": 0.718
+        },
+        {
+          "text": "are",
+          "start": 122.72,
+          "end": 123.2,
+          "confidence": 0.788
+        },
+        {
+          "text": "you",
+          "start": 123.2,
+          "end": 123.24,
+          "confidence": 0.986
+        },
+        {
+          "text": "telling",
+          "start": 123.24,
+          "end": 123.28,
+          "confidence": 0.865
+        },
+        {
+          "text": "me,",
+          "start": 123.28,
+          "end": 123.32,
+          "confidence": 0.952
+        },
+        {
+          "text": "dude?",
+          "start": 123.32,
+          "end": 123.36,
+          "confidence": 0.968
+        }
+      ]
+    },
+    {
+      "id": 56,
+      "seek": 11000,
+      "start": 123.52,
+      "end": 125.14,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1162933564521897,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0005178684368729591,
+      "confidence": 0.882,
+      "words": [
+        {
+          "text": "What",
+          "start": 123.52,
+          "end": 124.56,
+          "confidence": 0.718
+        },
+        {
+          "text": "are",
+          "start": 124.56,
+          "end": 124.74,
+          "confidence": 0.821
+        },
+        {
+          "text": "you",
+          "start": 124.74,
+          "end": 125.02,
+          "confidence": 0.989
+        },
+        {
+          "text": "telling",
+          "start": 125.02,
+          "end": 125.06,
+          "confidence": 0.878
+        },
+        {
+          "text": "me,",
+          "start": 125.06,
+          "end": 125.1,
+          "confidence": 0.952
+        },
+        {
+          "text": "dude?",
+          "start": 125.1,
+          "end": 125.14,
+          "confidence": 0.968
+        }
+      ]
+    },
+    {
+      "id": 57,
+      "seek": 11000,
+      "start": 125.52,
+      "end": 127.58,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1162933564521897,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0005178684368729591,
+      "confidence": 0.894,
+      "words": [
+        {
+          "text": "What",
+          "start": 125.52,
+          "end": 126.58,
+          "confidence": 0.747
+        },
+        {
+          "text": "are",
+          "start": 126.58,
+          "end": 126.9,
+          "confidence": 0.837
+        },
+        {
+          "text": "you",
+          "start": 126.9,
+          "end": 127.06,
+          "confidence": 0.991
+        },
+        {
+          "text": "telling",
+          "start": 127.06,
+          "end": 127.14,
+          "confidence": 0.883
+        },
+        {
+          "text": "me,",
+          "start": 127.14,
+          "end": 127.54,
+          "confidence": 0.962
+        },
+        {
+          "text": "dude?",
+          "start": 127.54,
+          "end": 127.58,
+          "confidence": 0.969
+        }
+      ]
+    },
+    {
+      "id": 58,
+      "seek": 11000,
+      "start": 127.58,
+      "end": 129.28,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1162933564521897,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0005178684368729591,
+      "confidence": 0.895,
+      "words": [
+        {
+          "text": "What",
+          "start": 127.58,
+          "end": 128.98,
+          "confidence": 0.719
+        },
+        {
+          "text": "are",
+          "start": 128.98,
+          "end": 129.02,
+          "confidence": 0.859
+        },
+        {
+          "text": "you",
+          "start": 129.02,
+          "end": 129.06,
+          "confidence": 0.992
+        },
+        {
+          "text": "telling",
+          "start": 129.06,
+          "end": 129.1,
+          "confidence": 0.896
+        },
+        {
+          "text": "me,",
+          "start": 129.1,
+          "end": 129.14,
+          "confidence": 0.965
+        },
+        {
+          "text": "dude?",
+          "start": 129.14,
+          "end": 129.28,
+          "confidence": 0.971
+        }
+      ]
+    },
+    {
+      "id": 59,
+      "seek": 11000,
+      "start": 129.72,
+      "end": 131.68,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1162933564521897,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0005178684368729591,
+      "confidence": 0.89,
+      "words": [
+        {
+          "text": "What",
+          "start": 129.72,
+          "end": 131.02,
+          "confidence": 0.703
+        },
+        {
+          "text": "are",
+          "start": 131.02,
+          "end": 131.46,
+          "confidence": 0.855
+        },
+        {
+          "text": "you",
+          "start": 131.46,
+          "end": 131.5,
+          "confidence": 0.992
+        },
+        {
+          "text": "telling",
+          "start": 131.5,
+          "end": 131.54,
+          "confidence": 0.89
+        },
+        {
+          "text": "me,",
+          "start": 131.54,
+          "end": 131.64,
+          "confidence": 0.964
+        },
+        {
+          "text": "dude?",
+          "start": 131.64,
+          "end": 131.68,
+          "confidence": 0.97
+        }
+      ]
+    },
+    {
+      "id": 60,
+      "seek": 11000,
+      "start": 131.68,
+      "end": 133.0,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1162933564521897,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0005178684368729591,
+      "confidence": 0.903,
+      "words": [
+        {
+          "text": "What",
+          "start": 131.68,
+          "end": 132.36,
+          "confidence": 0.746
+        },
+        {
+          "text": "are",
+          "start": 132.36,
+          "end": 132.4,
+          "confidence": 0.86
+        },
+        {
+          "text": "you",
+          "start": 132.4,
+          "end": 132.44,
+          "confidence": 0.993
+        },
+        {
+          "text": "telling",
+          "start": 132.44,
+          "end": 132.48,
+          "confidence": 0.903
+        },
+        {
+          "text": "me,",
+          "start": 132.48,
+          "end": 132.52,
+          "confidence": 0.969
+        },
+        {
+          "text": "dude?",
+          "start": 132.52,
+          "end": 133.0,
+          "confidence": 0.972
+        }
+      ]
+    },
+    {
+      "id": 61,
+      "seek": 11000,
+      "start": 133.72,
+      "end": 135.54,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1162933564521897,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0005178684368729591,
+      "confidence": 0.891,
+      "words": [
+        {
+          "text": "What",
+          "start": 133.72,
+          "end": 134.08,
+          "confidence": 0.692
+        },
+        {
+          "text": "are",
+          "start": 134.08,
+          "end": 134.14,
+          "confidence": 0.859
+        },
+        {
+          "text": "you",
+          "start": 134.14,
+          "end": 134.38,
+          "confidence": 0.993
+        },
+        {
+          "text": "telling",
+          "start": 134.38,
+          "end": 134.42,
+          "confidence": 0.9
+        },
+        {
+          "text": "me,",
+          "start": 134.42,
+          "end": 135.5,
+          "confidence": 0.971
+        },
+        {
+          "text": "dude?",
+          "start": 135.5,
+          "end": 135.54,
+          "confidence": 0.974
+        }
+      ]
+    },
+    {
+      "id": 62,
+      "seek": 11000,
+      "start": 135.54,
+      "end": 136.88,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.1162933564521897,
+      "compression_ratio": 9.840909090909092,
+      "no_speech_prob": 0.0005178684368729591,
+      "confidence": 0.855,
+      "words": [
+        {
+          "text": "What",
+          "start": 135.54,
+          "end": 135.58,
+          "confidence": 0.534
+        },
+        {
+          "text": "are",
+          "start": 135.58,
+          "end": 135.62,
+          "confidence": 0.856
+        },
+        {
+          "text": "you",
+          "start": 135.62,
+          "end": 135.66,
+          "confidence": 0.993
+        },
+        {
+          "text": "telling",
+          "start": 135.66,
+          "end": 135.7,
+          "confidence": 0.906
+        },
+        {
+          "text": "me,",
+          "start": 135.7,
+          "end": 135.74,
+          "confidence": 0.972
+        },
+        {
+          "text": "dude?",
+          "start": 135.74,
+          "end": 136.88,
+          "confidence": 0.975
+        }
+      ]
+    }
+  ],
+  "language": "en"
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_auto.cpu/smartphone.mp3.words.json b/tests/expected/tiny_auto.cpu/smartphone.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..f90643caf0519b49ba0cbc0381cd8d8ced1f218b
--- /dev/null
+++ b/tests/expected/tiny_auto.cpu/smartphone.mp3.words.json
@@ -0,0 +1,5038 @@
+{
+  "text": " C'est évidence que dit Nicolas. Mais je me l'étais jamais formulé comme ça. Ce qui fait la force du smartphone, c'est pas seulement la cumulation des fonctions, mais la manière dans quelques interagues entraîne. Et il est d'ailleurs, c'est la photo c'est hyper convaincant. Alors évidemment, il faudrait ajouter les interfaces les grand-attêtes qu'il a été beaucoup très souvent ementionné. Mais bon, il faudrait que les profites aussi de 20 ans pendant l'été, les ordinateurs nous ont appris à piquer sur des icônes. C'est ce que le smartphone ajoute le toucher, qui rend le contact plus direct, plus sensible. Et puis, évidemment, il faudrait parler aussi des applications qui permettent de contourner le côté tout flu de la navigation web pour aller directement en but. Bref, tout ça, ce sont les conditions qui permettent de créer cette objet, en Nicolas, dit qu'il est très fondablement inédit dans l'histoire de l'humanité. Mais ça s'assoulait d'une autre interrogation. Est-ce que le fait que cette objet soit inédit un d'huies que notre rapport a lui est aussi un rapport inédit? Je veux dire, est-ce que le rapport qu'on a au sein de foi n'est comparable à celui qu'on entretenait à d'autres objectes techniques comme la voiture ou le téléphone? Il n'y a pas d'équivalent. On s'est espécie de nous voter dans la relation à l'objet. C'est facilement éterréciant parce qu'on a impression de, comme le 10, les utilisateurs et les efforts, elles aident dépendant de cette objet d'un lieu, en fait, une espèce de relation de médiation avec le monde qui rendent un peu avec la même sédiforme de le jeu. Donc, à objets inédits, rapport inédits. Et, ce rapport, si j'en prends Nicolas, frère caractérisée par un mélange de dépenses et de rojets. Bon, en vrai, il faudrait remonter très très finement toute l'histoire des objectes techniques et de leur infération dans le vie pour déterminer si ce rapport est totalement inédit. Mais j'ai l'impression comme ça que Nicolas se trompe pas vraiment. Pour autant, je sache. Il y a eu plein de discussions autour de la voiture ou même du téléphone. Mais la dépense n'était pas du même mort, donc le rejet n'en plus n'était pas du même mort. On peut adorer sa bagnure, en avoir besoin pour plein de choses. Et là, le soir, quand on va se coucher, on la laisse. On l'a pas dans la main, quand on est collis, quand on n'en mène pas au chiot. On pouvait être émervé par son mome qui occupeait la ligne de téléphone pendant une heure chaque soir pour discuter avec un copain. Mais ça ne ressemble pas à ce qu'on peut ressentir à voir même mome aujourd'hui continuuellement avec son smartphone dans la main, comme c'était une sorte de estimateur extère de l'intempis de lâcher à l'éantrénée, ça m'a eu immédiate. Bon, je dis ça pour le mome, mais évidemment, va là pour nos aussi. Donc, rapport immédiate d'accord. Mais pourquoi, à ton impression qu'on en sortira jamais? Et puis, il faut en remettre la faute sur les gens qui ont créé cette route merveilleux et diabolique, qui a dit à bollique par coeur, merveilleux. Les économistes parlent de dépendance du santé. Ces vidéos, en fait, on est un santé qui a été établie, c'est un soit mon termine, soit définissant des beurs, on définisse un signalétique.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.42,
+      "end": 1.38,
+      "text": " C'est évidence que dit Nicolas.",
+      "tokens": [
+        383,
+        6,
+        377,
+        20090,
+        2778,
+        631,
+        6176,
+        38268,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.566579490710216,
+      "compression_ratio": 1.605421686746988,
+      "no_speech_prob": 0.14170263707637787,
+      "confidence": 0.625,
+      "words": [
+        {
+          "text": "C'est",
+          "start": 0.42,
+          "end": 0.66,
+          "confidence": 0.849
+        },
+        {
+          "text": "évidence",
+          "start": 0.66,
+          "end": 0.94,
+          "confidence": 0.368
+        },
+        {
+          "text": "que",
+          "start": 0.94,
+          "end": 1.06,
+          "confidence": 0.883
+        },
+        {
+          "text": "dit",
+          "start": 1.06,
+          "end": 1.16,
+          "confidence": 0.344
+        },
+        {
+          "text": "Nicolas.",
+          "start": 1.16,
+          "end": 1.38,
+          "confidence": 0.921
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 1.66,
+      "end": 3.62,
+      "text": " Mais je me l'étais jamais formulé comme ça.",
+      "tokens": [
+        6313,
+        1506,
+        385,
+        287,
+        6,
+        22824,
+        14540,
+        1254,
+        425,
+        526,
+        5173,
+        2788,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.566579490710216,
+      "compression_ratio": 1.605421686746988,
+      "no_speech_prob": 0.14170263707637787,
+      "confidence": 0.745,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 1.66,
+          "end": 1.9,
+          "confidence": 0.956
+        },
+        {
+          "text": "je",
+          "start": 1.9,
+          "end": 2.18,
+          "confidence": 0.629
+        },
+        {
+          "text": "me",
+          "start": 2.18,
+          "end": 2.3,
+          "confidence": 0.943
+        },
+        {
+          "text": "l'étais",
+          "start": 2.3,
+          "end": 2.54,
+          "confidence": 0.708
+        },
+        {
+          "text": "jamais",
+          "start": 2.54,
+          "end": 2.78,
+          "confidence": 0.962
+        },
+        {
+          "text": "formulé",
+          "start": 2.78,
+          "end": 3.2,
+          "confidence": 0.541
+        },
+        {
+          "text": "comme",
+          "start": 3.2,
+          "end": 3.34,
+          "confidence": 0.975
+        },
+        {
+          "text": "ça.",
+          "start": 3.34,
+          "end": 3.62,
+          "confidence": 0.979
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 4.14,
+      "end": 8.82,
+      "text": " Ce qui fait la force du smartphone, c'est pas seulement la cumulation des fonctions, mais la manière",
+      "tokens": [
+        8257,
+        1956,
+        3887,
+        635,
+        3464,
+        1581,
+        13307,
+        11,
+        269,
+        6,
+        377,
+        1736,
+        27772,
+        635,
+        12713,
+        2776,
+        730,
+        17290,
+        3916,
+        11,
+        2420,
+        635,
+        22267
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.566579490710216,
+      "compression_ratio": 1.605421686746988,
+      "no_speech_prob": 0.14170263707637787,
+      "confidence": 0.762,
+      "words": [
+        {
+          "text": "Ce",
+          "start": 4.14,
+          "end": 4.22,
+          "confidence": 0.39
+        },
+        {
+          "text": "qui",
+          "start": 4.22,
+          "end": 4.34,
+          "confidence": 0.934
+        },
+        {
+          "text": "fait",
+          "start": 4.34,
+          "end": 4.46,
+          "confidence": 0.735
+        },
+        {
+          "text": "la",
+          "start": 4.46,
+          "end": 4.56,
+          "confidence": 0.988
+        },
+        {
+          "text": "force",
+          "start": 4.56,
+          "end": 4.96,
+          "confidence": 0.933
+        },
+        {
+          "text": "du",
+          "start": 4.96,
+          "end": 5.16,
+          "confidence": 0.936
+        },
+        {
+          "text": "smartphone,",
+          "start": 5.16,
+          "end": 5.74,
+          "confidence": 0.909
+        },
+        {
+          "text": "c'est",
+          "start": 5.74,
+          "end": 6.12,
+          "confidence": 0.871
+        },
+        {
+          "text": "pas",
+          "start": 6.12,
+          "end": 6.2,
+          "confidence": 0.982
+        },
+        {
+          "text": "seulement",
+          "start": 6.2,
+          "end": 6.52,
+          "confidence": 0.991
+        },
+        {
+          "text": "la",
+          "start": 6.52,
+          "end": 6.76,
+          "confidence": 0.627
+        },
+        {
+          "text": "cumulation",
+          "start": 6.76,
+          "end": 7.18,
+          "confidence": 0.679
+        },
+        {
+          "text": "des",
+          "start": 7.18,
+          "end": 7.54,
+          "confidence": 0.752
+        },
+        {
+          "text": "fonctions,",
+          "start": 7.54,
+          "end": 8.1,
+          "confidence": 0.826
+        },
+        {
+          "text": "mais",
+          "start": 8.1,
+          "end": 8.42,
+          "confidence": 0.511
+        },
+        {
+          "text": "la",
+          "start": 8.42,
+          "end": 8.58,
+          "confidence": 0.717
+        },
+        {
+          "text": "manière",
+          "start": 8.58,
+          "end": 8.82,
+          "confidence": 0.457
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 8.9,
+      "end": 10.84,
+      "text": " dans quelques interagues entraîne.",
+      "tokens": [
+        2680,
+        16597,
+        728,
+        559,
+        1247,
+        22284,
+        24741,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.566579490710216,
+      "compression_ratio": 1.605421686746988,
+      "no_speech_prob": 0.14170263707637787,
+      "confidence": 0.3,
+      "words": [
+        {
+          "text": "dans",
+          "start": 8.9,
+          "end": 9.04,
+          "confidence": 0.329
+        },
+        {
+          "text": "quelques",
+          "start": 9.04,
+          "end": 9.26,
+          "confidence": 0.282
+        },
+        {
+          "text": "interagues",
+          "start": 9.26,
+          "end": 10.18,
+          "confidence": 0.238
+        },
+        {
+          "text": "entraîne.",
+          "start": 10.18,
+          "end": 10.84,
+          "confidence": 0.421
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 11.04,
+      "end": 12.92,
+      "text": " Et il est d'ailleurs, c'est la photo c'est hyper convaincant.",
+      "tokens": [
+        3790,
+        1930,
+        871,
+        274,
+        6,
+        19400,
+        11,
+        269,
+        6,
+        377,
+        635,
+        5052,
+        269,
+        6,
+        377,
+        9848,
+        3754,
+        491,
+        66,
+        394,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.566579490710216,
+      "compression_ratio": 1.605421686746988,
+      "no_speech_prob": 0.14170263707637787,
+      "confidence": 0.625,
+      "words": [
+        {
+          "text": "Et",
+          "start": 11.04,
+          "end": 11.1,
+          "confidence": 0.394
+        },
+        {
+          "text": "il",
+          "start": 11.1,
+          "end": 11.24,
+          "confidence": 0.128
+        },
+        {
+          "text": "est",
+          "start": 11.24,
+          "end": 11.38,
+          "confidence": 0.237
+        },
+        {
+          "text": "d'ailleurs,",
+          "start": 11.38,
+          "end": 11.62,
+          "confidence": 0.904
+        },
+        {
+          "text": "c'est",
+          "start": 11.62,
+          "end": 11.78,
+          "confidence": 0.879
+        },
+        {
+          "text": "la",
+          "start": 11.78,
+          "end": 11.82,
+          "confidence": 0.968
+        },
+        {
+          "text": "photo",
+          "start": 11.82,
+          "end": 11.92,
+          "confidence": 0.811
+        },
+        {
+          "text": "c'est",
+          "start": 11.92,
+          "end": 12.18,
+          "confidence": 0.792
+        },
+        {
+          "text": "hyper",
+          "start": 12.18,
+          "end": 12.38,
+          "confidence": 0.939
+        },
+        {
+          "text": "convaincant.",
+          "start": 12.38,
+          "end": 12.92,
+          "confidence": 0.494
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 0,
+      "start": 13.26,
+      "end": 18.03,
+      "text": " Alors évidemment, il faudrait ajouter les interfaces les grand-attêtes qu'il a été beaucoup",
+      "tokens": [
+        9946,
+        24724,
+        11,
+        1930,
+        38694,
+        8645,
+        17680,
+        23985,
+        1512,
+        28416,
+        1512,
+        2697,
+        12,
+        1591,
+        38262,
+        421,
+        6,
+        388,
+        257,
+        8862,
+        8796
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.566579490710216,
+      "compression_ratio": 1.605421686746988,
+      "no_speech_prob": 0.14170263707637787,
+      "confidence": 0.553,
+      "words": [
+        {
+          "text": "Alors",
+          "start": 13.26,
+          "end": 13.48,
+          "confidence": 0.904
+        },
+        {
+          "text": "évidemment,",
+          "start": 13.48,
+          "end": 13.92,
+          "confidence": 0.785
+        },
+        {
+          "text": "il",
+          "start": 13.92,
+          "end": 14.4,
+          "confidence": 0.961
+        },
+        {
+          "text": "faudrait",
+          "start": 14.4,
+          "end": 14.76,
+          "confidence": 0.85
+        },
+        {
+          "text": "ajouter",
+          "start": 14.76,
+          "end": 15.38,
+          "confidence": 0.874
+        },
+        {
+          "text": "les",
+          "start": 15.38,
+          "end": 15.62,
+          "confidence": 0.933
+        },
+        {
+          "text": "interfaces",
+          "start": 15.62,
+          "end": 15.86,
+          "confidence": 0.359
+        },
+        {
+          "text": "les",
+          "start": 15.86,
+          "end": 16.5,
+          "confidence": 0.414
+        },
+        {
+          "text": "grand-attêtes",
+          "start": 16.5,
+          "end": 16.94,
+          "confidence": 0.178
+        },
+        {
+          "text": "qu'il",
+          "start": 16.94,
+          "end": 17.18,
+          "confidence": 0.632
+        },
+        {
+          "text": "a",
+          "start": 17.18,
+          "end": 17.24,
+          "confidence": 0.969
+        },
+        {
+          "text": "été",
+          "start": 17.24,
+          "end": 17.5,
+          "confidence": 0.957
+        },
+        {
+          "text": "beaucoup",
+          "start": 17.5,
+          "end": 18.03,
+          "confidence": 0.572
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 0,
+      "start": 18.03,
+      "end": 19.26,
+      "text": " très souvent ementionné.",
+      "tokens": [
+        5732,
+        20847,
+        846,
+        1251,
+        15055,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.566579490710216,
+      "compression_ratio": 1.605421686746988,
+      "no_speech_prob": 0.14170263707637787,
+      "confidence": 0.541,
+      "words": [
+        {
+          "text": "très",
+          "start": 18.03,
+          "end": 18.66,
+          "confidence": 0.959
+        },
+        {
+          "text": "souvent",
+          "start": 18.66,
+          "end": 18.82,
+          "confidence": 0.994
+        },
+        {
+          "text": "ementionné.",
+          "start": 18.82,
+          "end": 19.26,
+          "confidence": 0.365
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 0,
+      "start": 19.86,
+      "end": 23.54,
+      "text": " Mais bon, il faudrait que les profites aussi de 20 ans pendant l'été, les ordinateurs",
+      "tokens": [
+        6313,
+        4428,
+        11,
+        1930,
+        38694,
+        8645,
+        631,
+        1512,
+        1740,
+        3324,
+        6212,
+        368,
+        945,
+        1567,
+        17338,
+        287,
+        6,
+        21210,
+        11,
+        1512,
+        4792,
+        13923,
+        2156
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.566579490710216,
+      "compression_ratio": 1.605421686746988,
+      "no_speech_prob": 0.14170263707637787,
+      "confidence": 0.648,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 19.86,
+          "end": 20.22,
+          "confidence": 0.975
+        },
+        {
+          "text": "bon,",
+          "start": 20.22,
+          "end": 20.56,
+          "confidence": 0.479
+        },
+        {
+          "text": "il",
+          "start": 20.56,
+          "end": 20.6,
+          "confidence": 0.978
+        },
+        {
+          "text": "faudrait",
+          "start": 20.6,
+          "end": 20.74,
+          "confidence": 0.753
+        },
+        {
+          "text": "que",
+          "start": 20.74,
+          "end": 20.92,
+          "confidence": 0.378
+        },
+        {
+          "text": "les",
+          "start": 20.92,
+          "end": 20.98,
+          "confidence": 0.182
+        },
+        {
+          "text": "profites",
+          "start": 20.98,
+          "end": 21.26,
+          "confidence": 0.622
+        },
+        {
+          "text": "aussi",
+          "start": 21.26,
+          "end": 21.7,
+          "confidence": 0.502
+        },
+        {
+          "text": "de",
+          "start": 21.7,
+          "end": 21.84,
+          "confidence": 0.468
+        },
+        {
+          "text": "20",
+          "start": 21.84,
+          "end": 22.08,
+          "confidence": 0.924
+        },
+        {
+          "text": "ans",
+          "start": 22.08,
+          "end": 22.28,
+          "confidence": 0.937
+        },
+        {
+          "text": "pendant",
+          "start": 22.28,
+          "end": 22.46,
+          "confidence": 0.903
+        },
+        {
+          "text": "l'été,",
+          "start": 22.46,
+          "end": 22.96,
+          "confidence": 0.499
+        },
+        {
+          "text": "les",
+          "start": 22.96,
+          "end": 23.04,
+          "confidence": 0.861
+        },
+        {
+          "text": "ordinateurs",
+          "start": 23.04,
+          "end": 23.54,
+          "confidence": 0.934
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 0,
+      "start": 23.58,
+      "end": 25.26,
+      "text": " nous ont appris à piquer sur des icônes.",
+      "tokens": [
+        4666,
+        6592,
+        724,
+        5714,
+        1531,
+        280,
+        23909,
+        1022,
+        730,
+        4376,
+        2851,
+        4081,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.566579490710216,
+      "compression_ratio": 1.605421686746988,
+      "no_speech_prob": 0.14170263707637787,
+      "confidence": 0.663,
+      "words": [
+        {
+          "text": "nous",
+          "start": 23.58,
+          "end": 23.74,
+          "confidence": 0.833
+        },
+        {
+          "text": "ont",
+          "start": 23.74,
+          "end": 23.86,
+          "confidence": 0.976
+        },
+        {
+          "text": "appris",
+          "start": 23.86,
+          "end": 24.06,
+          "confidence": 0.947
+        },
+        {
+          "text": "à",
+          "start": 24.06,
+          "end": 24.24,
+          "confidence": 0.24
+        },
+        {
+          "text": "piquer",
+          "start": 24.24,
+          "end": 24.42,
+          "confidence": 0.45
+        },
+        {
+          "text": "sur",
+          "start": 24.42,
+          "end": 24.68,
+          "confidence": 0.749
+        },
+        {
+          "text": "des",
+          "start": 24.68,
+          "end": 24.8,
+          "confidence": 0.96
+        },
+        {
+          "text": "icônes.",
+          "start": 24.8,
+          "end": 25.26,
+          "confidence": 0.656
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 2556,
+      "start": 25.58,
+      "end": 30.56,
+      "text": " C'est ce que le smartphone ajoute le toucher, qui rend le contact plus direct, plus sensible.",
+      "tokens": [
+        383,
+        6,
+        377,
+        1769,
+        631,
+        476,
+        13307,
+        17680,
+        14040,
+        476,
+        2557,
+        260,
+        11,
+        1956,
+        6125,
+        476,
+        3385,
+        1804,
+        2047,
+        11,
+        1804,
+        25380,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4095459938049316,
+      "compression_ratio": 1.7522658610271904,
+      "no_speech_prob": 0.0006256799097172916,
+      "confidence": 0.643,
+      "words": [
+        {
+          "text": "C'est",
+          "start": 25.58,
+          "end": 25.66,
+          "confidence": 0.449
+        },
+        {
+          "text": "ce",
+          "start": 25.66,
+          "end": 25.72,
+          "confidence": 0.491
+        },
+        {
+          "text": "que",
+          "start": 25.72,
+          "end": 25.94,
+          "confidence": 0.935
+        },
+        {
+          "text": "le",
+          "start": 25.94,
+          "end": 26.6,
+          "confidence": 0.377
+        },
+        {
+          "text": "smartphone",
+          "start": 26.6,
+          "end": 26.86,
+          "confidence": 0.977
+        },
+        {
+          "text": "ajoute",
+          "start": 26.86,
+          "end": 27.42,
+          "confidence": 0.813
+        },
+        {
+          "text": "le",
+          "start": 27.42,
+          "end": 27.64,
+          "confidence": 0.957
+        },
+        {
+          "text": "toucher,",
+          "start": 27.64,
+          "end": 28.06,
+          "confidence": 0.73
+        },
+        {
+          "text": "qui",
+          "start": 28.06,
+          "end": 28.18,
+          "confidence": 0.209
+        },
+        {
+          "text": "rend",
+          "start": 28.18,
+          "end": 28.34,
+          "confidence": 0.877
+        },
+        {
+          "text": "le",
+          "start": 28.34,
+          "end": 28.68,
+          "confidence": 0.991
+        },
+        {
+          "text": "contact",
+          "start": 28.68,
+          "end": 28.96,
+          "confidence": 0.854
+        },
+        {
+          "text": "plus",
+          "start": 28.96,
+          "end": 29.48,
+          "confidence": 0.865
+        },
+        {
+          "text": "direct,",
+          "start": 29.48,
+          "end": 29.96,
+          "confidence": 0.692
+        },
+        {
+          "text": "plus",
+          "start": 29.96,
+          "end": 30.24,
+          "confidence": 0.928
+        },
+        {
+          "text": "sensible.",
+          "start": 30.24,
+          "end": 30.56,
+          "confidence": 0.332
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 2556,
+      "start": 31.04,
+      "end": 34.34,
+      "text": " Et puis, évidemment, il faudrait parler aussi des applications qui permettent de contourner",
+      "tokens": [
+        3790,
+        9093,
+        11,
+        24724,
+        11,
+        1930,
+        38694,
+        8645,
+        16421,
+        6212,
+        730,
+        5821,
+        1956,
+        21540,
+        317,
+        368,
+        21234,
+        1193
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4095459938049316,
+      "compression_ratio": 1.7522658610271904,
+      "no_speech_prob": 0.0006256799097172916,
+      "confidence": 0.827,
+      "words": [
+        {
+          "text": "Et",
+          "start": 31.04,
+          "end": 31.24,
+          "confidence": 0.914
+        },
+        {
+          "text": "puis,",
+          "start": 31.24,
+          "end": 31.34,
+          "confidence": 0.713
+        },
+        {
+          "text": "évidemment,",
+          "start": 31.34,
+          "end": 31.64,
+          "confidence": 0.378
+        },
+        {
+          "text": "il",
+          "start": 31.64,
+          "end": 31.78,
+          "confidence": 0.935
+        },
+        {
+          "text": "faudrait",
+          "start": 31.78,
+          "end": 31.88,
+          "confidence": 0.99
+        },
+        {
+          "text": "parler",
+          "start": 31.88,
+          "end": 32.12,
+          "confidence": 0.882
+        },
+        {
+          "text": "aussi",
+          "start": 32.12,
+          "end": 32.3,
+          "confidence": 0.889
+        },
+        {
+          "text": "des",
+          "start": 32.3,
+          "end": 32.44,
+          "confidence": 0.927
+        },
+        {
+          "text": "applications",
+          "start": 32.44,
+          "end": 32.78,
+          "confidence": 0.839
+        },
+        {
+          "text": "qui",
+          "start": 32.78,
+          "end": 33.16,
+          "confidence": 0.652
+        },
+        {
+          "text": "permettent",
+          "start": 33.16,
+          "end": 33.68,
+          "confidence": 0.951
+        },
+        {
+          "text": "de",
+          "start": 33.68,
+          "end": 33.9,
+          "confidence": 0.952
+        },
+        {
+          "text": "contourner",
+          "start": 33.9,
+          "end": 34.34,
+          "confidence": 0.787
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 2556,
+      "start": 34.34,
+      "end": 37.72,
+      "text": " le côté tout flu de la navigation web pour aller directement en but.",
+      "tokens": [
+        476,
+        18437,
+        3486,
+        5029,
+        368,
+        635,
+        17346,
+        3670,
+        2016,
+        8722,
+        37297,
+        465,
+        457,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4095459938049316,
+      "compression_ratio": 1.7522658610271904,
+      "no_speech_prob": 0.0006256799097172916,
+      "confidence": 0.766,
+      "words": [
+        {
+          "text": "le",
+          "start": 34.34,
+          "end": 34.52,
+          "confidence": 0.989
+        },
+        {
+          "text": "côté",
+          "start": 34.52,
+          "end": 34.72,
+          "confidence": 0.983
+        },
+        {
+          "text": "tout",
+          "start": 34.72,
+          "end": 34.96,
+          "confidence": 0.954
+        },
+        {
+          "text": "flu",
+          "start": 34.96,
+          "end": 35.2,
+          "confidence": 0.548
+        },
+        {
+          "text": "de",
+          "start": 35.2,
+          "end": 35.42,
+          "confidence": 0.248
+        },
+        {
+          "text": "la",
+          "start": 35.42,
+          "end": 35.72,
+          "confidence": 0.902
+        },
+        {
+          "text": "navigation",
+          "start": 35.72,
+          "end": 36.04,
+          "confidence": 0.913
+        },
+        {
+          "text": "web",
+          "start": 36.04,
+          "end": 36.64,
+          "confidence": 0.93
+        },
+        {
+          "text": "pour",
+          "start": 36.64,
+          "end": 36.76,
+          "confidence": 0.746
+        },
+        {
+          "text": "aller",
+          "start": 36.76,
+          "end": 36.94,
+          "confidence": 0.992
+        },
+        {
+          "text": "directement",
+          "start": 36.94,
+          "end": 37.46,
+          "confidence": 0.986
+        },
+        {
+          "text": "en",
+          "start": 37.46,
+          "end": 37.68,
+          "confidence": 0.644
+        },
+        {
+          "text": "but.",
+          "start": 37.68,
+          "end": 37.72,
+          "confidence": 0.689
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 2556,
+      "start": 37.72,
+      "end": 43.06,
+      "text": " Bref, tout ça, ce sont les conditions qui permettent de créer cette objet, en Nicolas,",
+      "tokens": [
+        49957,
+        11,
+        3486,
+        2788,
+        11,
+        1769,
+        4900,
+        1512,
+        4487,
+        1956,
+        21540,
+        317,
+        368,
+        32062,
+        5550,
+        14964,
+        11,
+        465,
+        38268,
+        11
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4095459938049316,
+      "compression_ratio": 1.7522658610271904,
+      "no_speech_prob": 0.0006256799097172916,
+      "confidence": 0.725,
+      "words": [
+        {
+          "text": "Bref,",
+          "start": 37.72,
+          "end": 38.9,
+          "confidence": 0.967
+        },
+        {
+          "text": "tout",
+          "start": 38.9,
+          "end": 38.98,
+          "confidence": 0.786
+        },
+        {
+          "text": "ça,",
+          "start": 38.98,
+          "end": 39.36,
+          "confidence": 0.985
+        },
+        {
+          "text": "ce",
+          "start": 39.36,
+          "end": 39.68,
+          "confidence": 0.929
+        },
+        {
+          "text": "sont",
+          "start": 39.68,
+          "end": 39.84,
+          "confidence": 0.963
+        },
+        {
+          "text": "les",
+          "start": 39.84,
+          "end": 40.06,
+          "confidence": 0.976
+        },
+        {
+          "text": "conditions",
+          "start": 40.06,
+          "end": 40.54,
+          "confidence": 0.96
+        },
+        {
+          "text": "qui",
+          "start": 40.54,
+          "end": 40.9,
+          "confidence": 0.995
+        },
+        {
+          "text": "permettent",
+          "start": 40.9,
+          "end": 41.54,
+          "confidence": 0.986
+        },
+        {
+          "text": "de",
+          "start": 41.54,
+          "end": 41.58,
+          "confidence": 0.989
+        },
+        {
+          "text": "créer",
+          "start": 41.58,
+          "end": 41.92,
+          "confidence": 0.918
+        },
+        {
+          "text": "cette",
+          "start": 41.92,
+          "end": 42.3,
+          "confidence": 0.518
+        },
+        {
+          "text": "objet,",
+          "start": 42.3,
+          "end": 42.7,
+          "confidence": 0.213
+        },
+        {
+          "text": "en",
+          "start": 42.7,
+          "end": 42.8,
+          "confidence": 0.191
+        },
+        {
+          "text": "Nicolas,",
+          "start": 42.8,
+          "end": 43.06,
+          "confidence": 0.508
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 2556,
+      "start": 43.1,
+      "end": 46.48,
+      "text": " dit qu'il est très fondablement inédit dans l'histoire de l'humanité.",
+      "tokens": [
+        6176,
+        421,
+        6,
+        388,
+        871,
+        5732,
+        9557,
+        712,
+        518,
+        294,
+        7811,
+        270,
+        2680,
+        287,
+        6,
+        29093,
+        368,
+        287,
+        6,
+        18796,
+        5066,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4095459938049316,
+      "compression_ratio": 1.7522658610271904,
+      "no_speech_prob": 0.0006256799097172916,
+      "confidence": 0.768,
+      "words": [
+        {
+          "text": "dit",
+          "start": 43.1,
+          "end": 43.52,
+          "confidence": 0.551
+        },
+        {
+          "text": "qu'il",
+          "start": 43.52,
+          "end": 43.68,
+          "confidence": 0.969
+        },
+        {
+          "text": "est",
+          "start": 43.68,
+          "end": 43.8,
+          "confidence": 0.851
+        },
+        {
+          "text": "très",
+          "start": 43.8,
+          "end": 43.94,
+          "confidence": 0.368
+        },
+        {
+          "text": "fondablement",
+          "start": 43.94,
+          "end": 44.68,
+          "confidence": 0.593
+        },
+        {
+          "text": "inédit",
+          "start": 44.68,
+          "end": 45.52,
+          "confidence": 0.66
+        },
+        {
+          "text": "dans",
+          "start": 45.52,
+          "end": 45.74,
+          "confidence": 0.778
+        },
+        {
+          "text": "l'histoire",
+          "start": 45.74,
+          "end": 45.98,
+          "confidence": 0.825
+        },
+        {
+          "text": "de",
+          "start": 45.98,
+          "end": 46.08,
+          "confidence": 0.978
+        },
+        {
+          "text": "l'humanité.",
+          "start": 46.08,
+          "end": 46.48,
+          "confidence": 0.991
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 2556,
+      "start": 47.06,
+      "end": 48.76,
+      "text": " Mais ça s'assoulait d'une autre interrogation.",
+      "tokens": [
+        6313,
+        2788,
+        262,
+        6,
+        640,
+        263,
+        35235,
+        274,
+        6,
+        2613,
+        15081,
+        24871,
+        399,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4095459938049316,
+      "compression_ratio": 1.7522658610271904,
+      "no_speech_prob": 0.0006256799097172916,
+      "confidence": 0.697,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 47.06,
+          "end": 47.16,
+          "confidence": 0.939
+        },
+        {
+          "text": "ça",
+          "start": 47.16,
+          "end": 47.46,
+          "confidence": 0.854
+        },
+        {
+          "text": "s'assoulait",
+          "start": 47.46,
+          "end": 47.78,
+          "confidence": 0.591
+        },
+        {
+          "text": "d'une",
+          "start": 47.78,
+          "end": 48.02,
+          "confidence": 0.619
+        },
+        {
+          "text": "autre",
+          "start": 48.02,
+          "end": 48.14,
+          "confidence": 0.966
+        },
+        {
+          "text": "interrogation.",
+          "start": 48.14,
+          "end": 48.76,
+          "confidence": 0.833
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 2556,
+      "start": 49.26,
+      "end": 54.34,
+      "text": " Est-ce que le fait que cette objet soit inédit un d'huies que notre rapport a lui est aussi",
+      "tokens": [
+        4410,
+        12,
+        384,
+        631,
+        476,
+        3887,
+        631,
+        5550,
+        14964,
+        12703,
+        294,
+        7811,
+        270,
+        517,
+        274,
+        6,
+        12086,
+        530,
+        631,
+        10349,
+        18018,
+        257,
+        8783,
+        871,
+        6212
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4095459938049316,
+      "compression_ratio": 1.7522658610271904,
+      "no_speech_prob": 0.0006256799097172916,
+      "confidence": 0.697,
+      "words": [
+        {
+          "text": "Est-ce",
+          "start": 49.26,
+          "end": 49.7,
+          "confidence": 0.804
+        },
+        {
+          "text": "que",
+          "start": 49.7,
+          "end": 49.74,
+          "confidence": 0.989
+        },
+        {
+          "text": "le",
+          "start": 49.74,
+          "end": 49.78,
+          "confidence": 0.882
+        },
+        {
+          "text": "fait",
+          "start": 49.78,
+          "end": 49.96,
+          "confidence": 0.962
+        },
+        {
+          "text": "que",
+          "start": 49.96,
+          "end": 50.08,
+          "confidence": 0.935
+        },
+        {
+          "text": "cette",
+          "start": 50.08,
+          "end": 50.24,
+          "confidence": 0.95
+        },
+        {
+          "text": "objet",
+          "start": 50.24,
+          "end": 50.5,
+          "confidence": 0.968
+        },
+        {
+          "text": "soit",
+          "start": 50.5,
+          "end": 50.96,
+          "confidence": 0.991
+        },
+        {
+          "text": "inédit",
+          "start": 50.96,
+          "end": 51.78,
+          "confidence": 0.91
+        },
+        {
+          "text": "un",
+          "start": 51.78,
+          "end": 52.06,
+          "confidence": 0.442
+        },
+        {
+          "text": "d'huies",
+          "start": 52.06,
+          "end": 52.32,
+          "confidence": 0.298
+        },
+        {
+          "text": "que",
+          "start": 52.32,
+          "end": 52.4,
+          "confidence": 0.966
+        },
+        {
+          "text": "notre",
+          "start": 52.4,
+          "end": 52.58,
+          "confidence": 0.992
+        },
+        {
+          "text": "rapport",
+          "start": 52.58,
+          "end": 53.1,
+          "confidence": 0.714
+        },
+        {
+          "text": "a",
+          "start": 53.1,
+          "end": 53.44,
+          "confidence": 0.522
+        },
+        {
+          "text": "lui",
+          "start": 53.44,
+          "end": 53.62,
+          "confidence": 0.659
+        },
+        {
+          "text": "est",
+          "start": 53.62,
+          "end": 54.0,
+          "confidence": 0.643
+        },
+        {
+          "text": "aussi",
+          "start": 54.0,
+          "end": 54.34,
+          "confidence": 0.808
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 2556,
+      "start": 54.34,
+      "end": 55.32,
+      "text": " un rapport inédit?",
+      "tokens": [
+        517,
+        18018,
+        294,
+        7811,
+        270,
+        2506
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4095459938049316,
+      "compression_ratio": 1.7522658610271904,
+      "no_speech_prob": 0.0006256799097172916,
+      "confidence": 0.849,
+      "words": [
+        {
+          "text": "un",
+          "start": 54.34,
+          "end": 54.72,
+          "confidence": 0.506
+        },
+        {
+          "text": "rapport",
+          "start": 54.72,
+          "end": 54.94,
+          "confidence": 0.999
+        },
+        {
+          "text": "inédit?",
+          "start": 54.94,
+          "end": 55.32,
+          "confidence": 0.956
+        }
+      ]
+    },
+    {
+      "id": 17,
+      "seek": 5548,
+      "start": 55.6,
+      "end": 58.6,
+      "text": " Je veux dire, est-ce que le rapport qu'on a au sein de foi n'est comparable à celui",
+      "tokens": [
+        2588,
+        16389,
+        1264,
+        11,
+        871,
+        12,
+        384,
+        631,
+        476,
+        18018,
+        421,
+        6,
+        266,
+        257,
+        1609,
+        6195,
+        368,
+        6901,
+        297,
+        6,
+        377,
+        6311,
+        712,
+        1531,
+        22829
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6093524909167556,
+      "compression_ratio": 1.6292834890965733,
+      "no_speech_prob": 6.752492481609806e-05,
+      "confidence": 0.626,
+      "words": [
+        {
+          "text": "Je",
+          "start": 55.6,
+          "end": 55.84,
+          "confidence": 0.335
+        },
+        {
+          "text": "veux",
+          "start": 55.84,
+          "end": 55.94,
+          "confidence": 0.432
+        },
+        {
+          "text": "dire,",
+          "start": 55.94,
+          "end": 56.16,
+          "confidence": 0.992
+        },
+        {
+          "text": "est-ce",
+          "start": 56.16,
+          "end": 56.34,
+          "confidence": 0.951
+        },
+        {
+          "text": "que",
+          "start": 56.34,
+          "end": 56.4,
+          "confidence": 0.973
+        },
+        {
+          "text": "le",
+          "start": 56.4,
+          "end": 56.54,
+          "confidence": 0.987
+        },
+        {
+          "text": "rapport",
+          "start": 56.54,
+          "end": 56.76,
+          "confidence": 0.999
+        },
+        {
+          "text": "qu'on",
+          "start": 56.76,
+          "end": 57.1,
+          "confidence": 0.906
+        },
+        {
+          "text": "a",
+          "start": 57.1,
+          "end": 57.14,
+          "confidence": 0.974
+        },
+        {
+          "text": "au",
+          "start": 57.14,
+          "end": 57.26,
+          "confidence": 0.319
+        },
+        {
+          "text": "sein",
+          "start": 57.26,
+          "end": 57.36,
+          "confidence": 0.244
+        },
+        {
+          "text": "de",
+          "start": 57.36,
+          "end": 57.44,
+          "confidence": 0.177
+        },
+        {
+          "text": "foi",
+          "start": 57.44,
+          "end": 57.54,
+          "confidence": 0.163
+        },
+        {
+          "text": "n'est",
+          "start": 57.54,
+          "end": 57.78,
+          "confidence": 0.777
+        },
+        {
+          "text": "comparable",
+          "start": 57.78,
+          "end": 58.32,
+          "confidence": 0.606
+        },
+        {
+          "text": "à",
+          "start": 58.32,
+          "end": 58.46,
+          "confidence": 0.482
+        },
+        {
+          "text": "celui",
+          "start": 58.46,
+          "end": 58.6,
+          "confidence": 0.831
+        }
+      ]
+    },
+    {
+      "id": 18,
+      "seek": 5548,
+      "start": 58.72,
+      "end": 62.81,
+      "text": " qu'on entretenait à d'autres objectes techniques comme la voiture ou le téléphone?",
+      "tokens": [
+        421,
+        6,
+        266,
+        3962,
+        1147,
+        1001,
+        1531,
+        274,
+        6,
+        16752,
+        2657,
+        279,
+        7512,
+        5173,
+        635,
+        38859,
+        2820,
+        476,
+        47159,
+        2506
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6093524909167556,
+      "compression_ratio": 1.6292834890965733,
+      "no_speech_prob": 6.752492481609806e-05,
+      "confidence": 0.781,
+      "words": [
+        {
+          "text": "qu'on",
+          "start": 58.72,
+          "end": 58.88,
+          "confidence": 0.941
+        },
+        {
+          "text": "entretenait",
+          "start": 58.88,
+          "end": 59.38,
+          "confidence": 0.657
+        },
+        {
+          "text": "à",
+          "start": 59.38,
+          "end": 59.44,
+          "confidence": 0.973
+        },
+        {
+          "text": "d'autres",
+          "start": 59.44,
+          "end": 59.64,
+          "confidence": 0.909
+        },
+        {
+          "text": "objectes",
+          "start": 59.64,
+          "end": 60.02,
+          "confidence": 0.528
+        },
+        {
+          "text": "techniques",
+          "start": 60.02,
+          "end": 60.38,
+          "confidence": 0.547
+        },
+        {
+          "text": "comme",
+          "start": 60.38,
+          "end": 60.86,
+          "confidence": 0.662
+        },
+        {
+          "text": "la",
+          "start": 60.86,
+          "end": 61.46,
+          "confidence": 0.898
+        },
+        {
+          "text": "voiture",
+          "start": 61.46,
+          "end": 61.8,
+          "confidence": 0.954
+        },
+        {
+          "text": "ou",
+          "start": 61.8,
+          "end": 62.32,
+          "confidence": 0.74
+        },
+        {
+          "text": "le",
+          "start": 62.32,
+          "end": 62.6,
+          "confidence": 0.847
+        },
+        {
+          "text": "téléphone?",
+          "start": 62.6,
+          "end": 62.81,
+          "confidence": 0.979
+        }
+      ]
+    },
+    {
+      "id": 19,
+      "seek": 5548,
+      "start": 62.81,
+      "end": 66.07,
+      "text": " Il n'y a pas d'équivalent.",
+      "tokens": [
+        4416,
+        297,
+        6,
+        88,
+        257,
+        1736,
+        274,
+        6,
+        20183,
+        3576,
+        317,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6093524909167556,
+      "compression_ratio": 1.6292834890965733,
+      "no_speech_prob": 6.752492481609806e-05,
+      "confidence": 0.882,
+      "words": [
+        {
+          "text": "Il",
+          "start": 62.81,
+          "end": 65.42,
+          "confidence": 0.866
+        },
+        {
+          "text": "n'y",
+          "start": 65.42,
+          "end": 65.52,
+          "confidence": 0.865
+        },
+        {
+          "text": "a",
+          "start": 65.52,
+          "end": 65.56,
+          "confidence": 0.965
+        },
+        {
+          "text": "pas",
+          "start": 65.56,
+          "end": 65.62,
+          "confidence": 0.998
+        },
+        {
+          "text": "d'équivalent.",
+          "start": 65.62,
+          "end": 66.07,
+          "confidence": 0.858
+        }
+      ]
+    },
+    {
+      "id": 20,
+      "seek": 5548,
+      "start": 66.07,
+      "end": 69.74,
+      "text": " On s'est espécie de nous voter dans la relation à l'objet.",
+      "tokens": [
+        1282,
+        262,
+        6,
+        377,
+        7089,
+        526,
+        4260,
+        368,
+        4666,
+        21722,
+        2680,
+        635,
+        9721,
+        1531,
+        287,
+        6,
+        996,
+        7108,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6093524909167556,
+      "compression_ratio": 1.6292834890965733,
+      "no_speech_prob": 6.752492481609806e-05,
+      "confidence": 0.552,
+      "words": [
+        {
+          "text": "On",
+          "start": 66.07,
+          "end": 67.0,
+          "confidence": 0.29
+        },
+        {
+          "text": "s'est",
+          "start": 67.0,
+          "end": 67.26,
+          "confidence": 0.562
+        },
+        {
+          "text": "espécie",
+          "start": 67.26,
+          "end": 67.46,
+          "confidence": 0.233
+        },
+        {
+          "text": "de",
+          "start": 67.46,
+          "end": 67.58,
+          "confidence": 0.963
+        },
+        {
+          "text": "nous",
+          "start": 67.58,
+          "end": 67.8,
+          "confidence": 0.631
+        },
+        {
+          "text": "voter",
+          "start": 67.8,
+          "end": 68.24,
+          "confidence": 0.241
+        },
+        {
+          "text": "dans",
+          "start": 68.24,
+          "end": 68.68,
+          "confidence": 0.853
+        },
+        {
+          "text": "la",
+          "start": 68.68,
+          "end": 68.88,
+          "confidence": 0.61
+        },
+        {
+          "text": "relation",
+          "start": 68.88,
+          "end": 69.22,
+          "confidence": 0.932
+        },
+        {
+          "text": "à",
+          "start": 69.22,
+          "end": 69.34,
+          "confidence": 0.792
+        },
+        {
+          "text": "l'objet.",
+          "start": 69.34,
+          "end": 69.74,
+          "confidence": 0.889
+        }
+      ]
+    },
+    {
+      "id": 21,
+      "seek": 5548,
+      "start": 70.18,
+      "end": 74.78,
+      "text": " C'est facilement éterréciant parce qu'on a impression de, comme le 10, les utilisateurs",
+      "tokens": [
+        383,
+        6,
+        377,
+        23670,
+        518,
+        1136,
+        391,
+        10521,
+        537,
+        394,
+        6992,
+        421,
+        6,
+        266,
+        257,
+        9995,
+        368,
+        11,
+        5173,
+        476,
+        1266,
+        11,
+        1512,
+        33643,
+        25929
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6093524909167556,
+      "compression_ratio": 1.6292834890965733,
+      "no_speech_prob": 6.752492481609806e-05,
+      "confidence": 0.491,
+      "words": [
+        {
+          "text": "C'est",
+          "start": 70.18,
+          "end": 70.34,
+          "confidence": 0.907
+        },
+        {
+          "text": "facilement",
+          "start": 70.34,
+          "end": 70.72,
+          "confidence": 0.527
+        },
+        {
+          "text": "éterréciant",
+          "start": 70.72,
+          "end": 71.56,
+          "confidence": 0.277
+        },
+        {
+          "text": "parce",
+          "start": 71.56,
+          "end": 71.82,
+          "confidence": 0.298
+        },
+        {
+          "text": "qu'on",
+          "start": 71.82,
+          "end": 72.3,
+          "confidence": 0.775
+        },
+        {
+          "text": "a",
+          "start": 72.3,
+          "end": 72.4,
+          "confidence": 0.563
+        },
+        {
+          "text": "impression",
+          "start": 72.4,
+          "end": 72.74,
+          "confidence": 0.148
+        },
+        {
+          "text": "de,",
+          "start": 72.74,
+          "end": 73.36,
+          "confidence": 0.211
+        },
+        {
+          "text": "comme",
+          "start": 73.36,
+          "end": 73.8,
+          "confidence": 0.843
+        },
+        {
+          "text": "le",
+          "start": 73.8,
+          "end": 73.96,
+          "confidence": 0.9
+        },
+        {
+          "text": "10,",
+          "start": 73.96,
+          "end": 74.28,
+          "confidence": 0.395
+        },
+        {
+          "text": "les",
+          "start": 74.28,
+          "end": 74.32,
+          "confidence": 0.581
+        },
+        {
+          "text": "utilisateurs",
+          "start": 74.32,
+          "end": 74.78,
+          "confidence": 0.745
+        }
+      ]
+    },
+    {
+      "id": 22,
+      "seek": 5548,
+      "start": 74.8,
+      "end": 77.93,
+      "text": " et les efforts, elles aident dépendant de cette objet d'un lieu, en fait, une espèce de",
+      "tokens": [
+        1030,
+        1512,
+        6484,
+        11,
+        23576,
+        257,
+        1078,
+        45768,
+        394,
+        368,
+        5550,
+        14964,
+        274,
+        6,
+        409,
+        26036,
+        11,
+        465,
+        3887,
+        11,
+        2251,
+        7089,
+        30236,
+        368
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6093524909167556,
+      "compression_ratio": 1.6292834890965733,
+      "no_speech_prob": 6.752492481609806e-05,
+      "confidence": 0.464,
+      "words": [
+        {
+          "text": "et",
+          "start": 74.8,
+          "end": 74.92,
+          "confidence": 0.147
+        },
+        {
+          "text": "les",
+          "start": 74.92,
+          "end": 74.96,
+          "confidence": 0.242
+        },
+        {
+          "text": "efforts,",
+          "start": 74.96,
+          "end": 75.22,
+          "confidence": 0.108
+        },
+        {
+          "text": "elles",
+          "start": 75.22,
+          "end": 75.32,
+          "confidence": 0.108
+        },
+        {
+          "text": "aident",
+          "start": 75.32,
+          "end": 75.44,
+          "confidence": 0.289
+        },
+        {
+          "text": "dépendant",
+          "start": 75.44,
+          "end": 76.0,
+          "confidence": 0.576
+        },
+        {
+          "text": "de",
+          "start": 76.0,
+          "end": 76.16,
+          "confidence": 0.301
+        },
+        {
+          "text": "cette",
+          "start": 76.16,
+          "end": 76.2,
+          "confidence": 0.519
+        },
+        {
+          "text": "objet",
+          "start": 76.2,
+          "end": 76.48,
+          "confidence": 0.961
+        },
+        {
+          "text": "d'un",
+          "start": 76.48,
+          "end": 76.86,
+          "confidence": 0.883
+        },
+        {
+          "text": "lieu,",
+          "start": 76.86,
+          "end": 77.06,
+          "confidence": 0.333
+        },
+        {
+          "text": "en",
+          "start": 77.06,
+          "end": 77.18,
+          "confidence": 0.837
+        },
+        {
+          "text": "fait,",
+          "start": 77.18,
+          "end": 77.42,
+          "confidence": 0.958
+        },
+        {
+          "text": "une",
+          "start": 77.42,
+          "end": 77.46,
+          "confidence": 0.57
+        },
+        {
+          "text": "espèce",
+          "start": 77.46,
+          "end": 77.74,
+          "confidence": 0.961
+        },
+        {
+          "text": "de",
+          "start": 77.74,
+          "end": 77.93,
+          "confidence": 0.601
+        }
+      ]
+    },
+    {
+      "id": 23,
+      "seek": 5548,
+      "start": 77.93,
+      "end": 82.98,
+      "text": " relation de médiation avec le monde qui rendent un peu avec la même sédiforme de",
+      "tokens": [
+        9721,
+        368,
+        42436,
+        399,
+        4163,
+        476,
+        10431,
+        1956,
+        6125,
+        317,
+        517,
+        5604,
+        4163,
+        635,
+        5698,
+        262,
+        7811,
+        8629,
+        68,
+        368
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6093524909167556,
+      "compression_ratio": 1.6292834890965733,
+      "no_speech_prob": 6.752492481609806e-05,
+      "confidence": 0.556,
+      "words": [
+        {
+          "text": "relation",
+          "start": 77.93,
+          "end": 78.32,
+          "confidence": 0.839
+        },
+        {
+          "text": "de",
+          "start": 78.32,
+          "end": 78.7,
+          "confidence": 0.723
+        },
+        {
+          "text": "médiation",
+          "start": 78.7,
+          "end": 79.4,
+          "confidence": 0.872
+        },
+        {
+          "text": "avec",
+          "start": 79.4,
+          "end": 79.74,
+          "confidence": 0.964
+        },
+        {
+          "text": "le",
+          "start": 79.74,
+          "end": 79.88,
+          "confidence": 0.985
+        },
+        {
+          "text": "monde",
+          "start": 79.88,
+          "end": 80.24,
+          "confidence": 0.909
+        },
+        {
+          "text": "qui",
+          "start": 80.24,
+          "end": 81.02,
+          "confidence": 0.871
+        },
+        {
+          "text": "rendent",
+          "start": 81.02,
+          "end": 81.74,
+          "confidence": 0.623
+        },
+        {
+          "text": "un",
+          "start": 81.74,
+          "end": 81.84,
+          "confidence": 0.224
+        },
+        {
+          "text": "peu",
+          "start": 81.84,
+          "end": 81.88,
+          "confidence": 0.223
+        },
+        {
+          "text": "avec",
+          "start": 81.88,
+          "end": 82.1,
+          "confidence": 0.863
+        },
+        {
+          "text": "la",
+          "start": 82.1,
+          "end": 82.24,
+          "confidence": 0.565
+        },
+        {
+          "text": "même",
+          "start": 82.24,
+          "end": 82.32,
+          "confidence": 0.384
+        },
+        {
+          "text": "sédiforme",
+          "start": 82.32,
+          "end": 82.86,
+          "confidence": 0.29
+        },
+        {
+          "text": "de",
+          "start": 82.86,
+          "end": 82.98,
+          "confidence": 0.899
+        }
+      ]
+    },
+    {
+      "id": 24,
+      "seek": 8298,
+      "start": 83.0,
+      "end": 87.66,
+      "text": " le jeu. Donc, à objets inédits, rapport inédits.",
+      "tokens": [
+        476,
+        16748,
+        13,
+        7477,
+        11,
+        1531,
+        1111,
+        25349,
+        294,
+        7811,
+        1208,
+        11,
+        18018,
+        294,
+        7811,
+        1208,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4346100035167876,
+      "compression_ratio": 1.5907335907335907,
+      "no_speech_prob": 3.121094050584361e-05,
+      "confidence": 0.614,
+      "words": [
+        {
+          "text": "le",
+          "start": 83.0,
+          "end": 83.12,
+          "confidence": 0.128
+        },
+        {
+          "text": "jeu.",
+          "start": 83.12,
+          "end": 83.64,
+          "confidence": 0.505
+        },
+        {
+          "text": "Donc,",
+          "start": 83.64,
+          "end": 84.48,
+          "confidence": 0.513
+        },
+        {
+          "text": "à",
+          "start": 84.48,
+          "end": 84.86,
+          "confidence": 0.634
+        },
+        {
+          "text": "objets",
+          "start": 84.86,
+          "end": 85.36,
+          "confidence": 0.547
+        },
+        {
+          "text": "inédits,",
+          "start": 85.36,
+          "end": 86.24,
+          "confidence": 0.73
+        },
+        {
+          "text": "rapport",
+          "start": 86.24,
+          "end": 86.62,
+          "confidence": 0.928
+        },
+        {
+          "text": "inédits.",
+          "start": 86.62,
+          "end": 87.66,
+          "confidence": 0.921
+        }
+      ]
+    },
+    {
+      "id": 25,
+      "seek": 8298,
+      "start": 88.08,
+      "end": 93.78,
+      "text": " Et, ce rapport, si j'en prends Nicolas, frère caractérisée par un mélange de dépenses",
+      "tokens": [
+        3790,
+        11,
+        1769,
+        18018,
+        11,
+        1511,
+        361,
+        6,
+        268,
+        46750,
+        38268,
+        11,
+        431,
+        4212,
+        1032,
+        578,
+        4198,
+        50027,
+        971,
+        517,
+        41953,
+        933,
+        368,
+        27998,
+        9085
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4346100035167876,
+      "compression_ratio": 1.5907335907335907,
+      "no_speech_prob": 3.121094050584361e-05,
+      "confidence": 0.624,
+      "words": [
+        {
+          "text": "Et,",
+          "start": 88.08,
+          "end": 88.3,
+          "confidence": 0.87
+        },
+        {
+          "text": "ce",
+          "start": 88.3,
+          "end": 88.8,
+          "confidence": 0.462
+        },
+        {
+          "text": "rapport,",
+          "start": 88.8,
+          "end": 89.28,
+          "confidence": 0.997
+        },
+        {
+          "text": "si",
+          "start": 89.28,
+          "end": 89.56,
+          "confidence": 0.913
+        },
+        {
+          "text": "j'en",
+          "start": 89.56,
+          "end": 89.74,
+          "confidence": 0.771
+        },
+        {
+          "text": "prends",
+          "start": 89.74,
+          "end": 89.84,
+          "confidence": 0.313
+        },
+        {
+          "text": "Nicolas,",
+          "start": 89.84,
+          "end": 90.54,
+          "confidence": 0.358
+        },
+        {
+          "text": "frère",
+          "start": 90.54,
+          "end": 91.06,
+          "confidence": 0.405
+        },
+        {
+          "text": "caractérisée",
+          "start": 91.06,
+          "end": 91.7,
+          "confidence": 0.567
+        },
+        {
+          "text": "par",
+          "start": 91.7,
+          "end": 92.12,
+          "confidence": 0.868
+        },
+        {
+          "text": "un",
+          "start": 92.12,
+          "end": 92.32,
+          "confidence": 0.989
+        },
+        {
+          "text": "mélange",
+          "start": 92.32,
+          "end": 92.96,
+          "confidence": 0.932
+        },
+        {
+          "text": "de",
+          "start": 92.96,
+          "end": 93.24,
+          "confidence": 0.812
+        },
+        {
+          "text": "dépenses",
+          "start": 93.24,
+          "end": 93.78,
+          "confidence": 0.404
+        }
+      ]
+    },
+    {
+      "id": 26,
+      "seek": 8298,
+      "start": 94.36,
+      "end": 94.98,
+      "text": " et de rojets.",
+      "tokens": [
+        1030,
+        368,
+        744,
+        73,
+        1385,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4346100035167876,
+      "compression_ratio": 1.5907335907335907,
+      "no_speech_prob": 3.121094050584361e-05,
+      "confidence": 0.583,
+      "words": [
+        {
+          "text": "et",
+          "start": 94.36,
+          "end": 94.52,
+          "confidence": 0.986
+        },
+        {
+          "text": "de",
+          "start": 94.52,
+          "end": 94.56,
+          "confidence": 0.996
+        },
+        {
+          "text": "rojets.",
+          "start": 94.56,
+          "end": 94.98,
+          "confidence": 0.41
+        }
+      ]
+    },
+    {
+      "id": 27,
+      "seek": 8298,
+      "start": 95.8,
+      "end": 100.4,
+      "text": " Bon, en vrai, il faudrait remonter très très finement toute l'histoire des objectes",
+      "tokens": [
+        7368,
+        11,
+        465,
+        17815,
+        11,
+        1930,
+        38694,
+        8645,
+        890,
+        41806,
+        5732,
+        5732,
+        962,
+        1712,
+        14953,
+        287,
+        6,
+        29093,
+        730,
+        2657,
+        279
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4346100035167876,
+      "compression_ratio": 1.5907335907335907,
+      "no_speech_prob": 3.121094050584361e-05,
+      "confidence": 0.749,
+      "words": [
+        {
+          "text": "Bon,",
+          "start": 95.8,
+          "end": 96.06,
+          "confidence": 0.71
+        },
+        {
+          "text": "en",
+          "start": 96.06,
+          "end": 96.54,
+          "confidence": 0.92
+        },
+        {
+          "text": "vrai,",
+          "start": 96.54,
+          "end": 96.88,
+          "confidence": 0.994
+        },
+        {
+          "text": "il",
+          "start": 96.88,
+          "end": 97.1,
+          "confidence": 0.985
+        },
+        {
+          "text": "faudrait",
+          "start": 97.1,
+          "end": 97.5,
+          "confidence": 0.932
+        },
+        {
+          "text": "remonter",
+          "start": 97.5,
+          "end": 98.02,
+          "confidence": 0.574
+        },
+        {
+          "text": "très",
+          "start": 98.02,
+          "end": 98.46,
+          "confidence": 0.984
+        },
+        {
+          "text": "très",
+          "start": 98.46,
+          "end": 98.76,
+          "confidence": 0.597
+        },
+        {
+          "text": "finement",
+          "start": 98.76,
+          "end": 99.36,
+          "confidence": 0.476
+        },
+        {
+          "text": "toute",
+          "start": 99.36,
+          "end": 99.68,
+          "confidence": 0.367
+        },
+        {
+          "text": "l'histoire",
+          "start": 99.68,
+          "end": 100.02,
+          "confidence": 0.909
+        },
+        {
+          "text": "des",
+          "start": 100.02,
+          "end": 100.2,
+          "confidence": 0.949
+        },
+        {
+          "text": "objectes",
+          "start": 100.2,
+          "end": 100.4,
+          "confidence": 0.805
+        }
+      ]
+    },
+    {
+      "id": 28,
+      "seek": 8298,
+      "start": 100.4,
+      "end": 105.14,
+      "text": " techniques et de leur infération dans le vie pour déterminer si ce rapport est totalement",
+      "tokens": [
+        7512,
+        1030,
+        368,
+        9580,
+        1536,
+        526,
+        2405,
+        2680,
+        476,
+        4941,
+        2016,
+        2795,
+        29725,
+        260,
+        1511,
+        1769,
+        18018,
+        871,
+        45203
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4346100035167876,
+      "compression_ratio": 1.5907335907335907,
+      "no_speech_prob": 3.121094050584361e-05,
+      "confidence": 0.665,
+      "words": [
+        {
+          "text": "techniques",
+          "start": 100.4,
+          "end": 101.02,
+          "confidence": 0.954
+        },
+        {
+          "text": "et",
+          "start": 101.02,
+          "end": 101.52,
+          "confidence": 0.967
+        },
+        {
+          "text": "de",
+          "start": 101.52,
+          "end": 101.64,
+          "confidence": 0.973
+        },
+        {
+          "text": "leur",
+          "start": 101.64,
+          "end": 101.78,
+          "confidence": 0.811
+        },
+        {
+          "text": "infération",
+          "start": 101.78,
+          "end": 102.22,
+          "confidence": 0.227
+        },
+        {
+          "text": "dans",
+          "start": 102.22,
+          "end": 102.46,
+          "confidence": 0.518
+        },
+        {
+          "text": "le",
+          "start": 102.46,
+          "end": 102.54,
+          "confidence": 0.511
+        },
+        {
+          "text": "vie",
+          "start": 102.54,
+          "end": 102.78,
+          "confidence": 0.612
+        },
+        {
+          "text": "pour",
+          "start": 102.78,
+          "end": 103.06,
+          "confidence": 0.933
+        },
+        {
+          "text": "déterminer",
+          "start": 103.06,
+          "end": 103.64,
+          "confidence": 0.954
+        },
+        {
+          "text": "si",
+          "start": 103.64,
+          "end": 103.74,
+          "confidence": 0.488
+        },
+        {
+          "text": "ce",
+          "start": 103.74,
+          "end": 103.86,
+          "confidence": 0.98
+        },
+        {
+          "text": "rapport",
+          "start": 103.86,
+          "end": 104.1,
+          "confidence": 0.997
+        },
+        {
+          "text": "est",
+          "start": 104.1,
+          "end": 104.88,
+          "confidence": 0.942
+        },
+        {
+          "text": "totalement",
+          "start": 104.88,
+          "end": 105.14,
+          "confidence": 0.854
+        }
+      ]
+    },
+    {
+      "id": 29,
+      "seek": 8298,
+      "start": 105.26,
+      "end": 105.78,
+      "text": " inédit.",
+      "tokens": [
+        294,
+        7811,
+        270,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4346100035167876,
+      "compression_ratio": 1.5907335907335907,
+      "no_speech_prob": 3.121094050584361e-05,
+      "confidence": 0.943,
+      "words": [
+        {
+          "text": "inédit.",
+          "start": 105.26,
+          "end": 105.78,
+          "confidence": 0.943
+        }
+      ]
+    },
+    {
+      "id": 30,
+      "seek": 8298,
+      "start": 106.14,
+      "end": 109.36,
+      "text": " Mais j'ai l'impression comme ça que Nicolas se trompe pas vraiment.",
+      "tokens": [
+        6313,
+        361,
+        6,
+        1301,
+        287,
+        6,
+        36107,
+        5173,
+        2788,
+        631,
+        38268,
+        369,
+        504,
+        298,
+        494,
+        1736,
+        8322,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4346100035167876,
+      "compression_ratio": 1.5907335907335907,
+      "no_speech_prob": 3.121094050584361e-05,
+      "confidence": 0.798,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 106.14,
+          "end": 106.34,
+          "confidence": 0.872
+        },
+        {
+          "text": "j'ai",
+          "start": 106.34,
+          "end": 106.9,
+          "confidence": 0.924
+        },
+        {
+          "text": "l'impression",
+          "start": 106.9,
+          "end": 107.28,
+          "confidence": 0.967
+        },
+        {
+          "text": "comme",
+          "start": 107.28,
+          "end": 107.5,
+          "confidence": 0.709
+        },
+        {
+          "text": "ça",
+          "start": 107.5,
+          "end": 107.68,
+          "confidence": 0.955
+        },
+        {
+          "text": "que",
+          "start": 107.68,
+          "end": 107.96,
+          "confidence": 0.91
+        },
+        {
+          "text": "Nicolas",
+          "start": 107.96,
+          "end": 108.36,
+          "confidence": 0.986
+        },
+        {
+          "text": "se",
+          "start": 108.36,
+          "end": 108.66,
+          "confidence": 0.569
+        },
+        {
+          "text": "trompe",
+          "start": 108.66,
+          "end": 109.0,
+          "confidence": 0.532
+        },
+        {
+          "text": "pas",
+          "start": 109.0,
+          "end": 109.1,
+          "confidence": 0.715
+        },
+        {
+          "text": "vraiment.",
+          "start": 109.1,
+          "end": 109.36,
+          "confidence": 0.923
+        }
+      ]
+    },
+    {
+      "id": 31,
+      "seek": 10970,
+      "start": 109.72,
+      "end": 114.26,
+      "text": " Pour autant, je sache. Il y a eu plein de discussions autour de la voiture ou même",
+      "tokens": [
+        8732,
+        34081,
+        11,
+        1506,
+        262,
+        6000,
+        13,
+        4416,
+        288,
+        257,
+        2228,
+        21088,
+        368,
+        11088,
+        30249,
+        368,
+        635,
+        38859,
+        2820,
+        5698
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.394765736144266,
+      "compression_ratio": 1.7249190938511327,
+      "no_speech_prob": 9.048193533089943e-06,
+      "confidence": 0.829,
+      "words": [
+        {
+          "text": "Pour",
+          "start": 109.72,
+          "end": 110.08,
+          "confidence": 0.92
+        },
+        {
+          "text": "autant,",
+          "start": 110.08,
+          "end": 110.36,
+          "confidence": 0.986
+        },
+        {
+          "text": "je",
+          "start": 110.36,
+          "end": 110.4,
+          "confidence": 0.894
+        },
+        {
+          "text": "sache.",
+          "start": 110.4,
+          "end": 110.86,
+          "confidence": 0.531
+        },
+        {
+          "text": "Il",
+          "start": 110.86,
+          "end": 111.16,
+          "confidence": 0.851
+        },
+        {
+          "text": "y",
+          "start": 111.16,
+          "end": 111.22,
+          "confidence": 0.872
+        },
+        {
+          "text": "a",
+          "start": 111.22,
+          "end": 111.28,
+          "confidence": 0.939
+        },
+        {
+          "text": "eu",
+          "start": 111.28,
+          "end": 111.38,
+          "confidence": 0.891
+        },
+        {
+          "text": "plein",
+          "start": 111.38,
+          "end": 111.76,
+          "confidence": 0.833
+        },
+        {
+          "text": "de",
+          "start": 111.76,
+          "end": 112.04,
+          "confidence": 0.94
+        },
+        {
+          "text": "discussions",
+          "start": 112.04,
+          "end": 112.46,
+          "confidence": 0.711
+        },
+        {
+          "text": "autour",
+          "start": 112.46,
+          "end": 112.96,
+          "confidence": 0.97
+        },
+        {
+          "text": "de",
+          "start": 112.96,
+          "end": 113.46,
+          "confidence": 0.952
+        },
+        {
+          "text": "la",
+          "start": 113.46,
+          "end": 113.5,
+          "confidence": 0.955
+        },
+        {
+          "text": "voiture",
+          "start": 113.5,
+          "end": 113.8,
+          "confidence": 0.983
+        },
+        {
+          "text": "ou",
+          "start": 113.8,
+          "end": 114.02,
+          "confidence": 0.523
+        },
+        {
+          "text": "même",
+          "start": 114.02,
+          "end": 114.26,
+          "confidence": 0.963
+        }
+      ]
+    },
+    {
+      "id": 32,
+      "seek": 10970,
+      "start": 114.42,
+      "end": 118.76,
+      "text": " du téléphone. Mais la dépense n'était pas du même mort, donc le rejet n'en",
+      "tokens": [
+        1581,
+        47159,
+        13,
+        6313,
+        635,
+        27998,
+        1288,
+        297,
+        6,
+        9743,
+        1736,
+        1581,
+        5698,
+        6599,
+        11,
+        5926,
+        476,
+        319,
+        7108,
+        297,
+        6,
+        268
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.394765736144266,
+      "compression_ratio": 1.7249190938511327,
+      "no_speech_prob": 9.048193533089943e-06,
+      "confidence": 0.732,
+      "words": [
+        {
+          "text": "du",
+          "start": 114.42,
+          "end": 114.6,
+          "confidence": 0.677
+        },
+        {
+          "text": "téléphone.",
+          "start": 114.6,
+          "end": 115.16,
+          "confidence": 0.983
+        },
+        {
+          "text": "Mais",
+          "start": 115.16,
+          "end": 115.72,
+          "confidence": 0.649
+        },
+        {
+          "text": "la",
+          "start": 115.72,
+          "end": 116.0,
+          "confidence": 0.809
+        },
+        {
+          "text": "dépense",
+          "start": 116.0,
+          "end": 116.38,
+          "confidence": 0.766
+        },
+        {
+          "text": "n'était",
+          "start": 116.38,
+          "end": 116.62,
+          "confidence": 0.952
+        },
+        {
+          "text": "pas",
+          "start": 116.62,
+          "end": 117.02,
+          "confidence": 0.994
+        },
+        {
+          "text": "du",
+          "start": 117.02,
+          "end": 117.16,
+          "confidence": 0.98
+        },
+        {
+          "text": "même",
+          "start": 117.16,
+          "end": 117.32,
+          "confidence": 0.944
+        },
+        {
+          "text": "mort,",
+          "start": 117.32,
+          "end": 117.66,
+          "confidence": 0.519
+        },
+        {
+          "text": "donc",
+          "start": 117.66,
+          "end": 117.78,
+          "confidence": 0.871
+        },
+        {
+          "text": "le",
+          "start": 117.78,
+          "end": 118.32,
+          "confidence": 0.932
+        },
+        {
+          "text": "rejet",
+          "start": 118.32,
+          "end": 118.62,
+          "confidence": 0.524
+        },
+        {
+          "text": "n'en",
+          "start": 118.62,
+          "end": 118.76,
+          "confidence": 0.472
+        }
+      ]
+    },
+    {
+      "id": 33,
+      "seek": 10970,
+      "start": 118.76,
+      "end": 119.66,
+      "text": " plus n'était pas du même mort.",
+      "tokens": [
+        1804,
+        297,
+        6,
+        9743,
+        1736,
+        1581,
+        5698,
+        6599,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.394765736144266,
+      "compression_ratio": 1.7249190938511327,
+      "no_speech_prob": 9.048193533089943e-06,
+      "confidence": 0.853,
+      "words": [
+        {
+          "text": "plus",
+          "start": 118.76,
+          "end": 118.9,
+          "confidence": 0.313
+        },
+        {
+          "text": "n'était",
+          "start": 118.9,
+          "end": 119.1,
+          "confidence": 0.973
+        },
+        {
+          "text": "pas",
+          "start": 119.1,
+          "end": 119.26,
+          "confidence": 0.998
+        },
+        {
+          "text": "du",
+          "start": 119.26,
+          "end": 119.36,
+          "confidence": 0.988
+        },
+        {
+          "text": "même",
+          "start": 119.36,
+          "end": 119.5,
+          "confidence": 0.999
+        },
+        {
+          "text": "mort.",
+          "start": 119.5,
+          "end": 119.66,
+          "confidence": 0.984
+        }
+      ]
+    },
+    {
+      "id": 34,
+      "seek": 10970,
+      "start": 120.06,
+      "end": 122.94,
+      "text": " On peut adorer sa bagnure, en avoir besoin pour plein de choses.",
+      "tokens": [
+        1282,
+        5977,
+        614,
+        17618,
+        601,
+        3411,
+        77,
+        540,
+        11,
+        465,
+        10853,
+        19207,
+        2016,
+        21088,
+        368,
+        14488,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.394765736144266,
+      "compression_ratio": 1.7249190938511327,
+      "no_speech_prob": 9.048193533089943e-06,
+      "confidence": 0.753,
+      "words": [
+        {
+          "text": "On",
+          "start": 120.06,
+          "end": 120.22,
+          "confidence": 0.969
+        },
+        {
+          "text": "peut",
+          "start": 120.22,
+          "end": 120.32,
+          "confidence": 0.988
+        },
+        {
+          "text": "adorer",
+          "start": 120.32,
+          "end": 120.64,
+          "confidence": 0.854
+        },
+        {
+          "text": "sa",
+          "start": 120.64,
+          "end": 120.86,
+          "confidence": 0.918
+        },
+        {
+          "text": "bagnure,",
+          "start": 120.86,
+          "end": 121.38,
+          "confidence": 0.368
+        },
+        {
+          "text": "en",
+          "start": 121.38,
+          "end": 121.52,
+          "confidence": 0.56
+        },
+        {
+          "text": "avoir",
+          "start": 121.52,
+          "end": 121.66,
+          "confidence": 0.969
+        },
+        {
+          "text": "besoin",
+          "start": 121.66,
+          "end": 122.08,
+          "confidence": 0.997
+        },
+        {
+          "text": "pour",
+          "start": 122.08,
+          "end": 122.34,
+          "confidence": 0.92
+        },
+        {
+          "text": "plein",
+          "start": 122.34,
+          "end": 122.64,
+          "confidence": 0.9
+        },
+        {
+          "text": "de",
+          "start": 122.64,
+          "end": 122.78,
+          "confidence": 0.993
+        },
+        {
+          "text": "choses.",
+          "start": 122.78,
+          "end": 122.94,
+          "confidence": 0.994
+        }
+      ]
+    },
+    {
+      "id": 35,
+      "seek": 10970,
+      "start": 123.36,
+      "end": 126.38,
+      "text": " Et là, le soir, quand on va se coucher, on la laisse.",
+      "tokens": [
+        3790,
+        3684,
+        11,
+        476,
+        27105,
+        11,
+        6932,
+        322,
+        2773,
+        369,
+        1384,
+        6759,
+        11,
+        322,
+        635,
+        30969,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.394765736144266,
+      "compression_ratio": 1.7249190938511327,
+      "no_speech_prob": 9.048193533089943e-06,
+      "confidence": 0.826,
+      "words": [
+        {
+          "text": "Et",
+          "start": 123.36,
+          "end": 123.48,
+          "confidence": 0.557
+        },
+        {
+          "text": "là,",
+          "start": 123.48,
+          "end": 123.66,
+          "confidence": 0.527
+        },
+        {
+          "text": "le",
+          "start": 123.66,
+          "end": 124.02,
+          "confidence": 0.986
+        },
+        {
+          "text": "soir,",
+          "start": 124.02,
+          "end": 124.5,
+          "confidence": 0.966
+        },
+        {
+          "text": "quand",
+          "start": 124.5,
+          "end": 124.9,
+          "confidence": 0.774
+        },
+        {
+          "text": "on",
+          "start": 124.9,
+          "end": 125.02,
+          "confidence": 0.986
+        },
+        {
+          "text": "va",
+          "start": 125.02,
+          "end": 125.1,
+          "confidence": 0.968
+        },
+        {
+          "text": "se",
+          "start": 125.1,
+          "end": 125.2,
+          "confidence": 0.862
+        },
+        {
+          "text": "coucher,",
+          "start": 125.2,
+          "end": 125.64,
+          "confidence": 0.791
+        },
+        {
+          "text": "on",
+          "start": 125.64,
+          "end": 126.04,
+          "confidence": 0.974
+        },
+        {
+          "text": "la",
+          "start": 126.04,
+          "end": 126.12,
+          "confidence": 0.783
+        },
+        {
+          "text": "laisse.",
+          "start": 126.12,
+          "end": 126.38,
+          "confidence": 0.981
+        }
+      ]
+    },
+    {
+      "id": 36,
+      "seek": 10970,
+      "start": 127.06,
+      "end": 130.0,
+      "text": " On l'a pas dans la main, quand on est collis, quand on n'en mène pas au chiot.",
+      "tokens": [
+        1282,
+        287,
+        6,
+        64,
+        1736,
+        2680,
+        635,
+        2135,
+        11,
+        6932,
+        322,
+        871,
+        1263,
+        271,
+        11,
+        6932,
+        322,
+        297,
+        6,
+        268,
+        275,
+        18832,
+        1736,
+        1609,
+        417,
+        6471,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.394765736144266,
+      "compression_ratio": 1.7249190938511327,
+      "no_speech_prob": 9.048193533089943e-06,
+      "confidence": 0.66,
+      "words": [
+        {
+          "text": "On",
+          "start": 127.06,
+          "end": 127.3,
+          "confidence": 0.742
+        },
+        {
+          "text": "l'a",
+          "start": 127.3,
+          "end": 127.46,
+          "confidence": 0.714
+        },
+        {
+          "text": "pas",
+          "start": 127.46,
+          "end": 127.64,
+          "confidence": 0.99
+        },
+        {
+          "text": "dans",
+          "start": 127.64,
+          "end": 127.82,
+          "confidence": 0.967
+        },
+        {
+          "text": "la",
+          "start": 127.82,
+          "end": 127.94,
+          "confidence": 0.956
+        },
+        {
+          "text": "main,",
+          "start": 127.94,
+          "end": 128.3,
+          "confidence": 0.978
+        },
+        {
+          "text": "quand",
+          "start": 128.3,
+          "end": 128.44,
+          "confidence": 0.967
+        },
+        {
+          "text": "on",
+          "start": 128.44,
+          "end": 128.6,
+          "confidence": 0.993
+        },
+        {
+          "text": "est",
+          "start": 128.6,
+          "end": 128.66,
+          "confidence": 0.602
+        },
+        {
+          "text": "collis,",
+          "start": 128.66,
+          "end": 129.2,
+          "confidence": 0.346
+        },
+        {
+          "text": "quand",
+          "start": 129.2,
+          "end": 129.24,
+          "confidence": 0.524
+        },
+        {
+          "text": "on",
+          "start": 129.24,
+          "end": 129.32,
+          "confidence": 0.991
+        },
+        {
+          "text": "n'en",
+          "start": 129.32,
+          "end": 129.38,
+          "confidence": 0.537
+        },
+        {
+          "text": "mène",
+          "start": 129.38,
+          "end": 129.56,
+          "confidence": 0.434
+        },
+        {
+          "text": "pas",
+          "start": 129.56,
+          "end": 129.72,
+          "confidence": 0.998
+        },
+        {
+          "text": "au",
+          "start": 129.72,
+          "end": 129.82,
+          "confidence": 0.811
+        },
+        {
+          "text": "chiot.",
+          "start": 129.82,
+          "end": 130.0,
+          "confidence": 0.473
+        }
+      ]
+    },
+    {
+      "id": 37,
+      "seek": 10970,
+      "start": 130.88,
+      "end": 135.1,
+      "text": " On pouvait être émervé par son mome qui occupeait la ligne de téléphone pendant une",
+      "tokens": [
+        1282,
+        45913,
+        7418,
+        1136,
+        936,
+        15797,
+        971,
+        1872,
+        275,
+        423,
+        1956,
+        2678,
+        84,
+        494,
+        1001,
+        635,
+        34207,
+        368,
+        47159,
+        17338,
+        2251
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.394765736144266,
+      "compression_ratio": 1.7249190938511327,
+      "no_speech_prob": 9.048193533089943e-06,
+      "confidence": 0.672,
+      "words": [
+        {
+          "text": "On",
+          "start": 130.88,
+          "end": 131.0,
+          "confidence": 0.991
+        },
+        {
+          "text": "pouvait",
+          "start": 131.0,
+          "end": 131.24,
+          "confidence": 0.532
+        },
+        {
+          "text": "être",
+          "start": 131.24,
+          "end": 131.7,
+          "confidence": 0.545
+        },
+        {
+          "text": "émervé",
+          "start": 131.7,
+          "end": 132.2,
+          "confidence": 0.725
+        },
+        {
+          "text": "par",
+          "start": 132.2,
+          "end": 132.42,
+          "confidence": 0.82
+        },
+        {
+          "text": "son",
+          "start": 132.42,
+          "end": 132.68,
+          "confidence": 0.448
+        },
+        {
+          "text": "mome",
+          "start": 132.68,
+          "end": 133.04,
+          "confidence": 0.261
+        },
+        {
+          "text": "qui",
+          "start": 133.04,
+          "end": 133.26,
+          "confidence": 0.901
+        },
+        {
+          "text": "occupeait",
+          "start": 133.26,
+          "end": 133.72,
+          "confidence": 0.641
+        },
+        {
+          "text": "la",
+          "start": 133.72,
+          "end": 133.8,
+          "confidence": 0.8
+        },
+        {
+          "text": "ligne",
+          "start": 133.8,
+          "end": 134.0,
+          "confidence": 0.976
+        },
+        {
+          "text": "de",
+          "start": 134.0,
+          "end": 134.14,
+          "confidence": 0.964
+        },
+        {
+          "text": "téléphone",
+          "start": 134.14,
+          "end": 134.44,
+          "confidence": 0.977
+        },
+        {
+          "text": "pendant",
+          "start": 134.44,
+          "end": 134.8,
+          "confidence": 0.92
+        },
+        {
+          "text": "une",
+          "start": 134.8,
+          "end": 135.1,
+          "confidence": 0.838
+        }
+      ]
+    },
+    {
+      "id": 38,
+      "seek": 10970,
+      "start": 135.1,
+      "end": 136.84,
+      "text": " heure chaque soir pour discuter avec un copain.",
+      "tokens": [
+        30027,
+        18920,
+        27105,
+        2016,
+        2983,
+        20314,
+        4163,
+        517,
+        2971,
+        491,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.394765736144266,
+      "compression_ratio": 1.7249190938511327,
+      "no_speech_prob": 9.048193533089943e-06,
+      "confidence": 0.922,
+      "words": [
+        {
+          "text": "heure",
+          "start": 135.1,
+          "end": 135.36,
+          "confidence": 0.701
+        },
+        {
+          "text": "chaque",
+          "start": 135.36,
+          "end": 135.52,
+          "confidence": 0.957
+        },
+        {
+          "text": "soir",
+          "start": 135.52,
+          "end": 135.76,
+          "confidence": 0.997
+        },
+        {
+          "text": "pour",
+          "start": 135.76,
+          "end": 135.94,
+          "confidence": 0.983
+        },
+        {
+          "text": "discuter",
+          "start": 135.94,
+          "end": 136.26,
+          "confidence": 0.882
+        },
+        {
+          "text": "avec",
+          "start": 136.26,
+          "end": 136.44,
+          "confidence": 0.993
+        },
+        {
+          "text": "un",
+          "start": 136.44,
+          "end": 136.6,
+          "confidence": 0.976
+        },
+        {
+          "text": "copain.",
+          "start": 136.6,
+          "end": 136.84,
+          "confidence": 0.948
+        }
+      ]
+    },
+    {
+      "id": 39,
+      "seek": 13702,
+      "start": 137.26,
+      "end": 141.8,
+      "text": " Mais ça ne ressemble pas à ce qu'on peut ressentir à voir même mome aujourd'hui",
+      "tokens": [
+        6313,
+        2788,
+        408,
+        725,
+        37227,
+        1736,
+        1531,
+        1769,
+        421,
+        6,
+        266,
+        5977,
+        24689,
+        317,
+        347,
+        1531,
+        10695,
+        5698,
+        275,
+        423,
+        14023,
+        6,
+        10556
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5734858703613281,
+      "compression_ratio": 1.5562700964630225,
+      "no_speech_prob": 3.1260256037057843e-06,
+      "confidence": 0.716,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 137.26,
+          "end": 137.52,
+          "confidence": 0.967
+        },
+        {
+          "text": "ça",
+          "start": 137.52,
+          "end": 137.6,
+          "confidence": 0.859
+        },
+        {
+          "text": "ne",
+          "start": 137.6,
+          "end": 137.68,
+          "confidence": 0.681
+        },
+        {
+          "text": "ressemble",
+          "start": 137.68,
+          "end": 138.14,
+          "confidence": 0.743
+        },
+        {
+          "text": "pas",
+          "start": 138.14,
+          "end": 138.66,
+          "confidence": 0.524
+        },
+        {
+          "text": "à",
+          "start": 138.66,
+          "end": 138.94,
+          "confidence": 0.978
+        },
+        {
+          "text": "ce",
+          "start": 138.94,
+          "end": 139.02,
+          "confidence": 0.605
+        },
+        {
+          "text": "qu'on",
+          "start": 139.02,
+          "end": 139.16,
+          "confidence": 0.961
+        },
+        {
+          "text": "peut",
+          "start": 139.16,
+          "end": 139.3,
+          "confidence": 0.586
+        },
+        {
+          "text": "ressentir",
+          "start": 139.3,
+          "end": 140.04,
+          "confidence": 0.898
+        },
+        {
+          "text": "à",
+          "start": 140.04,
+          "end": 140.24,
+          "confidence": 0.352
+        },
+        {
+          "text": "voir",
+          "start": 140.24,
+          "end": 140.48,
+          "confidence": 0.918
+        },
+        {
+          "text": "même",
+          "start": 140.48,
+          "end": 140.86,
+          "confidence": 0.324
+        },
+        {
+          "text": "mome",
+          "start": 140.86,
+          "end": 141.18,
+          "confidence": 0.374
+        },
+        {
+          "text": "aujourd'hui",
+          "start": 141.18,
+          "end": 141.8,
+          "confidence": 0.949
+        }
+      ]
+    },
+    {
+      "id": 40,
+      "seek": 13702,
+      "start": 141.92,
+      "end": 145.76,
+      "text": " continuuellement avec son smartphone dans la main, comme c'était une sorte de estimateur",
+      "tokens": [
+        2993,
+        31816,
+        4163,
+        1872,
+        13307,
+        2680,
+        635,
+        2135,
+        11,
+        5173,
+        269,
+        6,
+        9743,
+        2251,
+        25559,
+        368,
+        8017,
+        15540
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5734858703613281,
+      "compression_ratio": 1.5562700964630225,
+      "no_speech_prob": 3.1260256037057843e-06,
+      "confidence": 0.584,
+      "words": [
+        {
+          "text": "continuuellement",
+          "start": 141.92,
+          "end": 142.8,
+          "confidence": 0.327
+        },
+        {
+          "text": "avec",
+          "start": 142.8,
+          "end": 143.18,
+          "confidence": 0.903
+        },
+        {
+          "text": "son",
+          "start": 143.18,
+          "end": 143.36,
+          "confidence": 0.866
+        },
+        {
+          "text": "smartphone",
+          "start": 143.36,
+          "end": 143.64,
+          "confidence": 0.467
+        },
+        {
+          "text": "dans",
+          "start": 143.64,
+          "end": 143.92,
+          "confidence": 0.554
+        },
+        {
+          "text": "la",
+          "start": 143.92,
+          "end": 144.0,
+          "confidence": 0.972
+        },
+        {
+          "text": "main,",
+          "start": 144.0,
+          "end": 144.26,
+          "confidence": 0.997
+        },
+        {
+          "text": "comme",
+          "start": 144.26,
+          "end": 144.52,
+          "confidence": 0.95
+        },
+        {
+          "text": "c'était",
+          "start": 144.52,
+          "end": 144.78,
+          "confidence": 0.574
+        },
+        {
+          "text": "une",
+          "start": 144.78,
+          "end": 144.94,
+          "confidence": 0.971
+        },
+        {
+          "text": "sorte",
+          "start": 144.94,
+          "end": 145.1,
+          "confidence": 0.642
+        },
+        {
+          "text": "de",
+          "start": 145.1,
+          "end": 145.18,
+          "confidence": 0.268
+        },
+        {
+          "text": "estimateur",
+          "start": 145.18,
+          "end": 145.76,
+          "confidence": 0.415
+        }
+      ]
+    },
+    {
+      "id": 41,
+      "seek": 13702,
+      "start": 145.94,
+      "end": 148.88,
+      "text": " extère de l'intempis de lâcher à l'éantrénée, ça m'a eu immédiate.",
+      "tokens": [
+        1279,
+        4212,
+        368,
+        287,
+        6,
+        686,
+        15970,
+        271,
+        368,
+        48835,
+        6759,
+        1531,
+        287,
+        6,
+        526,
+        394,
+        81,
+        3516,
+        3856,
+        11,
+        2788,
+        275,
+        6,
+        64,
+        2228,
+        3397,
+        526,
+        4504,
+        473,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5734858703613281,
+      "compression_ratio": 1.5562700964630225,
+      "no_speech_prob": 3.1260256037057843e-06,
+      "confidence": 0.401,
+      "words": [
+        {
+          "text": "extère",
+          "start": 145.94,
+          "end": 146.38,
+          "confidence": 0.357
+        },
+        {
+          "text": "de",
+          "start": 146.38,
+          "end": 146.46,
+          "confidence": 0.253
+        },
+        {
+          "text": "l'intempis",
+          "start": 146.46,
+          "end": 146.7,
+          "confidence": 0.153
+        },
+        {
+          "text": "de",
+          "start": 146.7,
+          "end": 146.9,
+          "confidence": 0.858
+        },
+        {
+          "text": "lâcher",
+          "start": 146.9,
+          "end": 147.32,
+          "confidence": 0.824
+        },
+        {
+          "text": "à",
+          "start": 147.32,
+          "end": 147.44,
+          "confidence": 0.494
+        },
+        {
+          "text": "l'éantrénée,",
+          "start": 147.44,
+          "end": 147.94,
+          "confidence": 0.476
+        },
+        {
+          "text": "ça",
+          "start": 147.94,
+          "end": 148.0,
+          "confidence": 0.772
+        },
+        {
+          "text": "m'a",
+          "start": 148.0,
+          "end": 148.26,
+          "confidence": 0.532
+        },
+        {
+          "text": "eu",
+          "start": 148.26,
+          "end": 148.42,
+          "confidence": 0.181
+        },
+        {
+          "text": "immédiate.",
+          "start": 148.42,
+          "end": 148.88,
+          "confidence": 0.537
+        }
+      ]
+    },
+    {
+      "id": 42,
+      "seek": 13702,
+      "start": 149.08,
+      "end": 152.02,
+      "text": " Bon, je dis ça pour le mome, mais évidemment, va là pour nos aussi.",
+      "tokens": [
+        7368,
+        11,
+        1506,
+        717,
+        2788,
+        2016,
+        476,
+        275,
+        423,
+        11,
+        2420,
+        24724,
+        11,
+        2773,
+        3684,
+        2016,
+        3269,
+        6212,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5734858703613281,
+      "compression_ratio": 1.5562700964630225,
+      "no_speech_prob": 3.1260256037057843e-06,
+      "confidence": 0.529,
+      "words": [
+        {
+          "text": "Bon,",
+          "start": 149.08,
+          "end": 149.3,
+          "confidence": 0.285
+        },
+        {
+          "text": "je",
+          "start": 149.3,
+          "end": 149.34,
+          "confidence": 0.425
+        },
+        {
+          "text": "dis",
+          "start": 149.34,
+          "end": 149.42,
+          "confidence": 0.316
+        },
+        {
+          "text": "ça",
+          "start": 149.42,
+          "end": 149.62,
+          "confidence": 0.953
+        },
+        {
+          "text": "pour",
+          "start": 149.62,
+          "end": 149.72,
+          "confidence": 0.971
+        },
+        {
+          "text": "le",
+          "start": 149.72,
+          "end": 149.82,
+          "confidence": 0.993
+        },
+        {
+          "text": "mome,",
+          "start": 149.82,
+          "end": 150.24,
+          "confidence": 0.575
+        },
+        {
+          "text": "mais",
+          "start": 150.24,
+          "end": 150.44,
+          "confidence": 0.713
+        },
+        {
+          "text": "évidemment,",
+          "start": 150.44,
+          "end": 151.1,
+          "confidence": 0.775
+        },
+        {
+          "text": "va",
+          "start": 151.1,
+          "end": 151.28,
+          "confidence": 0.381
+        },
+        {
+          "text": "là",
+          "start": 151.28,
+          "end": 151.42,
+          "confidence": 0.633
+        },
+        {
+          "text": "pour",
+          "start": 151.42,
+          "end": 151.62,
+          "confidence": 0.398
+        },
+        {
+          "text": "nos",
+          "start": 151.62,
+          "end": 151.7,
+          "confidence": 0.807
+        },
+        {
+          "text": "aussi.",
+          "start": 151.7,
+          "end": 152.02,
+          "confidence": 0.145
+        }
+      ]
+    },
+    {
+      "id": 43,
+      "seek": 13702,
+      "start": 152.66,
+      "end": 154.4,
+      "text": " Donc, rapport immédiate d'accord.",
+      "tokens": [
+        7477,
+        11,
+        18018,
+        3397,
+        526,
+        4504,
+        473,
+        274,
+        6,
+        19947,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5734858703613281,
+      "compression_ratio": 1.5562700964630225,
+      "no_speech_prob": 3.1260256037057843e-06,
+      "confidence": 0.851,
+      "words": [
+        {
+          "text": "Donc,",
+          "start": 152.66,
+          "end": 153.0,
+          "confidence": 0.985
+        },
+        {
+          "text": "rapport",
+          "start": 153.0,
+          "end": 153.42,
+          "confidence": 0.977
+        },
+        {
+          "text": "immédiate",
+          "start": 153.42,
+          "end": 154.26,
+          "confidence": 0.825
+        },
+        {
+          "text": "d'accord.",
+          "start": 154.26,
+          "end": 154.4,
+          "confidence": 0.806
+        }
+      ]
+    },
+    {
+      "id": 44,
+      "seek": 13702,
+      "start": 154.4,
+      "end": 157.95,
+      "text": " Mais pourquoi, à ton impression qu'on en sortira jamais?",
+      "tokens": [
+        6313,
+        19934,
+        11,
+        1531,
+        2952,
+        9995,
+        421,
+        6,
+        266,
+        465,
+        26906,
+        64,
+        14540,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5734858703613281,
+      "compression_ratio": 1.5562700964630225,
+      "no_speech_prob": 3.1260256037057843e-06,
+      "confidence": 0.791,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 154.4,
+          "end": 155.9,
+          "confidence": 0.984
+        },
+        {
+          "text": "pourquoi,",
+          "start": 155.9,
+          "end": 156.36,
+          "confidence": 0.959
+        },
+        {
+          "text": "à",
+          "start": 156.36,
+          "end": 156.48,
+          "confidence": 0.821
+        },
+        {
+          "text": "ton",
+          "start": 156.48,
+          "end": 156.66,
+          "confidence": 0.952
+        },
+        {
+          "text": "impression",
+          "start": 156.66,
+          "end": 156.96,
+          "confidence": 0.932
+        },
+        {
+          "text": "qu'on",
+          "start": 156.96,
+          "end": 157.28,
+          "confidence": 0.906
+        },
+        {
+          "text": "en",
+          "start": 157.28,
+          "end": 157.34,
+          "confidence": 0.789
+        },
+        {
+          "text": "sortira",
+          "start": 157.34,
+          "end": 157.84,
+          "confidence": 0.543
+        },
+        {
+          "text": "jamais?",
+          "start": 157.84,
+          "end": 157.95,
+          "confidence": 0.503
+        }
+      ]
+    },
+    {
+      "id": 45,
+      "seek": 13702,
+      "start": 157.95,
+      "end": 162.37,
+      "text": " Et puis, il faut en remettre la faute sur les gens qui ont créé cette",
+      "tokens": [
+        3790,
+        9093,
+        11,
+        1930,
+        8487,
+        465,
+        890,
+        40681,
+        635,
+        2050,
+        1169,
+        1022,
+        1512,
+        10668,
+        1956,
+        6592,
+        15609,
+        526,
+        5550
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5734858703613281,
+      "compression_ratio": 1.5562700964630225,
+      "no_speech_prob": 3.1260256037057843e-06,
+      "confidence": 0.82,
+      "words": [
+        {
+          "text": "Et",
+          "start": 157.95,
+          "end": 159.26,
+          "confidence": 0.838
+        },
+        {
+          "text": "puis,",
+          "start": 159.26,
+          "end": 159.58,
+          "confidence": 0.481
+        },
+        {
+          "text": "il",
+          "start": 159.58,
+          "end": 159.62,
+          "confidence": 0.665
+        },
+        {
+          "text": "faut",
+          "start": 159.62,
+          "end": 159.66,
+          "confidence": 0.942
+        },
+        {
+          "text": "en",
+          "start": 159.66,
+          "end": 159.72,
+          "confidence": 0.925
+        },
+        {
+          "text": "remettre",
+          "start": 159.72,
+          "end": 160.1,
+          "confidence": 0.985
+        },
+        {
+          "text": "la",
+          "start": 160.1,
+          "end": 160.28,
+          "confidence": 0.702
+        },
+        {
+          "text": "faute",
+          "start": 160.28,
+          "end": 160.62,
+          "confidence": 0.55
+        },
+        {
+          "text": "sur",
+          "start": 160.62,
+          "end": 160.9,
+          "confidence": 0.954
+        },
+        {
+          "text": "les",
+          "start": 160.9,
+          "end": 161.22,
+          "confidence": 0.81
+        },
+        {
+          "text": "gens",
+          "start": 161.22,
+          "end": 161.42,
+          "confidence": 0.985
+        },
+        {
+          "text": "qui",
+          "start": 161.42,
+          "end": 161.58,
+          "confidence": 0.981
+        },
+        {
+          "text": "ont",
+          "start": 161.58,
+          "end": 161.62,
+          "confidence": 0.955
+        },
+        {
+          "text": "créé",
+          "start": 161.62,
+          "end": 162.3,
+          "confidence": 0.957
+        },
+        {
+          "text": "cette",
+          "start": 162.3,
+          "end": 162.37,
+          "confidence": 0.9
+        }
+      ]
+    },
+    {
+      "id": 46,
+      "seek": 16228,
+      "start": 162.37,
+      "end": 165.3,
+      "text": " route merveilleux et diabolique, qui a dit à bollique par coeur, merveilleux.",
+      "tokens": [
+        7955,
+        3551,
+        303,
+        3409,
+        2449,
+        1030,
+        33227,
+        401,
+        1925,
+        11,
+        1956,
+        257,
+        6176,
+        1531,
+        748,
+        285,
+        1925,
+        971,
+        45781,
+        11,
+        3551,
+        303,
+        3409,
+        2449,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7643054464588994,
+      "compression_ratio": 1.544041450777202,
+      "no_speech_prob": 3.89045562769752e-05,
+      "confidence": 0.397,
+      "words": [
+        {
+          "text": "route",
+          "start": 162.37,
+          "end": 162.6,
+          "confidence": 0.076
+        },
+        {
+          "text": "merveilleux",
+          "start": 162.6,
+          "end": 163.3,
+          "confidence": 0.635
+        },
+        {
+          "text": "et",
+          "start": 163.3,
+          "end": 163.42,
+          "confidence": 0.837
+        },
+        {
+          "text": "diabolique,",
+          "start": 163.42,
+          "end": 163.82,
+          "confidence": 0.328
+        },
+        {
+          "text": "qui",
+          "start": 163.82,
+          "end": 163.9,
+          "confidence": 0.365
+        },
+        {
+          "text": "a",
+          "start": 163.9,
+          "end": 163.98,
+          "confidence": 0.054
+        },
+        {
+          "text": "dit",
+          "start": 163.98,
+          "end": 164.06,
+          "confidence": 0.085
+        },
+        {
+          "text": "à",
+          "start": 164.06,
+          "end": 164.1,
+          "confidence": 0.433
+        },
+        {
+          "text": "bollique",
+          "start": 164.1,
+          "end": 164.3,
+          "confidence": 0.297
+        },
+        {
+          "text": "par",
+          "start": 164.3,
+          "end": 164.52,
+          "confidence": 0.634
+        },
+        {
+          "text": "coeur,",
+          "start": 164.52,
+          "end": 164.78,
+          "confidence": 0.361
+        },
+        {
+          "text": "merveilleux.",
+          "start": 164.78,
+          "end": 165.3,
+          "confidence": 0.982
+        }
+      ]
+    },
+    {
+      "id": 47,
+      "seek": 16228,
+      "start": 167.36,
+      "end": 168.7,
+      "text": " Les économistes parlent de dépendance du santé.",
+      "tokens": [
+        6965,
+        31171,
+        22368,
+        13734,
+        317,
+        368,
+        45768,
+        719,
+        1581,
+        30068,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7643054464588994,
+      "compression_ratio": 1.544041450777202,
+      "no_speech_prob": 3.89045562769752e-05,
+      "confidence": 0.748,
+      "words": [
+        {
+          "text": "Les",
+          "start": 167.36,
+          "end": 167.4,
+          "confidence": 0.513
+        },
+        {
+          "text": "économistes",
+          "start": 167.4,
+          "end": 167.5,
+          "confidence": 0.937
+        },
+        {
+          "text": "parlent",
+          "start": 167.5,
+          "end": 167.78,
+          "confidence": 0.806
+        },
+        {
+          "text": "de",
+          "start": 167.78,
+          "end": 167.82,
+          "confidence": 0.855
+        },
+        {
+          "text": "dépendance",
+          "start": 167.82,
+          "end": 168.32,
+          "confidence": 0.758
+        },
+        {
+          "text": "du",
+          "start": 168.32,
+          "end": 168.5,
+          "confidence": 0.979
+        },
+        {
+          "text": "santé.",
+          "start": 168.5,
+          "end": 168.7,
+          "confidence": 0.389
+        }
+      ]
+    },
+    {
+      "id": 48,
+      "seek": 16228,
+      "start": 168.84,
+      "end": 172.66,
+      "text": " Ces vidéos, en fait, on est un santé qui a été établie, c'est un soit mon termine,",
+      "tokens": [
+        28414,
+        25417,
+        11,
+        465,
+        3887,
+        11,
+        322,
+        871,
+        517,
+        30068,
+        1956,
+        257,
+        8862,
+        4823,
+        455,
+        6302,
+        11,
+        269,
+        6,
+        377,
+        517,
+        12703,
+        1108,
+        1433,
+        533,
+        11
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7643054464588994,
+      "compression_ratio": 1.544041450777202,
+      "no_speech_prob": 3.89045562769752e-05,
+      "confidence": 0.487,
+      "words": [
+        {
+          "text": "Ces",
+          "start": 168.84,
+          "end": 169.14,
+          "confidence": 0.531
+        },
+        {
+          "text": "vidéos,",
+          "start": 169.14,
+          "end": 169.5,
+          "confidence": 0.725
+        },
+        {
+          "text": "en",
+          "start": 169.5,
+          "end": 169.62,
+          "confidence": 0.757
+        },
+        {
+          "text": "fait,",
+          "start": 169.62,
+          "end": 169.68,
+          "confidence": 0.974
+        },
+        {
+          "text": "on",
+          "start": 169.68,
+          "end": 169.74,
+          "confidence": 0.306
+        },
+        {
+          "text": "est",
+          "start": 169.74,
+          "end": 169.86,
+          "confidence": 0.82
+        },
+        {
+          "text": "un",
+          "start": 169.86,
+          "end": 170.16,
+          "confidence": 0.245
+        },
+        {
+          "text": "santé",
+          "start": 170.16,
+          "end": 170.72,
+          "confidence": 0.943
+        },
+        {
+          "text": "qui",
+          "start": 170.72,
+          "end": 170.88,
+          "confidence": 0.839
+        },
+        {
+          "text": "a",
+          "start": 170.88,
+          "end": 170.96,
+          "confidence": 0.533
+        },
+        {
+          "text": "été",
+          "start": 170.96,
+          "end": 171.08,
+          "confidence": 0.992
+        },
+        {
+          "text": "établie,",
+          "start": 171.08,
+          "end": 171.6,
+          "confidence": 0.316
+        },
+        {
+          "text": "c'est",
+          "start": 171.6,
+          "end": 171.74,
+          "confidence": 0.55
+        },
+        {
+          "text": "un",
+          "start": 171.74,
+          "end": 171.88,
+          "confidence": 0.651
+        },
+        {
+          "text": "soit",
+          "start": 171.88,
+          "end": 172.12,
+          "confidence": 0.284
+        },
+        {
+          "text": "mon",
+          "start": 172.12,
+          "end": 172.28,
+          "confidence": 0.225
+        },
+        {
+          "text": "termine,",
+          "start": 172.28,
+          "end": 172.66,
+          "confidence": 0.288
+        }
+      ]
+    },
+    {
+      "id": 49,
+      "seek": 17312,
+      "start": 173.14,
+      "end": 177.42,
+      "text": " soit définissant des beurs, on définisse un signalétique.",
+      "tokens": [
+        50364,
+        12703,
+        40763,
+        29492,
+        730,
+        312,
+        2156,
+        11,
+        322,
+        40763,
+        7746,
+        517,
+        6358,
+        42379,
+        13,
+        51436
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9428024291992188,
+      "compression_ratio": 1.0169491525423728,
+      "no_speech_prob": 6.687085260637105e-05,
+      "confidence": 0.403,
+      "words": [
+        {
+          "text": "soit",
+          "start": 173.14,
+          "end": 174.04,
+          "confidence": 0.127
+        },
+        {
+          "text": "définissant",
+          "start": 174.04,
+          "end": 175.5,
+          "confidence": 0.58
+        },
+        {
+          "text": "des",
+          "start": 175.5,
+          "end": 175.68,
+          "confidence": 0.813
+        },
+        {
+          "text": "beurs,",
+          "start": 175.68,
+          "end": 175.96,
+          "confidence": 0.378
+        },
+        {
+          "text": "on",
+          "start": 175.96,
+          "end": 176.04,
+          "confidence": 0.165
+        },
+        {
+          "text": "définisse",
+          "start": 176.04,
+          "end": 176.42,
+          "confidence": 0.536
+        },
+        {
+          "text": "un",
+          "start": 176.42,
+          "end": 176.6,
+          "confidence": 0.266
+        },
+        {
+          "text": "signalétique.",
+          "start": 176.6,
+          "end": 177.42,
+          "confidence": 0.544
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_auto/accurate_japanese.mp3.words.json b/tests/expected/tiny_auto/accurate_japanese.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..3c1037657d4da75adabfdbc3838722088aa93fc5
--- /dev/null
+++ b/tests/expected/tiny_auto/accurate_japanese.mp3.words.json
@@ -0,0 +1,1766 @@
+{
+  "text": "いきます ニュースタブでのサイトメイション機が 実際と違う検に関するご質問いただいております同じ度メインでデレクトリーごとに 別再度として管理上をしているサイトバリマスのサプテレクトリーごとにわけたサイトは それぞれ パブリシャーセンターに登録していくぐるニュース上ではサイトとして認識され パブリコンアイコンはサイトボトフのものが 正しく表示されますしかし ルグル検査結果のニュースタブでは パブリコンサイトメイショー機ともに 正しくない医療時にいいなりますこちらいたいです ものではありません パブリコンはサブテレクトリーごとに設定した",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.04,
+      "end": 6.62,
+      "text": "いきます ニュースタブでのサイトメイション機が 実際と違う検に関するご質問いただいております",
+      "tokens": [
+        50364,
+        47348,
+        15096,
+        233,
+        26167,
+        3384,
+        9550,
+        12144,
+        28889,
+        2474,
+        2972,
+        23607,
+        8040,
+        7588,
+        21647,
+        8040,
+        43891,
+        4824,
+        17543,
+        5142,
+        220,
+        33197,
+        34837,
+        3193,
+        49806,
+        38739,
+        250,
+        4108,
+        5196,
+        95,
+        22570,
+        9991,
+        43450,
+        11361,
+        32418,
+        18549,
+        6117,
+        19420,
+        50712
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4399989651095483,
+      "compression_ratio": 1.6122448979591837,
+      "no_speech_prob": 0.18976199626922607,
+      "confidence": 0.332,
+      "words": [
+        {
+          "text": "いきます",
+          "start": 0.04,
+          "end": 0.56,
+          "confidence": 0.0
+        },
+        {
+          "text": " ニ",
+          "start": 0.56,
+          "end": 1.02,
+          "confidence": 0.012
+        },
+        {
+          "text": "ュ",
+          "start": 1.02,
+          "end": 1.36,
+          "confidence": 0.567
+        },
+        {
+          "text": "ー",
+          "start": 1.36,
+          "end": 1.5,
+          "confidence": 0.612
+        },
+        {
+          "text": "ス",
+          "start": 1.5,
+          "end": 1.52,
+          "confidence": 0.963
+        },
+        {
+          "text": "タ",
+          "start": 1.52,
+          "end": 1.68,
+          "confidence": 0.956
+        },
+        {
+          "text": "ブ",
+          "start": 1.68,
+          "end": 1.8,
+          "confidence": 0.788
+        },
+        {
+          "text": "で",
+          "start": 1.8,
+          "end": 2.02,
+          "confidence": 0.836
+        },
+        {
+          "text": "の",
+          "start": 2.02,
+          "end": 2.28,
+          "confidence": 0.869
+        },
+        {
+          "text": "サ",
+          "start": 2.28,
+          "end": 2.58,
+          "confidence": 0.031
+        },
+        {
+          "text": "イ",
+          "start": 2.58,
+          "end": 2.66,
+          "confidence": 0.98
+        },
+        {
+          "text": "ト",
+          "start": 2.66,
+          "end": 2.78,
+          "confidence": 0.994
+        },
+        {
+          "text": "メ",
+          "start": 2.78,
+          "end": 2.94,
+          "confidence": 0.356
+        },
+        {
+          "text": "イ",
+          "start": 2.94,
+          "end": 3.0,
+          "confidence": 0.162
+        },
+        {
+          "text": "ショ",
+          "start": 3.0,
+          "end": 3.14,
+          "confidence": 0.931
+        },
+        {
+          "text": "ン",
+          "start": 3.14,
+          "end": 3.2,
+          "confidence": 0.978
+        },
+        {
+          "text": "機",
+          "start": 3.2,
+          "end": 3.34,
+          "confidence": 0.409
+        },
+        {
+          "text": "が",
+          "start": 3.34,
+          "end": 3.5,
+          "confidence": 0.445
+        },
+        {
+          "text": " ",
+          "start": 3.5,
+          "end": 3.64,
+          "confidence": 0.094
+        },
+        {
+          "text": "実",
+          "start": 3.64,
+          "end": 3.76,
+          "confidence": 0.702
+        },
+        {
+          "text": "際",
+          "start": 3.76,
+          "end": 3.9,
+          "confidence": 0.968
+        },
+        {
+          "text": "と",
+          "start": 3.9,
+          "end": 4.08,
+          "confidence": 0.932
+        },
+        {
+          "text": "違う",
+          "start": 4.08,
+          "end": 4.38,
+          "confidence": 0.942
+        },
+        {
+          "text": "検",
+          "start": 4.38,
+          "end": 4.64,
+          "confidence": 0.255
+        },
+        {
+          "text": "に",
+          "start": 4.64,
+          "end": 4.74,
+          "confidence": 0.207
+        },
+        {
+          "text": "関",
+          "start": 4.74,
+          "end": 4.94,
+          "confidence": 0.412
+        },
+        {
+          "text": "する",
+          "start": 4.94,
+          "end": 5.12,
+          "confidence": 0.992
+        },
+        {
+          "text": "ご",
+          "start": 5.12,
+          "end": 5.3,
+          "confidence": 0.5
+        },
+        {
+          "text": "質",
+          "start": 5.3,
+          "end": 5.46,
+          "confidence": 0.843
+        },
+        {
+          "text": "問",
+          "start": 5.46,
+          "end": 5.62,
+          "confidence": 0.977
+        },
+        {
+          "text": "いただ",
+          "start": 5.62,
+          "end": 5.94,
+          "confidence": 0.913
+        },
+        {
+          "text": "いて",
+          "start": 5.94,
+          "end": 6.14,
+          "confidence": 0.982
+        },
+        {
+          "text": "お",
+          "start": 6.14,
+          "end": 6.26,
+          "confidence": 0.806
+        },
+        {
+          "text": "ります",
+          "start": 6.26,
+          "end": 6.62,
+          "confidence": 0.963
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 6.92,
+      "end": 13.58,
+      "text": "同じ度メインでデレクトリーごとに 別再度として管理上をしているサイトバリマスの",
+      "tokens": [
+        50712,
+        13089,
+        9257,
+        13127,
+        21647,
+        8040,
+        4824,
+        2474,
+        31327,
+        16680,
+        10825,
+        7588,
+        12376,
+        3384,
+        9991,
+        3193,
+        4108,
+        220,
+        16158,
+        8623,
+        13127,
+        3193,
+        8822,
+        23131,
+        13876,
+        5708,
+        5998,
+        8822,
+        22979,
+        23607,
+        8040,
+        7588,
+        18593,
+        12376,
+        13258,
+        9550,
+        2972,
+        51044
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4399989651095483,
+      "compression_ratio": 1.6122448979591837,
+      "no_speech_prob": 0.18976199626922607,
+      "confidence": 0.25,
+      "words": [
+        {
+          "text": "同",
+          "start": 6.92,
+          "end": 7.26,
+          "confidence": 0.0
+        },
+        {
+          "text": "じ",
+          "start": 7.26,
+          "end": 7.44,
+          "confidence": 0.005
+        },
+        {
+          "text": "度",
+          "start": 7.44,
+          "end": 7.6,
+          "confidence": 0.003
+        },
+        {
+          "text": "メ",
+          "start": 7.6,
+          "end": 7.76,
+          "confidence": 0.002
+        },
+        {
+          "text": "イ",
+          "start": 7.76,
+          "end": 7.84,
+          "confidence": 0.684
+        },
+        {
+          "text": "ン",
+          "start": 7.84,
+          "end": 7.86,
+          "confidence": 0.889
+        },
+        {
+          "text": "で",
+          "start": 7.86,
+          "end": 8.0,
+          "confidence": 0.935
+        },
+        {
+          "text": "デ",
+          "start": 8.0,
+          "end": 8.12,
+          "confidence": 0.119
+        },
+        {
+          "text": "レ",
+          "start": 8.12,
+          "end": 8.28,
+          "confidence": 0.435
+        },
+        {
+          "text": "ク",
+          "start": 8.28,
+          "end": 8.36,
+          "confidence": 0.951
+        },
+        {
+          "text": "ト",
+          "start": 8.36,
+          "end": 8.5,
+          "confidence": 0.979
+        },
+        {
+          "text": "リ",
+          "start": 8.5,
+          "end": 8.62,
+          "confidence": 0.968
+        },
+        {
+          "text": "ー",
+          "start": 8.62,
+          "end": 8.72,
+          "confidence": 0.653
+        },
+        {
+          "text": "ご",
+          "start": 8.72,
+          "end": 8.84,
+          "confidence": 0.228
+        },
+        {
+          "text": "と",
+          "start": 8.84,
+          "end": 8.98,
+          "confidence": 0.993
+        },
+        {
+          "text": "に",
+          "start": 8.98,
+          "end": 9.14,
+          "confidence": 0.953
+        },
+        {
+          "text": " ",
+          "start": 9.14,
+          "end": 9.24,
+          "confidence": 0.042
+        },
+        {
+          "text": "別",
+          "start": 9.24,
+          "end": 9.4,
+          "confidence": 0.583
+        },
+        {
+          "text": "再",
+          "start": 9.4,
+          "end": 9.58,
+          "confidence": 0.443
+        },
+        {
+          "text": "度",
+          "start": 9.58,
+          "end": 9.74,
+          "confidence": 0.525
+        },
+        {
+          "text": "と",
+          "start": 9.74,
+          "end": 9.92,
+          "confidence": 0.876
+        },
+        {
+          "text": "して",
+          "start": 9.92,
+          "end": 10.42,
+          "confidence": 0.999
+        },
+        {
+          "text": "管",
+          "start": 10.42,
+          "end": 10.86,
+          "confidence": 0.314
+        },
+        {
+          "text": "理",
+          "start": 10.86,
+          "end": 11.06,
+          "confidence": 1.0
+        },
+        {
+          "text": "上",
+          "start": 11.06,
+          "end": 11.36,
+          "confidence": 0.208
+        },
+        {
+          "text": "を",
+          "start": 11.36,
+          "end": 11.56,
+          "confidence": 0.985
+        },
+        {
+          "text": "して",
+          "start": 11.56,
+          "end": 11.84,
+          "confidence": 0.937
+        },
+        {
+          "text": "いる",
+          "start": 11.84,
+          "end": 12.16,
+          "confidence": 0.942
+        },
+        {
+          "text": "サ",
+          "start": 12.16,
+          "end": 12.52,
+          "confidence": 0.078
+        },
+        {
+          "text": "イ",
+          "start": 12.52,
+          "end": 12.58,
+          "confidence": 0.978
+        },
+        {
+          "text": "ト",
+          "start": 12.58,
+          "end": 12.68,
+          "confidence": 0.982
+        },
+        {
+          "text": "バ",
+          "start": 12.68,
+          "end": 12.82,
+          "confidence": 0.259
+        },
+        {
+          "text": "リ",
+          "start": 12.82,
+          "end": 12.96,
+          "confidence": 0.363
+        },
+        {
+          "text": "マ",
+          "start": 12.96,
+          "end": 13.12,
+          "confidence": 0.114
+        },
+        {
+          "text": "ス",
+          "start": 13.12,
+          "end": 13.18,
+          "confidence": 0.881
+        },
+        {
+          "text": "の",
+          "start": 13.18,
+          "end": 13.58,
+          "confidence": 0.716
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 13.68,
+      "end": 20.72,
+      "text": "サプテレクトリーごとにわけたサイトは それぞれ パブリシャーセンターに登録していくぐるニュース上では",
+      "tokens": [
+        51044,
+        23607,
+        20953,
+        22985,
+        16680,
+        10825,
+        7588,
+        12376,
+        3384,
+        9991,
+        3193,
+        4108,
+        9206,
+        7625,
+        3368,
+        23607,
+        8040,
+        7588,
+        3065,
+        47765,
+        31563,
+        4132,
+        15096,
+        239,
+        28889,
+        12376,
+        11054,
+        17233,
+        3384,
+        31223,
+        4824,
+        30736,
+        4108,
+        46246,
+        8822,
+        49394,
+        35849,
+        4895,
+        34737,
+        26167,
+        3384,
+        9550,
+        5708,
+        16719,
+        51408
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4399989651095483,
+      "compression_ratio": 1.6122448979591837,
+      "no_speech_prob": 0.18976199626922607,
+      "confidence": 0.465,
+      "words": [
+        {
+          "text": "サ",
+          "start": 13.68,
+          "end": 14.22,
+          "confidence": 0.0
+        },
+        {
+          "text": "プ",
+          "start": 14.22,
+          "end": 14.32,
+          "confidence": 0.486
+        },
+        {
+          "text": "テ",
+          "start": 14.32,
+          "end": 14.42,
+          "confidence": 0.414
+        },
+        {
+          "text": "レ",
+          "start": 14.42,
+          "end": 14.6,
+          "confidence": 0.89
+        },
+        {
+          "text": "ク",
+          "start": 14.6,
+          "end": 14.68,
+          "confidence": 0.639
+        },
+        {
+          "text": "ト",
+          "start": 14.68,
+          "end": 14.78,
+          "confidence": 0.986
+        },
+        {
+          "text": "リ",
+          "start": 14.78,
+          "end": 14.92,
+          "confidence": 0.917
+        },
+        {
+          "text": "ー",
+          "start": 14.92,
+          "end": 15.04,
+          "confidence": 0.877
+        },
+        {
+          "text": "ご",
+          "start": 15.04,
+          "end": 15.1,
+          "confidence": 0.011
+        },
+        {
+          "text": "と",
+          "start": 15.1,
+          "end": 15.38,
+          "confidence": 0.985
+        },
+        {
+          "text": "に",
+          "start": 15.38,
+          "end": 15.86,
+          "confidence": 0.326
+        },
+        {
+          "text": "わ",
+          "start": 15.86,
+          "end": 16.02,
+          "confidence": 0.733
+        },
+        {
+          "text": "け",
+          "start": 16.02,
+          "end": 16.14,
+          "confidence": 0.989
+        },
+        {
+          "text": "た",
+          "start": 16.14,
+          "end": 16.28,
+          "confidence": 0.957
+        },
+        {
+          "text": "サ",
+          "start": 16.28,
+          "end": 16.42,
+          "confidence": 0.62
+        },
+        {
+          "text": "イ",
+          "start": 16.42,
+          "end": 16.52,
+          "confidence": 0.923
+        },
+        {
+          "text": "ト",
+          "start": 16.52,
+          "end": 16.6,
+          "confidence": 0.898
+        },
+        {
+          "text": "は",
+          "start": 16.6,
+          "end": 17.1,
+          "confidence": 0.989
+        },
+        {
+          "text": " それ",
+          "start": 17.1,
+          "end": 17.44,
+          "confidence": 0.057
+        },
+        {
+          "text": "ぞ",
+          "start": 17.44,
+          "end": 17.62,
+          "confidence": 0.824
+        },
+        {
+          "text": "れ",
+          "start": 17.62,
+          "end": 17.72,
+          "confidence": 0.996
+        },
+        {
+          "text": " パ",
+          "start": 17.72,
+          "end": 17.86,
+          "confidence": 0.096
+        },
+        {
+          "text": "ブ",
+          "start": 17.86,
+          "end": 17.94,
+          "confidence": 0.939
+        },
+        {
+          "text": "リ",
+          "start": 17.94,
+          "end": 18.04,
+          "confidence": 0.994
+        },
+        {
+          "text": "シ",
+          "start": 18.04,
+          "end": 18.18,
+          "confidence": 0.864
+        },
+        {
+          "text": "ャ",
+          "start": 18.18,
+          "end": 18.26,
+          "confidence": 0.87
+        },
+        {
+          "text": "ー",
+          "start": 18.26,
+          "end": 18.42,
+          "confidence": 0.815
+        },
+        {
+          "text": "セ",
+          "start": 18.42,
+          "end": 18.44,
+          "confidence": 0.619
+        },
+        {
+          "text": "ン",
+          "start": 18.44,
+          "end": 18.52,
+          "confidence": 0.801
+        },
+        {
+          "text": "ター",
+          "start": 18.52,
+          "end": 18.62,
+          "confidence": 0.998
+        },
+        {
+          "text": "に",
+          "start": 18.62,
+          "end": 18.76,
+          "confidence": 0.832
+        },
+        {
+          "text": "登録",
+          "start": 18.76,
+          "end": 19.12,
+          "confidence": 0.958
+        },
+        {
+          "text": "して",
+          "start": 19.12,
+          "end": 19.38,
+          "confidence": 0.727
+        },
+        {
+          "text": "いく",
+          "start": 19.38,
+          "end": 19.62,
+          "confidence": 0.781
+        },
+        {
+          "text": "ぐ",
+          "start": 19.62,
+          "end": 19.8,
+          "confidence": 0.084
+        },
+        {
+          "text": "る",
+          "start": 19.8,
+          "end": 19.88,
+          "confidence": 0.864
+        },
+        {
+          "text": "ニ",
+          "start": 19.88,
+          "end": 20.02,
+          "confidence": 0.718
+        },
+        {
+          "text": "ュ",
+          "start": 20.02,
+          "end": 20.14,
+          "confidence": 0.996
+        },
+        {
+          "text": "ー",
+          "start": 20.14,
+          "end": 20.16,
+          "confidence": 0.99
+        },
+        {
+          "text": "ス",
+          "start": 20.16,
+          "end": 20.22,
+          "confidence": 0.986
+        },
+        {
+          "text": "上",
+          "start": 20.22,
+          "end": 20.4,
+          "confidence": 0.167
+        },
+        {
+          "text": "では",
+          "start": 20.4,
+          "end": 20.72,
+          "confidence": 0.803
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 2088,
+      "start": 20.88,
+      "end": 27.0,
+      "text": "サイトとして認識され パブリコンアイコンはサイトボトフのものが 正しく表示されます",
+      "tokens": [
+        50364,
+        23607,
+        8040,
+        7588,
+        3193,
+        8822,
+        22041,
+        43143,
+        6722,
+        4132,
+        15096,
+        239,
+        28889,
+        12376,
+        18066,
+        4824,
+        12817,
+        8040,
+        18066,
+        4824,
+        3065,
+        23607,
+        8040,
+        7588,
+        37626,
+        7588,
+        17320,
+        2972,
+        44726,
+        5142,
+        220,
+        15789,
+        26568,
+        40053,
+        6722,
+        4132,
+        5368,
+        50684
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.35158648256395686,
+      "compression_ratio": 1.6926406926406927,
+      "no_speech_prob": 0.06365812569856644,
+      "confidence": 0.309,
+      "words": [
+        {
+          "text": "サ",
+          "start": 20.88,
+          "end": 21.26,
+          "confidence": 0.0
+        },
+        {
+          "text": "イ",
+          "start": 21.26,
+          "end": 21.34,
+          "confidence": 0.967
+        },
+        {
+          "text": "ト",
+          "start": 21.34,
+          "end": 21.44,
+          "confidence": 0.596
+        },
+        {
+          "text": "と",
+          "start": 21.44,
+          "end": 21.6,
+          "confidence": 0.75
+        },
+        {
+          "text": "して",
+          "start": 21.6,
+          "end": 21.82,
+          "confidence": 0.984
+        },
+        {
+          "text": "認",
+          "start": 21.82,
+          "end": 22.08,
+          "confidence": 0.081
+        },
+        {
+          "text": "識",
+          "start": 22.08,
+          "end": 22.2,
+          "confidence": 0.995
+        },
+        {
+          "text": "さ",
+          "start": 22.2,
+          "end": 22.36,
+          "confidence": 0.979
+        },
+        {
+          "text": "れ",
+          "start": 22.36,
+          "end": 22.62,
+          "confidence": 0.909
+        },
+        {
+          "text": " パ",
+          "start": 22.62,
+          "end": 22.86,
+          "confidence": 0.086
+        },
+        {
+          "text": "ブ",
+          "start": 22.86,
+          "end": 23.0,
+          "confidence": 0.087
+        },
+        {
+          "text": "リ",
+          "start": 23.0,
+          "end": 23.16,
+          "confidence": 0.007
+        },
+        {
+          "text": "コ",
+          "start": 23.16,
+          "end": 23.26,
+          "confidence": 0.645
+        },
+        {
+          "text": "ン",
+          "start": 23.26,
+          "end": 23.28,
+          "confidence": 0.921
+        },
+        {
+          "text": "ア",
+          "start": 23.28,
+          "end": 23.46,
+          "confidence": 0.084
+        },
+        {
+          "text": "イ",
+          "start": 23.46,
+          "end": 23.52,
+          "confidence": 0.944
+        },
+        {
+          "text": "コ",
+          "start": 23.52,
+          "end": 23.64,
+          "confidence": 0.258
+        },
+        {
+          "text": "ン",
+          "start": 23.64,
+          "end": 23.88,
+          "confidence": 0.956
+        },
+        {
+          "text": "は",
+          "start": 23.88,
+          "end": 23.9,
+          "confidence": 0.873
+        },
+        {
+          "text": "サ",
+          "start": 23.9,
+          "end": 24.04,
+          "confidence": 0.868
+        },
+        {
+          "text": "イ",
+          "start": 24.04,
+          "end": 24.16,
+          "confidence": 0.996
+        },
+        {
+          "text": "ト",
+          "start": 24.16,
+          "end": 24.24,
+          "confidence": 0.993
+        },
+        {
+          "text": "ボ",
+          "start": 24.24,
+          "end": 24.38,
+          "confidence": 0.656
+        },
+        {
+          "text": "ト",
+          "start": 24.38,
+          "end": 24.5,
+          "confidence": 0.892
+        },
+        {
+          "text": "フ",
+          "start": 24.5,
+          "end": 24.66,
+          "confidence": 0.018
+        },
+        {
+          "text": "の",
+          "start": 24.66,
+          "end": 24.7,
+          "confidence": 0.672
+        },
+        {
+          "text": "もの",
+          "start": 24.7,
+          "end": 24.9,
+          "confidence": 0.528
+        },
+        {
+          "text": "が",
+          "start": 24.9,
+          "end": 25.1,
+          "confidence": 0.195
+        },
+        {
+          "text": " ",
+          "start": 25.1,
+          "end": 25.32,
+          "confidence": 0.184
+        },
+        {
+          "text": "正",
+          "start": 25.32,
+          "end": 25.4,
+          "confidence": 0.433
+        },
+        {
+          "text": "しく",
+          "start": 25.4,
+          "end": 25.66,
+          "confidence": 0.982
+        },
+        {
+          "text": "表示",
+          "start": 25.66,
+          "end": 26.0,
+          "confidence": 0.706
+        },
+        {
+          "text": "さ",
+          "start": 26.0,
+          "end": 26.28,
+          "confidence": 0.995
+        },
+        {
+          "text": "れ",
+          "start": 26.28,
+          "end": 26.56,
+          "confidence": 0.986
+        },
+        {
+          "text": "ます",
+          "start": 26.56,
+          "end": 27.0,
+          "confidence": 0.866
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 2088,
+      "start": 27.26,
+      "end": 33.8,
+      "text": "しかし ルグル検査結果のニュースタブでは パブリコンサイトメイショー機ともに 正しくない医療時にいいなります",
+      "tokens": [
+        50684,
+        32156,
+        2849,
+        220,
+        9405,
+        23839,
+        9405,
+        38739,
+        250,
+        17238,
+        119,
+        35181,
+        2972,
+        34737,
+        26167,
+        3384,
+        9550,
+        12144,
+        28889,
+        16719,
+        15096,
+        239,
+        28889,
+        12376,
+        18066,
+        4824,
+        23607,
+        8040,
+        7588,
+        21647,
+        8040,
+        43891,
+        3384,
+        17543,
+        3193,
+        4801,
+        4108,
+        220,
+        15789,
+        26568,
+        9311,
+        9937,
+        119,
+        6651,
+        224,
+        6611,
+        4108,
+        13806,
+        3203,
+        19420,
+        51024
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.35158648256395686,
+      "compression_ratio": 1.6926406926406927,
+      "no_speech_prob": 0.06365812569856644,
+      "confidence": 0.359,
+      "words": [
+        {
+          "text": "しか",
+          "start": 27.26,
+          "end": 27.56,
+          "confidence": 0.0
+        },
+        {
+          "text": "し",
+          "start": 27.56,
+          "end": 27.74,
+          "confidence": 0.945
+        },
+        {
+          "text": " ",
+          "start": 27.74,
+          "end": 27.9,
+          "confidence": 0.02
+        },
+        {
+          "text": "ル",
+          "start": 27.9,
+          "end": 27.92,
+          "confidence": 0.176
+        },
+        {
+          "text": "グ",
+          "start": 27.92,
+          "end": 28.02,
+          "confidence": 0.43
+        },
+        {
+          "text": "ル",
+          "start": 28.02,
+          "end": 28.14,
+          "confidence": 0.988
+        },
+        {
+          "text": "検",
+          "start": 28.14,
+          "end": 28.32,
+          "confidence": 0.569
+        },
+        {
+          "text": "査",
+          "start": 28.32,
+          "end": 28.46,
+          "confidence": 0.293
+        },
+        {
+          "text": "結果",
+          "start": 28.46,
+          "end": 28.72,
+          "confidence": 0.962
+        },
+        {
+          "text": "の",
+          "start": 28.72,
+          "end": 28.92,
+          "confidence": 0.932
+        },
+        {
+          "text": "ニ",
+          "start": 28.92,
+          "end": 29.06,
+          "confidence": 0.797
+        },
+        {
+          "text": "ュ",
+          "start": 29.06,
+          "end": 29.14,
+          "confidence": 0.995
+        },
+        {
+          "text": "ー",
+          "start": 29.14,
+          "end": 29.2,
+          "confidence": 0.985
+        },
+        {
+          "text": "ス",
+          "start": 29.2,
+          "end": 29.24,
+          "confidence": 0.978
+        },
+        {
+          "text": "タ",
+          "start": 29.24,
+          "end": 29.34,
+          "confidence": 0.787
+        },
+        {
+          "text": "ブ",
+          "start": 29.34,
+          "end": 29.44,
+          "confidence": 0.571
+        },
+        {
+          "text": "では",
+          "start": 29.44,
+          "end": 29.66,
+          "confidence": 0.966
+        },
+        {
+          "text": " パ",
+          "start": 29.66,
+          "end": 30.02,
+          "confidence": 0.104
+        },
+        {
+          "text": "ブ",
+          "start": 30.02,
+          "end": 30.14,
+          "confidence": 0.052
+        },
+        {
+          "text": "リ",
+          "start": 30.14,
+          "end": 30.24,
+          "confidence": 0.013
+        },
+        {
+          "text": "コ",
+          "start": 30.24,
+          "end": 30.32,
+          "confidence": 0.834
+        },
+        {
+          "text": "ン",
+          "start": 30.32,
+          "end": 30.42,
+          "confidence": 0.934
+        },
+        {
+          "text": "サ",
+          "start": 30.42,
+          "end": 30.54,
+          "confidence": 0.495
+        },
+        {
+          "text": "イ",
+          "start": 30.54,
+          "end": 30.62,
+          "confidence": 0.969
+        },
+        {
+          "text": "ト",
+          "start": 30.62,
+          "end": 30.72,
+          "confidence": 0.955
+        },
+        {
+          "text": "メ",
+          "start": 30.72,
+          "end": 30.86,
+          "confidence": 0.254
+        },
+        {
+          "text": "イ",
+          "start": 30.86,
+          "end": 30.92,
+          "confidence": 0.503
+        },
+        {
+          "text": "ショ",
+          "start": 30.92,
+          "end": 31.04,
+          "confidence": 0.465
+        },
+        {
+          "text": "ー",
+          "start": 31.04,
+          "end": 31.08,
+          "confidence": 0.612
+        },
+        {
+          "text": "機",
+          "start": 31.08,
+          "end": 31.24,
+          "confidence": 0.115
+        },
+        {
+          "text": "と",
+          "start": 31.24,
+          "end": 31.42,
+          "confidence": 0.22
+        },
+        {
+          "text": "も",
+          "start": 31.42,
+          "end": 31.56,
+          "confidence": 0.836
+        },
+        {
+          "text": "に",
+          "start": 31.56,
+          "end": 31.66,
+          "confidence": 0.941
+        },
+        {
+          "text": " ",
+          "start": 31.66,
+          "end": 31.8,
+          "confidence": 0.378
+        },
+        {
+          "text": "正",
+          "start": 31.8,
+          "end": 31.92,
+          "confidence": 0.34
+        },
+        {
+          "text": "しく",
+          "start": 31.92,
+          "end": 32.18,
+          "confidence": 0.998
+        },
+        {
+          "text": "ない",
+          "start": 32.18,
+          "end": 32.4,
+          "confidence": 0.99
+        },
+        {
+          "text": "医",
+          "start": 32.4,
+          "end": 32.6,
+          "confidence": 0.268
+        },
+        {
+          "text": "療",
+          "start": 32.6,
+          "end": 32.76,
+          "confidence": 0.576
+        },
+        {
+          "text": "時",
+          "start": 32.76,
+          "end": 32.96,
+          "confidence": 0.463
+        },
+        {
+          "text": "に",
+          "start": 32.96,
+          "end": 33.12,
+          "confidence": 0.905
+        },
+        {
+          "text": "いい",
+          "start": 33.12,
+          "end": 33.36,
+          "confidence": 0.566
+        },
+        {
+          "text": "な",
+          "start": 33.36,
+          "end": 33.48,
+          "confidence": 0.835
+        },
+        {
+          "text": "ります",
+          "start": 33.48,
+          "end": 33.8,
+          "confidence": 0.963
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 2088,
+      "start": 34.02,
+      "end": 40.38,
+      "text": "こちらいたいです ものではありません パブリコンはサブテレクトリーごとに設定した",
+      "tokens": [
+        51024,
+        34395,
+        17679,
+        1764,
+        4767,
+        32505,
+        2972,
+        16719,
+        14498,
+        30250,
+        15096,
+        239,
+        28889,
+        12376,
+        18066,
+        4824,
+        3065,
+        23607,
+        28889,
+        22985,
+        16680,
+        10825,
+        7588,
+        12376,
+        3384,
+        9991,
+        3193,
+        4108,
+        39035,
+        12088,
+        8533,
+        51388
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.35158648256395686,
+      "compression_ratio": 1.6926406926406927,
+      "no_speech_prob": 0.06365812569856644,
+      "confidence": 0.194,
+      "words": [
+        {
+          "text": "こちら",
+          "start": 34.02,
+          "end": 34.48,
+          "confidence": 0.0
+        },
+        {
+          "text": "いた",
+          "start": 34.48,
+          "end": 34.82,
+          "confidence": 0.102
+        },
+        {
+          "text": "い",
+          "start": 34.82,
+          "end": 35.0,
+          "confidence": 0.002
+        },
+        {
+          "text": "です",
+          "start": 35.0,
+          "end": 35.14,
+          "confidence": 0.005
+        },
+        {
+          "text": " も",
+          "start": 35.14,
+          "end": 35.18,
+          "confidence": 0.003
+        },
+        {
+          "text": "の",
+          "start": 35.18,
+          "end": 35.28,
+          "confidence": 0.735
+        },
+        {
+          "text": "では",
+          "start": 35.28,
+          "end": 35.5,
+          "confidence": 0.984
+        },
+        {
+          "text": "あり",
+          "start": 35.5,
+          "end": 35.72,
+          "confidence": 0.96
+        },
+        {
+          "text": "ません",
+          "start": 35.72,
+          "end": 36.14,
+          "confidence": 1.0
+        },
+        {
+          "text": " パ",
+          "start": 36.14,
+          "end": 36.9,
+          "confidence": 0.222
+        },
+        {
+          "text": "ブ",
+          "start": 36.9,
+          "end": 37.02,
+          "confidence": 0.011
+        },
+        {
+          "text": "リ",
+          "start": 37.02,
+          "end": 37.06,
+          "confidence": 0.33
+        },
+        {
+          "text": "コ",
+          "start": 37.06,
+          "end": 37.18,
+          "confidence": 0.919
+        },
+        {
+          "text": "ン",
+          "start": 37.18,
+          "end": 37.94,
+          "confidence": 0.844
+        },
+        {
+          "text": "は",
+          "start": 37.94,
+          "end": 37.96,
+          "confidence": 0.942
+        },
+        {
+          "text": "サ",
+          "start": 37.96,
+          "end": 38.24,
+          "confidence": 0.27
+        },
+        {
+          "text": "ブ",
+          "start": 38.24,
+          "end": 38.32,
+          "confidence": 0.976
+        },
+        {
+          "text": "テ",
+          "start": 38.32,
+          "end": 38.42,
+          "confidence": 0.368
+        },
+        {
+          "text": "レ",
+          "start": 38.42,
+          "end": 38.56,
+          "confidence": 0.373
+        },
+        {
+          "text": "ク",
+          "start": 38.56,
+          "end": 38.66,
+          "confidence": 0.751
+        },
+        {
+          "text": "ト",
+          "start": 38.66,
+          "end": 38.78,
+          "confidence": 0.819
+        },
+        {
+          "text": "リ",
+          "start": 38.78,
+          "end": 38.92,
+          "confidence": 0.984
+        },
+        {
+          "text": "ー",
+          "start": 38.92,
+          "end": 38.96,
+          "confidence": 0.512
+        },
+        {
+          "text": "ご",
+          "start": 38.96,
+          "end": 39.08,
+          "confidence": 0.029
+        },
+        {
+          "text": "と",
+          "start": 39.08,
+          "end": 39.22,
+          "confidence": 0.975
+        },
+        {
+          "text": "に",
+          "start": 39.22,
+          "end": 39.56,
+          "confidence": 0.971
+        },
+        {
+          "text": "設",
+          "start": 39.56,
+          "end": 39.84,
+          "confidence": 0.666
+        },
+        {
+          "text": "定",
+          "start": 39.84,
+          "end": 40.06,
+          "confidence": 0.996
+        },
+        {
+          "text": "した",
+          "start": 40.06,
+          "end": 40.38,
+          "confidence": 0.938
+        }
+      ]
+    }
+  ],
+  "language": "ja",
+  "language_probs": {
+    "en": 0.006242657545953989,
+    "zh": 0.0014827612321823835,
+    "de": 0.00011256561992922798,
+    "es": 0.0013291386421769857,
+    "ru": 0.00022561925288755447,
+    "ko": 0.00042481819400563836,
+    "fr": 0.0003206696128472686,
+    "ja": 0.9862462282180786,
+    "pt": 0.0003521866456139833,
+    "tr": 8.698396413819864e-05,
+    "pl": 0.0008716703741811216,
+    "ca": 1.310503307649924e-06,
+    "nl": 1.0388754162704572e-05,
+    "ar": 1.634380350878928e-05,
+    "sv": 1.8519956938689575e-05,
+    "it": 0.0001502948289271444,
+    "id": 1.4650489902123809e-05,
+    "hi": 3.542034392012283e-05,
+    "fi": 3.327432932564989e-05,
+    "vi": 9.459067769057583e-06,
+    "he": 1.488120233261725e-05,
+    "uk": 2.396660238446202e-05,
+    "el": 3.683132672449574e-05,
+    "ms": 3.514470154186711e-05,
+    "cs": 1.2629512639250606e-05,
+    "ro": 2.034019234997686e-05,
+    "da": 7.294049737538444e-07,
+    "hu": 8.41306882648496e-06,
+    "ta": 3.047011659873533e-06,
+    "no": 4.935400852446037e-07,
+    "th": 2.396660238446202e-05,
+    "ur": 1.823282946133986e-05,
+    "hr": 3.2435270895803114e-06,
+    "bg": 5.906901492380712e-07,
+    "lt": 1.666117981358184e-07,
+    "la": 0.00018271202861797065,
+    "mi": 8.044702553888783e-05,
+    "ml": 1.6182557374122553e-06,
+    "cy": 6.168086838442832e-05,
+    "sk": 7.948603979457403e-07,
+    "te": 2.2118931610748405e-06,
+    "fa": 1.647198951104656e-05,
+    "lv": 2.2245595232561755e-07,
+    "bn": 1.0470233064552303e-05,
+    "sr": 5.132005185259914e-07,
+    "az": 6.641308232246956e-07,
+    "sl": 1.0286258884661947e-06,
+    "kn": 4.97411008382187e-07,
+    "et": 6.641308232246956e-07,
+    "mk": 2.2420069001327647e-07,
+    "br": 3.301538890809752e-05,
+    "eu": 3.920674862456508e-05,
+    "is": 1.7324887835457048e-07,
+    "hy": 1.6566315252930508e-06,
+    "ne": 9.148787967205863e-07,
+    "mn": 2.098585719068069e-05,
+    "bs": 1.1565151680770214e-06,
+    "kk": 2.4623628291919886e-07,
+    "sq": 8.798302815193892e-07,
+    "sw": 8.885971510608215e-06,
+    "gl": 4.239260306349024e-05,
+    "mr": 5.725165124204068e-07,
+    "pa": 1.6309478496623342e-06,
+    "si": 1.4423355423787143e-05,
+    "km": 4.045130481244996e-05,
+    "sn": 2.304845656908583e-05,
+    "yo": 3.3991873351624236e-06,
+    "so": 2.3866036258368695e-07,
+    "af": 9.969784287022776e-07,
+    "oc": 5.474488716572523e-06,
+    "ka": 1.0864454225156805e-06,
+    "be": 5.692566901416285e-06,
+    "tg": 1.913662650565584e-08,
+    "sd": 1.6959174899966456e-06,
+    "gu": 3.2115266890286875e-07,
+    "am": 1.2975741014997766e-07,
+    "yi": 4.197435828245943e-06,
+    "lo": 2.600773427730019e-07,
+    "uz": 3.430495609801909e-10,
+    "fo": 1.4281055200626724e-06,
+    "ht": 2.373014922341099e-06,
+    "ps": 1.5321337514251354e-06,
+    "tk": 7.745855623575437e-10,
+    "nn": 0.0009135027066804469,
+    "mt": 1.0673553418882875e-07,
+    "sa": 1.7262496839975938e-05,
+    "lb": 3.051601860093456e-09,
+    "my": 2.098585719068069e-05,
+    "bo": 1.303041608480271e-05,
+    "tl": 7.029382231849013e-06,
+    "mg": 1.3073606641711422e-09,
+    "as": 4.321581172916922e-07,
+    "tt": 3.4714515706468774e-09,
+    "haw": 2.8909242246299982e-05,
+    "ln": 8.594491305302654e-07,
+    "ha": 6.384976991569147e-09,
+    "ba": 5.375886957814657e-10,
+    "jw": 0.00019148056162521243,
+    "su": 3.087572864046706e-09
+  }
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_auto/accurate_jp_japanese.mp3.words.json b/tests/expected/tiny_auto/accurate_jp_japanese.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..97df2ecc55e5966301e8c2c89c03de20fa39ae73
--- /dev/null
+++ b/tests/expected/tiny_auto/accurate_jp_japanese.mp3.words.json
@@ -0,0 +1,1665 @@
+{
+  "text": "いきます ニュースタブでのサイトメイション機が 実際と違う検に関するご質問いただいております同じ度メインでデレクトリーごとに 別再度として管理上をしているサイトバリマスのサプテレクトリーごとにわけたサイトは それぞれ パブリシャーセンターに登録していくぐるニュース上ではサイトとして認識され パブリコンアイコンはサイトボトフのものが 正しく表示されますしかし ルグル検査結果のニュースタブでは パブリコンサイトメイショー機ともに 正しくない医療時にいいなりますこちらいたいです ものではありません パブリコンはサブテレクトリーごとに設定した",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.08,
+      "end": 6.62,
+      "text": "いきます ニュースタブでのサイトメイション機が 実際と違う検に関するご質問いただいております",
+      "tokens": [
+        50364,
+        47348,
+        15096,
+        233,
+        26167,
+        3384,
+        9550,
+        12144,
+        28889,
+        2474,
+        2972,
+        23607,
+        8040,
+        7588,
+        21647,
+        8040,
+        43891,
+        4824,
+        17543,
+        5142,
+        220,
+        33197,
+        34837,
+        3193,
+        49806,
+        38739,
+        250,
+        4108,
+        5196,
+        95,
+        22570,
+        9991,
+        43450,
+        11361,
+        32418,
+        18549,
+        6117,
+        19420,
+        50712
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4399989651095483,
+      "compression_ratio": 1.6122448979591837,
+      "no_speech_prob": 0.18976199626922607,
+      "confidence": 0.549,
+      "words": [
+        {
+          "text": "いきます",
+          "start": 0.08,
+          "end": 0.6,
+          "confidence": 0.173
+        },
+        {
+          "text": " ニ",
+          "start": 0.6,
+          "end": 1.32,
+          "confidence": 0.187
+        },
+        {
+          "text": "ュ",
+          "start": 1.32,
+          "end": 1.38,
+          "confidence": 0.974
+        },
+        {
+          "text": "ー",
+          "start": 1.38,
+          "end": 1.5,
+          "confidence": 0.945
+        },
+        {
+          "text": "ス",
+          "start": 1.5,
+          "end": 1.52,
+          "confidence": 0.961
+        },
+        {
+          "text": "タ",
+          "start": 1.52,
+          "end": 1.68,
+          "confidence": 0.87
+        },
+        {
+          "text": "ブ",
+          "start": 1.68,
+          "end": 1.8,
+          "confidence": 0.772
+        },
+        {
+          "text": "で",
+          "start": 1.8,
+          "end": 2.02,
+          "confidence": 0.948
+        },
+        {
+          "text": "の",
+          "start": 2.02,
+          "end": 2.26,
+          "confidence": 0.838
+        },
+        {
+          "text": "サ",
+          "start": 2.26,
+          "end": 2.56,
+          "confidence": 0.015
+        },
+        {
+          "text": "イ",
+          "start": 2.56,
+          "end": 2.66,
+          "confidence": 0.983
+        },
+        {
+          "text": "ト",
+          "start": 2.66,
+          "end": 2.76,
+          "confidence": 0.992
+        },
+        {
+          "text": "メ",
+          "start": 2.76,
+          "end": 2.94,
+          "confidence": 0.385
+        },
+        {
+          "text": "イ",
+          "start": 2.94,
+          "end": 3.0,
+          "confidence": 0.233
+        },
+        {
+          "text": "ショ",
+          "start": 3.0,
+          "end": 3.14,
+          "confidence": 0.894
+        },
+        {
+          "text": "ン",
+          "start": 3.14,
+          "end": 3.2,
+          "confidence": 0.983
+        },
+        {
+          "text": "機",
+          "start": 3.2,
+          "end": 3.32,
+          "confidence": 0.363
+        },
+        {
+          "text": "が",
+          "start": 3.32,
+          "end": 3.5,
+          "confidence": 0.64
+        },
+        {
+          "text": " ",
+          "start": 3.5,
+          "end": 3.6,
+          "confidence": 0.232
+        },
+        {
+          "text": "実",
+          "start": 3.6,
+          "end": 3.76,
+          "confidence": 0.75
+        },
+        {
+          "text": "際",
+          "start": 3.76,
+          "end": 3.9,
+          "confidence": 0.98
+        },
+        {
+          "text": "と",
+          "start": 3.9,
+          "end": 4.08,
+          "confidence": 0.928
+        },
+        {
+          "text": "違う",
+          "start": 4.08,
+          "end": 4.38,
+          "confidence": 0.898
+        },
+        {
+          "text": "検",
+          "start": 4.38,
+          "end": 4.64,
+          "confidence": 0.327
+        },
+        {
+          "text": "に",
+          "start": 4.64,
+          "end": 4.74,
+          "confidence": 0.187
+        },
+        {
+          "text": "関",
+          "start": 4.74,
+          "end": 4.94,
+          "confidence": 0.497
+        },
+        {
+          "text": "する",
+          "start": 4.94,
+          "end": 5.12,
+          "confidence": 0.988
+        },
+        {
+          "text": "ご",
+          "start": 5.12,
+          "end": 5.3,
+          "confidence": 0.649
+        },
+        {
+          "text": "質",
+          "start": 5.3,
+          "end": 5.46,
+          "confidence": 0.893
+        },
+        {
+          "text": "問",
+          "start": 5.46,
+          "end": 5.62,
+          "confidence": 0.992
+        },
+        {
+          "text": "いただ",
+          "start": 5.62,
+          "end": 5.92,
+          "confidence": 0.936
+        },
+        {
+          "text": "いて",
+          "start": 5.92,
+          "end": 6.14,
+          "confidence": 0.981
+        },
+        {
+          "text": "お",
+          "start": 6.14,
+          "end": 6.26,
+          "confidence": 0.817
+        },
+        {
+          "text": "ります",
+          "start": 6.26,
+          "end": 6.62,
+          "confidence": 0.971
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 6.94,
+      "end": 13.58,
+      "text": "同じ度メインでデレクトリーごとに 別再度として管理上をしているサイトバリマスの",
+      "tokens": [
+        50712,
+        13089,
+        9257,
+        13127,
+        21647,
+        8040,
+        4824,
+        2474,
+        31327,
+        16680,
+        10825,
+        7588,
+        12376,
+        3384,
+        9991,
+        3193,
+        4108,
+        220,
+        16158,
+        8623,
+        13127,
+        3193,
+        8822,
+        23131,
+        13876,
+        5708,
+        5998,
+        8822,
+        22979,
+        23607,
+        8040,
+        7588,
+        18593,
+        12376,
+        13258,
+        9550,
+        2972,
+        51044
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4399989651095483,
+      "compression_ratio": 1.6122448979591837,
+      "no_speech_prob": 0.18976199626922607,
+      "confidence": 0.525,
+      "words": [
+        {
+          "text": "同",
+          "start": 6.94,
+          "end": 7.28,
+          "confidence": 0.469
+        },
+        {
+          "text": "じ",
+          "start": 7.28,
+          "end": 7.44,
+          "confidence": 0.218
+        },
+        {
+          "text": "度",
+          "start": 7.44,
+          "end": 7.62,
+          "confidence": 0.139
+        },
+        {
+          "text": "メ",
+          "start": 7.62,
+          "end": 7.74,
+          "confidence": 0.209
+        },
+        {
+          "text": "イ",
+          "start": 7.74,
+          "end": 7.82,
+          "confidence": 0.904
+        },
+        {
+          "text": "ン",
+          "start": 7.82,
+          "end": 7.84,
+          "confidence": 0.911
+        },
+        {
+          "text": "で",
+          "start": 7.84,
+          "end": 8.0,
+          "confidence": 0.979
+        },
+        {
+          "text": "デ",
+          "start": 8.0,
+          "end": 8.14,
+          "confidence": 0.37
+        },
+        {
+          "text": "レ",
+          "start": 8.14,
+          "end": 8.28,
+          "confidence": 0.674
+        },
+        {
+          "text": "ク",
+          "start": 8.28,
+          "end": 8.36,
+          "confidence": 0.974
+        },
+        {
+          "text": "ト",
+          "start": 8.36,
+          "end": 8.5,
+          "confidence": 0.979
+        },
+        {
+          "text": "リ",
+          "start": 8.5,
+          "end": 8.62,
+          "confidence": 0.96
+        },
+        {
+          "text": "ー",
+          "start": 8.62,
+          "end": 8.72,
+          "confidence": 0.701
+        },
+        {
+          "text": "ご",
+          "start": 8.72,
+          "end": 8.86,
+          "confidence": 0.267
+        },
+        {
+          "text": "と",
+          "start": 8.86,
+          "end": 9.0,
+          "confidence": 0.993
+        },
+        {
+          "text": "に",
+          "start": 9.0,
+          "end": 9.14,
+          "confidence": 0.967
+        },
+        {
+          "text": " ",
+          "start": 9.14,
+          "end": 9.34,
+          "confidence": 0.12
+        },
+        {
+          "text": "別",
+          "start": 9.34,
+          "end": 9.4,
+          "confidence": 0.527
+        },
+        {
+          "text": "再",
+          "start": 9.4,
+          "end": 9.58,
+          "confidence": 0.341
+        },
+        {
+          "text": "度",
+          "start": 9.58,
+          "end": 9.74,
+          "confidence": 0.323
+        },
+        {
+          "text": "と",
+          "start": 9.74,
+          "end": 9.92,
+          "confidence": 0.891
+        },
+        {
+          "text": "して",
+          "start": 9.92,
+          "end": 10.4,
+          "confidence": 0.998
+        },
+        {
+          "text": "管",
+          "start": 10.4,
+          "end": 10.86,
+          "confidence": 0.418
+        },
+        {
+          "text": "理",
+          "start": 10.86,
+          "end": 11.08,
+          "confidence": 1.0
+        },
+        {
+          "text": "上",
+          "start": 11.08,
+          "end": 11.36,
+          "confidence": 0.472
+        },
+        {
+          "text": "を",
+          "start": 11.36,
+          "end": 11.56,
+          "confidence": 0.987
+        },
+        {
+          "text": "して",
+          "start": 11.56,
+          "end": 11.84,
+          "confidence": 0.931
+        },
+        {
+          "text": "いる",
+          "start": 11.84,
+          "end": 12.16,
+          "confidence": 0.939
+        },
+        {
+          "text": "サ",
+          "start": 12.16,
+          "end": 12.52,
+          "confidence": 0.069
+        },
+        {
+          "text": "イ",
+          "start": 12.52,
+          "end": 12.58,
+          "confidence": 0.985
+        },
+        {
+          "text": "ト",
+          "start": 12.58,
+          "end": 12.7,
+          "confidence": 0.976
+        },
+        {
+          "text": "バ",
+          "start": 12.7,
+          "end": 12.82,
+          "confidence": 0.297
+        },
+        {
+          "text": "リ",
+          "start": 12.82,
+          "end": 12.96,
+          "confidence": 0.362
+        },
+        {
+          "text": "マ",
+          "start": 12.96,
+          "end": 13.12,
+          "confidence": 0.19
+        },
+        {
+          "text": "ス",
+          "start": 13.12,
+          "end": 13.22,
+          "confidence": 0.859
+        },
+        {
+          "text": "の",
+          "start": 13.22,
+          "end": 13.58,
+          "confidence": 0.701
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 13.68,
+      "end": 20.74,
+      "text": "サプテレクトリーごとにわけたサイトは それぞれ パブリシャーセンターに登録していくぐるニュース上では",
+      "tokens": [
+        51044,
+        23607,
+        20953,
+        22985,
+        16680,
+        10825,
+        7588,
+        12376,
+        3384,
+        9991,
+        3193,
+        4108,
+        9206,
+        7625,
+        3368,
+        23607,
+        8040,
+        7588,
+        3065,
+        47765,
+        31563,
+        4132,
+        15096,
+        239,
+        28889,
+        12376,
+        11054,
+        17233,
+        3384,
+        31223,
+        4824,
+        30736,
+        4108,
+        46246,
+        8822,
+        49394,
+        35849,
+        4895,
+        34737,
+        26167,
+        3384,
+        9550,
+        5708,
+        16719,
+        51408
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4399989651095483,
+      "compression_ratio": 1.6122448979591837,
+      "no_speech_prob": 0.18976199626922607,
+      "confidence": 0.622,
+      "words": [
+        {
+          "text": "サ",
+          "start": 13.68,
+          "end": 14.22,
+          "confidence": 0.397
+        },
+        {
+          "text": "プ",
+          "start": 14.22,
+          "end": 14.32,
+          "confidence": 0.532
+        },
+        {
+          "text": "テ",
+          "start": 14.32,
+          "end": 14.42,
+          "confidence": 0.637
+        },
+        {
+          "text": "レ",
+          "start": 14.42,
+          "end": 14.58,
+          "confidence": 0.825
+        },
+        {
+          "text": "ク",
+          "start": 14.58,
+          "end": 14.66,
+          "confidence": 0.474
+        },
+        {
+          "text": "ト",
+          "start": 14.66,
+          "end": 14.78,
+          "confidence": 0.973
+        },
+        {
+          "text": "リ",
+          "start": 14.78,
+          "end": 14.92,
+          "confidence": 0.873
+        },
+        {
+          "text": "ー",
+          "start": 14.92,
+          "end": 15.04,
+          "confidence": 0.917
+        },
+        {
+          "text": "ご",
+          "start": 15.04,
+          "end": 15.1,
+          "confidence": 0.016
+        },
+        {
+          "text": "と",
+          "start": 15.1,
+          "end": 15.38,
+          "confidence": 0.991
+        },
+        {
+          "text": "に",
+          "start": 15.38,
+          "end": 15.86,
+          "confidence": 0.493
+        },
+        {
+          "text": "わ",
+          "start": 15.86,
+          "end": 16.02,
+          "confidence": 0.756
+        },
+        {
+          "text": "け",
+          "start": 16.02,
+          "end": 16.14,
+          "confidence": 0.988
+        },
+        {
+          "text": "た",
+          "start": 16.14,
+          "end": 16.28,
+          "confidence": 0.951
+        },
+        {
+          "text": "サ",
+          "start": 16.28,
+          "end": 16.42,
+          "confidence": 0.802
+        },
+        {
+          "text": "イ",
+          "start": 16.42,
+          "end": 16.5,
+          "confidence": 0.981
+        },
+        {
+          "text": "ト",
+          "start": 16.5,
+          "end": 16.6,
+          "confidence": 0.904
+        },
+        {
+          "text": "は",
+          "start": 16.6,
+          "end": 17.08,
+          "confidence": 0.976
+        },
+        {
+          "text": " それ",
+          "start": 17.08,
+          "end": 17.44,
+          "confidence": 0.128
+        },
+        {
+          "text": "ぞ",
+          "start": 17.44,
+          "end": 17.6,
+          "confidence": 0.85
+        },
+        {
+          "text": "れ",
+          "start": 17.6,
+          "end": 17.72,
+          "confidence": 0.995
+        },
+        {
+          "text": " パ",
+          "start": 17.72,
+          "end": 17.86,
+          "confidence": 0.177
+        },
+        {
+          "text": "ブ",
+          "start": 17.86,
+          "end": 17.94,
+          "confidence": 0.941
+        },
+        {
+          "text": "リ",
+          "start": 17.94,
+          "end": 18.04,
+          "confidence": 0.991
+        },
+        {
+          "text": "シ",
+          "start": 18.04,
+          "end": 18.18,
+          "confidence": 0.755
+        },
+        {
+          "text": "ャ",
+          "start": 18.18,
+          "end": 18.26,
+          "confidence": 0.825
+        },
+        {
+          "text": "ー",
+          "start": 18.26,
+          "end": 18.42,
+          "confidence": 0.765
+        },
+        {
+          "text": "セ",
+          "start": 18.42,
+          "end": 18.44,
+          "confidence": 0.588
+        },
+        {
+          "text": "ン",
+          "start": 18.44,
+          "end": 18.52,
+          "confidence": 0.832
+        },
+        {
+          "text": "ター",
+          "start": 18.52,
+          "end": 18.6,
+          "confidence": 0.998
+        },
+        {
+          "text": "に",
+          "start": 18.6,
+          "end": 18.76,
+          "confidence": 0.858
+        },
+        {
+          "text": "登録",
+          "start": 18.76,
+          "end": 19.12,
+          "confidence": 0.902
+        },
+        {
+          "text": "して",
+          "start": 19.12,
+          "end": 19.38,
+          "confidence": 0.766
+        },
+        {
+          "text": "いく",
+          "start": 19.38,
+          "end": 19.62,
+          "confidence": 0.877
+        },
+        {
+          "text": "ぐ",
+          "start": 19.62,
+          "end": 19.78,
+          "confidence": 0.221
+        },
+        {
+          "text": "る",
+          "start": 19.78,
+          "end": 19.9,
+          "confidence": 0.85
+        },
+        {
+          "text": "ニ",
+          "start": 19.9,
+          "end": 20.02,
+          "confidence": 0.68
+        },
+        {
+          "text": "ュ",
+          "start": 20.02,
+          "end": 20.14,
+          "confidence": 0.996
+        },
+        {
+          "text": "ー",
+          "start": 20.14,
+          "end": 20.16,
+          "confidence": 0.989
+        },
+        {
+          "text": "ス",
+          "start": 20.16,
+          "end": 20.22,
+          "confidence": 0.982
+        },
+        {
+          "text": "上",
+          "start": 20.22,
+          "end": 20.4,
+          "confidence": 0.236
+        },
+        {
+          "text": "では",
+          "start": 20.4,
+          "end": 20.74,
+          "confidence": 0.763
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 2088,
+      "start": 20.9,
+      "end": 27.0,
+      "text": "サイトとして認識され パブリコンアイコンはサイトボトフのものが 正しく表示されます",
+      "tokens": [
+        50364,
+        23607,
+        8040,
+        7588,
+        3193,
+        8822,
+        22041,
+        43143,
+        6722,
+        4132,
+        15096,
+        239,
+        28889,
+        12376,
+        18066,
+        4824,
+        12817,
+        8040,
+        18066,
+        4824,
+        3065,
+        23607,
+        8040,
+        7588,
+        37626,
+        7588,
+        17320,
+        2972,
+        44726,
+        5142,
+        220,
+        15789,
+        26568,
+        40053,
+        6722,
+        4132,
+        5368,
+        50684
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.35158648256395686,
+      "compression_ratio": 1.6926406926406927,
+      "no_speech_prob": 0.06365812569856644,
+      "confidence": 0.389,
+      "words": [
+        {
+          "text": "サ",
+          "start": 20.9,
+          "end": 21.26,
+          "confidence": 0.002
+        },
+        {
+          "text": "イ",
+          "start": 21.26,
+          "end": 21.34,
+          "confidence": 0.939
+        },
+        {
+          "text": "ト",
+          "start": 21.34,
+          "end": 21.44,
+          "confidence": 0.379
+        },
+        {
+          "text": "と",
+          "start": 21.44,
+          "end": 21.58,
+          "confidence": 0.831
+        },
+        {
+          "text": "して",
+          "start": 21.58,
+          "end": 21.8,
+          "confidence": 0.981
+        },
+        {
+          "text": "認",
+          "start": 21.8,
+          "end": 22.08,
+          "confidence": 0.179
+        },
+        {
+          "text": "識",
+          "start": 22.08,
+          "end": 22.2,
+          "confidence": 0.986
+        },
+        {
+          "text": "さ",
+          "start": 22.2,
+          "end": 22.34,
+          "confidence": 0.982
+        },
+        {
+          "text": "れ",
+          "start": 22.34,
+          "end": 22.64,
+          "confidence": 0.948
+        },
+        {
+          "text": " パ",
+          "start": 22.64,
+          "end": 22.86,
+          "confidence": 0.141
+        },
+        {
+          "text": "ブ",
+          "start": 22.86,
+          "end": 23.0,
+          "confidence": 0.051
+        },
+        {
+          "text": "リ",
+          "start": 23.0,
+          "end": 23.18,
+          "confidence": 0.007
+        },
+        {
+          "text": "コ",
+          "start": 23.18,
+          "end": 23.22,
+          "confidence": 0.817
+        },
+        {
+          "text": "ン",
+          "start": 23.22,
+          "end": 23.3,
+          "confidence": 0.887
+        },
+        {
+          "text": "ア",
+          "start": 23.3,
+          "end": 23.46,
+          "confidence": 0.107
+        },
+        {
+          "text": "イ",
+          "start": 23.46,
+          "end": 23.52,
+          "confidence": 0.957
+        },
+        {
+          "text": "コ",
+          "start": 23.52,
+          "end": 23.64,
+          "confidence": 0.308
+        },
+        {
+          "text": "ン",
+          "start": 23.64,
+          "end": 23.86,
+          "confidence": 0.893
+        },
+        {
+          "text": "は",
+          "start": 23.86,
+          "end": 23.88,
+          "confidence": 0.834
+        },
+        {
+          "text": "サ",
+          "start": 23.88,
+          "end": 24.04,
+          "confidence": 0.642
+        },
+        {
+          "text": "イ",
+          "start": 24.04,
+          "end": 24.16,
+          "confidence": 0.997
+        },
+        {
+          "text": "ト",
+          "start": 24.16,
+          "end": 24.24,
+          "confidence": 0.989
+        },
+        {
+          "text": "ボ",
+          "start": 24.24,
+          "end": 24.38,
+          "confidence": 0.588
+        },
+        {
+          "text": "ト",
+          "start": 24.38,
+          "end": 24.52,
+          "confidence": 0.861
+        },
+        {
+          "text": "フ",
+          "start": 24.52,
+          "end": 24.66,
+          "confidence": 0.037
+        },
+        {
+          "text": "の",
+          "start": 24.66,
+          "end": 24.72,
+          "confidence": 0.66
+        },
+        {
+          "text": "もの",
+          "start": 24.72,
+          "end": 24.9,
+          "confidence": 0.501
+        },
+        {
+          "text": "が",
+          "start": 24.9,
+          "end": 25.08,
+          "confidence": 0.338
+        },
+        {
+          "text": " ",
+          "start": 25.08,
+          "end": 25.32,
+          "confidence": 0.283
+        },
+        {
+          "text": "正",
+          "start": 25.32,
+          "end": 25.4,
+          "confidence": 0.631
+        },
+        {
+          "text": "しく",
+          "start": 25.4,
+          "end": 25.66,
+          "confidence": 0.979
+        },
+        {
+          "text": "表示",
+          "start": 25.66,
+          "end": 26.0,
+          "confidence": 0.665
+        },
+        {
+          "text": "さ",
+          "start": 26.0,
+          "end": 26.28,
+          "confidence": 0.993
+        },
+        {
+          "text": "れ",
+          "start": 26.28,
+          "end": 26.6,
+          "confidence": 0.986
+        },
+        {
+          "text": "ます",
+          "start": 26.6,
+          "end": 27.0,
+          "confidence": 0.888
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 2088,
+      "start": 27.28,
+      "end": 33.8,
+      "text": "しかし ルグル検査結果のニュースタブでは パブリコンサイトメイショー機ともに 正しくない医療時にいいなります",
+      "tokens": [
+        50684,
+        32156,
+        2849,
+        220,
+        9405,
+        23839,
+        9405,
+        38739,
+        250,
+        17238,
+        119,
+        35181,
+        2972,
+        34737,
+        26167,
+        3384,
+        9550,
+        12144,
+        28889,
+        16719,
+        15096,
+        239,
+        28889,
+        12376,
+        18066,
+        4824,
+        23607,
+        8040,
+        7588,
+        21647,
+        8040,
+        43891,
+        3384,
+        17543,
+        3193,
+        4801,
+        4108,
+        220,
+        15789,
+        26568,
+        9311,
+        9937,
+        119,
+        6651,
+        224,
+        6611,
+        4108,
+        13806,
+        3203,
+        19420,
+        51024
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.35158648256395686,
+      "compression_ratio": 1.6926406926406927,
+      "no_speech_prob": 0.06365812569856644,
+      "confidence": 0.502,
+      "words": [
+        {
+          "text": "しか",
+          "start": 27.28,
+          "end": 27.58,
+          "confidence": 0.909
+        },
+        {
+          "text": "し",
+          "start": 27.58,
+          "end": 27.72,
+          "confidence": 0.989
+        },
+        {
+          "text": " ",
+          "start": 27.72,
+          "end": 27.86,
+          "confidence": 0.065
+        },
+        {
+          "text": "ル",
+          "start": 27.86,
+          "end": 27.9,
+          "confidence": 0.236
+        },
+        {
+          "text": "グ",
+          "start": 27.9,
+          "end": 28.0,
+          "confidence": 0.538
+        },
+        {
+          "text": "ル",
+          "start": 28.0,
+          "end": 28.14,
+          "confidence": 0.989
+        },
+        {
+          "text": "検",
+          "start": 28.14,
+          "end": 28.32,
+          "confidence": 0.565
+        },
+        {
+          "text": "査",
+          "start": 28.32,
+          "end": 28.46,
+          "confidence": 0.728
+        },
+        {
+          "text": "結果",
+          "start": 28.46,
+          "end": 28.72,
+          "confidence": 0.976
+        },
+        {
+          "text": "の",
+          "start": 28.72,
+          "end": 28.92,
+          "confidence": 0.96
+        },
+        {
+          "text": "ニ",
+          "start": 28.92,
+          "end": 29.06,
+          "confidence": 0.777
+        },
+        {
+          "text": "ュ",
+          "start": 29.06,
+          "end": 29.14,
+          "confidence": 0.995
+        },
+        {
+          "text": "ー",
+          "start": 29.14,
+          "end": 29.2,
+          "confidence": 0.98
+        },
+        {
+          "text": "ス",
+          "start": 29.2,
+          "end": 29.26,
+          "confidence": 0.971
+        },
+        {
+          "text": "タ",
+          "start": 29.26,
+          "end": 29.34,
+          "confidence": 0.806
+        },
+        {
+          "text": "ブ",
+          "start": 29.34,
+          "end": 29.44,
+          "confidence": 0.685
+        },
+        {
+          "text": "では",
+          "start": 29.44,
+          "end": 29.68,
+          "confidence": 0.942
+        },
+        {
+          "text": " パ",
+          "start": 29.68,
+          "end": 30.02,
+          "confidence": 0.123
+        },
+        {
+          "text": "ブ",
+          "start": 30.02,
+          "end": 30.14,
+          "confidence": 0.041
+        },
+        {
+          "text": "リ",
+          "start": 30.14,
+          "end": 30.32,
+          "confidence": 0.021
+        },
+        {
+          "text": "コ",
+          "start": 30.32,
+          "end": 30.34,
+          "confidence": 0.89
+        },
+        {
+          "text": "ン",
+          "start": 30.34,
+          "end": 30.42,
+          "confidence": 0.918
+        },
+        {
+          "text": "サ",
+          "start": 30.42,
+          "end": 30.54,
+          "confidence": 0.426
+        },
+        {
+          "text": "イ",
+          "start": 30.54,
+          "end": 30.62,
+          "confidence": 0.979
+        },
+        {
+          "text": "ト",
+          "start": 30.62,
+          "end": 30.72,
+          "confidence": 0.956
+        },
+        {
+          "text": "メ",
+          "start": 30.72,
+          "end": 30.86,
+          "confidence": 0.251
+        },
+        {
+          "text": "イ",
+          "start": 30.86,
+          "end": 30.92,
+          "confidence": 0.622
+        },
+        {
+          "text": "ショ",
+          "start": 30.92,
+          "end": 31.02,
+          "confidence": 0.416
+        },
+        {
+          "text": "ー",
+          "start": 31.02,
+          "end": 31.08,
+          "confidence": 0.618
+        },
+        {
+          "text": "機",
+          "start": 31.08,
+          "end": 31.24,
+          "confidence": 0.126
+        },
+        {
+          "text": "と",
+          "start": 31.24,
+          "end": 31.42,
+          "confidence": 0.357
+        },
+        {
+          "text": "も",
+          "start": 31.42,
+          "end": 31.54,
+          "confidence": 0.81
+        },
+        {
+          "text": "に",
+          "start": 31.54,
+          "end": 31.66,
+          "confidence": 0.919
+        },
+        {
+          "text": " ",
+          "start": 31.66,
+          "end": 31.8,
+          "confidence": 0.402
+        },
+        {
+          "text": "正",
+          "start": 31.8,
+          "end": 31.96,
+          "confidence": 0.437
+        },
+        {
+          "text": "しく",
+          "start": 31.96,
+          "end": 32.18,
+          "confidence": 0.998
+        },
+        {
+          "text": "ない",
+          "start": 32.18,
+          "end": 32.4,
+          "confidence": 0.981
+        },
+        {
+          "text": "医",
+          "start": 32.4,
+          "end": 32.6,
+          "confidence": 0.234
+        },
+        {
+          "text": "療",
+          "start": 32.6,
+          "end": 32.76,
+          "confidence": 0.686
+        },
+        {
+          "text": "時",
+          "start": 32.76,
+          "end": 32.96,
+          "confidence": 0.452
+        },
+        {
+          "text": "に",
+          "start": 32.96,
+          "end": 33.12,
+          "confidence": 0.925
+        },
+        {
+          "text": "いい",
+          "start": 33.12,
+          "end": 33.36,
+          "confidence": 0.577
+        },
+        {
+          "text": "な",
+          "start": 33.36,
+          "end": 33.48,
+          "confidence": 0.807
+        },
+        {
+          "text": "ります",
+          "start": 33.48,
+          "end": 33.8,
+          "confidence": 0.941
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 2088,
+      "start": 34.04,
+      "end": 40.36,
+      "text": "こちらいたいです ものではありません パブリコンはサブテレクトリーごとに設定した",
+      "tokens": [
+        51024,
+        34395,
+        17679,
+        1764,
+        4767,
+        32505,
+        2972,
+        16719,
+        14498,
+        30250,
+        15096,
+        239,
+        28889,
+        12376,
+        18066,
+        4824,
+        3065,
+        23607,
+        28889,
+        22985,
+        16680,
+        10825,
+        7588,
+        12376,
+        3384,
+        9991,
+        3193,
+        4108,
+        39035,
+        12088,
+        8533,
+        51388
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.35158648256395686,
+      "compression_ratio": 1.6926406926406927,
+      "no_speech_prob": 0.06365812569856644,
+      "confidence": 0.364,
+      "words": [
+        {
+          "text": "こちら",
+          "start": 34.04,
+          "end": 34.54,
+          "confidence": 0.408
+        },
+        {
+          "text": "いた",
+          "start": 34.54,
+          "end": 34.82,
+          "confidence": 0.254
+        },
+        {
+          "text": "い",
+          "start": 34.82,
+          "end": 34.98,
+          "confidence": 0.11
+        },
+        {
+          "text": "です",
+          "start": 34.98,
+          "end": 35.04,
+          "confidence": 0.021
+        },
+        {
+          "text": " も",
+          "start": 35.04,
+          "end": 35.18,
+          "confidence": 0.009
+        },
+        {
+          "text": "の",
+          "start": 35.18,
+          "end": 35.28,
+          "confidence": 0.812
+        },
+        {
+          "text": "では",
+          "start": 35.28,
+          "end": 35.5,
+          "confidence": 0.995
+        },
+        {
+          "text": "あり",
+          "start": 35.5,
+          "end": 35.72,
+          "confidence": 0.981
+        },
+        {
+          "text": "ません",
+          "start": 35.72,
+          "end": 36.18,
+          "confidence": 0.999
+        },
+        {
+          "text": " パ",
+          "start": 36.18,
+          "end": 36.9,
+          "confidence": 0.273
+        },
+        {
+          "text": "ブ",
+          "start": 36.9,
+          "end": 37.02,
+          "confidence": 0.011
+        },
+        {
+          "text": "リ",
+          "start": 37.02,
+          "end": 37.1,
+          "confidence": 0.237
+        },
+        {
+          "text": "コ",
+          "start": 37.1,
+          "end": 37.18,
+          "confidence": 0.951
+        },
+        {
+          "text": "ン",
+          "start": 37.18,
+          "end": 37.84,
+          "confidence": 0.832
+        },
+        {
+          "text": "は",
+          "start": 37.84,
+          "end": 37.86,
+          "confidence": 0.95
+        },
+        {
+          "text": "サ",
+          "start": 37.86,
+          "end": 38.22,
+          "confidence": 0.307
+        },
+        {
+          "text": "ブ",
+          "start": 38.22,
+          "end": 38.32,
+          "confidence": 0.98
+        },
+        {
+          "text": "テ",
+          "start": 38.32,
+          "end": 38.42,
+          "confidence": 0.318
+        },
+        {
+          "text": "レ",
+          "start": 38.42,
+          "end": 38.56,
+          "confidence": 0.394
+        },
+        {
+          "text": "ク",
+          "start": 38.56,
+          "end": 38.66,
+          "confidence": 0.751
+        },
+        {
+          "text": "ト",
+          "start": 38.66,
+          "end": 38.78,
+          "confidence": 0.731
+        },
+        {
+          "text": "リ",
+          "start": 38.78,
+          "end": 38.92,
+          "confidence": 0.988
+        },
+        {
+          "text": "ー",
+          "start": 38.92,
+          "end": 38.96,
+          "confidence": 0.528
+        },
+        {
+          "text": "ご",
+          "start": 38.96,
+          "end": 39.08,
+          "confidence": 0.051
+        },
+        {
+          "text": "と",
+          "start": 39.08,
+          "end": 39.24,
+          "confidence": 0.973
+        },
+        {
+          "text": "に",
+          "start": 39.24,
+          "end": 39.52,
+          "confidence": 0.978
+        },
+        {
+          "text": "設",
+          "start": 39.52,
+          "end": 39.84,
+          "confidence": 0.621
+        },
+        {
+          "text": "定",
+          "start": 39.84,
+          "end": 40.04,
+          "confidence": 0.996
+        },
+        {
+          "text": "した",
+          "start": 40.04,
+          "end": 40.36,
+          "confidence": 0.894
+        }
+      ]
+    }
+  ],
+  "language": "Japanese"
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_auto/bonjour.wav.words.json b/tests/expected/tiny_auto/bonjour.wav.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..d20b7b91e5bc59af96ae7a92889c21d219960337
--- /dev/null
+++ b/tests/expected/tiny_auto/bonjour.wav.words.json
@@ -0,0 +1,133 @@
+{
+  "text": " Bonjour !",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.14,
+      "end": 0.96,
+      "text": " Bonjour !",
+      "tokens": [
+        50364,
+        25431,
+        2298,
+        50414
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6977285861968994,
+      "compression_ratio": 0.5294117647058824,
+      "no_speech_prob": 0.019094161689281464,
+      "confidence": 0.829,
+      "words": [
+        {
+          "text": "Bonjour !",
+          "start": 0.14,
+          "end": 0.96,
+          "confidence": 0.829
+        }
+      ]
+    }
+  ],
+  "language": "fr",
+  "language_probs": {
+    "en": 0.007364001125097275,
+    "zh": 0.041395243257284164,
+    "de": 0.0015925770858302712,
+    "es": 0.0021767946891486645,
+    "ru": 0.10325776785612106,
+    "ko": 0.006601048167794943,
+    "fr": 0.4052142798900604,
+    "ja": 0.0019210146274417639,
+    "pt": 0.33332017064094543,
+    "tr": 0.007421758491545916,
+    "pl": 0.05315254256129265,
+    "ca": 6.396045500878245e-05,
+    "nl": 0.0077174073085188866,
+    "ar": 0.001450057839974761,
+    "sv": 0.0062011112459003925,
+    "it": 0.0026052820030599833,
+    "id": 0.0002559504355303943,
+    "hi": 0.00036094794631935656,
+    "fi": 5.62248460482806e-05,
+    "vi": 0.0011927851010113955,
+    "he": 0.0003260892990510911,
+    "uk": 0.0017354920273646712,
+    "el": 0.00019095065363217145,
+    "ms": 0.0005904714344069362,
+    "cs": 0.0007178307278081775,
+    "ro": 0.0009003614541143179,
+    "da": 0.0001010177584248595,
+    "hu": 8.880029781721532e-05,
+    "ta": 7.943290256662294e-06,
+    "no": 0.000378270196961239,
+    "th": 5.119330307934433e-05,
+    "ur": 0.00023213693930301815,
+    "hr": 0.0004253006190992892,
+    "bg": 0.0004319981671869755,
+    "lt": 0.0001386153162457049,
+    "la": 0.0008864026167429984,
+    "mi": 5.62248460482806e-05,
+    "ml": 3.6652261314884527e-06,
+    "cy": 0.0005050569889135659,
+    "sk": 0.0006384518346749246,
+    "te": 1.9506836906657554e-05,
+    "fa": 0.00011627071216935292,
+    "lv": 2.100969140883535e-05,
+    "bn": 3.5322318581165746e-05,
+    "sr": 0.00010141311940969899,
+    "az": 3.2924017432378605e-05,
+    "sl": 0.0004972267779521644,
+    "kn": 1.1376539532648167e-06,
+    "et": 3.886401827912778e-06,
+    "mk": 4.178275776212104e-05,
+    "br": 0.001669006422162056,
+    "eu": 5.513735595741309e-05,
+    "is": 9.506873539066873e-06,
+    "hy": 4.2434403439983726e-06,
+    "ne": 3.3047945180442184e-06,
+    "mn": 3.559935430530459e-05,
+    "bs": 0.0002661463222466409,
+    "kk": 1.3045214473095257e-05,
+    "sq": 0.00017049974121619016,
+    "sw": 3.068856312893331e-05,
+    "gl": 0.00019395769049879164,
+    "mr": 2.1512002490453597e-07,
+    "pa": 2.8322670004854444e-06,
+    "si": 2.838228283508215e-05,
+    "km": 0.00015223913942463696,
+    "sn": 0.00028110656421631575,
+    "yo": 0.0003637789050117135,
+    "so": 8.307013672492758e-07,
+    "af": 2.2277508833212778e-05,
+    "oc": 0.0004253006190992892,
+    "ka": 1.5580286572003388e-06,
+    "be": 0.00017318472964689136,
+    "tg": 2.0718216831028258e-07,
+    "sd": 3.5322318581165746e-05,
+    "gu": 8.50400795116002e-07,
+    "am": 2.665870624696254e-06,
+    "yi": 2.8604887120309286e-05,
+    "lo": 1.2943694855493959e-05,
+    "uz": 1.491831658206877e-09,
+    "fo": 5.892313129152171e-05,
+    "ht": 0.00017938153177965432,
+    "ps": 9.036155461217277e-06,
+    "tk": 1.281216821524822e-08,
+    "nn": 0.0024094919208437204,
+    "mt": 8.099957085505594e-06,
+    "sa": 5.600564327323809e-05,
+    "lb": 6.14076256510998e-08,
+    "my": 3.849208223982714e-05,
+    "bo": 9.126193617703393e-05,
+    "tl": 6.483123797806911e-06,
+    "mg": 1.4993576158417454e-08,
+    "as": 2.3480320123780984e-06,
+    "tt": 1.376765368377164e-07,
+    "haw": 0.0002519823028706014,
+    "ln": 2.1592100893030874e-05,
+    "ha": 7.02048819078982e-09,
+    "ba": 1.902783886009729e-08,
+    "jw": 0.0002855333441402763,
+    "su": 9.264376821249698e-09
+  }
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_auto/bonjour_vous_allez_bien.mp3.words.json b/tests/expected/tiny_auto/bonjour_vous_allez_bien.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..8ba2f58d60ffd0cfbf7a7dd0c3fc0e4187d7ddeb
--- /dev/null
+++ b/tests/expected/tiny_auto/bonjour_vous_allez_bien.mp3.words.json
@@ -0,0 +1,255 @@
+{
+  "text": " Боже улыл! Эскому зарегиан! Боже улыл! Эскому зарегиан!",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.44,
+      "end": 1.88,
+      "text": " Боже улыл!",
+      "tokens": [
+        50364,
+        5697,
+        9292,
+        1595,
+        30975,
+        693,
+        0,
+        50464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9443809107730263,
+      "compression_ratio": 0.8166666666666667,
+      "no_speech_prob": 0.04302893579006195,
+      "confidence": 0.317,
+      "words": [
+        {
+          "text": "Боже",
+          "start": 0.44,
+          "end": 0.86,
+          "confidence": 0.423
+        },
+        {
+          "text": "улыл!",
+          "start": 0.86,
+          "end": 1.88,
+          "confidence": 0.261
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 1.88,
+      "end": 3.14,
+      "text": " Эскому зарегиан!",
+      "tokens": [
+        50464,
+        5381,
+        4218,
+        4161,
+        17821,
+        4953,
+        435,
+        1416,
+        0,
+        50564
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9443809107730263,
+      "compression_ratio": 0.8166666666666667,
+      "no_speech_prob": 0.04302893579006195,
+      "confidence": 0.395,
+      "words": [
+        {
+          "text": "Эскому",
+          "start": 1.88,
+          "end": 2.3,
+          "confidence": 0.286
+        },
+        {
+          "text": "зарегиан!",
+          "start": 2.3,
+          "end": 3.14,
+          "confidence": 0.505
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 3000,
+      "start": 32.98,
+      "end": 34.02,
+      "text": " Боже улыл!",
+      "tokens": [
+        50364,
+        5697,
+        9292,
+        1595,
+        30975,
+        693,
+        0,
+        50564
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3071819355613307,
+      "compression_ratio": 0.8166666666666667,
+      "no_speech_prob": 0.2232234627008438,
+      "confidence": 0.577,
+      "words": [
+        {
+          "text": "Боже",
+          "start": 32.98,
+          "end": 33.36,
+          "confidence": 0.446
+        },
+        {
+          "text": "улыл!",
+          "start": 33.36,
+          "end": 34.02,
+          "confidence": 0.686
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 3000,
+      "start": 34.42,
+      "end": 35.72,
+      "text": " Эскому зарегиан!",
+      "tokens": [
+        50564,
+        5381,
+        4218,
+        4161,
+        17821,
+        4953,
+        435,
+        1416,
+        0,
+        50664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3071819355613307,
+      "compression_ratio": 0.8166666666666667,
+      "no_speech_prob": 0.2232234627008438,
+      "confidence": 0.849,
+      "words": [
+        {
+          "text": "Эскому",
+          "start": 34.42,
+          "end": 34.84,
+          "confidence": 0.691
+        },
+        {
+          "text": "зарегиан!",
+          "start": 34.84,
+          "end": 35.72,
+          "confidence": 0.992
+        }
+      ]
+    }
+  ],
+  "language": "ru",
+  "language_probs": {
+    "en": 0.05109040066599846,
+    "zh": 0.0006792841013520956,
+    "de": 0.0007287654443643987,
+    "es": 0.01429856475442648,
+    "ru": 0.5119792819023132,
+    "ko": 0.0008257994195446372,
+    "fr": 0.021297650411725044,
+    "ja": 0.001567091909237206,
+    "pt": 0.2036512941122055,
+    "tr": 0.0052192131988704205,
+    "pl": 0.10648154467344284,
+    "ca": 0.00012226558465044945,
+    "nl": 0.008672517724335194,
+    "ar": 0.0009284712723456323,
+    "sv": 0.0007879833574406803,
+    "it": 0.0003537872398737818,
+    "id": 0.00035935858613811433,
+    "hi": 3.0913583032088354e-05,
+    "fi": 7.021122291916981e-05,
+    "vi": 3.714352715178393e-05,
+    "he": 0.00010457931057317182,
+    "uk": 0.00486484169960022,
+    "el": 0.00486484169960022,
+    "ms": 0.0002489204052835703,
+    "cs": 0.0018037117552012205,
+    "ro": 0.0008388038841076195,
+    "da": 1.0725262654887047e-05,
+    "hu": 0.0007637396920472383,
+    "ta": 3.6562209970725235e-06,
+    "no": 0.0001316852285526693,
+    "th": 1.203341184918827e-06,
+    "ur": 0.00010581205424387008,
+    "hr": 0.0008453827467747033,
+    "bg": 0.007534814067184925,
+    "lt": 0.00010581205424387008,
+    "la": 0.002408271422609687,
+    "mi": 6.268220658967039e-06,
+    "ml": 4.929601345793344e-06,
+    "cy": 0.000450736639322713,
+    "sk": 0.0019200412789359689,
+    "te": 1.409809283359209e-05,
+    "fa": 6.318325904430822e-05,
+    "lv": 9.672004671301693e-05,
+    "bn": 2.209294143540319e-05,
+    "sr": 0.00021542265312746167,
+    "az": 5.341388168744743e-05,
+    "sl": 0.0004969748551957309,
+    "kn": 5.667552613886073e-07,
+    "et": 3.4956110539496876e-06,
+    "mk": 0.0002403213584329933,
+    "br": 0.0026866206899285316,
+    "eu": 4.677075776271522e-05,
+    "is": 5.4680560424458236e-05,
+    "hy": 4.1673874875414185e-06,
+    "ne": 1.0363322644479922e-06,
+    "mn": 9.958069313142914e-06,
+    "bs": 0.00044374860590323806,
+    "kk": 1.220088051923085e-05,
+    "sq": 0.00021881508291698992,
+    "sw": 1.3558002137870062e-05,
+    "gl": 0.0006635484169237316,
+    "mr": 8.262362030109216e-07,
+    "pa": 1.8348761159359128e-06,
+    "si": 0.00010457931057317182,
+    "km": 0.00046869192738085985,
+    "sn": 0.00016134412726387382,
+    "yo": 0.00029444784740917385,
+    "so": 4.1667655636956624e-07,
+    "af": 1.9119846911053173e-05,
+    "oc": 0.0002670526155270636,
+    "ka": 6.517918791359989e-06,
+    "be": 0.00028762698639184237,
+    "tg": 3.018845688984584e-07,
+    "sd": 1.2836458154197317e-05,
+    "gu": 2.184769272162157e-07,
+    "am": 1.0373449867984164e-06,
+    "yi": 0.00014072682824917138,
+    "lo": 9.43591373925301e-07,
+    "uz": 1.9715000743047995e-09,
+    "fo": 8.352842087333556e-06,
+    "ht": 4.658841862692498e-05,
+    "ps": 3.831686626654118e-06,
+    "tk": 1.198291865733836e-08,
+    "nn": 0.03350590169429779,
+    "mt": 1.2393017641443294e-05,
+    "sa": 6.752147601218894e-05,
+    "lb": 8.849924171272505e-08,
+    "my": 2.0073605355719337e-06,
+    "bo": 4.703858849097742e-06,
+    "tl": 7.429171546391444e-06,
+    "mg": 8.09222822084621e-09,
+    "as": 1.8674148805075674e-06,
+    "tt": 9.030228511619498e-07,
+    "haw": 0.0020279677119106054,
+    "ln": 7.2146781349147204e-06,
+    "ha": 3.7193925717105003e-09,
+    "ba": 1.6799896584984708e-08,
+    "jw": 0.0009730295278131962,
+    "su": 1.2147872929801906e-08
+  }
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_auto/empty.mp3.words.json b/tests/expected/tiny_auto/empty.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..44c624e28480469c66fd29b1192e68a3a82f1904
--- /dev/null
+++ b/tests/expected/tiny_auto/empty.mp3.words.json
@@ -0,0 +1,106 @@
+{
+  "text": "",
+  "segments": [],
+  "language": "en",
+  "language_probs": {
+    "en": 0.481865257024765,
+    "zh": 0.018109099939465523,
+    "de": 0.013043494895100594,
+    "es": 0.011969382874667645,
+    "ru": 0.01839427463710308,
+    "ko": 0.05078822001814842,
+    "fr": 0.019888954237103462,
+    "ja": 0.06370270252227783,
+    "pt": 0.009542823769152164,
+    "tr": 0.002145992126315832,
+    "pl": 0.01648852229118347,
+    "ca": 0.00040956982411444187,
+    "nl": 0.008226429112255573,
+    "ar": 0.001984718255698681,
+    "sv": 0.0016844086349010468,
+    "it": 0.0077886260114610195,
+    "id": 0.0019387423526495695,
+    "hi": 0.0013964237878099084,
+    "fi": 0.0012615637388080359,
+    "vi": 0.0008145267493091524,
+    "he": 0.000482591160107404,
+    "uk": 0.000624519307166338,
+    "el": 0.0008145267493091524,
+    "ms": 0.002820853376761079,
+    "cs": 0.0010377340950071812,
+    "ro": 0.0007533141179010272,
+    "da": 0.00025036497390829027,
+    "hu": 0.0009672744781710207,
+    "ta": 0.00022094632731750607,
+    "no": 0.00029270630329847336,
+    "th": 0.0009748608572408557,
+    "ur": 0.0001483363303123042,
+    "hr": 0.00012887685443274677,
+    "bg": 0.0003877728886436671,
+    "lt": 2.365429827477783e-05,
+    "la": 0.015856856480240822,
+    "mi": 0.0006443436723202467,
+    "ml": 0.0004979101940989494,
+    "cy": 0.00882566999644041,
+    "sk": 0.00016940542263910174,
+    "te": 0.00014603660383727401,
+    "fa": 0.0002665121282916516,
+    "lv": 3.233158713555895e-05,
+    "bn": 0.0007711784564889967,
+    "sr": 4.023731162305921e-05,
+    "az": 2.9209157219156623e-05,
+    "sl": 0.00010274958185618743,
+    "kn": 1.463002718082862e-05,
+    "et": 2.9901832022005692e-05,
+    "mk": 1.9996876289951615e-05,
+    "br": 0.0027127882931381464,
+    "eu": 0.00014718198508489877,
+    "is": 4.087095658178441e-05,
+    "hy": 4.023731162305921e-05,
+    "ne": 3.414896491449326e-05,
+    "mn": 0.00015667440311517566,
+    "bs": 8.720243931747973e-05,
+    "kk": 1.0293509149050806e-05,
+    "sq": 3.037271926586982e-05,
+    "sw": 6.92527974024415e-05,
+    "gl": 0.000482591160107404,
+    "mr": 4.471296415431425e-05,
+    "pa": 1.7716249203658663e-05,
+    "si": 0.0001483363303123042,
+    "km": 0.0005912830238230526,
+    "sn": 0.00034489232348278165,
+    "yo": 0.00016677902021910995,
+    "so": 2.9491400255210465e-06,
+    "af": 6.111538095865399e-05,
+    "oc": 0.00018898540292866528,
+    "ka": 2.6182920919382013e-05,
+    "be": 6.0167876654304564e-05,
+    "tg": 1.8398510803763202e-07,
+    "sd": 3.1092986318981275e-05,
+    "gu": 1.0333797035855241e-05,
+    "am": 5.155722647032235e-06,
+    "yi": 8.25616079964675e-05,
+    "lo": 1.0914664926531259e-05,
+    "uz": 2.2382069531090565e-09,
+    "fo": 0.00017207316705025733,
+    "ht": 7.089507562341169e-05,
+    "ps": 1.2128717571613379e-05,
+    "tk": 1.972132324112863e-08,
+    "nn": 0.21719369292259216,
+    "mt": 1.3320791367732454e-05,
+    "sa": 0.0002484166470821947,
+    "lb": 1.790224075648439e-07,
+    "my": 0.00010274958185618743,
+    "bo": 4.4887969124829397e-05,
+    "tl": 0.0003642789088189602,
+    "mg": 2.4045375468517705e-08,
+    "as": 1.7441585441702046e-05,
+    "tt": 9.323910887815146e-08,
+    "haw": 0.0036504557356238365,
+    "ln": 6.170591859699925e-06,
+    "ha": 2.120961006824018e-08,
+    "ba": 1.7063216617430044e-08,
+    "jw": 0.003679086221382022,
+    "su": 3.741536147572333e-08
+  }
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_auto/gaenswein15.mp3.words.json b/tests/expected/tiny_auto/gaenswein15.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..bf47cbea2c554abe6c88811b63d56b929eca013b
--- /dev/null
+++ b/tests/expected/tiny_auto/gaenswein15.mp3.words.json
@@ -0,0 +1,438 @@
+{
+  "text": " Wie wieder zu dazu ist Meshfuchs von 1962 als Meshale für die außerordentliche Form des grullischen Rätus ist dann nicht so weitergegangen wie sich Papstbälle dick das gewünscht hatte. Das hat er als Meshale im Rätus",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.92,
+      "end": 8.04,
+      "text": " Wie wieder zu dazu ist Meshfuchs von 1962 als Meshale für die außerordentliche Form des grullischen",
+      "tokens": [
+        50364,
+        9233,
+        6216,
+        2164,
+        13034,
+        1418,
+        376,
+        14935,
+        69,
+        37503,
+        2957,
+        39498,
+        3907,
+        376,
+        14935,
+        1220,
+        2959,
+        978,
+        39428,
+        765,
+        7698,
+        68,
+        10126,
+        730,
+        677,
+        858,
+        6282,
+        50764
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6858572118422565,
+      "compression_ratio": 1.3293413173652695,
+      "no_speech_prob": 0.04553895816206932,
+      "confidence": 0.503,
+      "words": [
+        {
+          "text": "Wie",
+          "start": 0.92,
+          "end": 1.1,
+          "confidence": 0.459
+        },
+        {
+          "text": "wieder",
+          "start": 1.1,
+          "end": 1.4,
+          "confidence": 0.891
+        },
+        {
+          "text": "zu",
+          "start": 1.4,
+          "end": 1.6,
+          "confidence": 0.283
+        },
+        {
+          "text": "dazu",
+          "start": 1.6,
+          "end": 1.92,
+          "confidence": 0.173
+        },
+        {
+          "text": "ist",
+          "start": 1.92,
+          "end": 2.14,
+          "confidence": 0.649
+        },
+        {
+          "text": "Meshfuchs",
+          "start": 2.14,
+          "end": 2.74,
+          "confidence": 0.333
+        },
+        {
+          "text": "von",
+          "start": 2.74,
+          "end": 3.22,
+          "confidence": 0.626
+        },
+        {
+          "text": "1962",
+          "start": 3.22,
+          "end": 4.84,
+          "confidence": 0.182
+        },
+        {
+          "text": "als",
+          "start": 4.84,
+          "end": 5.24,
+          "confidence": 0.883
+        },
+        {
+          "text": "Meshale",
+          "start": 5.24,
+          "end": 5.78,
+          "confidence": 0.389
+        },
+        {
+          "text": "für",
+          "start": 5.78,
+          "end": 5.92,
+          "confidence": 0.935
+        },
+        {
+          "text": "die",
+          "start": 5.92,
+          "end": 6.08,
+          "confidence": 0.973
+        },
+        {
+          "text": "außerordentliche",
+          "start": 6.08,
+          "end": 7.04,
+          "confidence": 0.898
+        },
+        {
+          "text": "Form",
+          "start": 7.04,
+          "end": 7.4,
+          "confidence": 0.64
+        },
+        {
+          "text": "des",
+          "start": 7.4,
+          "end": 7.62,
+          "confidence": 0.974
+        },
+        {
+          "text": "grullischen",
+          "start": 7.62,
+          "end": 8.04,
+          "confidence": 0.371
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 9.42,
+      "end": 12.78,
+      "text": " Rätus ist dann nicht so weitergegangen wie sich Papstbälle dick das gewünscht hatte.",
+      "tokens": [
+        50764,
+        497,
+        3628,
+        301,
+        1418,
+        3594,
+        1979,
+        370,
+        8988,
+        432,
+        47152,
+        3355,
+        3041,
+        15919,
+        372,
+        65,
+        31447,
+        18659,
+        1482,
+        6906,
+        3412,
+        82,
+        4701,
+        13299,
+        13,
+        51014
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6858572118422565,
+      "compression_ratio": 1.3293413173652695,
+      "no_speech_prob": 0.04553895816206932,
+      "confidence": 0.63,
+      "words": [
+        {
+          "text": "Rätus",
+          "start": 9.42,
+          "end": 9.44,
+          "confidence": 0.381
+        },
+        {
+          "text": "ist",
+          "start": 9.44,
+          "end": 9.62,
+          "confidence": 0.897
+        },
+        {
+          "text": "dann",
+          "start": 9.62,
+          "end": 9.78,
+          "confidence": 0.586
+        },
+        {
+          "text": "nicht",
+          "start": 9.78,
+          "end": 9.96,
+          "confidence": 0.979
+        },
+        {
+          "text": "so",
+          "start": 9.96,
+          "end": 10.12,
+          "confidence": 0.991
+        },
+        {
+          "text": "weitergegangen",
+          "start": 10.12,
+          "end": 10.88,
+          "confidence": 0.703
+        },
+        {
+          "text": "wie",
+          "start": 10.88,
+          "end": 11.04,
+          "confidence": 0.77
+        },
+        {
+          "text": "sich",
+          "start": 11.04,
+          "end": 11.24,
+          "confidence": 0.968
+        },
+        {
+          "text": "Papstbälle",
+          "start": 11.24,
+          "end": 11.72,
+          "confidence": 0.453
+        },
+        {
+          "text": "dick",
+          "start": 11.72,
+          "end": 11.9,
+          "confidence": 0.249
+        },
+        {
+          "text": "das",
+          "start": 11.9,
+          "end": 12.08,
+          "confidence": 0.833
+        },
+        {
+          "text": "gewünscht",
+          "start": 12.08,
+          "end": 12.58,
+          "confidence": 0.801
+        },
+        {
+          "text": "hatte.",
+          "start": 12.58,
+          "end": 12.78,
+          "confidence": 0.906
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 14.0,
+      "end": 15.28,
+      "text": " Das hat er als Meshale im Rätus",
+      "tokens": [
+        51014,
+        2846,
+        2385,
+        1189,
+        3907,
+        376,
+        14935,
+        1220,
+        566,
+        497,
+        3628,
+        301,
+        51164
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6858572118422565,
+      "compression_ratio": 1.3293413173652695,
+      "no_speech_prob": 0.04553895816206932,
+      "confidence": 0.409,
+      "words": [
+        {
+          "text": "Das",
+          "start": 14.0,
+          "end": 14.2,
+          "confidence": 0.938
+        },
+        {
+          "text": "hat",
+          "start": 14.2,
+          "end": 14.4,
+          "confidence": 0.955
+        },
+        {
+          "text": "er",
+          "start": 14.4,
+          "end": 14.56,
+          "confidence": 0.736
+        },
+        {
+          "text": "als",
+          "start": 14.56,
+          "end": 14.7,
+          "confidence": 0.83
+        },
+        {
+          "text": "Meshale",
+          "start": 14.7,
+          "end": 15.1,
+          "confidence": 0.188
+        },
+        {
+          "text": "im",
+          "start": 15.1,
+          "end": 15.12,
+          "confidence": 0.05
+        },
+        {
+          "text": "Rätus",
+          "start": 15.12,
+          "end": 15.28,
+          "confidence": 0.665
+        }
+      ]
+    }
+  ],
+  "language": "de",
+  "language_probs": {
+    "en": 0.003979361150413752,
+    "zh": 0.0001519044308224693,
+    "de": 0.9890514016151428,
+    "es": 0.00012993074778933078,
+    "ru": 0.00024085355107672513,
+    "ko": 5.632081229123287e-05,
+    "fr": 0.00034500681795179844,
+    "ja": 4.632823765859939e-05,
+    "pt": 0.0002543920709285885,
+    "tr": 0.0002227531367680058,
+    "pl": 0.00029741442995145917,
+    "ca": 6.455285301854019e-07,
+    "nl": 0.00042602652683854103,
+    "ar": 0.00012993074778933078,
+    "sv": 0.0003266458516009152,
+    "it": 0.0001239807897945866,
+    "id": 5.086642431706423e-07,
+    "hi": 3.259598452132195e-05,
+    "fi": 2.2755664758733474e-05,
+    "vi": 3.600468971853843e-06,
+    "he": 5.632081229123287e-05,
+    "uk": 7.864147846703418e-06,
+    "el": 5.798658548883395e-06,
+    "ms": 3.1037982353154803e-06,
+    "cs": 5.664333002641797e-06,
+    "ro": 9.48597244132543e-06,
+    "da": 0.00040021486347541213,
+    "hu": 3.0861257982905954e-05,
+    "ta": 3.001986499384657e-07,
+    "no": 6.042340464773588e-05,
+    "th": 4.016613729618257e-06,
+    "ur": 3.993743666796945e-05,
+    "hr": 2.361245378779131e-06,
+    "bg": 2.149938154616393e-06,
+    "lt": 4.0872319573281857e-07,
+    "la": 0.001671855105087161,
+    "mi": 1.2469075045373756e-05,
+    "ml": 6.898509923303209e-07,
+    "cy": 0.00010941266373265535,
+    "sk": 8.720533628547855e-07,
+    "te": 4.853707764596038e-07,
+    "fa": 1.208544199471362e-05,
+    "lv": 1.674373606874724e-06,
+    "bn": 2.893058081099298e-06,
+    "sr": 1.9575409169192426e-06,
+    "az": 5.077475179859903e-06,
+    "sl": 1.5277430065907538e-05,
+    "kn": 9.483140672728041e-08,
+    "et": 2.3246375349117443e-06,
+    "mk": 2.1370587433011679e-07,
+    "br": 9.358560782857239e-05,
+    "eu": 7.049376108625438e-06,
+    "is": 6.319019576039864e-06,
+    "hy": 1.0418302736070473e-05,
+    "ne": 6.660197868768591e-07,
+    "mn": 4.921257186651928e-06,
+    "bs": 3.0796443297731457e-06,
+    "kk": 5.166745040696696e-07,
+    "sq": 1.8246288391310372e-06,
+    "sw": 1.111024857891607e-06,
+    "gl": 4.998756139684701e-06,
+    "mr": 3.495994747026998e-07,
+    "pa": 3.07317634451465e-07,
+    "si": 1.1898074262717273e-05,
+    "km": 4.5967710320837796e-05,
+    "sn": 3.469824878266081e-05,
+    "yo": 5.7087581808445975e-06,
+    "so": 7.356683795478602e-08,
+    "af": 1.3169968042348046e-05,
+    "oc": 1.4019357877259608e-05,
+    "ka": 1.5546031590929488e-06,
+    "be": 1.0097765880345833e-05,
+    "tg": 1.7748824632235483e-08,
+    "sd": 2.634159272929537e-06,
+    "gu": 8.111359761642234e-08,
+    "am": 2.7226835186411336e-07,
+    "yi": 0.0002860206877812743,
+    "lo": 2.0471769346386282e-07,
+    "uz": 3.1354466245581136e-10,
+    "fo": 1.7861124433693476e-05,
+    "ht": 8.113782314467244e-06,
+    "ps": 4.5596365794153826e-07,
+    "tk": 1.6308678851828518e-09,
+    "nn": 0.0009751844918355346,
+    "mt": 1.0477962177901645e-06,
+    "sa": 6.368580670823576e-06,
+    "lb": 8.4853121506967e-07,
+    "my": 1.5185909205683856e-06,
+    "bo": 1.5852650676606572e-06,
+    "tl": 6.556940661539556e-07,
+    "mg": 1.8946131330466187e-09,
+    "as": 5.553116366741051e-08,
+    "tt": 4.195181535493475e-09,
+    "haw": 5.676254295394756e-05,
+    "ln": 4.454012980659172e-07,
+    "ha": 2.018775591139388e-09,
+    "ba": 9.71490776713324e-10,
+    "jw": 5.9023703215643764e-05,
+    "su": 8.410887541998591e-10
+  }
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_auto/gloria.mp3.words.json b/tests/expected/tiny_auto/gloria.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..4c527d14675e524f00c5e964423d5067a1ce477b
--- /dev/null
+++ b/tests/expected/tiny_auto/gloria.mp3.words.json
@@ -0,0 +1,677 @@
+{
+  "text": " Hello. You're my girlfriend. How are you? I'm okay. Why will be? I said she could stay with us, but she feels better. Oh, she can. There's more to be for long. What if you can stay as long as you want? My girlfriend. Really, mixture. I agree.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 1.34,
+      "end": 1.78,
+      "text": " Hello.",
+      "tokens": [
+        50364,
+        2425,
+        13,
+        50464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5507037403819325,
+      "compression_ratio": 1.4319526627218935,
+      "no_speech_prob": 0.11146047711372375,
+      "confidence": 0.407,
+      "words": [
+        {
+          "text": "Hello.",
+          "start": 1.34,
+          "end": 1.78,
+          "confidence": 0.407
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 1.96,
+      "end": 4.26,
+      "text": " You're my girlfriend.",
+      "tokens": [
+        50464,
+        509,
+        434,
+        452,
+        10369,
+        13,
+        50614
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5507037403819325,
+      "compression_ratio": 1.4319526627218935,
+      "no_speech_prob": 0.11146047711372375,
+      "confidence": 0.175,
+      "words": [
+        {
+          "text": "You're",
+          "start": 1.96,
+          "end": 3.12,
+          "confidence": 0.192
+        },
+        {
+          "text": "my",
+          "start": 3.12,
+          "end": 3.2,
+          "confidence": 0.206
+        },
+        {
+          "text": "girlfriend.",
+          "start": 3.2,
+          "end": 4.26,
+          "confidence": 0.123
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 5.52,
+      "end": 6.54,
+      "text": " How are you?",
+      "tokens": [
+        50614,
+        1012,
+        366,
+        291,
+        30,
+        50714
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5507037403819325,
+      "compression_ratio": 1.4319526627218935,
+      "no_speech_prob": 0.11146047711372375,
+      "confidence": 0.627,
+      "words": [
+        {
+          "text": "How",
+          "start": 5.52,
+          "end": 5.8,
+          "confidence": 0.49
+        },
+        {
+          "text": "are",
+          "start": 5.8,
+          "end": 6.16,
+          "confidence": 0.524
+        },
+        {
+          "text": "you?",
+          "start": 6.16,
+          "end": 6.54,
+          "confidence": 0.959
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 6.76,
+      "end": 7.8,
+      "text": " I'm okay.",
+      "tokens": [
+        50714,
+        286,
+        478,
+        1392,
+        13,
+        50764
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5507037403819325,
+      "compression_ratio": 1.4319526627218935,
+      "no_speech_prob": 0.11146047711372375,
+      "confidence": 0.836,
+      "words": [
+        {
+          "text": "I'm",
+          "start": 6.76,
+          "end": 7.1,
+          "confidence": 0.838
+        },
+        {
+          "text": "okay.",
+          "start": 7.1,
+          "end": 7.8,
+          "confidence": 0.83
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 8.38,
+      "end": 9.14,
+      "text": " Why will be?",
+      "tokens": [
+        50764,
+        1545,
+        486,
+        312,
+        30,
+        50814
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5507037403819325,
+      "compression_ratio": 1.4319526627218935,
+      "no_speech_prob": 0.11146047711372375,
+      "confidence": 0.382,
+      "words": [
+        {
+          "text": "Why",
+          "start": 8.38,
+          "end": 8.66,
+          "confidence": 0.343
+        },
+        {
+          "text": "will",
+          "start": 8.66,
+          "end": 8.96,
+          "confidence": 0.523
+        },
+        {
+          "text": "be?",
+          "start": 8.96,
+          "end": 9.14,
+          "confidence": 0.311
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 0,
+      "start": 9.4,
+      "end": 11.52,
+      "text": " I said she could stay with us, but she feels better.",
+      "tokens": [
+        50814,
+        286,
+        848,
+        750,
+        727,
+        1754,
+        365,
+        505,
+        11,
+        457,
+        750,
+        3417,
+        1101,
+        13,
+        50964
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5507037403819325,
+      "compression_ratio": 1.4319526627218935,
+      "no_speech_prob": 0.11146047711372375,
+      "confidence": 0.692,
+      "words": [
+        {
+          "text": "I",
+          "start": 9.4,
+          "end": 9.52,
+          "confidence": 0.285
+        },
+        {
+          "text": "said",
+          "start": 9.52,
+          "end": 9.66,
+          "confidence": 0.621
+        },
+        {
+          "text": "she",
+          "start": 9.66,
+          "end": 9.82,
+          "confidence": 0.849
+        },
+        {
+          "text": "could",
+          "start": 9.82,
+          "end": 9.98,
+          "confidence": 0.912
+        },
+        {
+          "text": "stay",
+          "start": 9.98,
+          "end": 10.14,
+          "confidence": 0.992
+        },
+        {
+          "text": "with",
+          "start": 10.14,
+          "end": 10.26,
+          "confidence": 0.986
+        },
+        {
+          "text": "us,",
+          "start": 10.26,
+          "end": 10.44,
+          "confidence": 0.782
+        },
+        {
+          "text": "but",
+          "start": 10.64,
+          "end": 10.72,
+          "confidence": 0.227
+        },
+        {
+          "text": "she",
+          "start": 10.72,
+          "end": 10.94,
+          "confidence": 0.971
+        },
+        {
+          "text": "feels",
+          "start": 10.94,
+          "end": 11.24,
+          "confidence": 0.762
+        },
+        {
+          "text": "better.",
+          "start": 11.24,
+          "end": 11.52,
+          "confidence": 0.987
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 0,
+      "start": 12.18,
+      "end": 13.44,
+      "text": " Oh, she can.",
+      "tokens": [
+        50964,
+        876,
+        11,
+        750,
+        393,
+        13,
+        51064
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5507037403819325,
+      "compression_ratio": 1.4319526627218935,
+      "no_speech_prob": 0.11146047711372375,
+      "confidence": 0.287,
+      "words": [
+        {
+          "text": "Oh,",
+          "start": 12.18,
+          "end": 12.6,
+          "confidence": 0.181
+        },
+        {
+          "text": "she",
+          "start": 12.8,
+          "end": 12.96,
+          "confidence": 0.686
+        },
+        {
+          "text": "can.",
+          "start": 12.96,
+          "end": 13.44,
+          "confidence": 0.191
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 0,
+      "start": 13.5,
+      "end": 15.2,
+      "text": " There's more to be for long.",
+      "tokens": [
+        51064,
+        821,
+        311,
+        544,
+        281,
+        312,
+        337,
+        938,
+        13,
+        51114
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5507037403819325,
+      "compression_ratio": 1.4319526627218935,
+      "no_speech_prob": 0.11146047711372375,
+      "confidence": 0.682,
+      "words": [
+        {
+          "text": "There's",
+          "start": 13.5,
+          "end": 14.44,
+          "confidence": 0.518
+        },
+        {
+          "text": "more",
+          "start": 14.44,
+          "end": 14.56,
+          "confidence": 0.814
+        },
+        {
+          "text": "to",
+          "start": 14.56,
+          "end": 14.74,
+          "confidence": 0.414
+        },
+        {
+          "text": "be",
+          "start": 14.74,
+          "end": 14.8,
+          "confidence": 0.949
+        },
+        {
+          "text": "for",
+          "start": 14.8,
+          "end": 15.0,
+          "confidence": 0.987
+        },
+        {
+          "text": "long.",
+          "start": 15.0,
+          "end": 15.2,
+          "confidence": 0.814
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 0,
+      "start": 15.38,
+      "end": 16.86,
+      "text": " What if you can stay as long as you want?",
+      "tokens": [
+        51114,
+        708,
+        498,
+        291,
+        393,
+        1754,
+        382,
+        938,
+        382,
+        291,
+        528,
+        30,
+        51214
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5507037403819325,
+      "compression_ratio": 1.4319526627218935,
+      "no_speech_prob": 0.11146047711372375,
+      "confidence": 0.771,
+      "words": [
+        {
+          "text": "What",
+          "start": 15.38,
+          "end": 15.54,
+          "confidence": 0.387
+        },
+        {
+          "text": "if",
+          "start": 15.54,
+          "end": 15.62,
+          "confidence": 0.918
+        },
+        {
+          "text": "you",
+          "start": 15.62,
+          "end": 15.7,
+          "confidence": 0.97
+        },
+        {
+          "text": "can",
+          "start": 15.7,
+          "end": 15.98,
+          "confidence": 0.946
+        },
+        {
+          "text": "stay",
+          "start": 15.98,
+          "end": 16.12,
+          "confidence": 0.958
+        },
+        {
+          "text": "as",
+          "start": 16.12,
+          "end": 16.24,
+          "confidence": 0.308
+        },
+        {
+          "text": "long",
+          "start": 16.24,
+          "end": 16.36,
+          "confidence": 0.993
+        },
+        {
+          "text": "as",
+          "start": 16.36,
+          "end": 16.54,
+          "confidence": 0.992
+        },
+        {
+          "text": "you",
+          "start": 16.54,
+          "end": 16.62,
+          "confidence": 0.959
+        },
+        {
+          "text": "want?",
+          "start": 16.62,
+          "end": 16.86,
+          "confidence": 0.82
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 0,
+      "start": 16.86,
+      "end": 17.74,
+      "text": " My girlfriend.",
+      "tokens": [
+        51214,
+        1222,
+        10369,
+        13,
+        51264
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5507037403819325,
+      "compression_ratio": 1.4319526627218935,
+      "no_speech_prob": 0.11146047711372375,
+      "confidence": 0.141,
+      "words": [
+        {
+          "text": "My",
+          "start": 16.86,
+          "end": 17.34,
+          "confidence": 0.125
+        },
+        {
+          "text": "girlfriend.",
+          "start": 17.34,
+          "end": 17.74,
+          "confidence": 0.159
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 0,
+      "start": 17.98,
+      "end": 18.9,
+      "text": " Really, mixture.",
+      "tokens": [
+        51264,
+        4083,
+        11,
+        9925,
+        13,
+        51314
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5507037403819325,
+      "compression_ratio": 1.4319526627218935,
+      "no_speech_prob": 0.11146047711372375,
+      "confidence": 0.439,
+      "words": [
+        {
+          "text": "Really,",
+          "start": 17.98,
+          "end": 18.34,
+          "confidence": 0.704
+        },
+        {
+          "text": "mixture.",
+          "start": 18.7,
+          "end": 18.9,
+          "confidence": 0.273
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 0,
+      "start": 19.72,
+      "end": 20.22,
+      "text": " I agree.",
+      "tokens": [
+        51314,
+        286,
+        3986,
+        13,
+        51364
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5507037403819325,
+      "compression_ratio": 1.4319526627218935,
+      "no_speech_prob": 0.11146047711372375,
+      "confidence": 0.16,
+      "words": [
+        {
+          "text": "I",
+          "start": 19.72,
+          "end": 20.06,
+          "confidence": 0.098
+        },
+        {
+          "text": "agree.",
+          "start": 20.06,
+          "end": 20.22,
+          "confidence": 0.259
+        }
+      ]
+    }
+  ],
+  "language": "en",
+  "language_probs": {
+    "en": 0.8432613015174866,
+    "zh": 0.0022250444162636995,
+    "de": 0.003997680731117725,
+    "es": 0.005014214664697647,
+    "ru": 0.006747363600879908,
+    "ko": 0.00396657083183527,
+    "fr": 0.004710419103503227,
+    "ja": 0.0019181080861017108,
+    "pt": 0.0026839158963412046,
+    "tr": 0.001666481141000986,
+    "pl": 0.0017193809617310762,
+    "ca": 0.0010107719572260976,
+    "nl": 0.005379467271268368,
+    "ar": 0.002295674756169319,
+    "sv": 0.003212226554751396,
+    "it": 0.001200321363285184,
+    "id": 0.00030586906359530985,
+    "hi": 0.0005284943035803735,
+    "fi": 0.0010428574169054627,
+    "vi": 0.0002763296652119607,
+    "he": 0.00021689364803023636,
+    "uk": 0.0008713398710824549,
+    "el": 0.0014365967363119125,
+    "ms": 0.0031133966986089945,
+    "cs": 0.0003689485020004213,
+    "ro": 0.00020375273015815765,
+    "da": 0.0017464574193581939,
+    "hu": 0.0004180734104011208,
+    "ta": 0.0002575675898697227,
+    "no": 0.000508248049300164,
+    "th": 0.0001611816551303491,
+    "ur": 0.0008185480255633593,
+    "hr": 7.886112871346995e-05,
+    "bg": 8.232354593928903e-05,
+    "lt": 0.0001188479145639576,
+    "la": 0.00432252325117588,
+    "mi": 0.0036972500383853912,
+    "ml": 0.0003281495883129537,
+    "cy": 0.06814596056938171,
+    "sk": 4.4933716708328575e-05,
+    "te": 0.0001057055196724832,
+    "fa": 9.219799540005624e-05,
+    "lv": 0.00012651293945964426,
+    "bn": 0.0001188479145639576,
+    "sr": 4.6541510528186336e-05,
+    "az": 2.8118798581999727e-05,
+    "sl": 0.000240079389186576,
+    "kn": 7.249770078487927e-06,
+    "et": 0.00010488291445653886,
+    "mk": 2.29498964472441e-05,
+    "br": 0.0006526034558191895,
+    "eu": 4.475853347685188e-05,
+    "is": 0.0007570332381874323,
+    "hy": 1.1405487384763546e-05,
+    "ne": 8.866594725986943e-05,
+    "mn": 4.2876046791207045e-05,
+    "bs": 0.0001756458223098889,
+    "kk": 1.1316729796817526e-05,
+    "sq": 4.9737089284462854e-05,
+    "sw": 0.0003011270018760115,
+    "gl": 0.0005538573605008423,
+    "mr": 1.3650581422552932e-05,
+    "pa": 8.643010005471297e-06,
+    "si": 3.431755612837151e-05,
+    "km": 0.0001798111479729414,
+    "sn": 0.0002595876867417246,
+    "yo": 0.00017157700494863093,
+    "so": 2.795035015878966e-06,
+    "af": 0.000512234284542501,
+    "oc": 7.437312160618603e-05,
+    "ka": 7.931271284178365e-06,
+    "be": 9.112384577747434e-05,
+    "tg": 3.491570339519967e-07,
+    "sd": 6.386368477251381e-05,
+    "gu": 3.547084133970202e-06,
+    "am": 8.247217010648455e-06,
+    "yi": 0.0001245515450136736,
+    "lo": 3.1302906791097485e-06,
+    "uz": 2.5990114504992334e-09,
+    "fo": 0.00025357434060424566,
+    "ht": 0.0002135310205630958,
+    "ps": 1.2773540220223367e-05,
+    "tk": 4.470028258651837e-08,
+    "nn": 0.00795033760368824,
+    "mt": 4.2376526835141703e-05,
+    "sa": 0.00010488291445653886,
+    "lb": 5.612301947621745e-07,
+    "my": 2.5904251742758788e-05,
+    "bo": 5.570289431489073e-05,
+    "tl": 0.0005582012236118317,
+    "mg": 8.244755633768364e-08,
+    "as": 4.501483999774791e-06,
+    "tt": 7.206338068499463e-07,
+    "haw": 0.004565494600683451,
+    "ln": 9.909259460982867e-06,
+    "ha": 1.484210372382222e-07,
+    "ba": 4.651499807550863e-08,
+    "jw": 0.0009569796384312212,
+    "su": 8.875615975512119e-08
+  }
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_auto/japanese.mp3.words.json b/tests/expected/tiny_auto/japanese.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..aef90205227e57c0ebaaad94ef18635489395ab4
--- /dev/null
+++ b/tests/expected/tiny_auto/japanese.mp3.words.json
@@ -0,0 +1,1619 @@
+{
+  "text": "いきます 入室タブでの最図免証記が実際と違う県に関するご質問いただいております同じ度面でデレクトリーごとに 別再度として管理上をしている際と針ます サプテレクトリーごとにわけたサイトはそれぞれ パブリシャーセンターに登録していくグルニュース上では 別再度として認識され パンコン愛行は最図ごと物物は正しく表示されますしかし グルニュースタブでは バブコン最図免証記ともに正しくない以上 時にいいなります こちらいたしても ではありませんパブコンはサプテレクトリーごとに 設定した",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.08,
+      "end": 6.62,
+      "text": "いきます 入室タブでの最図免証記が実際と違う県に関するご質問いただいております",
+      "tokens": [
+        50364,
+        47348,
+        220,
+        14028,
+        2415,
+        97,
+        12144,
+        28889,
+        2474,
+        2972,
+        8661,
+        3919,
+        111,
+        2347,
+        235,
+        5396,
+        120,
+        16958,
+        5142,
+        33197,
+        34837,
+        3193,
+        49806,
+        2862,
+        234,
+        4108,
+        5196,
+        95,
+        22570,
+        9991,
+        43450,
+        11361,
+        32418,
+        18549,
+        6117,
+        19420,
+        50712
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5681739258610345,
+      "compression_ratio": 1.582191780821918,
+      "no_speech_prob": 0.189762145280838,
+      "confidence": 0.551,
+      "words": [
+        {
+          "text": "いきます",
+          "start": 0.08,
+          "end": 0.6,
+          "confidence": 0.153
+        },
+        {
+          "text": " ",
+          "start": 0.6,
+          "end": 1.18,
+          "confidence": 0.305
+        },
+        {
+          "text": "入",
+          "start": 1.18,
+          "end": 1.38,
+          "confidence": 0.435
+        },
+        {
+          "text": "室",
+          "start": 1.38,
+          "end": 1.52,
+          "confidence": 0.501
+        },
+        {
+          "text": "タ",
+          "start": 1.52,
+          "end": 1.68,
+          "confidence": 0.201
+        },
+        {
+          "text": "ブ",
+          "start": 1.68,
+          "end": 1.78,
+          "confidence": 0.837
+        },
+        {
+          "text": "で",
+          "start": 1.78,
+          "end": 1.98,
+          "confidence": 0.947
+        },
+        {
+          "text": "の",
+          "start": 1.98,
+          "end": 2.22,
+          "confidence": 0.907
+        },
+        {
+          "text": "最",
+          "start": 2.22,
+          "end": 2.64,
+          "confidence": 0.277
+        },
+        {
+          "text": "図",
+          "start": 2.64,
+          "end": 2.78,
+          "confidence": 0.349
+        },
+        {
+          "text": "免",
+          "start": 2.78,
+          "end": 2.98,
+          "confidence": 0.647
+        },
+        {
+          "text": "証",
+          "start": 2.98,
+          "end": 3.18,
+          "confidence": 0.282
+        },
+        {
+          "text": "記",
+          "start": 3.18,
+          "end": 3.32,
+          "confidence": 0.299
+        },
+        {
+          "text": "が",
+          "start": 3.32,
+          "end": 3.5,
+          "confidence": 0.976
+        },
+        {
+          "text": "実",
+          "start": 3.5,
+          "end": 3.74,
+          "confidence": 0.343
+        },
+        {
+          "text": "際",
+          "start": 3.74,
+          "end": 3.9,
+          "confidence": 0.975
+        },
+        {
+          "text": "と",
+          "start": 3.9,
+          "end": 4.08,
+          "confidence": 0.91
+        },
+        {
+          "text": "違う",
+          "start": 4.08,
+          "end": 4.38,
+          "confidence": 0.803
+        },
+        {
+          "text": "県",
+          "start": 4.38,
+          "end": 4.6,
+          "confidence": 0.405
+        },
+        {
+          "text": "に",
+          "start": 4.6,
+          "end": 4.74,
+          "confidence": 0.988
+        },
+        {
+          "text": "関",
+          "start": 4.74,
+          "end": 4.94,
+          "confidence": 0.543
+        },
+        {
+          "text": "する",
+          "start": 4.94,
+          "end": 5.12,
+          "confidence": 0.947
+        },
+        {
+          "text": "ご",
+          "start": 5.12,
+          "end": 5.3,
+          "confidence": 0.499
+        },
+        {
+          "text": "質",
+          "start": 5.3,
+          "end": 5.46,
+          "confidence": 0.943
+        },
+        {
+          "text": "問",
+          "start": 5.46,
+          "end": 5.6,
+          "confidence": 0.99
+        },
+        {
+          "text": "いただ",
+          "start": 5.6,
+          "end": 5.92,
+          "confidence": 0.922
+        },
+        {
+          "text": "いて",
+          "start": 5.92,
+          "end": 6.16,
+          "confidence": 0.982
+        },
+        {
+          "text": "お",
+          "start": 6.16,
+          "end": 6.26,
+          "confidence": 0.79
+        },
+        {
+          "text": "ります",
+          "start": 6.26,
+          "end": 6.62,
+          "confidence": 0.975
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 6.92,
+      "end": 12.9,
+      "text": "同じ度面でデレクトリーごとに 別再度として管理上をしている際と針",
+      "tokens": [
+        50712,
+        13089,
+        9257,
+        13127,
+        8833,
+        2474,
+        31327,
+        16680,
+        10825,
+        7588,
+        12376,
+        3384,
+        9991,
+        3193,
+        4108,
+        220,
+        16158,
+        8623,
+        13127,
+        3193,
+        8822,
+        23131,
+        13876,
+        5708,
+        5998,
+        8822,
+        22979,
+        34837,
+        3193,
+        5873,
+        251,
+        51010
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5681739258610345,
+      "compression_ratio": 1.582191780821918,
+      "no_speech_prob": 0.189762145280838,
+      "confidence": 0.524,
+      "words": [
+        {
+          "text": "同",
+          "start": 6.92,
+          "end": 7.3,
+          "confidence": 0.83
+        },
+        {
+          "text": "じ",
+          "start": 7.3,
+          "end": 7.42,
+          "confidence": 0.227
+        },
+        {
+          "text": "度",
+          "start": 7.42,
+          "end": 7.6,
+          "confidence": 0.138
+        },
+        {
+          "text": "面",
+          "start": 7.6,
+          "end": 7.76,
+          "confidence": 0.296
+        },
+        {
+          "text": "で",
+          "start": 7.76,
+          "end": 8.0,
+          "confidence": 0.567
+        },
+        {
+          "text": "デ",
+          "start": 8.0,
+          "end": 8.16,
+          "confidence": 0.51
+        },
+        {
+          "text": "レ",
+          "start": 8.16,
+          "end": 8.28,
+          "confidence": 0.481
+        },
+        {
+          "text": "ク",
+          "start": 8.28,
+          "end": 8.36,
+          "confidence": 0.98
+        },
+        {
+          "text": "ト",
+          "start": 8.36,
+          "end": 8.5,
+          "confidence": 0.984
+        },
+        {
+          "text": "リ",
+          "start": 8.5,
+          "end": 8.62,
+          "confidence": 0.967
+        },
+        {
+          "text": "ー",
+          "start": 8.62,
+          "end": 8.7,
+          "confidence": 0.644
+        },
+        {
+          "text": "ご",
+          "start": 8.7,
+          "end": 8.84,
+          "confidence": 0.227
+        },
+        {
+          "text": "と",
+          "start": 8.84,
+          "end": 8.98,
+          "confidence": 0.988
+        },
+        {
+          "text": "に",
+          "start": 8.98,
+          "end": 9.14,
+          "confidence": 0.988
+        },
+        {
+          "text": " ",
+          "start": 9.14,
+          "end": 9.38,
+          "confidence": 0.261
+        },
+        {
+          "text": "別",
+          "start": 9.38,
+          "end": 9.42,
+          "confidence": 0.405
+        },
+        {
+          "text": "再",
+          "start": 9.42,
+          "end": 9.58,
+          "confidence": 0.427
+        },
+        {
+          "text": "度",
+          "start": 9.58,
+          "end": 9.74,
+          "confidence": 0.327
+        },
+        {
+          "text": "と",
+          "start": 9.74,
+          "end": 9.9,
+          "confidence": 0.886
+        },
+        {
+          "text": "して",
+          "start": 9.9,
+          "end": 10.3,
+          "confidence": 0.998
+        },
+        {
+          "text": "管",
+          "start": 10.3,
+          "end": 10.88,
+          "confidence": 0.821
+        },
+        {
+          "text": "理",
+          "start": 10.88,
+          "end": 11.06,
+          "confidence": 1.0
+        },
+        {
+          "text": "上",
+          "start": 11.06,
+          "end": 11.38,
+          "confidence": 0.466
+        },
+        {
+          "text": "を",
+          "start": 11.38,
+          "end": 11.54,
+          "confidence": 0.966
+        },
+        {
+          "text": "して",
+          "start": 11.54,
+          "end": 11.84,
+          "confidence": 0.916
+        },
+        {
+          "text": "いる",
+          "start": 11.84,
+          "end": 12.16,
+          "confidence": 0.979
+        },
+        {
+          "text": "際",
+          "start": 12.16,
+          "end": 12.54,
+          "confidence": 0.122
+        },
+        {
+          "text": "と",
+          "start": 12.54,
+          "end": 12.7,
+          "confidence": 0.712
+        },
+        {
+          "text": "針",
+          "start": 12.7,
+          "end": 12.9,
+          "confidence": 0.264
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 12.9,
+      "end": 19.55,
+      "text": "ます サプテレクトリーごとにわけたサイトはそれぞれ パブリシャーセンターに登録していく",
+      "tokens": [
+        51010,
+        5368,
+        220,
+        23607,
+        20953,
+        22985,
+        16680,
+        10825,
+        7588,
+        12376,
+        3384,
+        9991,
+        3193,
+        4108,
+        9206,
+        7625,
+        3368,
+        23607,
+        8040,
+        7588,
+        3065,
+        13873,
+        31563,
+        4132,
+        15096,
+        239,
+        28889,
+        12376,
+        11054,
+        17233,
+        3384,
+        31223,
+        4824,
+        30736,
+        4108,
+        46246,
+        8822,
+        49394,
+        51340
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5681739258610345,
+      "compression_ratio": 1.582191780821918,
+      "no_speech_prob": 0.189762145280838,
+      "confidence": 0.715,
+      "words": [
+        {
+          "text": "ます",
+          "start": 12.9,
+          "end": 13.22,
+          "confidence": 0.344
+        },
+        {
+          "text": " ",
+          "start": 13.22,
+          "end": 14.1,
+          "confidence": 0.34
+        },
+        {
+          "text": "サ",
+          "start": 14.1,
+          "end": 14.22,
+          "confidence": 0.555
+        },
+        {
+          "text": "プ",
+          "start": 14.22,
+          "end": 14.32,
+          "confidence": 0.786
+        },
+        {
+          "text": "テ",
+          "start": 14.32,
+          "end": 14.42,
+          "confidence": 0.622
+        },
+        {
+          "text": "レ",
+          "start": 14.42,
+          "end": 14.58,
+          "confidence": 0.865
+        },
+        {
+          "text": "ク",
+          "start": 14.58,
+          "end": 14.68,
+          "confidence": 0.996
+        },
+        {
+          "text": "ト",
+          "start": 14.68,
+          "end": 14.78,
+          "confidence": 0.999
+        },
+        {
+          "text": "リ",
+          "start": 14.78,
+          "end": 14.92,
+          "confidence": 0.996
+        },
+        {
+          "text": "ー",
+          "start": 14.92,
+          "end": 15.04,
+          "confidence": 0.996
+        },
+        {
+          "text": "ご",
+          "start": 15.04,
+          "end": 15.1,
+          "confidence": 0.965
+        },
+        {
+          "text": "と",
+          "start": 15.1,
+          "end": 15.38,
+          "confidence": 0.998
+        },
+        {
+          "text": "に",
+          "start": 15.38,
+          "end": 15.84,
+          "confidence": 0.625
+        },
+        {
+          "text": "わ",
+          "start": 15.84,
+          "end": 16.02,
+          "confidence": 0.739
+        },
+        {
+          "text": "け",
+          "start": 16.02,
+          "end": 16.14,
+          "confidence": 0.992
+        },
+        {
+          "text": "た",
+          "start": 16.14,
+          "end": 16.28,
+          "confidence": 0.885
+        },
+        {
+          "text": "サ",
+          "start": 16.28,
+          "end": 16.42,
+          "confidence": 0.304
+        },
+        {
+          "text": "イ",
+          "start": 16.42,
+          "end": 16.5,
+          "confidence": 0.976
+        },
+        {
+          "text": "ト",
+          "start": 16.5,
+          "end": 16.6,
+          "confidence": 0.932
+        },
+        {
+          "text": "は",
+          "start": 16.6,
+          "end": 17.08,
+          "confidence": 0.894
+        },
+        {
+          "text": "それ",
+          "start": 17.08,
+          "end": 17.46,
+          "confidence": 0.474
+        },
+        {
+          "text": "ぞ",
+          "start": 17.46,
+          "end": 17.64,
+          "confidence": 0.919
+        },
+        {
+          "text": "れ",
+          "start": 17.64,
+          "end": 17.72,
+          "confidence": 0.998
+        },
+        {
+          "text": " パ",
+          "start": 17.72,
+          "end": 17.86,
+          "confidence": 0.506
+        },
+        {
+          "text": "ブ",
+          "start": 17.86,
+          "end": 17.94,
+          "confidence": 0.961
+        },
+        {
+          "text": "リ",
+          "start": 17.94,
+          "end": 18.06,
+          "confidence": 0.988
+        },
+        {
+          "text": "シ",
+          "start": 18.06,
+          "end": 18.18,
+          "confidence": 0.542
+        },
+        {
+          "text": "ャ",
+          "start": 18.18,
+          "end": 18.26,
+          "confidence": 0.911
+        },
+        {
+          "text": "ー",
+          "start": 18.26,
+          "end": 18.42,
+          "confidence": 0.546
+        },
+        {
+          "text": "セ",
+          "start": 18.42,
+          "end": 18.44,
+          "confidence": 0.367
+        },
+        {
+          "text": "ン",
+          "start": 18.44,
+          "end": 18.48,
+          "confidence": 0.915
+        },
+        {
+          "text": "ター",
+          "start": 18.48,
+          "end": 18.6,
+          "confidence": 0.996
+        },
+        {
+          "text": "に",
+          "start": 18.6,
+          "end": 18.76,
+          "confidence": 0.707
+        },
+        {
+          "text": "登録",
+          "start": 18.76,
+          "end": 19.12,
+          "confidence": 0.668
+        },
+        {
+          "text": "して",
+          "start": 19.12,
+          "end": 19.38,
+          "confidence": 0.438
+        },
+        {
+          "text": "いく",
+          "start": 19.38,
+          "end": 19.55,
+          "confidence": 0.806
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 19.55,
+      "end": 27.08,
+      "text": "グルニュース上では 別再度として認識され パンコン愛行は最図ごと物物は正しく表示されます",
+      "tokens": [
+        51340,
+        23839,
+        9405,
+        34737,
+        26167,
+        3384,
+        9550,
+        5708,
+        16719,
+        220,
+        16158,
+        8623,
+        13127,
+        3193,
+        8822,
+        22041,
+        43143,
+        6722,
+        4132,
+        220,
+        23268,
+        1047,
+        111,
+        18066,
+        4824,
+        15157,
+        8082,
+        3065,
+        8661,
+        3919,
+        111,
+        9991,
+        3193,
+        23516,
+        23516,
+        3065,
+        15789,
+        26568,
+        40053,
+        6722,
+        4132,
+        5368,
+        51727
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5681739258610345,
+      "compression_ratio": 1.582191780821918,
+      "no_speech_prob": 0.189762145280838,
+      "confidence": 0.554,
+      "words": [
+        {
+          "text": "グ",
+          "start": 19.55,
+          "end": 19.78,
+          "confidence": 0.701
+        },
+        {
+          "text": "ル",
+          "start": 19.78,
+          "end": 19.88,
+          "confidence": 0.976
+        },
+        {
+          "text": "ニ",
+          "start": 19.88,
+          "end": 20.02,
+          "confidence": 0.899
+        },
+        {
+          "text": "ュ",
+          "start": 20.02,
+          "end": 20.14,
+          "confidence": 0.996
+        },
+        {
+          "text": "ー",
+          "start": 20.14,
+          "end": 20.18,
+          "confidence": 0.994
+        },
+        {
+          "text": "ス",
+          "start": 20.18,
+          "end": 20.22,
+          "confidence": 0.958
+        },
+        {
+          "text": "上",
+          "start": 20.22,
+          "end": 20.42,
+          "confidence": 0.313
+        },
+        {
+          "text": "では",
+          "start": 20.42,
+          "end": 20.82,
+          "confidence": 0.783
+        },
+        {
+          "text": " ",
+          "start": 20.82,
+          "end": 21.1,
+          "confidence": 0.595
+        },
+        {
+          "text": "別",
+          "start": 21.1,
+          "end": 21.16,
+          "confidence": 0.294
+        },
+        {
+          "text": "再",
+          "start": 21.16,
+          "end": 21.34,
+          "confidence": 0.84
+        },
+        {
+          "text": "度",
+          "start": 21.34,
+          "end": 21.46,
+          "confidence": 1.0
+        },
+        {
+          "text": "と",
+          "start": 21.46,
+          "end": 21.64,
+          "confidence": 0.992
+        },
+        {
+          "text": "して",
+          "start": 21.64,
+          "end": 21.82,
+          "confidence": 0.994
+        },
+        {
+          "text": "認",
+          "start": 21.82,
+          "end": 22.04,
+          "confidence": 0.497
+        },
+        {
+          "text": "識",
+          "start": 22.04,
+          "end": 22.2,
+          "confidence": 0.99
+        },
+        {
+          "text": "さ",
+          "start": 22.2,
+          "end": 22.34,
+          "confidence": 0.994
+        },
+        {
+          "text": "れ",
+          "start": 22.34,
+          "end": 22.7,
+          "confidence": 0.958
+        },
+        {
+          "text": " ",
+          "start": 22.7,
+          "end": 22.76,
+          "confidence": 0.204
+        },
+        {
+          "text": "パ",
+          "start": 22.76,
+          "end": 22.9,
+          "confidence": 0.039
+        },
+        {
+          "text": "ン",
+          "start": 22.9,
+          "end": 23.0,
+          "confidence": 0.332
+        },
+        {
+          "text": "コ",
+          "start": 23.0,
+          "end": 23.24,
+          "confidence": 0.918
+        },
+        {
+          "text": "ン",
+          "start": 23.24,
+          "end": 23.4,
+          "confidence": 0.807
+        },
+        {
+          "text": "愛",
+          "start": 23.4,
+          "end": 23.48,
+          "confidence": 0.239
+        },
+        {
+          "text": "行",
+          "start": 23.48,
+          "end": 23.64,
+          "confidence": 0.134
+        },
+        {
+          "text": "は",
+          "start": 23.64,
+          "end": 23.86,
+          "confidence": 0.959
+        },
+        {
+          "text": "最",
+          "start": 23.86,
+          "end": 24.1,
+          "confidence": 0.729
+        },
+        {
+          "text": "図",
+          "start": 24.1,
+          "end": 24.3,
+          "confidence": 0.948
+        },
+        {
+          "text": "ご",
+          "start": 24.3,
+          "end": 24.42,
+          "confidence": 0.154
+        },
+        {
+          "text": "と",
+          "start": 24.42,
+          "end": 24.52,
+          "confidence": 0.969
+        },
+        {
+          "text": "物",
+          "start": 24.52,
+          "end": 24.76,
+          "confidence": 0.238
+        },
+        {
+          "text": "物",
+          "start": 24.76,
+          "end": 24.92,
+          "confidence": 0.197
+        },
+        {
+          "text": "は",
+          "start": 24.92,
+          "end": 25.08,
+          "confidence": 0.566
+        },
+        {
+          "text": "正",
+          "start": 25.08,
+          "end": 25.36,
+          "confidence": 0.454
+        },
+        {
+          "text": "しく",
+          "start": 25.36,
+          "end": 25.64,
+          "confidence": 0.955
+        },
+        {
+          "text": "表示",
+          "start": 25.64,
+          "end": 26.0,
+          "confidence": 0.414
+        },
+        {
+          "text": "さ",
+          "start": 26.0,
+          "end": 26.28,
+          "confidence": 0.712
+        },
+        {
+          "text": "れ",
+          "start": 26.28,
+          "end": 26.62,
+          "confidence": 0.976
+        },
+        {
+          "text": "ます",
+          "start": 26.62,
+          "end": 27.08,
+          "confidence": 0.474
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 2726,
+      "start": 27.36,
+      "end": 32.39,
+      "text": "しかし グルニュースタブでは バブコン最図免証記ともに正しくない",
+      "tokens": [
+        50364,
+        32156,
+        2849,
+        220,
+        23839,
+        9405,
+        34737,
+        26167,
+        3384,
+        9550,
+        12144,
+        28889,
+        16719,
+        15096,
+        238,
+        28889,
+        18066,
+        4824,
+        8661,
+        3919,
+        111,
+        2347,
+        235,
+        5396,
+        120,
+        16958,
+        3193,
+        4801,
+        4108,
+        15789,
+        26568,
+        9311,
+        50620
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.44616998208535685,
+      "compression_ratio": 1.375,
+      "no_speech_prob": 0.3626025915145874,
+      "confidence": 0.806,
+      "words": [
+        {
+          "text": "しか",
+          "start": 27.36,
+          "end": 27.58,
+          "confidence": 0.959
+        },
+        {
+          "text": "し",
+          "start": 27.58,
+          "end": 27.74,
+          "confidence": 0.992
+        },
+        {
+          "text": " ",
+          "start": 27.74,
+          "end": 27.84,
+          "confidence": 0.249
+        },
+        {
+          "text": "グ",
+          "start": 27.84,
+          "end": 27.92,
+          "confidence": 0.445
+        },
+        {
+          "text": "ル",
+          "start": 27.92,
+          "end": 28.04,
+          "confidence": 0.995
+        },
+        {
+          "text": "ニ",
+          "start": 28.04,
+          "end": 28.24,
+          "confidence": 0.884
+        },
+        {
+          "text": "ュ",
+          "start": 28.24,
+          "end": 28.7,
+          "confidence": 0.995
+        },
+        {
+          "text": "ー",
+          "start": 28.7,
+          "end": 29.18,
+          "confidence": 0.999
+        },
+        {
+          "text": "ス",
+          "start": 29.18,
+          "end": 29.2,
+          "confidence": 0.97
+        },
+        {
+          "text": "タ",
+          "start": 29.2,
+          "end": 29.34,
+          "confidence": 0.992
+        },
+        {
+          "text": "ブ",
+          "start": 29.34,
+          "end": 29.44,
+          "confidence": 0.996
+        },
+        {
+          "text": "では",
+          "start": 29.44,
+          "end": 29.72,
+          "confidence": 0.979
+        },
+        {
+          "text": " バ",
+          "start": 29.72,
+          "end": 30.06,
+          "confidence": 0.503
+        },
+        {
+          "text": "ブ",
+          "start": 30.06,
+          "end": 30.16,
+          "confidence": 0.631
+        },
+        {
+          "text": "コ",
+          "start": 30.16,
+          "end": 30.34,
+          "confidence": 0.631
+        },
+        {
+          "text": "ン",
+          "start": 30.34,
+          "end": 30.42,
+          "confidence": 0.981
+        },
+        {
+          "text": "最",
+          "start": 30.42,
+          "end": 30.6,
+          "confidence": 0.659
+        },
+        {
+          "text": "図",
+          "start": 30.6,
+          "end": 30.88,
+          "confidence": 0.957
+        },
+        {
+          "text": "免",
+          "start": 30.88,
+          "end": 30.94,
+          "confidence": 0.977
+        },
+        {
+          "text": "証",
+          "start": 30.94,
+          "end": 31.12,
+          "confidence": 0.997
+        },
+        {
+          "text": "記",
+          "start": 31.12,
+          "end": 31.26,
+          "confidence": 0.994
+        },
+        {
+          "text": "と",
+          "start": 31.26,
+          "end": 31.42,
+          "confidence": 0.722
+        },
+        {
+          "text": "も",
+          "start": 31.42,
+          "end": 31.54,
+          "confidence": 0.839
+        },
+        {
+          "text": "に",
+          "start": 31.54,
+          "end": 31.66,
+          "confidence": 0.945
+        },
+        {
+          "text": "正",
+          "start": 31.66,
+          "end": 31.96,
+          "confidence": 0.481
+        },
+        {
+          "text": "しく",
+          "start": 31.96,
+          "end": 32.18,
+          "confidence": 0.999
+        },
+        {
+          "text": "ない",
+          "start": 32.18,
+          "end": 32.39,
+          "confidence": 0.938
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 2726,
+      "start": 32.39,
+      "end": 36.34,
+      "text": "以上 時にいいなります こちらいたしても ではありません",
+      "tokens": [
+        50620,
+        29497,
+        220,
+        6611,
+        4108,
+        13806,
+        3203,
+        19420,
+        14384,
+        28567,
+        17679,
+        8822,
+        4801,
+        220,
+        16719,
+        14498,
+        30250,
+        50838
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.44616998208535685,
+      "compression_ratio": 1.375,
+      "no_speech_prob": 0.3626025915145874,
+      "confidence": 0.456,
+      "words": [
+        {
+          "text": "以上",
+          "start": 32.39,
+          "end": 32.74,
+          "confidence": 0.31
+        },
+        {
+          "text": " ",
+          "start": 32.74,
+          "end": 33.04,
+          "confidence": 0.128
+        },
+        {
+          "text": "時",
+          "start": 33.04,
+          "end": 33.1,
+          "confidence": 0.355
+        },
+        {
+          "text": "に",
+          "start": 33.1,
+          "end": 33.12,
+          "confidence": 0.791
+        },
+        {
+          "text": "いい",
+          "start": 33.12,
+          "end": 33.36,
+          "confidence": 0.621
+        },
+        {
+          "text": "な",
+          "start": 33.36,
+          "end": 33.48,
+          "confidence": 0.793
+        },
+        {
+          "text": "ります",
+          "start": 33.48,
+          "end": 34.02,
+          "confidence": 0.896
+        },
+        {
+          "text": " こ",
+          "start": 34.02,
+          "end": 34.38,
+          "confidence": 0.328
+        },
+        {
+          "text": "ちら",
+          "start": 34.38,
+          "end": 34.56,
+          "confidence": 0.684
+        },
+        {
+          "text": "いた",
+          "start": 34.56,
+          "end": 34.84,
+          "confidence": 0.571
+        },
+        {
+          "text": "して",
+          "start": 34.84,
+          "end": 35.04,
+          "confidence": 0.437
+        },
+        {
+          "text": "も",
+          "start": 35.04,
+          "end": 35.18,
+          "confidence": 0.422
+        },
+        {
+          "text": " ",
+          "start": 35.18,
+          "end": 35.38,
+          "confidence": 0.244
+        },
+        {
+          "text": "では",
+          "start": 35.38,
+          "end": 35.46,
+          "confidence": 0.139
+        },
+        {
+          "text": "あり",
+          "start": 35.46,
+          "end": 35.72,
+          "confidence": 0.903
+        },
+        {
+          "text": "ません",
+          "start": 35.72,
+          "end": 36.34,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 2726,
+      "start": 36.42,
+      "end": 40.4,
+      "text": "パブコンはサプテレクトリーごとに 設定した",
+      "tokens": [
+        50838,
+        23268,
+        28889,
+        18066,
+        4824,
+        3065,
+        23607,
+        20953,
+        22985,
+        16680,
+        10825,
+        7588,
+        12376,
+        3384,
+        9991,
+        3193,
+        4108,
+        220,
+        39035,
+        12088,
+        8533,
+        51042
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.44616998208535685,
+      "compression_ratio": 1.375,
+      "no_speech_prob": 0.3626025915145874,
+      "confidence": 0.849,
+      "words": [
+        {
+          "text": "パ",
+          "start": 36.42,
+          "end": 36.92,
+          "confidence": 0.482
+        },
+        {
+          "text": "ブ",
+          "start": 36.92,
+          "end": 37.04,
+          "confidence": 0.648
+        },
+        {
+          "text": "コ",
+          "start": 37.04,
+          "end": 37.2,
+          "confidence": 0.689
+        },
+        {
+          "text": "ン",
+          "start": 37.2,
+          "end": 37.72,
+          "confidence": 0.994
+        },
+        {
+          "text": "は",
+          "start": 37.72,
+          "end": 37.74,
+          "confidence": 0.975
+        },
+        {
+          "text": "サ",
+          "start": 37.74,
+          "end": 38.22,
+          "confidence": 0.668
+        },
+        {
+          "text": "プ",
+          "start": 38.22,
+          "end": 38.32,
+          "confidence": 0.572
+        },
+        {
+          "text": "テ",
+          "start": 38.32,
+          "end": 38.42,
+          "confidence": 0.984
+        },
+        {
+          "text": "レ",
+          "start": 38.42,
+          "end": 38.56,
+          "confidence": 0.997
+        },
+        {
+          "text": "ク",
+          "start": 38.56,
+          "end": 38.68,
+          "confidence": 0.997
+        },
+        {
+          "text": "ト",
+          "start": 38.68,
+          "end": 38.78,
+          "confidence": 0.998
+        },
+        {
+          "text": "リ",
+          "start": 38.78,
+          "end": 38.92,
+          "confidence": 0.999
+        },
+        {
+          "text": "ー",
+          "start": 38.92,
+          "end": 38.96,
+          "confidence": 0.987
+        },
+        {
+          "text": "ご",
+          "start": 38.96,
+          "end": 39.08,
+          "confidence": 0.959
+        },
+        {
+          "text": "と",
+          "start": 39.08,
+          "end": 39.26,
+          "confidence": 0.999
+        },
+        {
+          "text": "に",
+          "start": 39.26,
+          "end": 39.58,
+          "confidence": 0.974
+        },
+        {
+          "text": " ",
+          "start": 39.58,
+          "end": 39.66,
+          "confidence": 0.663
+        },
+        {
+          "text": "設",
+          "start": 39.66,
+          "end": 39.82,
+          "confidence": 0.911
+        },
+        {
+          "text": "定",
+          "start": 39.82,
+          "end": 40.02,
+          "confidence": 0.999
+        },
+        {
+          "text": "した",
+          "start": 40.02,
+          "end": 40.4,
+          "confidence": 0.873
+        }
+      ]
+    }
+  ],
+  "language": "ja",
+  "language_probs": {
+    "en": 0.006242657545953989,
+    "zh": 0.0014827612321823835,
+    "de": 0.00011256561992922798,
+    "es": 0.0013291386421769857,
+    "ru": 0.00022561925288755447,
+    "ko": 0.00042481819400563836,
+    "fr": 0.0003206696128472686,
+    "ja": 0.9862462282180786,
+    "pt": 0.0003521866456139833,
+    "tr": 8.698396413819864e-05,
+    "pl": 0.0008716703741811216,
+    "ca": 1.310503307649924e-06,
+    "nl": 1.0388754162704572e-05,
+    "ar": 1.634380350878928e-05,
+    "sv": 1.8519956938689575e-05,
+    "it": 0.0001502948289271444,
+    "id": 1.4650489902123809e-05,
+    "hi": 3.542034392012283e-05,
+    "fi": 3.327432932564989e-05,
+    "vi": 9.459067769057583e-06,
+    "he": 1.488120233261725e-05,
+    "uk": 2.396660238446202e-05,
+    "el": 3.683132672449574e-05,
+    "ms": 3.514470154186711e-05,
+    "cs": 1.2629512639250606e-05,
+    "ro": 2.034019234997686e-05,
+    "da": 7.294049737538444e-07,
+    "hu": 8.41306882648496e-06,
+    "ta": 3.047011659873533e-06,
+    "no": 4.935400852446037e-07,
+    "th": 2.396660238446202e-05,
+    "ur": 1.823282946133986e-05,
+    "hr": 3.2435270895803114e-06,
+    "bg": 5.906901492380712e-07,
+    "lt": 1.666117981358184e-07,
+    "la": 0.00018271202861797065,
+    "mi": 8.044702553888783e-05,
+    "ml": 1.6182557374122553e-06,
+    "cy": 6.168086838442832e-05,
+    "sk": 7.948603979457403e-07,
+    "te": 2.2118931610748405e-06,
+    "fa": 1.647198951104656e-05,
+    "lv": 2.2245595232561755e-07,
+    "bn": 1.0470233064552303e-05,
+    "sr": 5.132005185259914e-07,
+    "az": 6.641308232246956e-07,
+    "sl": 1.0286258884661947e-06,
+    "kn": 4.97411008382187e-07,
+    "et": 6.641308232246956e-07,
+    "mk": 2.2420069001327647e-07,
+    "br": 3.301538890809752e-05,
+    "eu": 3.920674862456508e-05,
+    "is": 1.7324887835457048e-07,
+    "hy": 1.6566315252930508e-06,
+    "ne": 9.148787967205863e-07,
+    "mn": 2.098585719068069e-05,
+    "bs": 1.1565151680770214e-06,
+    "kk": 2.4623628291919886e-07,
+    "sq": 8.798302815193892e-07,
+    "sw": 8.885971510608215e-06,
+    "gl": 4.239260306349024e-05,
+    "mr": 5.725165124204068e-07,
+    "pa": 1.6309478496623342e-06,
+    "si": 1.4423355423787143e-05,
+    "km": 4.045130481244996e-05,
+    "sn": 2.304845656908583e-05,
+    "yo": 3.3991873351624236e-06,
+    "so": 2.3866036258368695e-07,
+    "af": 9.969784287022776e-07,
+    "oc": 5.474488716572523e-06,
+    "ka": 1.0864454225156805e-06,
+    "be": 5.692566901416285e-06,
+    "tg": 1.913662650565584e-08,
+    "sd": 1.6959174899966456e-06,
+    "gu": 3.2115266890286875e-07,
+    "am": 1.2975741014997766e-07,
+    "yi": 4.197435828245943e-06,
+    "lo": 2.600773427730019e-07,
+    "uz": 3.430495609801909e-10,
+    "fo": 1.4281055200626724e-06,
+    "ht": 2.373014922341099e-06,
+    "ps": 1.5321337514251354e-06,
+    "tk": 7.745855623575437e-10,
+    "nn": 0.0009135027066804469,
+    "mt": 1.0673553418882875e-07,
+    "sa": 1.7262496839975938e-05,
+    "lb": 3.051601860093456e-09,
+    "my": 2.098585719068069e-05,
+    "bo": 1.303041608480271e-05,
+    "tl": 7.029382231849013e-06,
+    "mg": 1.3073606641711422e-09,
+    "as": 4.321581172916922e-07,
+    "tt": 3.4714515706468774e-09,
+    "haw": 2.8909242246299982e-05,
+    "ln": 8.594491305302654e-07,
+    "ha": 6.384976991569147e-09,
+    "ba": 5.375886957814657e-10,
+    "jw": 0.00019148056162521243,
+    "su": 3.087572864046706e-09
+  }
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_auto/jp_japanese.mp3.words.json b/tests/expected/tiny_auto/jp_japanese.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..11667c628b7040a6f550c2ae1dfa9837a6a5be74
--- /dev/null
+++ b/tests/expected/tiny_auto/jp_japanese.mp3.words.json
@@ -0,0 +1,1518 @@
+{
+  "text": "いきます 入室タブでの最図免証記が実際と違う県に関するご質問いただいております同じ度面でデレクトリーごとに 別再度として管理上をしている際と針ます サプテレクトリーごとにわけたサイトはそれぞれ パブリシャーセンターに登録していくグルニュース上では 別再度として認識され パンコン愛行は最図ごと物物は正しく表示されますしかし グルニュースタブでは バブコン最図免証記ともに正しくない以上 時にいいなります こちらいたしても ではありませんパブコンはサプテレクトリーごとに 設定した",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.08,
+      "end": 6.62,
+      "text": "いきます 入室タブでの最図免証記が実際と違う県に関するご質問いただいております",
+      "tokens": [
+        50364,
+        47348,
+        220,
+        14028,
+        2415,
+        97,
+        12144,
+        28889,
+        2474,
+        2972,
+        8661,
+        3919,
+        111,
+        2347,
+        235,
+        5396,
+        120,
+        16958,
+        5142,
+        33197,
+        34837,
+        3193,
+        49806,
+        2862,
+        234,
+        4108,
+        5196,
+        95,
+        22570,
+        9991,
+        43450,
+        11361,
+        32418,
+        18549,
+        6117,
+        19420,
+        50712
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5681739258610345,
+      "compression_ratio": 1.582191780821918,
+      "no_speech_prob": 0.189762145280838,
+      "confidence": 0.551,
+      "words": [
+        {
+          "text": "いきます",
+          "start": 0.08,
+          "end": 0.6,
+          "confidence": 0.153
+        },
+        {
+          "text": " ",
+          "start": 0.6,
+          "end": 1.18,
+          "confidence": 0.305
+        },
+        {
+          "text": "入",
+          "start": 1.18,
+          "end": 1.38,
+          "confidence": 0.435
+        },
+        {
+          "text": "室",
+          "start": 1.38,
+          "end": 1.52,
+          "confidence": 0.501
+        },
+        {
+          "text": "タ",
+          "start": 1.52,
+          "end": 1.68,
+          "confidence": 0.201
+        },
+        {
+          "text": "ブ",
+          "start": 1.68,
+          "end": 1.78,
+          "confidence": 0.837
+        },
+        {
+          "text": "で",
+          "start": 1.78,
+          "end": 1.98,
+          "confidence": 0.947
+        },
+        {
+          "text": "の",
+          "start": 1.98,
+          "end": 2.22,
+          "confidence": 0.907
+        },
+        {
+          "text": "最",
+          "start": 2.22,
+          "end": 2.64,
+          "confidence": 0.277
+        },
+        {
+          "text": "図",
+          "start": 2.64,
+          "end": 2.78,
+          "confidence": 0.349
+        },
+        {
+          "text": "免",
+          "start": 2.78,
+          "end": 2.98,
+          "confidence": 0.647
+        },
+        {
+          "text": "証",
+          "start": 2.98,
+          "end": 3.18,
+          "confidence": 0.282
+        },
+        {
+          "text": "記",
+          "start": 3.18,
+          "end": 3.32,
+          "confidence": 0.299
+        },
+        {
+          "text": "が",
+          "start": 3.32,
+          "end": 3.5,
+          "confidence": 0.976
+        },
+        {
+          "text": "実",
+          "start": 3.5,
+          "end": 3.74,
+          "confidence": 0.343
+        },
+        {
+          "text": "際",
+          "start": 3.74,
+          "end": 3.9,
+          "confidence": 0.975
+        },
+        {
+          "text": "と",
+          "start": 3.9,
+          "end": 4.08,
+          "confidence": 0.91
+        },
+        {
+          "text": "違う",
+          "start": 4.08,
+          "end": 4.38,
+          "confidence": 0.803
+        },
+        {
+          "text": "県",
+          "start": 4.38,
+          "end": 4.6,
+          "confidence": 0.405
+        },
+        {
+          "text": "に",
+          "start": 4.6,
+          "end": 4.74,
+          "confidence": 0.988
+        },
+        {
+          "text": "関",
+          "start": 4.74,
+          "end": 4.94,
+          "confidence": 0.543
+        },
+        {
+          "text": "する",
+          "start": 4.94,
+          "end": 5.12,
+          "confidence": 0.947
+        },
+        {
+          "text": "ご",
+          "start": 5.12,
+          "end": 5.3,
+          "confidence": 0.499
+        },
+        {
+          "text": "質",
+          "start": 5.3,
+          "end": 5.46,
+          "confidence": 0.943
+        },
+        {
+          "text": "問",
+          "start": 5.46,
+          "end": 5.6,
+          "confidence": 0.99
+        },
+        {
+          "text": "いただ",
+          "start": 5.6,
+          "end": 5.92,
+          "confidence": 0.922
+        },
+        {
+          "text": "いて",
+          "start": 5.92,
+          "end": 6.16,
+          "confidence": 0.982
+        },
+        {
+          "text": "お",
+          "start": 6.16,
+          "end": 6.26,
+          "confidence": 0.79
+        },
+        {
+          "text": "ります",
+          "start": 6.26,
+          "end": 6.62,
+          "confidence": 0.975
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 6.92,
+      "end": 12.9,
+      "text": "同じ度面でデレクトリーごとに 別再度として管理上をしている際と針",
+      "tokens": [
+        50712,
+        13089,
+        9257,
+        13127,
+        8833,
+        2474,
+        31327,
+        16680,
+        10825,
+        7588,
+        12376,
+        3384,
+        9991,
+        3193,
+        4108,
+        220,
+        16158,
+        8623,
+        13127,
+        3193,
+        8822,
+        23131,
+        13876,
+        5708,
+        5998,
+        8822,
+        22979,
+        34837,
+        3193,
+        5873,
+        251,
+        51010
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5681739258610345,
+      "compression_ratio": 1.582191780821918,
+      "no_speech_prob": 0.189762145280838,
+      "confidence": 0.524,
+      "words": [
+        {
+          "text": "同",
+          "start": 6.92,
+          "end": 7.3,
+          "confidence": 0.83
+        },
+        {
+          "text": "じ",
+          "start": 7.3,
+          "end": 7.42,
+          "confidence": 0.227
+        },
+        {
+          "text": "度",
+          "start": 7.42,
+          "end": 7.6,
+          "confidence": 0.138
+        },
+        {
+          "text": "面",
+          "start": 7.6,
+          "end": 7.76,
+          "confidence": 0.296
+        },
+        {
+          "text": "で",
+          "start": 7.76,
+          "end": 8.0,
+          "confidence": 0.567
+        },
+        {
+          "text": "デ",
+          "start": 8.0,
+          "end": 8.16,
+          "confidence": 0.51
+        },
+        {
+          "text": "レ",
+          "start": 8.16,
+          "end": 8.28,
+          "confidence": 0.481
+        },
+        {
+          "text": "ク",
+          "start": 8.28,
+          "end": 8.36,
+          "confidence": 0.98
+        },
+        {
+          "text": "ト",
+          "start": 8.36,
+          "end": 8.5,
+          "confidence": 0.984
+        },
+        {
+          "text": "リ",
+          "start": 8.5,
+          "end": 8.62,
+          "confidence": 0.967
+        },
+        {
+          "text": "ー",
+          "start": 8.62,
+          "end": 8.7,
+          "confidence": 0.644
+        },
+        {
+          "text": "ご",
+          "start": 8.7,
+          "end": 8.84,
+          "confidence": 0.227
+        },
+        {
+          "text": "と",
+          "start": 8.84,
+          "end": 8.98,
+          "confidence": 0.988
+        },
+        {
+          "text": "に",
+          "start": 8.98,
+          "end": 9.14,
+          "confidence": 0.988
+        },
+        {
+          "text": " ",
+          "start": 9.14,
+          "end": 9.38,
+          "confidence": 0.261
+        },
+        {
+          "text": "別",
+          "start": 9.38,
+          "end": 9.42,
+          "confidence": 0.405
+        },
+        {
+          "text": "再",
+          "start": 9.42,
+          "end": 9.58,
+          "confidence": 0.427
+        },
+        {
+          "text": "度",
+          "start": 9.58,
+          "end": 9.74,
+          "confidence": 0.327
+        },
+        {
+          "text": "と",
+          "start": 9.74,
+          "end": 9.9,
+          "confidence": 0.886
+        },
+        {
+          "text": "して",
+          "start": 9.9,
+          "end": 10.3,
+          "confidence": 0.998
+        },
+        {
+          "text": "管",
+          "start": 10.3,
+          "end": 10.88,
+          "confidence": 0.821
+        },
+        {
+          "text": "理",
+          "start": 10.88,
+          "end": 11.06,
+          "confidence": 1.0
+        },
+        {
+          "text": "上",
+          "start": 11.06,
+          "end": 11.38,
+          "confidence": 0.466
+        },
+        {
+          "text": "を",
+          "start": 11.38,
+          "end": 11.54,
+          "confidence": 0.966
+        },
+        {
+          "text": "して",
+          "start": 11.54,
+          "end": 11.84,
+          "confidence": 0.916
+        },
+        {
+          "text": "いる",
+          "start": 11.84,
+          "end": 12.16,
+          "confidence": 0.979
+        },
+        {
+          "text": "際",
+          "start": 12.16,
+          "end": 12.54,
+          "confidence": 0.122
+        },
+        {
+          "text": "と",
+          "start": 12.54,
+          "end": 12.7,
+          "confidence": 0.712
+        },
+        {
+          "text": "針",
+          "start": 12.7,
+          "end": 12.9,
+          "confidence": 0.264
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 12.9,
+      "end": 19.55,
+      "text": "ます サプテレクトリーごとにわけたサイトはそれぞれ パブリシャーセンターに登録していく",
+      "tokens": [
+        51010,
+        5368,
+        220,
+        23607,
+        20953,
+        22985,
+        16680,
+        10825,
+        7588,
+        12376,
+        3384,
+        9991,
+        3193,
+        4108,
+        9206,
+        7625,
+        3368,
+        23607,
+        8040,
+        7588,
+        3065,
+        13873,
+        31563,
+        4132,
+        15096,
+        239,
+        28889,
+        12376,
+        11054,
+        17233,
+        3384,
+        31223,
+        4824,
+        30736,
+        4108,
+        46246,
+        8822,
+        49394,
+        51340
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5681739258610345,
+      "compression_ratio": 1.582191780821918,
+      "no_speech_prob": 0.189762145280838,
+      "confidence": 0.715,
+      "words": [
+        {
+          "text": "ます",
+          "start": 12.9,
+          "end": 13.22,
+          "confidence": 0.344
+        },
+        {
+          "text": " ",
+          "start": 13.22,
+          "end": 14.1,
+          "confidence": 0.34
+        },
+        {
+          "text": "サ",
+          "start": 14.1,
+          "end": 14.22,
+          "confidence": 0.555
+        },
+        {
+          "text": "プ",
+          "start": 14.22,
+          "end": 14.32,
+          "confidence": 0.786
+        },
+        {
+          "text": "テ",
+          "start": 14.32,
+          "end": 14.42,
+          "confidence": 0.622
+        },
+        {
+          "text": "レ",
+          "start": 14.42,
+          "end": 14.58,
+          "confidence": 0.865
+        },
+        {
+          "text": "ク",
+          "start": 14.58,
+          "end": 14.68,
+          "confidence": 0.996
+        },
+        {
+          "text": "ト",
+          "start": 14.68,
+          "end": 14.78,
+          "confidence": 0.999
+        },
+        {
+          "text": "リ",
+          "start": 14.78,
+          "end": 14.92,
+          "confidence": 0.996
+        },
+        {
+          "text": "ー",
+          "start": 14.92,
+          "end": 15.04,
+          "confidence": 0.996
+        },
+        {
+          "text": "ご",
+          "start": 15.04,
+          "end": 15.1,
+          "confidence": 0.965
+        },
+        {
+          "text": "と",
+          "start": 15.1,
+          "end": 15.38,
+          "confidence": 0.998
+        },
+        {
+          "text": "に",
+          "start": 15.38,
+          "end": 15.84,
+          "confidence": 0.625
+        },
+        {
+          "text": "わ",
+          "start": 15.84,
+          "end": 16.02,
+          "confidence": 0.739
+        },
+        {
+          "text": "け",
+          "start": 16.02,
+          "end": 16.14,
+          "confidence": 0.992
+        },
+        {
+          "text": "た",
+          "start": 16.14,
+          "end": 16.28,
+          "confidence": 0.885
+        },
+        {
+          "text": "サ",
+          "start": 16.28,
+          "end": 16.42,
+          "confidence": 0.304
+        },
+        {
+          "text": "イ",
+          "start": 16.42,
+          "end": 16.5,
+          "confidence": 0.976
+        },
+        {
+          "text": "ト",
+          "start": 16.5,
+          "end": 16.6,
+          "confidence": 0.932
+        },
+        {
+          "text": "は",
+          "start": 16.6,
+          "end": 17.08,
+          "confidence": 0.894
+        },
+        {
+          "text": "それ",
+          "start": 17.08,
+          "end": 17.46,
+          "confidence": 0.474
+        },
+        {
+          "text": "ぞ",
+          "start": 17.46,
+          "end": 17.64,
+          "confidence": 0.919
+        },
+        {
+          "text": "れ",
+          "start": 17.64,
+          "end": 17.72,
+          "confidence": 0.998
+        },
+        {
+          "text": " パ",
+          "start": 17.72,
+          "end": 17.86,
+          "confidence": 0.506
+        },
+        {
+          "text": "ブ",
+          "start": 17.86,
+          "end": 17.94,
+          "confidence": 0.961
+        },
+        {
+          "text": "リ",
+          "start": 17.94,
+          "end": 18.06,
+          "confidence": 0.988
+        },
+        {
+          "text": "シ",
+          "start": 18.06,
+          "end": 18.18,
+          "confidence": 0.542
+        },
+        {
+          "text": "ャ",
+          "start": 18.18,
+          "end": 18.26,
+          "confidence": 0.911
+        },
+        {
+          "text": "ー",
+          "start": 18.26,
+          "end": 18.42,
+          "confidence": 0.546
+        },
+        {
+          "text": "セ",
+          "start": 18.42,
+          "end": 18.44,
+          "confidence": 0.367
+        },
+        {
+          "text": "ン",
+          "start": 18.44,
+          "end": 18.48,
+          "confidence": 0.915
+        },
+        {
+          "text": "ター",
+          "start": 18.48,
+          "end": 18.6,
+          "confidence": 0.996
+        },
+        {
+          "text": "に",
+          "start": 18.6,
+          "end": 18.76,
+          "confidence": 0.707
+        },
+        {
+          "text": "登録",
+          "start": 18.76,
+          "end": 19.12,
+          "confidence": 0.668
+        },
+        {
+          "text": "して",
+          "start": 19.12,
+          "end": 19.38,
+          "confidence": 0.438
+        },
+        {
+          "text": "いく",
+          "start": 19.38,
+          "end": 19.55,
+          "confidence": 0.806
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 19.55,
+      "end": 27.08,
+      "text": "グルニュース上では 別再度として認識され パンコン愛行は最図ごと物物は正しく表示されます",
+      "tokens": [
+        51340,
+        23839,
+        9405,
+        34737,
+        26167,
+        3384,
+        9550,
+        5708,
+        16719,
+        220,
+        16158,
+        8623,
+        13127,
+        3193,
+        8822,
+        22041,
+        43143,
+        6722,
+        4132,
+        220,
+        23268,
+        1047,
+        111,
+        18066,
+        4824,
+        15157,
+        8082,
+        3065,
+        8661,
+        3919,
+        111,
+        9991,
+        3193,
+        23516,
+        23516,
+        3065,
+        15789,
+        26568,
+        40053,
+        6722,
+        4132,
+        5368,
+        51727
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5681739258610345,
+      "compression_ratio": 1.582191780821918,
+      "no_speech_prob": 0.189762145280838,
+      "confidence": 0.554,
+      "words": [
+        {
+          "text": "グ",
+          "start": 19.55,
+          "end": 19.78,
+          "confidence": 0.701
+        },
+        {
+          "text": "ル",
+          "start": 19.78,
+          "end": 19.88,
+          "confidence": 0.976
+        },
+        {
+          "text": "ニ",
+          "start": 19.88,
+          "end": 20.02,
+          "confidence": 0.899
+        },
+        {
+          "text": "ュ",
+          "start": 20.02,
+          "end": 20.14,
+          "confidence": 0.996
+        },
+        {
+          "text": "ー",
+          "start": 20.14,
+          "end": 20.18,
+          "confidence": 0.994
+        },
+        {
+          "text": "ス",
+          "start": 20.18,
+          "end": 20.22,
+          "confidence": 0.958
+        },
+        {
+          "text": "上",
+          "start": 20.22,
+          "end": 20.42,
+          "confidence": 0.313
+        },
+        {
+          "text": "では",
+          "start": 20.42,
+          "end": 20.82,
+          "confidence": 0.783
+        },
+        {
+          "text": " ",
+          "start": 20.82,
+          "end": 21.1,
+          "confidence": 0.595
+        },
+        {
+          "text": "別",
+          "start": 21.1,
+          "end": 21.16,
+          "confidence": 0.294
+        },
+        {
+          "text": "再",
+          "start": 21.16,
+          "end": 21.34,
+          "confidence": 0.84
+        },
+        {
+          "text": "度",
+          "start": 21.34,
+          "end": 21.46,
+          "confidence": 1.0
+        },
+        {
+          "text": "と",
+          "start": 21.46,
+          "end": 21.64,
+          "confidence": 0.992
+        },
+        {
+          "text": "して",
+          "start": 21.64,
+          "end": 21.82,
+          "confidence": 0.994
+        },
+        {
+          "text": "認",
+          "start": 21.82,
+          "end": 22.04,
+          "confidence": 0.497
+        },
+        {
+          "text": "識",
+          "start": 22.04,
+          "end": 22.2,
+          "confidence": 0.99
+        },
+        {
+          "text": "さ",
+          "start": 22.2,
+          "end": 22.34,
+          "confidence": 0.994
+        },
+        {
+          "text": "れ",
+          "start": 22.34,
+          "end": 22.7,
+          "confidence": 0.958
+        },
+        {
+          "text": " ",
+          "start": 22.7,
+          "end": 22.76,
+          "confidence": 0.204
+        },
+        {
+          "text": "パ",
+          "start": 22.76,
+          "end": 22.9,
+          "confidence": 0.039
+        },
+        {
+          "text": "ン",
+          "start": 22.9,
+          "end": 23.0,
+          "confidence": 0.332
+        },
+        {
+          "text": "コ",
+          "start": 23.0,
+          "end": 23.24,
+          "confidence": 0.918
+        },
+        {
+          "text": "ン",
+          "start": 23.24,
+          "end": 23.4,
+          "confidence": 0.807
+        },
+        {
+          "text": "愛",
+          "start": 23.4,
+          "end": 23.48,
+          "confidence": 0.239
+        },
+        {
+          "text": "行",
+          "start": 23.48,
+          "end": 23.64,
+          "confidence": 0.134
+        },
+        {
+          "text": "は",
+          "start": 23.64,
+          "end": 23.86,
+          "confidence": 0.959
+        },
+        {
+          "text": "最",
+          "start": 23.86,
+          "end": 24.1,
+          "confidence": 0.729
+        },
+        {
+          "text": "図",
+          "start": 24.1,
+          "end": 24.3,
+          "confidence": 0.948
+        },
+        {
+          "text": "ご",
+          "start": 24.3,
+          "end": 24.42,
+          "confidence": 0.154
+        },
+        {
+          "text": "と",
+          "start": 24.42,
+          "end": 24.52,
+          "confidence": 0.969
+        },
+        {
+          "text": "物",
+          "start": 24.52,
+          "end": 24.76,
+          "confidence": 0.238
+        },
+        {
+          "text": "物",
+          "start": 24.76,
+          "end": 24.92,
+          "confidence": 0.197
+        },
+        {
+          "text": "は",
+          "start": 24.92,
+          "end": 25.08,
+          "confidence": 0.566
+        },
+        {
+          "text": "正",
+          "start": 25.08,
+          "end": 25.36,
+          "confidence": 0.454
+        },
+        {
+          "text": "しく",
+          "start": 25.36,
+          "end": 25.64,
+          "confidence": 0.955
+        },
+        {
+          "text": "表示",
+          "start": 25.64,
+          "end": 26.0,
+          "confidence": 0.414
+        },
+        {
+          "text": "さ",
+          "start": 26.0,
+          "end": 26.28,
+          "confidence": 0.712
+        },
+        {
+          "text": "れ",
+          "start": 26.28,
+          "end": 26.62,
+          "confidence": 0.976
+        },
+        {
+          "text": "ます",
+          "start": 26.62,
+          "end": 27.08,
+          "confidence": 0.474
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 2726,
+      "start": 27.36,
+      "end": 32.39,
+      "text": "しかし グルニュースタブでは バブコン最図免証記ともに正しくない",
+      "tokens": [
+        50364,
+        32156,
+        2849,
+        220,
+        23839,
+        9405,
+        34737,
+        26167,
+        3384,
+        9550,
+        12144,
+        28889,
+        16719,
+        15096,
+        238,
+        28889,
+        18066,
+        4824,
+        8661,
+        3919,
+        111,
+        2347,
+        235,
+        5396,
+        120,
+        16958,
+        3193,
+        4801,
+        4108,
+        15789,
+        26568,
+        9311,
+        50620
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.44616998208535685,
+      "compression_ratio": 1.375,
+      "no_speech_prob": 0.3626025915145874,
+      "confidence": 0.806,
+      "words": [
+        {
+          "text": "しか",
+          "start": 27.36,
+          "end": 27.58,
+          "confidence": 0.959
+        },
+        {
+          "text": "し",
+          "start": 27.58,
+          "end": 27.74,
+          "confidence": 0.992
+        },
+        {
+          "text": " ",
+          "start": 27.74,
+          "end": 27.84,
+          "confidence": 0.249
+        },
+        {
+          "text": "グ",
+          "start": 27.84,
+          "end": 27.92,
+          "confidence": 0.445
+        },
+        {
+          "text": "ル",
+          "start": 27.92,
+          "end": 28.04,
+          "confidence": 0.995
+        },
+        {
+          "text": "ニ",
+          "start": 28.04,
+          "end": 28.24,
+          "confidence": 0.884
+        },
+        {
+          "text": "ュ",
+          "start": 28.24,
+          "end": 28.7,
+          "confidence": 0.995
+        },
+        {
+          "text": "ー",
+          "start": 28.7,
+          "end": 29.18,
+          "confidence": 0.999
+        },
+        {
+          "text": "ス",
+          "start": 29.18,
+          "end": 29.2,
+          "confidence": 0.97
+        },
+        {
+          "text": "タ",
+          "start": 29.2,
+          "end": 29.34,
+          "confidence": 0.992
+        },
+        {
+          "text": "ブ",
+          "start": 29.34,
+          "end": 29.44,
+          "confidence": 0.996
+        },
+        {
+          "text": "では",
+          "start": 29.44,
+          "end": 29.72,
+          "confidence": 0.979
+        },
+        {
+          "text": " バ",
+          "start": 29.72,
+          "end": 30.06,
+          "confidence": 0.503
+        },
+        {
+          "text": "ブ",
+          "start": 30.06,
+          "end": 30.16,
+          "confidence": 0.631
+        },
+        {
+          "text": "コ",
+          "start": 30.16,
+          "end": 30.34,
+          "confidence": 0.631
+        },
+        {
+          "text": "ン",
+          "start": 30.34,
+          "end": 30.42,
+          "confidence": 0.981
+        },
+        {
+          "text": "最",
+          "start": 30.42,
+          "end": 30.6,
+          "confidence": 0.659
+        },
+        {
+          "text": "図",
+          "start": 30.6,
+          "end": 30.88,
+          "confidence": 0.957
+        },
+        {
+          "text": "免",
+          "start": 30.88,
+          "end": 30.94,
+          "confidence": 0.977
+        },
+        {
+          "text": "証",
+          "start": 30.94,
+          "end": 31.12,
+          "confidence": 0.997
+        },
+        {
+          "text": "記",
+          "start": 31.12,
+          "end": 31.26,
+          "confidence": 0.994
+        },
+        {
+          "text": "と",
+          "start": 31.26,
+          "end": 31.42,
+          "confidence": 0.722
+        },
+        {
+          "text": "も",
+          "start": 31.42,
+          "end": 31.54,
+          "confidence": 0.839
+        },
+        {
+          "text": "に",
+          "start": 31.54,
+          "end": 31.66,
+          "confidence": 0.945
+        },
+        {
+          "text": "正",
+          "start": 31.66,
+          "end": 31.96,
+          "confidence": 0.481
+        },
+        {
+          "text": "しく",
+          "start": 31.96,
+          "end": 32.18,
+          "confidence": 0.999
+        },
+        {
+          "text": "ない",
+          "start": 32.18,
+          "end": 32.39,
+          "confidence": 0.938
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 2726,
+      "start": 32.39,
+      "end": 36.34,
+      "text": "以上 時にいいなります こちらいたしても ではありません",
+      "tokens": [
+        50620,
+        29497,
+        220,
+        6611,
+        4108,
+        13806,
+        3203,
+        19420,
+        14384,
+        28567,
+        17679,
+        8822,
+        4801,
+        220,
+        16719,
+        14498,
+        30250,
+        50838
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.44616998208535685,
+      "compression_ratio": 1.375,
+      "no_speech_prob": 0.3626025915145874,
+      "confidence": 0.456,
+      "words": [
+        {
+          "text": "以上",
+          "start": 32.39,
+          "end": 32.74,
+          "confidence": 0.31
+        },
+        {
+          "text": " ",
+          "start": 32.74,
+          "end": 33.04,
+          "confidence": 0.128
+        },
+        {
+          "text": "時",
+          "start": 33.04,
+          "end": 33.1,
+          "confidence": 0.355
+        },
+        {
+          "text": "に",
+          "start": 33.1,
+          "end": 33.12,
+          "confidence": 0.791
+        },
+        {
+          "text": "いい",
+          "start": 33.12,
+          "end": 33.36,
+          "confidence": 0.621
+        },
+        {
+          "text": "な",
+          "start": 33.36,
+          "end": 33.48,
+          "confidence": 0.793
+        },
+        {
+          "text": "ります",
+          "start": 33.48,
+          "end": 34.02,
+          "confidence": 0.896
+        },
+        {
+          "text": " こ",
+          "start": 34.02,
+          "end": 34.38,
+          "confidence": 0.328
+        },
+        {
+          "text": "ちら",
+          "start": 34.38,
+          "end": 34.56,
+          "confidence": 0.684
+        },
+        {
+          "text": "いた",
+          "start": 34.56,
+          "end": 34.84,
+          "confidence": 0.571
+        },
+        {
+          "text": "して",
+          "start": 34.84,
+          "end": 35.04,
+          "confidence": 0.437
+        },
+        {
+          "text": "も",
+          "start": 35.04,
+          "end": 35.18,
+          "confidence": 0.422
+        },
+        {
+          "text": " ",
+          "start": 35.18,
+          "end": 35.38,
+          "confidence": 0.244
+        },
+        {
+          "text": "では",
+          "start": 35.38,
+          "end": 35.46,
+          "confidence": 0.139
+        },
+        {
+          "text": "あり",
+          "start": 35.46,
+          "end": 35.72,
+          "confidence": 0.903
+        },
+        {
+          "text": "ません",
+          "start": 35.72,
+          "end": 36.34,
+          "confidence": 0.997
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 2726,
+      "start": 36.42,
+      "end": 40.4,
+      "text": "パブコンはサプテレクトリーごとに 設定した",
+      "tokens": [
+        50838,
+        23268,
+        28889,
+        18066,
+        4824,
+        3065,
+        23607,
+        20953,
+        22985,
+        16680,
+        10825,
+        7588,
+        12376,
+        3384,
+        9991,
+        3193,
+        4108,
+        220,
+        39035,
+        12088,
+        8533,
+        51042
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.44616998208535685,
+      "compression_ratio": 1.375,
+      "no_speech_prob": 0.3626025915145874,
+      "confidence": 0.849,
+      "words": [
+        {
+          "text": "パ",
+          "start": 36.42,
+          "end": 36.92,
+          "confidence": 0.482
+        },
+        {
+          "text": "ブ",
+          "start": 36.92,
+          "end": 37.04,
+          "confidence": 0.648
+        },
+        {
+          "text": "コ",
+          "start": 37.04,
+          "end": 37.2,
+          "confidence": 0.689
+        },
+        {
+          "text": "ン",
+          "start": 37.2,
+          "end": 37.72,
+          "confidence": 0.994
+        },
+        {
+          "text": "は",
+          "start": 37.72,
+          "end": 37.74,
+          "confidence": 0.975
+        },
+        {
+          "text": "サ",
+          "start": 37.74,
+          "end": 38.22,
+          "confidence": 0.668
+        },
+        {
+          "text": "プ",
+          "start": 38.22,
+          "end": 38.32,
+          "confidence": 0.572
+        },
+        {
+          "text": "テ",
+          "start": 38.32,
+          "end": 38.42,
+          "confidence": 0.984
+        },
+        {
+          "text": "レ",
+          "start": 38.42,
+          "end": 38.56,
+          "confidence": 0.997
+        },
+        {
+          "text": "ク",
+          "start": 38.56,
+          "end": 38.68,
+          "confidence": 0.997
+        },
+        {
+          "text": "ト",
+          "start": 38.68,
+          "end": 38.78,
+          "confidence": 0.998
+        },
+        {
+          "text": "リ",
+          "start": 38.78,
+          "end": 38.92,
+          "confidence": 0.999
+        },
+        {
+          "text": "ー",
+          "start": 38.92,
+          "end": 38.96,
+          "confidence": 0.987
+        },
+        {
+          "text": "ご",
+          "start": 38.96,
+          "end": 39.08,
+          "confidence": 0.959
+        },
+        {
+          "text": "と",
+          "start": 39.08,
+          "end": 39.26,
+          "confidence": 0.999
+        },
+        {
+          "text": "に",
+          "start": 39.26,
+          "end": 39.58,
+          "confidence": 0.974
+        },
+        {
+          "text": " ",
+          "start": 39.58,
+          "end": 39.66,
+          "confidence": 0.663
+        },
+        {
+          "text": "設",
+          "start": 39.66,
+          "end": 39.82,
+          "confidence": 0.911
+        },
+        {
+          "text": "定",
+          "start": 39.82,
+          "end": 40.02,
+          "confidence": 0.999
+        },
+        {
+          "text": "した",
+          "start": 40.02,
+          "end": 40.4,
+          "confidence": 0.873
+        }
+      ]
+    }
+  ],
+  "language": "Japanese"
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_auto/laugh1.mp3.words.json b/tests/expected/tiny_auto/laugh1.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..cc02e90afb5f0b83143a69184da958427ed4a000
--- /dev/null
+++ b/tests/expected/tiny_auto/laugh1.mp3.words.json
@@ -0,0 +1,171 @@
+{
+  "text": " You can't do it, you can't.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.0,
+      "end": 1.7,
+      "text": " You can't do it, you can't.",
+      "tokens": [
+        50364,
+        509,
+        393,
+        380,
+        360,
+        309,
+        11,
+        291,
+        393,
+        380,
+        13,
+        50464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -1.3003114553598256,
+      "compression_ratio": 0.9310344827586207,
+      "no_speech_prob": 0.4180056154727936,
+      "confidence": 0.277,
+      "words": [
+        {
+          "text": "You",
+          "start": 0.0,
+          "end": 0.56,
+          "confidence": 0.081
+        },
+        {
+          "text": "can't",
+          "start": 0.56,
+          "end": 0.82,
+          "confidence": 0.302
+        },
+        {
+          "text": "do",
+          "start": 0.82,
+          "end": 1.04,
+          "confidence": 0.118
+        },
+        {
+          "text": "it,",
+          "start": 1.04,
+          "end": 1.2,
+          "confidence": 0.374
+        },
+        {
+          "text": "you",
+          "start": 1.26,
+          "end": 1.5,
+          "confidence": 0.141
+        },
+        {
+          "text": "can't.",
+          "start": 1.5,
+          "end": 1.7,
+          "confidence": 0.868
+        }
+      ]
+    }
+  ],
+  "language": "en",
+  "language_probs": {
+    "en": 0.2290046215057373,
+    "zh": 0.008879472501575947,
+    "de": 0.02778141386806965,
+    "es": 0.03680439293384552,
+    "ru": 0.018077710643410683,
+    "ko": 0.06068018823862076,
+    "fr": 0.05030563846230507,
+    "ja": 0.027565214782953262,
+    "pt": 0.053550075739622116,
+    "tr": 0.052719857543706894,
+    "pl": 0.02609822154045105,
+    "ca": 0.0011647333158180118,
+    "nl": 0.012231990694999695,
+    "ar": 0.04652511328458786,
+    "sv": 0.05790143832564354,
+    "it": 0.018219497054815292,
+    "id": 0.006198871415108442,
+    "hi": 0.02866329252719879,
+    "fi": 0.007714619394391775,
+    "vi": 0.0017484717536717653,
+    "he": 0.006247490178793669,
+    "uk": 0.00416172482073307,
+    "el": 0.023394295945763588,
+    "ms": 0.0023163489531725645,
+    "cs": 0.0035045240074396133,
+    "ro": 0.003819013712927699,
+    "da": 0.004903710447251797,
+    "hu": 0.019854480400681496,
+    "ta": 0.004097203724086285,
+    "no": 0.005219973158091307,
+    "th": 0.006808128207921982,
+    "ur": 0.03651798143982887,
+    "hr": 0.000954348302911967,
+    "bg": 0.0005249864771030843,
+    "lt": 0.0007880979683250189,
+    "la": 0.005219973158091307,
+    "mi": 0.002624767366796732,
+    "ml": 0.002624767366796732,
+    "cy": 0.01487031951546669,
+    "sk": 0.00025685937725938857,
+    "te": 0.0010814183624461293,
+    "fa": 0.006496361456811428,
+    "lv": 0.00022229323803912848,
+    "bn": 0.0018612387357279658,
+    "sr": 0.0006533561972901225,
+    "az": 0.0015190986450761557,
+    "sl": 0.0012302036629989743,
+    "kn": 0.00015218414773698896,
+    "et": 0.0005480361869558692,
+    "mk": 0.0001639087568037212,
+    "br": 0.001776006305590272,
+    "eu": 0.001264306134544313,
+    "is": 0.0007374632405117154,
+    "hy": 0.00030862365383654833,
+    "ne": 0.00043864260078407824,
+    "mn": 0.0007520083454437554,
+    "bs": 0.0013617111835628748,
+    "kk": 8.570168574806303e-05,
+    "sq": 0.0002609043149277568,
+    "sw": 0.001304439501836896,
+    "gl": 0.004827686119824648,
+    "mr": 0.00020801107166334987,
+    "pa": 0.0009395524975843728,
+    "si": 0.0011830752482637763,
+    "km": 0.0007260299171321094,
+    "sn": 0.001996817532926798,
+    "yo": 0.0009035589173436165,
+    "so": 4.6595199819421396e-05,
+    "af": 0.0001509998255642131,
+    "oc": 0.00048175465781241655,
+    "ka": 0.00022316329705063254,
+    "be": 0.000393196678487584,
+    "tg": 3.2651128094585147e-06,
+    "sd": 0.002860309323295951,
+    "gu": 0.00046876014675945044,
+    "am": 8.241849718615413e-05,
+    "yi": 0.0008259196765720844,
+    "lo": 7.160643872339278e-05,
+    "uz": 4.3158429718914704e-08,
+    "fo": 0.0010941657237708569,
+    "ht": 0.001555123133584857,
+    "ps": 0.0002712975547183305,
+    "tk": 3.5393944131101307e-07,
+    "nn": 0.007959508337080479,
+    "mt": 0.0004912564181722701,
+    "sa": 0.0012892422964796424,
+    "lb": 7.492898248528945e-07,
+    "my": 0.00042348948772996664,
+    "bo": 0.0012398521648719907,
+    "tl": 0.011401468887925148,
+    "mg": 4.178579331437504e-07,
+    "as": 0.0001984855334740132,
+    "tt": 1.6100466382340528e-06,
+    "haw": 0.004535190761089325,
+    "ln": 8.082438580458984e-05,
+    "ha": 7.570124580524862e-07,
+    "ba": 2.531344307499239e-07,
+    "jw": 0.010300369001924992,
+    "su": 1.0605447187117534e-06
+  }
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_auto/laugh2.mp3.words.json b/tests/expected/tiny_auto/laugh2.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..5404314b300353b004f212ff9f0f0b9b3bb91c35
--- /dev/null
+++ b/tests/expected/tiny_auto/laugh2.mp3.words.json
@@ -0,0 +1,133 @@
+{
+  "text": " Haha.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.18,
+      "end": 0.56,
+      "text": " Haha.",
+      "tokens": [
+        50364,
+        19131,
+        13,
+        50401
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -1.316188430786133,
+      "compression_ratio": 0.38461538461538464,
+      "no_speech_prob": 0.5721203088760376,
+      "confidence": 0.079,
+      "words": [
+        {
+          "text": "Haha.",
+          "start": 0.18,
+          "end": 0.56,
+          "confidence": 0.079
+        }
+      ]
+    }
+  ],
+  "language": "en",
+  "language_probs": {
+    "en": 0.6548641920089722,
+    "zh": 0.038717932999134064,
+    "de": 0.025590991601347923,
+    "es": 0.011994256637990475,
+    "ru": 0.011355933733284473,
+    "ko": 0.04633929580450058,
+    "fr": 0.02422906644642353,
+    "ja": 0.014243531040847301,
+    "pt": 0.019468599930405617,
+    "tr": 0.0092684431001544,
+    "pl": 0.007989896461367607,
+    "ca": 0.0003766233567148447,
+    "nl": 0.02767045982182026,
+    "ar": 0.0034096697345376015,
+    "sv": 0.004660465754568577,
+    "it": 0.0023070976603776217,
+    "id": 0.0032282101456075907,
+    "hi": 0.019166767597198486,
+    "fi": 0.00038405158556997776,
+    "vi": 0.0028937491588294506,
+    "he": 0.0006482097669504583,
+    "uk": 0.0007608000887557864,
+    "el": 0.0010562663665041327,
+    "ms": 0.0037156471516937017,
+    "cs": 0.0018179493490606546,
+    "ro": 0.003383135423064232,
+    "da": 0.001361581147648394,
+    "hu": 0.001269133179448545,
+    "ta": 0.0015980799216777086,
+    "no": 0.0012741003884002566,
+    "th": 0.00850520096719265,
+    "ur": 0.002117111813277006,
+    "hr": 0.0002384630497545004,
+    "bg": 0.00032088710577227175,
+    "lt": 0.00015098540461622179,
+    "la": 0.001875657238997519,
+    "mi": 0.0015489121433347464,
+    "ml": 0.001011841231957078,
+    "cy": 0.01327643170952797,
+    "sk": 0.0001626176672289148,
+    "te": 0.0011112901847809553,
+    "fa": 0.0003551896952558309,
+    "lv": 0.00010540479706833139,
+    "bn": 0.0016813284019008279,
+    "sr": 9.122024493990466e-05,
+    "az": 9.979525930248201e-05,
+    "sl": 0.0002431663015158847,
+    "kn": 2.787499215628486e-05,
+    "et": 4.0085364162223414e-05,
+    "mk": 3.091512917308137e-05,
+    "br": 0.0008587384945712984,
+    "eu": 0.00010057795589091256,
+    "is": 0.00015577819431200624,
+    "hy": 0.00014748783723916858,
+    "ne": 0.00018141313921660185,
+    "mn": 0.0002681112091522664,
+    "bs": 0.0002431663015158847,
+    "kk": 2.7335841878084466e-05,
+    "sq": 6.172270514070988e-05,
+    "sw": 0.00029909968725405633,
+    "gl": 0.0007259605336003006,
+    "mr": 0.00017310561088379472,
+    "pa": 8.081665873760357e-05,
+    "si": 0.0005147830815985799,
+    "km": 0.0007637778180651367,
+    "sn": 0.000816219428088516,
+    "yo": 0.00030619261087849736,
+    "so": 3.4114727895939723e-06,
+    "af": 4.6590746933361515e-05,
+    "oc": 0.00016325415344908834,
+    "ka": 4.385352076496929e-05,
+    "be": 7.833019481040537e-05,
+    "tg": 2.4760939254520054e-07,
+    "sd": 0.00022054229339119047,
+    "gu": 8.875974162947387e-05,
+    "am": 1.856874951045029e-05,
+    "yi": 0.00012468329805415124,
+    "lo": 5.362561932997778e-05,
+    "uz": 3.726850383856117e-09,
+    "fo": 0.00023022523964755237,
+    "ht": 0.0003962427144870162,
+    "ps": 4.604794958140701e-05,
+    "tk": 2.9428679937382185e-08,
+    "nn": 0.00637010158970952,
+    "mt": 3.388737604836933e-05,
+    "sa": 0.00042015372309833765,
+    "lb": 1.55556463710127e-07,
+    "my": 0.00015885064203757793,
+    "bo": 0.0005587917985394597,
+    "tl": 0.0009579920442774892,
+    "mg": 3.7639857453086734e-08,
+    "as": 4.351224924903363e-05,
+    "tt": 1.580061166350788e-07,
+    "haw": 0.0029623722657561302,
+    "ln": 1.3479466360877268e-05,
+    "ha": 5.124700308556385e-08,
+    "ba": 2.5718332352653306e-08,
+    "jw": 0.0032030881848186255,
+    "su": 1.0352179913297732e-07
+  }
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_auto/punctuations.mp3.words.json b/tests/expected/tiny_auto/punctuations.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..2d18126b77ff7c4b54b4a194d6fce0742720f8be
--- /dev/null
+++ b/tests/expected/tiny_auto/punctuations.mp3.words.json
@@ -0,0 +1,172 @@
+{
+  "text": " Dima, est ce que l'on vole ?",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.42,
+      "end": 2.58,
+      "text": " Dima, est ce que l'on vole ?",
+      "tokens": [
+        50364,
+        413,
+        4775,
+        11,
+        871,
+        1769,
+        631,
+        287,
+        6,
+        266,
+        49877,
+        2506,
+        50494
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.8432660784040179,
+      "compression_ratio": 0.7777777777777778,
+      "no_speech_prob": 0.0010773586109280586,
+      "confidence": 0.456,
+      "words": [
+        {
+          "text": "Dima,",
+          "start": 0.42,
+          "end": 0.84,
+          "confidence": 0.247
+        },
+        {
+          "text": "est",
+          "start": 1.2,
+          "end": 1.4,
+          "confidence": 0.93
+        },
+        {
+          "text": "ce",
+          "start": 1.4,
+          "end": 1.56,
+          "confidence": 0.587
+        },
+        {
+          "text": "que",
+          "start": 1.56,
+          "end": 1.68,
+          "confidence": 0.916
+        },
+        {
+          "text": "l'on",
+          "start": 1.68,
+          "end": 2.02,
+          "confidence": 0.481
+        },
+        {
+          "text": "vole ?",
+          "start": 2.02,
+          "end": 2.58,
+          "confidence": 0.249
+        }
+      ]
+    }
+  ],
+  "language": "fr",
+  "language_probs": {
+    "en": 0.0004427048552315682,
+    "zh": 4.150092354393564e-05,
+    "de": 8.062254346441478e-05,
+    "es": 2.3646514819120057e-05,
+    "ru": 2.6379595510661602e-05,
+    "ko": 3.101747779510333e-06,
+    "fr": 0.988398015499115,
+    "ja": 9.801208216231316e-05,
+    "pt": 0.001104298629797995,
+    "tr": 4.841759619012009e-06,
+    "pl": 1.2756338037434034e-05,
+    "ca": 6.920935220477986e-07,
+    "nl": 4.487320256885141e-05,
+    "ar": 7.114913751138374e-05,
+    "sv": 2.070558002742473e-05,
+    "it": 0.001104298629797995,
+    "id": 8.380914664485317e-07,
+    "hi": 1.2980614201296703e-06,
+    "fi": 7.67460761608163e-08,
+    "vi": 1.0109312142958515e-06,
+    "he": 0.00013501734065357596,
+    "uk": 1.5262780550528987e-07,
+    "el": 2.2388070647139102e-05,
+    "ms": 2.1869453121325932e-05,
+    "cs": 2.8241736345080426e-06,
+    "ro": 1.1890214409504551e-05,
+    "da": 2.891146777983522e-06,
+    "hu": 5.8402770264365245e-06,
+    "ta": 6.398907625992933e-09,
+    "no": 5.306464458953997e-07,
+    "th": 1.6217863958445378e-06,
+    "ur": 1.8377247670287034e-06,
+    "hr": 1.6565119054234856e-08,
+    "bg": 3.9280556052290194e-07,
+    "lt": 1.0570640363027906e-08,
+    "la": 0.0002483348944224417,
+    "mi": 3.647076312063291e-07,
+    "ml": 9.549777857387198e-09,
+    "cy": 1.612552114238497e-05,
+    "sk": 1.099336799370576e-07,
+    "te": 1.5392920271750654e-09,
+    "fa": 8.348240498889936e-07,
+    "lv": 1.160957729950951e-08,
+    "bn": 2.7854085260514694e-07,
+    "sr": 2.6419332499472148e-08,
+    "az": 8.428907705138045e-08,
+    "sl": 1.6473258028781856e-06,
+    "kn": 9.501843756254402e-10,
+    "et": 2.3914541458225358e-08,
+    "mk": 7.015159297907303e-08,
+    "br": 0.006159283686429262,
+    "eu": 5.074120508652413e-06,
+    "is": 4.916538287602634e-08,
+    "hy": 1.4967571360102738e-07,
+    "ne": 3.332702558367373e-09,
+    "mn": 5.39976134916742e-08,
+    "bs": 3.017182592657264e-08,
+    "kk": 4.051535995586164e-09,
+    "sq": 8.852010751070338e-07,
+    "sw": 8.512894851264718e-07,
+    "gl": 2.0225936168571934e-05,
+    "mr": 4.171988976509056e-09,
+    "pa": 1.5442691392308916e-07,
+    "si": 4.0212069052358856e-07,
+    "km": 4.5211646693132934e-07,
+    "sn": 9.78062416834291e-06,
+    "yo": 3.778702375711873e-05,
+    "so": 3.365910217212331e-08,
+    "af": 1.2073853383753885e-07,
+    "oc": 0.0013851008843630552,
+    "ka": 9.43992901625279e-08,
+    "be": 3.1317190973823017e-07,
+    "tg": 5.346487252921861e-09,
+    "sd": 8.413717296207324e-07,
+    "gu": 1.0570640363027906e-08,
+    "am": 3.2879388101036966e-08,
+    "yi": 6.464596935984446e-06,
+    "lo": 3.0235324288696575e-07,
+    "uz": 7.551113380410701e-12,
+    "fo": 1.4766532103749341e-06,
+    "ht": 0.00015419464034494013,
+    "ps": 1.3681467692094884e-07,
+    "tk": 1.9360801850609732e-10,
+    "nn": 8.1254867836833e-05,
+    "mt": 3.9127417039708234e-07,
+    "sa": 1.975150354383004e-07,
+    "lb": 5.274675629607373e-08,
+    "my": 1.925918923006975e-06,
+    "bo": 1.5870780600835133e-07,
+    "tl": 5.953688742010854e-08,
+    "mg": 8.492480607635855e-10,
+    "as": 5.976990280487371e-08,
+    "tt": 1.1517511389058654e-09,
+    "haw": 0.00011458773951744661,
+    "ln": 5.761833017459139e-05,
+    "ha": 8.982996013706668e-10,
+    "ba": 3.282146221472715e-10,
+    "jw": 3.3276894555456238e-06,
+    "su": 2.5238919287851047e-10
+  }
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_auto/radio_short.mp3.words.json b/tests/expected/tiny_auto/radio_short.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..a10f3dc9d16b9207b21ee7c2bbba0081024b834a
--- /dev/null
+++ b/tests/expected/tiny_auto/radio_short.mp3.words.json
@@ -0,0 +1,2934 @@
+{
+  "text": " What are you telling me, guys? What are you telling me, dude? What are you telling me, dude? What are you telling me, dude? What are you telling me, guys? What are you telling me, guys? What are you telling me, dude? What are you telling me, dude? The most important thing is not to be alert. It's what you do. Yes, man. The reference of the book. Good evening, good evening. All of you, this is your BFFM TV. It's called the BFFM story with the actuality. There are 60 minutes of the report of the analysis of the actions you need. As you can see, it's a bit of a report of the reports of the reports. So, what is it, guys? So, we are ready to do it. The report is ready to be told by the leaders of the CFT's CFT's CFT's CFT. The report of the CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's C The CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's C",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 5.0,
+      "end": 6.12,
+      "text": " What are you telling me, guys?",
+      "tokens": [
+        50364,
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        1074,
+        30,
+        50664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.39804049236018485,
+      "compression_ratio": 4.660377358490566,
+      "no_speech_prob": 0.5096546411514282,
+      "confidence": 0.342,
+      "words": [
+        {
+          "text": "What",
+          "start": 5.0,
+          "end": 5.22,
+          "confidence": 0.041
+        },
+        {
+          "text": "are",
+          "start": 5.22,
+          "end": 5.3,
+          "confidence": 0.602
+        },
+        {
+          "text": "you",
+          "start": 5.3,
+          "end": 5.46,
+          "confidence": 0.97
+        },
+        {
+          "text": "telling",
+          "start": 5.46,
+          "end": 5.7,
+          "confidence": 0.355
+        },
+        {
+          "text": "me,",
+          "start": 5.7,
+          "end": 5.94,
+          "confidence": 0.612
+        },
+        {
+          "text": "guys?",
+          "start": 6.02,
+          "end": 6.12,
+          "confidence": 0.304
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 6.76,
+      "end": 7.57,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        50664,
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30,
+        50764
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.39804049236018485,
+      "compression_ratio": 4.660377358490566,
+      "no_speech_prob": 0.5096546411514282,
+      "confidence": 0.677,
+      "words": [
+        {
+          "text": "What",
+          "start": 6.76,
+          "end": 6.92,
+          "confidence": 0.884
+        },
+        {
+          "text": "are",
+          "start": 6.92,
+          "end": 7.06,
+          "confidence": 0.936
+        },
+        {
+          "text": "you",
+          "start": 7.06,
+          "end": 7.18,
+          "confidence": 0.993
+        },
+        {
+          "text": "telling",
+          "start": 7.18,
+          "end": 7.3,
+          "confidence": 0.906
+        },
+        {
+          "text": "me,",
+          "start": 7.3,
+          "end": 7.44,
+          "confidence": 0.984
+        },
+        {
+          "text": "dude?",
+          "start": 7.48,
+          "end": 7.57,
+          "confidence": 0.132
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 7.57,
+      "end": 9.36,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        50764,
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30,
+        50864
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.39804049236018485,
+      "compression_ratio": 4.660377358490566,
+      "no_speech_prob": 0.5096546411514282,
+      "confidence": 0.826,
+      "words": [
+        {
+          "text": "What",
+          "start": 7.57,
+          "end": 9.12,
+          "confidence": 0.544
+        },
+        {
+          "text": "are",
+          "start": 9.12,
+          "end": 9.28,
+          "confidence": 0.852
+        },
+        {
+          "text": "you",
+          "start": 9.28,
+          "end": 9.3,
+          "confidence": 0.994
+        },
+        {
+          "text": "telling",
+          "start": 9.3,
+          "end": 9.32,
+          "confidence": 0.849
+        },
+        {
+          "text": "me,",
+          "start": 9.32,
+          "end": 9.34,
+          "confidence": 0.951
+        },
+        {
+          "text": "dude?",
+          "start": 9.34,
+          "end": 9.36,
+          "confidence": 0.855
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 11.22,
+      "end": 12.5,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        50864,
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30,
+        50964
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.39804049236018485,
+      "compression_ratio": 4.660377358490566,
+      "no_speech_prob": 0.5096546411514282,
+      "confidence": 0.774,
+      "words": [
+        {
+          "text": "What",
+          "start": 11.22,
+          "end": 11.44,
+          "confidence": 0.423
+        },
+        {
+          "text": "are",
+          "start": 11.44,
+          "end": 11.56,
+          "confidence": 0.791
+        },
+        {
+          "text": "you",
+          "start": 11.56,
+          "end": 11.68,
+          "confidence": 0.994
+        },
+        {
+          "text": "telling",
+          "start": 11.68,
+          "end": 11.7,
+          "confidence": 0.809
+        },
+        {
+          "text": "me,",
+          "start": 11.7,
+          "end": 12.48,
+          "confidence": 0.956
+        },
+        {
+          "text": "dude?",
+          "start": 12.48,
+          "end": 12.5,
+          "confidence": 0.837
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 12.5,
+      "end": 13.54,
+      "text": " What are you telling me, guys?",
+      "tokens": [
+        50964,
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        1074,
+        30,
+        51164
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.39804049236018485,
+      "compression_ratio": 4.660377358490566,
+      "no_speech_prob": 0.5096546411514282,
+      "confidence": 0.76,
+      "words": [
+        {
+          "text": "What",
+          "start": 12.5,
+          "end": 12.52,
+          "confidence": 0.504
+        },
+        {
+          "text": "are",
+          "start": 12.52,
+          "end": 12.54,
+          "confidence": 0.845
+        },
+        {
+          "text": "you",
+          "start": 12.54,
+          "end": 12.64,
+          "confidence": 0.994
+        },
+        {
+          "text": "telling",
+          "start": 12.64,
+          "end": 12.66,
+          "confidence": 0.844
+        },
+        {
+          "text": "me,",
+          "start": 12.66,
+          "end": 13.04,
+          "confidence": 0.962
+        },
+        {
+          "text": "guys?",
+          "start": 13.52,
+          "end": 13.54,
+          "confidence": 0.563
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 0,
+      "start": 20.32,
+      "end": 21.4,
+      "text": " What are you telling me, guys?",
+      "tokens": [
+        51164,
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        1074,
+        30,
+        51414
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.39804049236018485,
+      "compression_ratio": 4.660377358490566,
+      "no_speech_prob": 0.5096546411514282,
+      "confidence": 0.935,
+      "words": [
+        {
+          "text": "What",
+          "start": 20.32,
+          "end": 20.72,
+          "confidence": 0.885
+        },
+        {
+          "text": "are",
+          "start": 20.72,
+          "end": 20.78,
+          "confidence": 0.936
+        },
+        {
+          "text": "you",
+          "start": 20.78,
+          "end": 20.8,
+          "confidence": 0.996
+        },
+        {
+          "text": "telling",
+          "start": 20.8,
+          "end": 21.04,
+          "confidence": 0.935
+        },
+        {
+          "text": "me,",
+          "start": 21.04,
+          "end": 21.3,
+          "confidence": 0.896
+        },
+        {
+          "text": "guys?",
+          "start": 21.38,
+          "end": 21.4,
+          "confidence": 0.969
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 0,
+      "start": 22.08,
+      "end": 22.96,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        51414,
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30,
+        51514
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.39804049236018485,
+      "compression_ratio": 4.660377358490566,
+      "no_speech_prob": 0.5096546411514282,
+      "confidence": 0.953,
+      "words": [
+        {
+          "text": "What",
+          "start": 22.08,
+          "end": 22.24,
+          "confidence": 0.95
+        },
+        {
+          "text": "are",
+          "start": 22.24,
+          "end": 22.36,
+          "confidence": 0.965
+        },
+        {
+          "text": "you",
+          "start": 22.36,
+          "end": 22.44,
+          "confidence": 0.997
+        },
+        {
+          "text": "telling",
+          "start": 22.44,
+          "end": 22.6,
+          "confidence": 0.864
+        },
+        {
+          "text": "me,",
+          "start": 22.6,
+          "end": 22.78,
+          "confidence": 0.984
+        },
+        {
+          "text": "dude?",
+          "start": 22.94,
+          "end": 22.96,
+          "confidence": 0.967
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 0,
+      "start": 22.96,
+      "end": 23.08,
+      "text": " What are you telling me, dude?",
+      "tokens": [
+        51514,
+        708,
+        366,
+        291,
+        3585,
+        385,
+        11,
+        6449,
+        30,
+        51664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.39804049236018485,
+      "compression_ratio": 4.660377358490566,
+      "no_speech_prob": 0.5096546411514282,
+      "confidence": 0.856,
+      "words": [
+        {
+          "text": "What",
+          "start": 22.96,
+          "end": 22.98,
+          "confidence": 0.541
+        },
+        {
+          "text": "are",
+          "start": 22.98,
+          "end": 23.0,
+          "confidence": 0.889
+        },
+        {
+          "text": "you",
+          "start": 23.0,
+          "end": 23.02,
+          "confidence": 0.996
+        },
+        {
+          "text": "telling",
+          "start": 23.02,
+          "end": 23.04,
+          "confidence": 0.882
+        },
+        {
+          "text": "me,",
+          "start": 23.04,
+          "end": 23.06,
+          "confidence": 0.975
+        },
+        {
+          "text": "dude?",
+          "start": 23.06,
+          "end": 23.08,
+          "confidence": 0.955
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 2600,
+      "start": 26.54,
+      "end": 32.48,
+      "text": " The most important thing is not to be alert.",
+      "tokens": [
+        50414,
+        440,
+        881,
+        1021,
+        551,
+        307,
+        406,
+        281,
+        312,
+        9615,
+        13,
+        50664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9188781111207727,
+      "compression_ratio": 1.3594771241830066,
+      "no_speech_prob": 0.09051438421010971,
+      "confidence": 0.276,
+      "words": [
+        {
+          "text": "The",
+          "start": 26.54,
+          "end": 31.02,
+          "confidence": 0.182
+        },
+        {
+          "text": "most",
+          "start": 31.02,
+          "end": 31.18,
+          "confidence": 0.518
+        },
+        {
+          "text": "important",
+          "start": 31.18,
+          "end": 31.5,
+          "confidence": 0.995
+        },
+        {
+          "text": "thing",
+          "start": 31.5,
+          "end": 31.68,
+          "confidence": 0.217
+        },
+        {
+          "text": "is",
+          "start": 31.68,
+          "end": 31.9,
+          "confidence": 0.507
+        },
+        {
+          "text": "not",
+          "start": 31.9,
+          "end": 32.22,
+          "confidence": 0.284
+        },
+        {
+          "text": "to",
+          "start": 32.22,
+          "end": 32.4,
+          "confidence": 0.343
+        },
+        {
+          "text": "be",
+          "start": 32.4,
+          "end": 32.42,
+          "confidence": 0.247
+        },
+        {
+          "text": "alert.",
+          "start": 32.42,
+          "end": 32.48,
+          "confidence": 0.038
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 2600,
+      "start": 33.42,
+      "end": 34.06,
+      "text": " It's what you do.",
+      "tokens": [
+        50664,
+        467,
+        311,
+        437,
+        291,
+        360,
+        13,
+        50764
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9188781111207727,
+      "compression_ratio": 1.3594771241830066,
+      "no_speech_prob": 0.09051438421010971,
+      "confidence": 0.502,
+      "words": [
+        {
+          "text": "It's",
+          "start": 33.42,
+          "end": 33.64,
+          "confidence": 0.307
+        },
+        {
+          "text": "what",
+          "start": 33.64,
+          "end": 33.72,
+          "confidence": 0.616
+        },
+        {
+          "text": "you",
+          "start": 33.72,
+          "end": 33.88,
+          "confidence": 0.898
+        },
+        {
+          "text": "do.",
+          "start": 33.88,
+          "end": 34.06,
+          "confidence": 0.614
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 2600,
+      "start": 34.86,
+      "end": 35.5,
+      "text": " Yes, man.",
+      "tokens": [
+        50764,
+        1079,
+        11,
+        587,
+        13,
+        50864
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9188781111207727,
+      "compression_ratio": 1.3594771241830066,
+      "no_speech_prob": 0.09051438421010971,
+      "confidence": 0.088,
+      "words": [
+        {
+          "text": "Yes,",
+          "start": 34.86,
+          "end": 34.88,
+          "confidence": 0.065
+        },
+        {
+          "text": "man.",
+          "start": 35.48,
+          "end": 35.5,
+          "confidence": 0.12
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 2600,
+      "start": 37.14,
+      "end": 38.64,
+      "text": " The reference of the book.",
+      "tokens": [
+        50864,
+        440,
+        6408,
+        295,
+        264,
+        1446,
+        13,
+        51014
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9188781111207727,
+      "compression_ratio": 1.3594771241830066,
+      "no_speech_prob": 0.09051438421010971,
+      "confidence": 0.268,
+      "words": [
+        {
+          "text": "The",
+          "start": 37.14,
+          "end": 37.28,
+          "confidence": 0.385
+        },
+        {
+          "text": "reference",
+          "start": 37.28,
+          "end": 37.74,
+          "confidence": 0.543
+        },
+        {
+          "text": "of",
+          "start": 37.74,
+          "end": 37.92,
+          "confidence": 0.781
+        },
+        {
+          "text": "the",
+          "start": 37.92,
+          "end": 38.2,
+          "confidence": 0.37
+        },
+        {
+          "text": "book.",
+          "start": 38.2,
+          "end": 38.64,
+          "confidence": 0.023
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 2600,
+      "start": 44.94,
+      "end": 45.65,
+      "text": " Good evening, good evening.",
+      "tokens": [
+        51264,
+        2205,
+        5634,
+        11,
+        665,
+        5634,
+        13,
+        51364
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9188781111207727,
+      "compression_ratio": 1.3594771241830066,
+      "no_speech_prob": 0.09051438421010971,
+      "confidence": 0.398,
+      "words": [
+        {
+          "text": "Good",
+          "start": 44.94,
+          "end": 45.16,
+          "confidence": 0.134
+        },
+        {
+          "text": "evening,",
+          "start": 45.16,
+          "end": 45.4,
+          "confidence": 0.782
+        },
+        {
+          "text": "good",
+          "start": 45.46,
+          "end": 45.58,
+          "confidence": 0.328
+        },
+        {
+          "text": "evening.",
+          "start": 45.58,
+          "end": 45.65,
+          "confidence": 0.733
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 2600,
+      "start": 45.65,
+      "end": 47.76,
+      "text": " All of you, this is your BFFM TV.",
+      "tokens": [
+        51364,
+        1057,
+        295,
+        291,
+        11,
+        341,
+        307,
+        428,
+        363,
+        6345,
+        44,
+        3558,
+        13,
+        51464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9188781111207727,
+      "compression_ratio": 1.3594771241830066,
+      "no_speech_prob": 0.09051438421010971,
+      "confidence": 0.327,
+      "words": [
+        {
+          "text": "All",
+          "start": 45.65,
+          "end": 46.28,
+          "confidence": 0.146
+        },
+        {
+          "text": "of",
+          "start": 46.28,
+          "end": 46.3,
+          "confidence": 0.355
+        },
+        {
+          "text": "you,",
+          "start": 46.3,
+          "end": 46.5,
+          "confidence": 0.953
+        },
+        {
+          "text": "this",
+          "start": 46.54,
+          "end": 46.68,
+          "confidence": 0.226
+        },
+        {
+          "text": "is",
+          "start": 46.68,
+          "end": 46.82,
+          "confidence": 0.254
+        },
+        {
+          "text": "your",
+          "start": 46.82,
+          "end": 47.08,
+          "confidence": 0.184
+        },
+        {
+          "text": "BFFM",
+          "start": 47.08,
+          "end": 47.62,
+          "confidence": 0.326
+        },
+        {
+          "text": "TV.",
+          "start": 47.62,
+          "end": 47.76,
+          "confidence": 0.775
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 2600,
+      "start": 47.76,
+      "end": 51.42,
+      "text": " It's called the BFFM story with the actuality.",
+      "tokens": [
+        51464,
+        467,
+        311,
+        1219,
+        264,
+        363,
+        6345,
+        44,
+        1657,
+        365,
+        264,
+        3539,
+        507,
+        13,
+        51664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9188781111207727,
+      "compression_ratio": 1.3594771241830066,
+      "no_speech_prob": 0.09051438421010971,
+      "confidence": 0.385,
+      "words": [
+        {
+          "text": "It's",
+          "start": 47.76,
+          "end": 48.22,
+          "confidence": 0.351
+        },
+        {
+          "text": "called",
+          "start": 48.22,
+          "end": 48.38,
+          "confidence": 0.215
+        },
+        {
+          "text": "the",
+          "start": 48.38,
+          "end": 48.72,
+          "confidence": 0.207
+        },
+        {
+          "text": "BFFM",
+          "start": 48.72,
+          "end": 49.8,
+          "confidence": 0.849
+        },
+        {
+          "text": "story",
+          "start": 49.8,
+          "end": 50.06,
+          "confidence": 0.467
+        },
+        {
+          "text": "with",
+          "start": 50.06,
+          "end": 50.22,
+          "confidence": 0.368
+        },
+        {
+          "text": "the",
+          "start": 50.22,
+          "end": 50.66,
+          "confidence": 0.179
+        },
+        {
+          "text": "actuality.",
+          "start": 50.66,
+          "end": 51.42,
+          "confidence": 0.322
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 5200,
+      "start": 52.0,
+      "end": 56.02,
+      "text": " There are 60 minutes of the report of the analysis of the actions you need.",
+      "tokens": [
+        50364,
+        821,
+        366,
+        4060,
+        2077,
+        295,
+        264,
+        2275,
+        295,
+        264,
+        5215,
+        295,
+        264,
+        5909,
+        291,
+        643,
+        13,
+        50564
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4928334554036458,
+      "compression_ratio": 3.419753086419753,
+      "no_speech_prob": 0.2597074508666992,
+      "confidence": 0.299,
+      "words": [
+        {
+          "text": "There",
+          "start": 52.0,
+          "end": 52.16,
+          "confidence": 0.088
+        },
+        {
+          "text": "are",
+          "start": 52.16,
+          "end": 52.3,
+          "confidence": 0.683
+        },
+        {
+          "text": "60",
+          "start": 52.3,
+          "end": 52.7,
+          "confidence": 0.201
+        },
+        {
+          "text": "minutes",
+          "start": 52.7,
+          "end": 53.12,
+          "confidence": 0.804
+        },
+        {
+          "text": "of",
+          "start": 53.12,
+          "end": 53.74,
+          "confidence": 0.217
+        },
+        {
+          "text": "the",
+          "start": 53.74,
+          "end": 53.86,
+          "confidence": 0.16
+        },
+        {
+          "text": "report",
+          "start": 53.86,
+          "end": 54.16,
+          "confidence": 0.072
+        },
+        {
+          "text": "of",
+          "start": 54.16,
+          "end": 54.4,
+          "confidence": 0.56
+        },
+        {
+          "text": "the",
+          "start": 54.4,
+          "end": 54.52,
+          "confidence": 0.584
+        },
+        {
+          "text": "analysis",
+          "start": 54.52,
+          "end": 54.7,
+          "confidence": 0.128
+        },
+        {
+          "text": "of",
+          "start": 54.7,
+          "end": 54.82,
+          "confidence": 0.838
+        },
+        {
+          "text": "the",
+          "start": 54.82,
+          "end": 55.22,
+          "confidence": 0.549
+        },
+        {
+          "text": "actions",
+          "start": 55.22,
+          "end": 55.24,
+          "confidence": 0.321
+        },
+        {
+          "text": "you",
+          "start": 55.24,
+          "end": 55.66,
+          "confidence": 0.557
+        },
+        {
+          "text": "need.",
+          "start": 55.66,
+          "end": 56.02,
+          "confidence": 0.163
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 5200,
+      "start": 56.7,
+      "end": 59.8,
+      "text": " As you can see, it's a bit of a report of the reports of the reports.",
+      "tokens": [
+        50564,
+        1018,
+        291,
+        393,
+        536,
+        11,
+        309,
+        311,
+        257,
+        857,
+        295,
+        257,
+        2275,
+        295,
+        264,
+        7122,
+        295,
+        264,
+        7122,
+        13,
+        50764
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4928334554036458,
+      "compression_ratio": 3.419753086419753,
+      "no_speech_prob": 0.2597074508666992,
+      "confidence": 0.287,
+      "words": [
+        {
+          "text": "As",
+          "start": 56.7,
+          "end": 56.9,
+          "confidence": 0.289
+        },
+        {
+          "text": "you",
+          "start": 56.9,
+          "end": 56.96,
+          "confidence": 0.158
+        },
+        {
+          "text": "can",
+          "start": 56.96,
+          "end": 57.34,
+          "confidence": 0.266
+        },
+        {
+          "text": "see,",
+          "start": 57.34,
+          "end": 57.36,
+          "confidence": 0.922
+        },
+        {
+          "text": "it's",
+          "start": 57.64,
+          "end": 57.66,
+          "confidence": 0.309
+        },
+        {
+          "text": "a",
+          "start": 57.66,
+          "end": 57.68,
+          "confidence": 0.456
+        },
+        {
+          "text": "bit",
+          "start": 57.68,
+          "end": 57.7,
+          "confidence": 0.491
+        },
+        {
+          "text": "of",
+          "start": 57.7,
+          "end": 57.96,
+          "confidence": 0.106
+        },
+        {
+          "text": "a",
+          "start": 57.96,
+          "end": 58.1,
+          "confidence": 0.441
+        },
+        {
+          "text": "report",
+          "start": 58.1,
+          "end": 59.06,
+          "confidence": 0.058
+        },
+        {
+          "text": "of",
+          "start": 59.06,
+          "end": 59.32,
+          "confidence": 0.53
+        },
+        {
+          "text": "the",
+          "start": 59.32,
+          "end": 59.46,
+          "confidence": 0.706
+        },
+        {
+          "text": "reports",
+          "start": 59.46,
+          "end": 59.72,
+          "confidence": 0.095
+        },
+        {
+          "text": "of",
+          "start": 59.72,
+          "end": 59.76,
+          "confidence": 0.291
+        },
+        {
+          "text": "the",
+          "start": 59.76,
+          "end": 59.78,
+          "confidence": 0.746
+        },
+        {
+          "text": "reports.",
+          "start": 59.78,
+          "end": 59.8,
+          "confidence": 0.123
+        }
+      ]
+    },
+    {
+      "id": 17,
+      "seek": 5200,
+      "start": 59.8,
+      "end": 60.62,
+      "text": " So, what is it, guys?",
+      "tokens": [
+        50764,
+        407,
+        11,
+        437,
+        307,
+        309,
+        11,
+        1074,
+        30,
+        50814
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4928334554036458,
+      "compression_ratio": 3.419753086419753,
+      "no_speech_prob": 0.2597074508666992,
+      "confidence": 0.234,
+      "words": [
+        {
+          "text": "So,",
+          "start": 59.8,
+          "end": 60.02,
+          "confidence": 0.153
+        },
+        {
+          "text": "what",
+          "start": 60.18,
+          "end": 60.2,
+          "confidence": 0.266
+        },
+        {
+          "text": "is",
+          "start": 60.2,
+          "end": 60.42,
+          "confidence": 0.34
+        },
+        {
+          "text": "it,",
+          "start": 60.42,
+          "end": 60.58,
+          "confidence": 0.189
+        },
+        {
+          "text": "guys?",
+          "start": 60.58,
+          "end": 60.62,
+          "confidence": 0.267
+        }
+      ]
+    },
+    {
+      "id": 18,
+      "seek": 5200,
+      "start": 60.62,
+      "end": 62.98,
+      "text": " So, we are ready to do it.",
+      "tokens": [
+        50814,
+        407,
+        11,
+        321,
+        366,
+        1919,
+        281,
+        360,
+        309,
+        13,
+        50914
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4928334554036458,
+      "compression_ratio": 3.419753086419753,
+      "no_speech_prob": 0.2597074508666992,
+      "confidence": 0.393,
+      "words": [
+        {
+          "text": "So,",
+          "start": 60.62,
+          "end": 62.06,
+          "confidence": 0.172
+        },
+        {
+          "text": "we",
+          "start": 62.08,
+          "end": 62.26,
+          "confidence": 0.36
+        },
+        {
+          "text": "are",
+          "start": 62.26,
+          "end": 62.44,
+          "confidence": 0.246
+        },
+        {
+          "text": "ready",
+          "start": 62.44,
+          "end": 62.68,
+          "confidence": 0.477
+        },
+        {
+          "text": "to",
+          "start": 62.68,
+          "end": 62.7,
+          "confidence": 0.886
+        },
+        {
+          "text": "do",
+          "start": 62.7,
+          "end": 62.92,
+          "confidence": 0.589
+        },
+        {
+          "text": "it.",
+          "start": 62.92,
+          "end": 62.98,
+          "confidence": 0.381
+        }
+      ]
+    },
+    {
+      "id": 19,
+      "seek": 5200,
+      "start": 63.0,
+      "end": 66.94,
+      "text": " The report is ready to be told by the leaders of the CFT's CFT's CFT's CFT.",
+      "tokens": [
+        50914,
+        440,
+        2275,
+        307,
+        1919,
+        281,
+        312,
+        1907,
+        538,
+        264,
+        3523,
+        295,
+        264,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        13,
+        51114
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4928334554036458,
+      "compression_ratio": 3.419753086419753,
+      "no_speech_prob": 0.2597074508666992,
+      "confidence": 0.35,
+      "words": [
+        {
+          "text": "The",
+          "start": 63.0,
+          "end": 63.44,
+          "confidence": 0.495
+        },
+        {
+          "text": "report",
+          "start": 63.44,
+          "end": 63.46,
+          "confidence": 0.387
+        },
+        {
+          "text": "is",
+          "start": 63.46,
+          "end": 63.62,
+          "confidence": 0.522
+        },
+        {
+          "text": "ready",
+          "start": 63.62,
+          "end": 63.88,
+          "confidence": 0.055
+        },
+        {
+          "text": "to",
+          "start": 63.88,
+          "end": 64.26,
+          "confidence": 0.458
+        },
+        {
+          "text": "be",
+          "start": 64.26,
+          "end": 64.68,
+          "confidence": 0.209
+        },
+        {
+          "text": "told",
+          "start": 64.68,
+          "end": 64.7,
+          "confidence": 0.047
+        },
+        {
+          "text": "by",
+          "start": 64.7,
+          "end": 65.04,
+          "confidence": 0.645
+        },
+        {
+          "text": "the",
+          "start": 65.04,
+          "end": 65.08,
+          "confidence": 0.891
+        },
+        {
+          "text": "leaders",
+          "start": 65.08,
+          "end": 65.46,
+          "confidence": 0.569
+        },
+        {
+          "text": "of",
+          "start": 65.46,
+          "end": 65.94,
+          "confidence": 0.835
+        },
+        {
+          "text": "the",
+          "start": 65.94,
+          "end": 66.02,
+          "confidence": 0.738
+        },
+        {
+          "text": "CFT's",
+          "start": 66.02,
+          "end": 66.36,
+          "confidence": 0.098
+        },
+        {
+          "text": "CFT's",
+          "start": 66.36,
+          "end": 66.62,
+          "confidence": 0.406
+        },
+        {
+          "text": "CFT's",
+          "start": 66.62,
+          "end": 66.64,
+          "confidence": 0.512
+        },
+        {
+          "text": "CFT.",
+          "start": 66.64,
+          "end": 66.94,
+          "confidence": 0.876
+        }
+      ]
+    },
+    {
+      "id": 20,
+      "seek": 6700,
+      "start": 67.0,
+      "end": 97.0,
+      "text": " The report of the CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's C",
+      "tokens": [
+        50364,
+        440,
+        2275,
+        295,
+        264,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.09771199932012857,
+      "compression_ratio": 13.264705882352942,
+      "no_speech_prob": 0.7763262987136841,
+      "confidence": 0.908,
+      "words": [
+        {
+          "text": "The",
+          "start": 67.0,
+          "end": 67.84,
+          "confidence": 0.342
+        },
+        {
+          "text": "report",
+          "start": 67.84,
+          "end": 67.86,
+          "confidence": 0.626
+        },
+        {
+          "text": "of",
+          "start": 67.86,
+          "end": 68.16,
+          "confidence": 0.375
+        },
+        {
+          "text": "the",
+          "start": 68.16,
+          "end": 68.36,
+          "confidence": 0.865
+        },
+        {
+          "text": "CFT's",
+          "start": 68.36,
+          "end": 68.68,
+          "confidence": 0.859
+        },
+        {
+          "text": "CFT's",
+          "start": 68.68,
+          "end": 68.82,
+          "confidence": 0.845
+        },
+        {
+          "text": "CFT's",
+          "start": 68.82,
+          "end": 68.94,
+          "confidence": 0.816
+        },
+        {
+          "text": "CFT's",
+          "start": 68.94,
+          "end": 69.04,
+          "confidence": 0.814
+        },
+        {
+          "text": "CFT's",
+          "start": 69.04,
+          "end": 69.24,
+          "confidence": 0.828
+        },
+        {
+          "text": "CFT's",
+          "start": 69.24,
+          "end": 69.64,
+          "confidence": 0.852
+        },
+        {
+          "text": "CFT's",
+          "start": 69.64,
+          "end": 69.88,
+          "confidence": 0.881
+        },
+        {
+          "text": "CFT's",
+          "start": 69.88,
+          "end": 70.34,
+          "confidence": 0.888
+        },
+        {
+          "text": "CFT's",
+          "start": 70.34,
+          "end": 70.92,
+          "confidence": 0.899
+        },
+        {
+          "text": "CFT's",
+          "start": 70.92,
+          "end": 71.62,
+          "confidence": 0.9
+        },
+        {
+          "text": "CFT's",
+          "start": 71.62,
+          "end": 73.26,
+          "confidence": 0.897
+        },
+        {
+          "text": "CFT's",
+          "start": 73.26,
+          "end": 74.0,
+          "confidence": 0.9
+        },
+        {
+          "text": "CFT's",
+          "start": 74.0,
+          "end": 74.4,
+          "confidence": 0.9
+        },
+        {
+          "text": "CFT's",
+          "start": 74.4,
+          "end": 74.96,
+          "confidence": 0.902
+        },
+        {
+          "text": "CFT's",
+          "start": 74.96,
+          "end": 76.3,
+          "confidence": 0.904
+        },
+        {
+          "text": "CFT's",
+          "start": 76.3,
+          "end": 76.32,
+          "confidence": 0.902
+        },
+        {
+          "text": "CFT's",
+          "start": 76.32,
+          "end": 76.38,
+          "confidence": 0.9
+        },
+        {
+          "text": "CFT's",
+          "start": 76.38,
+          "end": 76.5,
+          "confidence": 0.904
+        },
+        {
+          "text": "CFT's",
+          "start": 76.5,
+          "end": 77.4,
+          "confidence": 0.901
+        },
+        {
+          "text": "CFT's",
+          "start": 77.4,
+          "end": 77.42,
+          "confidence": 0.901
+        },
+        {
+          "text": "CFT's",
+          "start": 77.42,
+          "end": 78.0,
+          "confidence": 0.899
+        },
+        {
+          "text": "CFT's",
+          "start": 78.0,
+          "end": 78.02,
+          "confidence": 0.899
+        },
+        {
+          "text": "CFT's",
+          "start": 78.02,
+          "end": 78.06,
+          "confidence": 0.902
+        },
+        {
+          "text": "CFT's",
+          "start": 78.06,
+          "end": 78.08,
+          "confidence": 0.903
+        },
+        {
+          "text": "CFT's",
+          "start": 78.08,
+          "end": 78.1,
+          "confidence": 0.902
+        },
+        {
+          "text": "CFT's",
+          "start": 78.1,
+          "end": 78.98,
+          "confidence": 0.904
+        },
+        {
+          "text": "CFT's",
+          "start": 78.98,
+          "end": 79.24,
+          "confidence": 0.903
+        },
+        {
+          "text": "CFT's",
+          "start": 79.24,
+          "end": 81.7,
+          "confidence": 0.906
+        },
+        {
+          "text": "CFT's",
+          "start": 81.7,
+          "end": 81.72,
+          "confidence": 0.906
+        },
+        {
+          "text": "CFT's",
+          "start": 81.72,
+          "end": 81.94,
+          "confidence": 0.91
+        },
+        {
+          "text": "CFT's",
+          "start": 81.94,
+          "end": 82.32,
+          "confidence": 0.916
+        },
+        {
+          "text": "CFT's",
+          "start": 82.32,
+          "end": 82.34,
+          "confidence": 0.916
+        },
+        {
+          "text": "CFT's",
+          "start": 82.34,
+          "end": 82.36,
+          "confidence": 0.916
+        },
+        {
+          "text": "CFT's",
+          "start": 82.36,
+          "end": 82.44,
+          "confidence": 0.919
+        },
+        {
+          "text": "CFT's",
+          "start": 82.44,
+          "end": 82.54,
+          "confidence": 0.918
+        },
+        {
+          "text": "CFT's",
+          "start": 82.54,
+          "end": 82.56,
+          "confidence": 0.923
+        },
+        {
+          "text": "CFT's",
+          "start": 82.56,
+          "end": 82.58,
+          "confidence": 0.922
+        },
+        {
+          "text": "CFT's",
+          "start": 82.58,
+          "end": 82.6,
+          "confidence": 0.922
+        },
+        {
+          "text": "CFT's",
+          "start": 82.6,
+          "end": 82.62,
+          "confidence": 0.927
+        },
+        {
+          "text": "CFT's",
+          "start": 82.62,
+          "end": 82.68,
+          "confidence": 0.928
+        },
+        {
+          "text": "CFT's",
+          "start": 82.68,
+          "end": 83.12,
+          "confidence": 0.931
+        },
+        {
+          "text": "CFT's",
+          "start": 83.12,
+          "end": 83.24,
+          "confidence": 0.933
+        },
+        {
+          "text": "CFT's",
+          "start": 83.24,
+          "end": 83.54,
+          "confidence": 0.93
+        },
+        {
+          "text": "CFT's",
+          "start": 83.54,
+          "end": 83.56,
+          "confidence": 0.935
+        },
+        {
+          "text": "CFT's",
+          "start": 83.56,
+          "end": 83.58,
+          "confidence": 0.932
+        },
+        {
+          "text": "CFT's",
+          "start": 83.58,
+          "end": 83.7,
+          "confidence": 0.936
+        },
+        {
+          "text": "CFT's",
+          "start": 83.7,
+          "end": 83.72,
+          "confidence": 0.938
+        },
+        {
+          "text": "CFT's",
+          "start": 83.72,
+          "end": 83.74,
+          "confidence": 0.94
+        },
+        {
+          "text": "CFT's",
+          "start": 83.74,
+          "end": 83.76,
+          "confidence": 0.942
+        },
+        {
+          "text": "CFT's",
+          "start": 83.76,
+          "end": 83.78,
+          "confidence": 0.939
+        },
+        {
+          "text": "CFT's",
+          "start": 83.78,
+          "end": 84.02,
+          "confidence": 0.947
+        },
+        {
+          "text": "CFT's",
+          "start": 84.02,
+          "end": 84.04,
+          "confidence": 0.945
+        },
+        {
+          "text": "CFT's",
+          "start": 84.04,
+          "end": 84.28,
+          "confidence": 0.947
+        },
+        {
+          "text": "CFT's",
+          "start": 84.28,
+          "end": 84.4,
+          "confidence": 0.948
+        },
+        {
+          "text": "CFT's",
+          "start": 84.4,
+          "end": 84.54,
+          "confidence": 0.952
+        },
+        {
+          "text": "CFT's",
+          "start": 84.54,
+          "end": 84.56,
+          "confidence": 0.954
+        },
+        {
+          "text": "CFT's",
+          "start": 84.56,
+          "end": 84.58,
+          "confidence": 0.956
+        },
+        {
+          "text": "CFT's",
+          "start": 84.58,
+          "end": 85.02,
+          "confidence": 0.954
+        },
+        {
+          "text": "CFT's",
+          "start": 85.02,
+          "end": 85.98,
+          "confidence": 0.954
+        },
+        {
+          "text": "CFT's",
+          "start": 85.98,
+          "end": 86.62,
+          "confidence": 0.954
+        },
+        {
+          "text": "CFT's",
+          "start": 86.62,
+          "end": 86.8,
+          "confidence": 0.952
+        },
+        {
+          "text": "CFT's",
+          "start": 86.8,
+          "end": 87.28,
+          "confidence": 0.95
+        },
+        {
+          "text": "CFT's",
+          "start": 87.28,
+          "end": 87.58,
+          "confidence": 0.952
+        },
+        {
+          "text": "CFT's",
+          "start": 87.58,
+          "end": 87.66,
+          "confidence": 0.951
+        },
+        {
+          "text": "CFT's",
+          "start": 87.66,
+          "end": 87.68,
+          "confidence": 0.952
+        },
+        {
+          "text": "CFT's",
+          "start": 87.68,
+          "end": 87.7,
+          "confidence": 0.954
+        },
+        {
+          "text": "CFT's",
+          "start": 87.7,
+          "end": 88.84,
+          "confidence": 0.949
+        },
+        {
+          "text": "CFT's",
+          "start": 88.84,
+          "end": 88.86,
+          "confidence": 0.948
+        },
+        {
+          "text": "CFT's",
+          "start": 88.86,
+          "end": 89.2,
+          "confidence": 0.95
+        },
+        {
+          "text": "CFT's",
+          "start": 89.2,
+          "end": 90.42,
+          "confidence": 0.954
+        },
+        {
+          "text": "CFT's",
+          "start": 90.42,
+          "end": 90.82,
+          "confidence": 0.951
+        },
+        {
+          "text": "CFT's",
+          "start": 90.82,
+          "end": 96.98,
+          "confidence": 0.95
+        },
+        {
+          "text": "C",
+          "start": 96.98,
+          "end": 97.0,
+          "confidence": 0.974
+        }
+      ]
+    },
+    {
+      "id": 21,
+      "seek": 9700,
+      "start": 97.0,
+      "end": 127.0,
+      "text": " The CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's CFT's C",
+      "tokens": [
+        50364,
+        440,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383,
+        25469,
+        311,
+        383
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.046164204721493574,
+      "compression_ratio": 21.095238095238095,
+      "no_speech_prob": 0.1808893084526062,
+      "confidence": 0.955,
+      "words": [
+        {
+          "text": "The",
+          "start": 97.0,
+          "end": 97.94,
+          "confidence": 0.245
+        },
+        {
+          "text": "CFT's",
+          "start": 97.94,
+          "end": 97.96,
+          "confidence": 0.471
+        },
+        {
+          "text": "CFT's",
+          "start": 97.96,
+          "end": 99.74,
+          "confidence": 0.915
+        },
+        {
+          "text": "CFT's",
+          "start": 99.74,
+          "end": 102.98,
+          "confidence": 0.915
+        },
+        {
+          "text": "CFT's",
+          "start": 102.98,
+          "end": 104.02,
+          "confidence": 0.918
+        },
+        {
+          "text": "CFT's",
+          "start": 104.02,
+          "end": 104.12,
+          "confidence": 0.93
+        },
+        {
+          "text": "CFT's",
+          "start": 104.12,
+          "end": 104.28,
+          "confidence": 0.94
+        },
+        {
+          "text": "CFT's",
+          "start": 104.28,
+          "end": 104.3,
+          "confidence": 0.95
+        },
+        {
+          "text": "CFT's",
+          "start": 104.3,
+          "end": 104.82,
+          "confidence": 0.96
+        },
+        {
+          "text": "CFT's",
+          "start": 104.82,
+          "end": 105.08,
+          "confidence": 0.965
+        },
+        {
+          "text": "CFT's",
+          "start": 105.08,
+          "end": 105.94,
+          "confidence": 0.967
+        },
+        {
+          "text": "CFT's",
+          "start": 105.94,
+          "end": 106.88,
+          "confidence": 0.969
+        },
+        {
+          "text": "CFT's",
+          "start": 106.88,
+          "end": 108.96,
+          "confidence": 0.97
+        },
+        {
+          "text": "CFT's",
+          "start": 108.96,
+          "end": 108.98,
+          "confidence": 0.971
+        },
+        {
+          "text": "CFT's",
+          "start": 108.98,
+          "end": 109.06,
+          "confidence": 0.971
+        },
+        {
+          "text": "CFT's",
+          "start": 109.06,
+          "end": 109.7,
+          "confidence": 0.971
+        },
+        {
+          "text": "CFT's",
+          "start": 109.7,
+          "end": 109.72,
+          "confidence": 0.971
+        },
+        {
+          "text": "CFT's",
+          "start": 109.72,
+          "end": 110.12,
+          "confidence": 0.97
+        },
+        {
+          "text": "CFT's",
+          "start": 110.12,
+          "end": 110.44,
+          "confidence": 0.971
+        },
+        {
+          "text": "CFT's",
+          "start": 110.44,
+          "end": 110.82,
+          "confidence": 0.973
+        },
+        {
+          "text": "CFT's",
+          "start": 110.82,
+          "end": 110.84,
+          "confidence": 0.973
+        },
+        {
+          "text": "CFT's",
+          "start": 110.84,
+          "end": 110.86,
+          "confidence": 0.974
+        },
+        {
+          "text": "CFT's",
+          "start": 110.86,
+          "end": 110.88,
+          "confidence": 0.973
+        },
+        {
+          "text": "CFT's",
+          "start": 110.88,
+          "end": 110.9,
+          "confidence": 0.972
+        },
+        {
+          "text": "CFT's",
+          "start": 110.9,
+          "end": 111.54,
+          "confidence": 0.972
+        },
+        {
+          "text": "CFT's",
+          "start": 111.54,
+          "end": 111.76,
+          "confidence": 0.971
+        },
+        {
+          "text": "CFT's",
+          "start": 111.76,
+          "end": 111.78,
+          "confidence": 0.971
+        },
+        {
+          "text": "CFT's",
+          "start": 111.78,
+          "end": 111.8,
+          "confidence": 0.971
+        },
+        {
+          "text": "CFT's",
+          "start": 111.8,
+          "end": 111.82,
+          "confidence": 0.972
+        },
+        {
+          "text": "CFT's",
+          "start": 111.82,
+          "end": 111.84,
+          "confidence": 0.973
+        },
+        {
+          "text": "CFT's",
+          "start": 111.84,
+          "end": 111.86,
+          "confidence": 0.973
+        },
+        {
+          "text": "CFT's",
+          "start": 111.86,
+          "end": 111.88,
+          "confidence": 0.973
+        },
+        {
+          "text": "CFT's",
+          "start": 111.88,
+          "end": 111.9,
+          "confidence": 0.974
+        },
+        {
+          "text": "CFT's",
+          "start": 111.9,
+          "end": 111.92,
+          "confidence": 0.974
+        },
+        {
+          "text": "CFT's",
+          "start": 111.92,
+          "end": 111.94,
+          "confidence": 0.974
+        },
+        {
+          "text": "CFT's",
+          "start": 111.94,
+          "end": 111.96,
+          "confidence": 0.974
+        },
+        {
+          "text": "CFT's",
+          "start": 111.96,
+          "end": 111.98,
+          "confidence": 0.974
+        },
+        {
+          "text": "CFT's",
+          "start": 111.98,
+          "end": 112.0,
+          "confidence": 0.976
+        },
+        {
+          "text": "CFT's",
+          "start": 112.0,
+          "end": 112.02,
+          "confidence": 0.975
+        },
+        {
+          "text": "CFT's",
+          "start": 112.02,
+          "end": 112.04,
+          "confidence": 0.975
+        },
+        {
+          "text": "CFT's",
+          "start": 112.04,
+          "end": 112.58,
+          "confidence": 0.977
+        },
+        {
+          "text": "CFT's",
+          "start": 112.58,
+          "end": 112.76,
+          "confidence": 0.976
+        },
+        {
+          "text": "CFT's",
+          "start": 112.76,
+          "end": 112.78,
+          "confidence": 0.978
+        },
+        {
+          "text": "CFT's",
+          "start": 112.78,
+          "end": 112.8,
+          "confidence": 0.978
+        },
+        {
+          "text": "CFT's",
+          "start": 112.8,
+          "end": 112.82,
+          "confidence": 0.977
+        },
+        {
+          "text": "CFT's",
+          "start": 112.82,
+          "end": 112.84,
+          "confidence": 0.979
+        },
+        {
+          "text": "CFT's",
+          "start": 112.84,
+          "end": 112.86,
+          "confidence": 0.978
+        },
+        {
+          "text": "CFT's",
+          "start": 112.86,
+          "end": 112.88,
+          "confidence": 0.978
+        },
+        {
+          "text": "CFT's",
+          "start": 112.88,
+          "end": 113.2,
+          "confidence": 0.979
+        },
+        {
+          "text": "CFT's",
+          "start": 113.2,
+          "end": 113.22,
+          "confidence": 0.978
+        },
+        {
+          "text": "CFT's",
+          "start": 113.22,
+          "end": 113.24,
+          "confidence": 0.978
+        },
+        {
+          "text": "CFT's",
+          "start": 113.24,
+          "end": 113.26,
+          "confidence": 0.977
+        },
+        {
+          "text": "CFT's",
+          "start": 113.26,
+          "end": 114.64,
+          "confidence": 0.979
+        },
+        {
+          "text": "CFT's",
+          "start": 114.64,
+          "end": 114.66,
+          "confidence": 0.977
+        },
+        {
+          "text": "CFT's",
+          "start": 114.66,
+          "end": 115.04,
+          "confidence": 0.977
+        },
+        {
+          "text": "CFT's",
+          "start": 115.04,
+          "end": 115.86,
+          "confidence": 0.975
+        },
+        {
+          "text": "CFT's",
+          "start": 115.86,
+          "end": 116.02,
+          "confidence": 0.976
+        },
+        {
+          "text": "CFT's",
+          "start": 116.02,
+          "end": 118.04,
+          "confidence": 0.976
+        },
+        {
+          "text": "CFT's",
+          "start": 118.04,
+          "end": 118.24,
+          "confidence": 0.976
+        },
+        {
+          "text": "CFT's",
+          "start": 118.24,
+          "end": 120.92,
+          "confidence": 0.975
+        },
+        {
+          "text": "CFT's",
+          "start": 120.92,
+          "end": 120.94,
+          "confidence": 0.974
+        },
+        {
+          "text": "CFT's",
+          "start": 120.94,
+          "end": 121.06,
+          "confidence": 0.976
+        },
+        {
+          "text": "CFT's",
+          "start": 121.06,
+          "end": 121.08,
+          "confidence": 0.975
+        },
+        {
+          "text": "CFT's",
+          "start": 121.08,
+          "end": 121.1,
+          "confidence": 0.973
+        },
+        {
+          "text": "CFT's",
+          "start": 121.1,
+          "end": 122.26,
+          "confidence": 0.975
+        },
+        {
+          "text": "CFT's",
+          "start": 122.26,
+          "end": 122.28,
+          "confidence": 0.974
+        },
+        {
+          "text": "CFT's",
+          "start": 122.28,
+          "end": 122.3,
+          "confidence": 0.974
+        },
+        {
+          "text": "CFT's",
+          "start": 122.3,
+          "end": 122.32,
+          "confidence": 0.976
+        },
+        {
+          "text": "CFT's",
+          "start": 122.32,
+          "end": 122.34,
+          "confidence": 0.975
+        },
+        {
+          "text": "CFT's",
+          "start": 122.34,
+          "end": 122.36,
+          "confidence": 0.975
+        },
+        {
+          "text": "CFT's",
+          "start": 122.36,
+          "end": 122.38,
+          "confidence": 0.975
+        },
+        {
+          "text": "CFT's",
+          "start": 122.38,
+          "end": 122.4,
+          "confidence": 0.975
+        },
+        {
+          "text": "CFT's",
+          "start": 122.4,
+          "end": 122.56,
+          "confidence": 0.973
+        },
+        {
+          "text": "CFT's",
+          "start": 122.56,
+          "end": 126.98,
+          "confidence": 0.972
+        },
+        {
+          "text": "C",
+          "start": 126.98,
+          "end": 127.0,
+          "confidence": 0.992
+        }
+      ]
+    }
+  ],
+  "language": "en",
+  "language_probs": {
+    "en": 0.6579782962799072,
+    "zh": 0.05073783919215202,
+    "de": 0.003372770268470049,
+    "es": 0.008955760858952999,
+    "ru": 0.014423510059714317,
+    "ko": 0.011957507580518723,
+    "fr": 0.009168140590190887,
+    "ja": 0.05153684318065643,
+    "pt": 0.01365590374916792,
+    "tr": 0.0036184543278068304,
+    "pl": 0.002318068640306592,
+    "ca": 0.00034455020795576274,
+    "nl": 0.005965822376310825,
+    "ar": 0.0007181041873991489,
+    "sv": 0.0017634937539696693,
+    "it": 0.0032183199655264616,
+    "id": 0.0022643706761300564,
+    "hi": 0.00909679289907217,
+    "fi": 0.0007069710409268737,
+    "vi": 0.010470344685018063,
+    "he": 0.00012430129572749138,
+    "uk": 0.0007886832463555038,
+    "el": 0.00020413922902662307,
+    "ms": 0.004610029980540276,
+    "cs": 0.0006798874237574637,
+    "ro": 0.00173615338280797,
+    "da": 0.00031127515831030905,
+    "hu": 0.0025064300280064344,
+    "ta": 0.008955760858952999,
+    "no": 0.0006094471318647265,
+    "th": 0.0027100970037281513,
+    "ur": 0.000907768786419183,
+    "hr": 0.0001365182688459754,
+    "bg": 0.0006960105383768678,
+    "lt": 3.660014772322029e-05,
+    "la": 0.007720347959548235,
+    "mi": 0.0006487531354650855,
+    "ml": 0.00268900697119534,
+    "cy": 0.002318068640306592,
+    "sk": 0.00011953939247177914,
+    "te": 0.0032946402207016945,
+    "fa": 0.0002017609222093597,
+    "lv": 4.278990672901273e-05,
+    "bn": 0.00012975878780707717,
+    "sr": 4.4148200686322525e-05,
+    "az": 1.3783741451334208e-05,
+    "sl": 0.00034997606417164207,
+    "kn": 0.00013866812514606863,
+    "et": 4.329430157667957e-05,
+    "mk": 2.1017694962210953e-05,
+    "br": 0.0018194729927927256,
+    "eu": 0.0001441920321667567,
+    "is": 5.2222891099518165e-05,
+    "hy": 4.554961560643278e-05,
+    "ne": 0.00013975570618640631,
+    "mn": 0.0001553009351482615,
+    "bs": 0.00010715441749198362,
+    "kk": 5.928312930336688e-06,
+    "sq": 5.141325164004229e-05,
+    "sw": 6.0816717450506985e-05,
+    "gl": 0.000690594082698226,
+    "mr": 0.0001006622624117881,
+    "pa": 7.110193837434053e-05,
+    "si": 0.0003137165040243417,
+    "km": 0.0006693467148579657,
+    "sn": 0.00011273637937847525,
+    "yo": 0.0001277470582863316,
+    "so": 2.5547203676978825e-06,
+    "af": 5.8031713706441224e-05,
+    "oc": 4.2291387217119336e-05,
+    "ka": 1.008440085570328e-05,
+    "be": 2.5352179363835603e-05,
+    "tg": 1.1112863518292215e-07,
+    "sd": 0.00013812750694341958,
+    "gu": 0.0001318021968472749,
+    "am": 8.198559044103604e-06,
+    "yi": 5.848686851095408e-05,
+    "lo": 8.558519766665995e-06,
+    "uz": 2.218585981594856e-09,
+    "fo": 0.00011722728959284723,
+    "ht": 3.896065027220175e-05,
+    "ps": 1.9667322703753598e-05,
+    "tk": 2.7027908799936995e-08,
+    "nn": 0.04045173153281212,
+    "mt": 1.362315560982097e-05,
+    "sa": 0.00033394951606169343,
+    "lb": 7.04052212086026e-08,
+    "my": 0.00013231804769020528,
+    "bo": 7.480583735741675e-05,
+    "tl": 0.0008395488257519901,
+    "mg": 2.9800533596358036e-08,
+    "as": 1.531692578282673e-05,
+    "tt": 9.253462707192739e-08,
+    "haw": 0.04076899588108063,
+    "ln": 6.850153113191482e-06,
+    "ha": 5.209765774338848e-08,
+    "ba": 2.150648192866811e-08,
+    "jw": 0.006974753458052874,
+    "su": 8.510132687433725e-08
+  }
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_auto/smartphone.mp3.words.json b/tests/expected/tiny_auto/smartphone.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..94c4ca676fbb4401dd2052668ed22176a027ace8
--- /dev/null
+++ b/tests/expected/tiny_auto/smartphone.mp3.words.json
@@ -0,0 +1,5192 @@
+{
+  "text": " C'est évidence que dit Nicolas, mais je me l'étais jamais formulé comme ça. Ce qui fait la force du smartphone, c'est pas seulement la cumulation des fonctions, mais la manière dans quelques interagues entraîne. Et il est d'ailleurs, c'est la photo c'est hyper convaincant. Alors évidemment, il faudrait ajouter les interfaces les grand-attachilles à été beaucoup très souvent mentionnées. Mais bon, il faudrait que les profites aussi de 20 ans pendant l'été, les ordinateurs nous ont appris à piquer sur des icônes, sauf que, alors le smartphone ajoute le toucher, qui rend le contact plus direct, plus sensible. Et puis, évidemment, il faudrait parler aussi des applications qui permettent de contourner le côté tout flu de la navigation web pour aller directement en but. Bref, tout ça, ce sont les conditions qui permettent de créer cette objet, en Nicolas, dit qu'il est très symbolablement inédit dans l'histoire de l'humanité. Mais ça s'assoulait d'une autre interrogation. Est-ce que le fait que cette objet soit inédit un d'huits que notre rapport a lui est aussi un rapport inédit ? Est-ce que le rapport qu'on a au sein de foi n'est comparable à celui qu'on entretenait à d'autres objectes techniques comme la voiture ou le téléphone ? Il n'y a pas d'équivalent. On s'est espèrent de nous voter dans la relation à l'objet. C'est facilement éterricion. Parce que la passion de l'utilisateur et ses affices a dépendance, cette objet d'un lieu en fait, une espèce de relation de médiation avec le monde qui rendent encore avec la maille de celles formes de rogeur. Donc, à objets inédits, rapport inédits. Et, ce rapport, si j'en prends Nicolas, frère caractérisée par un mélange de dépendance et de rogeur. Bon, en vrai, il faudrait remonter très, très filmant tout l'histoire des objectes techniques et de leur infertion dans nos vieux pour déterminer si ce rapport est totalement inédit. Mais j'ai l'impression comme ça que Nicolas se trompe pas vraiment. Pour autant, je sache. Il y a eu plein de discussions autour de la voiture ou même du téléphone. Mais, la dépense n'était pas du même mort, donc le rejet n'en plus n'était pas du même mort. On peut adorer sa bagnure. On a par besoin pour plein de choses. Et là, le soir, quand on va se coucher, on la laisse. On la pade en la main quand on est colis, qu'on n'a même pas au chiot. On pouvait être émervé par son mome qui occupeait la ligne de téléphone pendant une heure chaque soir pour discuter avec un copain. Mais ça ne ressemble pas à ce qu'on peut ressentir à voir même mome aujourd'hui. Continuellement avec son smartphone dans la main, comme c'était une sorte de estimateur extère de tomber de lâcher à l'éantrénée, ça m'a eu immédiate. Bon, je dis ça pour le mome, mais évidemment, va là, bon aussi. Donc, rapport immédiate d'accord. Mais pourquoi, à ton impression qu'on en sortira, j'amé? Et puis, il faut en remettre la faute sur les gens qui ont créé cette critique merveilleux et diabolique et diabolique par que merveilleux. Les économistes parlent de dépendance du santé. Ces vidéos, en fait, on est un santé qui a été étabis, un soit mon termine, en marchand dessus, soit des finissants débordes, des finissants, une signalétique.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.42,
+      "end": 3.66,
+      "text": " C'est évidence que dit Nicolas, mais je me l'étais jamais formulé comme ça.",
+      "tokens": [
+        50364,
+        383,
+        6,
+        377,
+        20090,
+        2778,
+        631,
+        6176,
+        38268,
+        11,
+        2420,
+        1506,
+        385,
+        287,
+        6,
+        22824,
+        14540,
+        49990,
+        526,
+        5173,
+        2788,
+        13,
+        50545
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5389881480823864,
+      "compression_ratio": 1.6505681818181819,
+      "no_speech_prob": 0.14073368906974792,
+      "confidence": 0.709,
+      "words": [
+        {
+          "text": "C'est",
+          "start": 0.42,
+          "end": 0.68,
+          "confidence": 0.849
+        },
+        {
+          "text": "évidence",
+          "start": 0.68,
+          "end": 0.94,
+          "confidence": 0.368
+        },
+        {
+          "text": "que",
+          "start": 0.94,
+          "end": 1.08,
+          "confidence": 0.883
+        },
+        {
+          "text": "dit",
+          "start": 1.08,
+          "end": 1.2,
+          "confidence": 0.343
+        },
+        {
+          "text": "Nicolas,",
+          "start": 1.2,
+          "end": 1.44,
+          "confidence": 0.921
+        },
+        {
+          "text": "mais",
+          "start": 1.88,
+          "end": 2.14,
+          "confidence": 0.914
+        },
+        {
+          "text": "je",
+          "start": 2.14,
+          "end": 2.26,
+          "confidence": 0.778
+        },
+        {
+          "text": "me",
+          "start": 2.26,
+          "end": 2.34,
+          "confidence": 0.954
+        },
+        {
+          "text": "l'étais",
+          "start": 2.34,
+          "end": 2.58,
+          "confidence": 0.72
+        },
+        {
+          "text": "jamais",
+          "start": 2.58,
+          "end": 2.86,
+          "confidence": 0.946
+        },
+        {
+          "text": "formulé",
+          "start": 2.86,
+          "end": 3.26,
+          "confidence": 0.53
+        },
+        {
+          "text": "comme",
+          "start": 3.26,
+          "end": 3.46,
+          "confidence": 0.968
+        },
+        {
+          "text": "ça.",
+          "start": 3.46,
+          "end": 3.66,
+          "confidence": 0.96
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 4.14,
+      "end": 8.9,
+      "text": " Ce qui fait la force du smartphone, c'est pas seulement la cumulation des fonctions, mais la manière",
+      "tokens": [
+        50545,
+        8257,
+        1956,
+        3887,
+        635,
+        3464,
+        1581,
+        13307,
+        11,
+        269,
+        6,
+        377,
+        1736,
+        27772,
+        635,
+        12713,
+        2776,
+        730,
+        17290,
+        3916,
+        11,
+        2420,
+        635,
+        22267,
+        50806
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5389881480823864,
+      "compression_ratio": 1.6505681818181819,
+      "no_speech_prob": 0.14073368906974792,
+      "confidence": 0.789,
+      "words": [
+        {
+          "text": "Ce",
+          "start": 4.14,
+          "end": 4.26,
+          "confidence": 0.392
+        },
+        {
+          "text": "qui",
+          "start": 4.26,
+          "end": 4.38,
+          "confidence": 0.94
+        },
+        {
+          "text": "fait",
+          "start": 4.38,
+          "end": 4.56,
+          "confidence": 0.732
+        },
+        {
+          "text": "la",
+          "start": 4.56,
+          "end": 4.72,
+          "confidence": 0.988
+        },
+        {
+          "text": "force",
+          "start": 4.72,
+          "end": 5.02,
+          "confidence": 0.93
+        },
+        {
+          "text": "du",
+          "start": 5.02,
+          "end": 5.2,
+          "confidence": 0.938
+        },
+        {
+          "text": "smartphone,",
+          "start": 5.2,
+          "end": 5.58,
+          "confidence": 0.909
+        },
+        {
+          "text": "c'est",
+          "start": 5.9,
+          "end": 6.2,
+          "confidence": 0.947
+        },
+        {
+          "text": "pas",
+          "start": 6.2,
+          "end": 6.26,
+          "confidence": 0.983
+        },
+        {
+          "text": "seulement",
+          "start": 6.26,
+          "end": 6.6,
+          "confidence": 0.993
+        },
+        {
+          "text": "la",
+          "start": 6.6,
+          "end": 6.8,
+          "confidence": 0.633
+        },
+        {
+          "text": "cumulation",
+          "start": 6.8,
+          "end": 7.34,
+          "confidence": 0.689
+        },
+        {
+          "text": "des",
+          "start": 7.34,
+          "end": 7.56,
+          "confidence": 0.792
+        },
+        {
+          "text": "fonctions,",
+          "start": 7.56,
+          "end": 8.14,
+          "confidence": 0.834
+        },
+        {
+          "text": "mais",
+          "start": 8.38,
+          "end": 8.5,
+          "confidence": 0.668
+        },
+        {
+          "text": "la",
+          "start": 8.5,
+          "end": 8.62,
+          "confidence": 0.719
+        },
+        {
+          "text": "manière",
+          "start": 8.62,
+          "end": 8.9,
+          "confidence": 0.498
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 8.9,
+      "end": 10.98,
+      "text": " dans quelques interagues entraîne.",
+      "tokens": [
+        50806,
+        2680,
+        16597,
+        728,
+        559,
+        1247,
+        22284,
+        24741,
+        13,
+        50906
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5389881480823864,
+      "compression_ratio": 1.6505681818181819,
+      "no_speech_prob": 0.14073368906974792,
+      "confidence": 0.303,
+      "words": [
+        {
+          "text": "dans",
+          "start": 8.9,
+          "end": 9.06,
+          "confidence": 0.284
+        },
+        {
+          "text": "quelques",
+          "start": 9.06,
+          "end": 9.28,
+          "confidence": 0.281
+        },
+        {
+          "text": "interagues",
+          "start": 9.28,
+          "end": 10.38,
+          "confidence": 0.246
+        },
+        {
+          "text": "entraîne.",
+          "start": 10.38,
+          "end": 10.98,
+          "confidence": 0.446
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 11.0,
+      "end": 12.96,
+      "text": " Et il est d'ailleurs, c'est la photo c'est hyper convaincant.",
+      "tokens": [
+        50906,
+        3790,
+        1930,
+        871,
+        274,
+        6,
+        19400,
+        11,
+        269,
+        6,
+        377,
+        635,
+        5052,
+        269,
+        6,
+        377,
+        9848,
+        3754,
+        491,
+        66,
+        394,
+        13,
+        51006
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5389881480823864,
+      "compression_ratio": 1.6505681818181819,
+      "no_speech_prob": 0.14073368906974792,
+      "confidence": 0.63,
+      "words": [
+        {
+          "text": "Et",
+          "start": 11.0,
+          "end": 11.12,
+          "confidence": 0.36
+        },
+        {
+          "text": "il",
+          "start": 11.12,
+          "end": 11.28,
+          "confidence": 0.144
+        },
+        {
+          "text": "est",
+          "start": 11.28,
+          "end": 11.38,
+          "confidence": 0.241
+        },
+        {
+          "text": "d'ailleurs,",
+          "start": 11.38,
+          "end": 11.6,
+          "confidence": 0.904
+        },
+        {
+          "text": "c'est",
+          "start": 11.7,
+          "end": 11.78,
+          "confidence": 0.886
+        },
+        {
+          "text": "la",
+          "start": 11.78,
+          "end": 11.8,
+          "confidence": 0.969
+        },
+        {
+          "text": "photo",
+          "start": 11.8,
+          "end": 12.02,
+          "confidence": 0.809
+        },
+        {
+          "text": "c'est",
+          "start": 12.02,
+          "end": 12.26,
+          "confidence": 0.785
+        },
+        {
+          "text": "hyper",
+          "start": 12.26,
+          "end": 12.46,
+          "confidence": 0.938
+        },
+        {
+          "text": "convaincant.",
+          "start": 12.46,
+          "end": 12.96,
+          "confidence": 0.51
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 13.3,
+      "end": 18.8,
+      "text": " Alors évidemment, il faudrait ajouter les interfaces les grand-attachilles à été beaucoup très souvent",
+      "tokens": [
+        51006,
+        9946,
+        24724,
+        11,
+        1930,
+        38694,
+        8645,
+        17680,
+        23985,
+        1512,
+        28416,
+        1512,
+        2697,
+        12,
+        1591,
+        608,
+        14835,
+        1531,
+        8862,
+        8796,
+        5732,
+        20847,
+        51306
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5389881480823864,
+      "compression_ratio": 1.6505681818181819,
+      "no_speech_prob": 0.14073368906974792,
+      "confidence": 0.532,
+      "words": [
+        {
+          "text": "Alors",
+          "start": 13.3,
+          "end": 13.56,
+          "confidence": 0.894
+        },
+        {
+          "text": "évidemment,",
+          "start": 13.56,
+          "end": 13.82,
+          "confidence": 0.778
+        },
+        {
+          "text": "il",
+          "start": 14.38,
+          "end": 14.4,
+          "confidence": 0.964
+        },
+        {
+          "text": "faudrait",
+          "start": 14.4,
+          "end": 14.76,
+          "confidence": 0.856
+        },
+        {
+          "text": "ajouter",
+          "start": 14.76,
+          "end": 15.38,
+          "confidence": 0.883
+        },
+        {
+          "text": "les",
+          "start": 15.38,
+          "end": 15.6,
+          "confidence": 0.934
+        },
+        {
+          "text": "interfaces",
+          "start": 15.6,
+          "end": 16.0,
+          "confidence": 0.38
+        },
+        {
+          "text": "les",
+          "start": 16.0,
+          "end": 16.5,
+          "confidence": 0.463
+        },
+        {
+          "text": "grand-attachilles",
+          "start": 16.5,
+          "end": 17.16,
+          "confidence": 0.213
+        },
+        {
+          "text": "à",
+          "start": 17.16,
+          "end": 17.32,
+          "confidence": 0.406
+        },
+        {
+          "text": "été",
+          "start": 17.32,
+          "end": 17.72,
+          "confidence": 0.894
+        },
+        {
+          "text": "beaucoup",
+          "start": 17.72,
+          "end": 18.28,
+          "confidence": 0.797
+        },
+        {
+          "text": "très",
+          "start": 18.28,
+          "end": 18.64,
+          "confidence": 0.493
+        },
+        {
+          "text": "souvent",
+          "start": 18.64,
+          "end": 18.8,
+          "confidence": 0.822
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 0,
+      "start": 18.8,
+      "end": 19.84,
+      "text": " mentionnées.",
+      "tokens": [
+        51306,
+        2152,
+        77,
+        6836,
+        13,
+        51356
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5389881480823864,
+      "compression_ratio": 1.6505681818181819,
+      "no_speech_prob": 0.14073368906974792,
+      "confidence": 0.626,
+      "words": [
+        {
+          "text": "mentionnées.",
+          "start": 18.8,
+          "end": 19.84,
+          "confidence": 0.626
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 0,
+      "start": 20.02,
+      "end": 23.58,
+      "text": " Mais bon, il faudrait que les profites aussi de 20 ans pendant l'été, les ordinateurs",
+      "tokens": [
+        51356,
+        6313,
+        4428,
+        11,
+        1930,
+        38694,
+        8645,
+        631,
+        1512,
+        1740,
+        3324,
+        6212,
+        368,
+        945,
+        1567,
+        17338,
+        287,
+        6,
+        21210,
+        11,
+        1512,
+        4792,
+        13923,
+        2156,
+        51543
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5389881480823864,
+      "compression_ratio": 1.6505681818181819,
+      "no_speech_prob": 0.14073368906974792,
+      "confidence": 0.658,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 20.02,
+          "end": 20.26,
+          "confidence": 0.98
+        },
+        {
+          "text": "bon,",
+          "start": 20.26,
+          "end": 20.46,
+          "confidence": 0.568
+        },
+        {
+          "text": "il",
+          "start": 20.6,
+          "end": 20.68,
+          "confidence": 0.975
+        },
+        {
+          "text": "faudrait",
+          "start": 20.68,
+          "end": 20.78,
+          "confidence": 0.771
+        },
+        {
+          "text": "que",
+          "start": 20.78,
+          "end": 20.92,
+          "confidence": 0.388
+        },
+        {
+          "text": "les",
+          "start": 20.92,
+          "end": 20.96,
+          "confidence": 0.22
+        },
+        {
+          "text": "profites",
+          "start": 20.96,
+          "end": 21.36,
+          "confidence": 0.57
+        },
+        {
+          "text": "aussi",
+          "start": 21.36,
+          "end": 21.72,
+          "confidence": 0.52
+        },
+        {
+          "text": "de",
+          "start": 21.72,
+          "end": 21.92,
+          "confidence": 0.492
+        },
+        {
+          "text": "20",
+          "start": 21.92,
+          "end": 22.14,
+          "confidence": 0.915
+        },
+        {
+          "text": "ans",
+          "start": 22.14,
+          "end": 22.32,
+          "confidence": 0.942
+        },
+        {
+          "text": "pendant",
+          "start": 22.32,
+          "end": 22.52,
+          "confidence": 0.916
+        },
+        {
+          "text": "l'été,",
+          "start": 22.52,
+          "end": 22.86,
+          "confidence": 0.48
+        },
+        {
+          "text": "les",
+          "start": 22.98,
+          "end": 23.1,
+          "confidence": 0.903
+        },
+        {
+          "text": "ordinateurs",
+          "start": 23.1,
+          "end": 23.58,
+          "confidence": 0.946
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 0,
+      "start": 23.58,
+      "end": 28.07,
+      "text": " nous ont appris à piquer sur des icônes, sauf que, alors le smartphone ajoute le toucher,",
+      "tokens": [
+        51543,
+        4666,
+        6592,
+        724,
+        5714,
+        1531,
+        280,
+        23909,
+        1022,
+        730,
+        4376,
+        2851,
+        4081,
+        11,
+        601,
+        2947,
+        631,
+        11,
+        11246,
+        476,
+        13307,
+        17680,
+        14040,
+        476,
+        2557,
+        260,
+        11,
+        51766
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5389881480823864,
+      "compression_ratio": 1.6505681818181819,
+      "no_speech_prob": 0.14073368906974792,
+      "confidence": 0.656,
+      "words": [
+        {
+          "text": "nous",
+          "start": 23.58,
+          "end": 23.78,
+          "confidence": 0.767
+        },
+        {
+          "text": "ont",
+          "start": 23.78,
+          "end": 23.9,
+          "confidence": 0.98
+        },
+        {
+          "text": "appris",
+          "start": 23.9,
+          "end": 24.12,
+          "confidence": 0.952
+        },
+        {
+          "text": "à",
+          "start": 24.12,
+          "end": 24.26,
+          "confidence": 0.34
+        },
+        {
+          "text": "piquer",
+          "start": 24.26,
+          "end": 24.54,
+          "confidence": 0.449
+        },
+        {
+          "text": "sur",
+          "start": 24.54,
+          "end": 24.72,
+          "confidence": 0.816
+        },
+        {
+          "text": "des",
+          "start": 24.72,
+          "end": 24.9,
+          "confidence": 0.96
+        },
+        {
+          "text": "icônes,",
+          "start": 24.9,
+          "end": 25.56,
+          "confidence": 0.599
+        },
+        {
+          "text": "sauf",
+          "start": 25.64,
+          "end": 25.8,
+          "confidence": 0.522
+        },
+        {
+          "text": "que,",
+          "start": 25.8,
+          "end": 26.36,
+          "confidence": 0.915
+        },
+        {
+          "text": "alors",
+          "start": 26.36,
+          "end": 26.58,
+          "confidence": 0.396
+        },
+        {
+          "text": "le",
+          "start": 26.58,
+          "end": 26.72,
+          "confidence": 0.824
+        },
+        {
+          "text": "smartphone",
+          "start": 26.72,
+          "end": 27.0,
+          "confidence": 0.977
+        },
+        {
+          "text": "ajoute",
+          "start": 27.0,
+          "end": 27.5,
+          "confidence": 0.674
+        },
+        {
+          "text": "le",
+          "start": 27.5,
+          "end": 27.62,
+          "confidence": 0.552
+        },
+        {
+          "text": "toucher,",
+          "start": 27.62,
+          "end": 28.07,
+          "confidence": 0.631
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 2804,
+      "start": 28.07,
+      "end": 30.6,
+      "text": " qui rend le contact plus direct, plus sensible.",
+      "tokens": [
+        50364,
+        1956,
+        6125,
+        476,
+        3385,
+        1804,
+        2047,
+        11,
+        1804,
+        25380,
+        13,
+        50496
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4256427271836469,
+      "compression_ratio": 1.7156549520766773,
+      "no_speech_prob": 0.12921307981014252,
+      "confidence": 0.742,
+      "words": [
+        {
+          "text": "qui",
+          "start": 28.07,
+          "end": 28.26,
+          "confidence": 0.305
+        },
+        {
+          "text": "rend",
+          "start": 28.26,
+          "end": 28.5,
+          "confidence": 0.763
+        },
+        {
+          "text": "le",
+          "start": 28.5,
+          "end": 28.72,
+          "confidence": 0.988
+        },
+        {
+          "text": "contact",
+          "start": 28.72,
+          "end": 29.06,
+          "confidence": 0.817
+        },
+        {
+          "text": "plus",
+          "start": 29.06,
+          "end": 29.48,
+          "confidence": 0.84
+        },
+        {
+          "text": "direct,",
+          "start": 29.48,
+          "end": 30.02,
+          "confidence": 0.944
+        },
+        {
+          "text": "plus",
+          "start": 30.18,
+          "end": 30.24,
+          "confidence": 0.992
+        },
+        {
+          "text": "sensible.",
+          "start": 30.24,
+          "end": 30.6,
+          "confidence": 0.618
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 2804,
+      "start": 31.1,
+      "end": 34.76,
+      "text": " Et puis, évidemment, il faudrait parler aussi des applications qui permettent de contourner le côté",
+      "tokens": [
+        50496,
+        3790,
+        9093,
+        11,
+        24724,
+        11,
+        1930,
+        38694,
+        8645,
+        16421,
+        6212,
+        730,
+        5821,
+        1956,
+        21540,
+        317,
+        368,
+        21234,
+        1193,
+        476,
+        18437,
+        50698
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4256427271836469,
+      "compression_ratio": 1.7156549520766773,
+      "no_speech_prob": 0.12921307981014252,
+      "confidence": 0.777,
+      "words": [
+        {
+          "text": "Et",
+          "start": 31.1,
+          "end": 31.24,
+          "confidence": 0.949
+        },
+        {
+          "text": "puis,",
+          "start": 31.24,
+          "end": 31.36,
+          "confidence": 0.721
+        },
+        {
+          "text": "évidemment,",
+          "start": 31.42,
+          "end": 31.62,
+          "confidence": 0.213
+        },
+        {
+          "text": "il",
+          "start": 31.7,
+          "end": 31.76,
+          "confidence": 0.959
+        },
+        {
+          "text": "faudrait",
+          "start": 31.76,
+          "end": 31.94,
+          "confidence": 0.994
+        },
+        {
+          "text": "parler",
+          "start": 31.94,
+          "end": 32.14,
+          "confidence": 0.847
+        },
+        {
+          "text": "aussi",
+          "start": 32.14,
+          "end": 32.36,
+          "confidence": 0.925
+        },
+        {
+          "text": "des",
+          "start": 32.36,
+          "end": 32.46,
+          "confidence": 0.921
+        },
+        {
+          "text": "applications",
+          "start": 32.46,
+          "end": 32.88,
+          "confidence": 0.857
+        },
+        {
+          "text": "qui",
+          "start": 32.88,
+          "end": 33.2,
+          "confidence": 0.663
+        },
+        {
+          "text": "permettent",
+          "start": 33.2,
+          "end": 33.8,
+          "confidence": 0.952
+        },
+        {
+          "text": "de",
+          "start": 33.8,
+          "end": 33.96,
+          "confidence": 0.951
+        },
+        {
+          "text": "contourner",
+          "start": 33.96,
+          "end": 34.4,
+          "confidence": 0.721
+        },
+        {
+          "text": "le",
+          "start": 34.4,
+          "end": 34.52,
+          "confidence": 0.654
+        },
+        {
+          "text": "côté",
+          "start": 34.52,
+          "end": 34.76,
+          "confidence": 0.641
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 2804,
+      "start": 34.8,
+      "end": 37.86,
+      "text": " tout flu de la navigation web pour aller directement en but.",
+      "tokens": [
+        50698,
+        3486,
+        5029,
+        368,
+        635,
+        17346,
+        3670,
+        2016,
+        8722,
+        37297,
+        465,
+        457,
+        13,
+        50860
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4256427271836469,
+      "compression_ratio": 1.7156549520766773,
+      "no_speech_prob": 0.12921307981014252,
+      "confidence": 0.735,
+      "words": [
+        {
+          "text": "tout",
+          "start": 34.8,
+          "end": 35.04,
+          "confidence": 0.945
+        },
+        {
+          "text": "flu",
+          "start": 35.04,
+          "end": 35.32,
+          "confidence": 0.484
+        },
+        {
+          "text": "de",
+          "start": 35.32,
+          "end": 35.64,
+          "confidence": 0.35
+        },
+        {
+          "text": "la",
+          "start": 35.64,
+          "end": 35.78,
+          "confidence": 0.921
+        },
+        {
+          "text": "navigation",
+          "start": 35.78,
+          "end": 36.24,
+          "confidence": 0.903
+        },
+        {
+          "text": "web",
+          "start": 36.24,
+          "end": 36.64,
+          "confidence": 0.913
+        },
+        {
+          "text": "pour",
+          "start": 36.64,
+          "end": 36.84,
+          "confidence": 0.57
+        },
+        {
+          "text": "aller",
+          "start": 36.84,
+          "end": 37.06,
+          "confidence": 0.991
+        },
+        {
+          "text": "directement",
+          "start": 37.06,
+          "end": 37.48,
+          "confidence": 0.981
+        },
+        {
+          "text": "en",
+          "start": 37.48,
+          "end": 37.7,
+          "confidence": 0.654
+        },
+        {
+          "text": "but.",
+          "start": 37.7,
+          "end": 37.86,
+          "confidence": 0.768
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 2804,
+      "start": 38.78,
+      "end": 43.12,
+      "text": " Bref, tout ça, ce sont les conditions qui permettent de créer cette objet, en Nicolas,",
+      "tokens": [
+        50860,
+        49957,
+        11,
+        3486,
+        2788,
+        11,
+        1769,
+        4900,
+        1512,
+        4487,
+        1956,
+        21540,
+        317,
+        368,
+        32062,
+        5550,
+        14964,
+        11,
+        465,
+        38268,
+        11,
+        51121
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4256427271836469,
+      "compression_ratio": 1.7156549520766773,
+      "no_speech_prob": 0.12921307981014252,
+      "confidence": 0.737,
+      "words": [
+        {
+          "text": "Bref,",
+          "start": 38.78,
+          "end": 38.8,
+          "confidence": 0.972
+        },
+        {
+          "text": "tout",
+          "start": 38.84,
+          "end": 39.04,
+          "confidence": 0.817
+        },
+        {
+          "text": "ça,",
+          "start": 39.04,
+          "end": 39.46,
+          "confidence": 0.984
+        },
+        {
+          "text": "ce",
+          "start": 39.54,
+          "end": 39.76,
+          "confidence": 0.905
+        },
+        {
+          "text": "sont",
+          "start": 39.76,
+          "end": 39.96,
+          "confidence": 0.98
+        },
+        {
+          "text": "les",
+          "start": 39.96,
+          "end": 40.1,
+          "confidence": 0.982
+        },
+        {
+          "text": "conditions",
+          "start": 40.1,
+          "end": 40.64,
+          "confidence": 0.956
+        },
+        {
+          "text": "qui",
+          "start": 40.64,
+          "end": 40.96,
+          "confidence": 0.995
+        },
+        {
+          "text": "permettent",
+          "start": 40.96,
+          "end": 41.58,
+          "confidence": 0.994
+        },
+        {
+          "text": "de",
+          "start": 41.58,
+          "end": 41.64,
+          "confidence": 0.993
+        },
+        {
+          "text": "créer",
+          "start": 41.64,
+          "end": 42.08,
+          "confidence": 0.91
+        },
+        {
+          "text": "cette",
+          "start": 42.08,
+          "end": 42.34,
+          "confidence": 0.473
+        },
+        {
+          "text": "objet,",
+          "start": 42.34,
+          "end": 42.64,
+          "confidence": 0.235
+        },
+        {
+          "text": "en",
+          "start": 42.7,
+          "end": 42.84,
+          "confidence": 0.221
+        },
+        {
+          "text": "Nicolas,",
+          "start": 42.84,
+          "end": 43.12,
+          "confidence": 0.537
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 2804,
+      "start": 43.12,
+      "end": 46.58,
+      "text": " dit qu'il est très symbolablement inédit dans l'histoire de l'humanité.",
+      "tokens": [
+        51121,
+        6176,
+        421,
+        6,
+        388,
+        871,
+        5732,
+        5986,
+        712,
+        518,
+        294,
+        7811,
+        270,
+        2680,
+        287,
+        6,
+        29093,
+        368,
+        287,
+        6,
+        18796,
+        5066,
+        13,
+        51290
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4256427271836469,
+      "compression_ratio": 1.7156549520766773,
+      "no_speech_prob": 0.12921307981014252,
+      "confidence": 0.717,
+      "words": [
+        {
+          "text": "dit",
+          "start": 43.12,
+          "end": 43.56,
+          "confidence": 0.696
+        },
+        {
+          "text": "qu'il",
+          "start": 43.56,
+          "end": 43.76,
+          "confidence": 0.958
+        },
+        {
+          "text": "est",
+          "start": 43.76,
+          "end": 43.9,
+          "confidence": 0.849
+        },
+        {
+          "text": "très",
+          "start": 43.9,
+          "end": 44.08,
+          "confidence": 0.443
+        },
+        {
+          "text": "symbolablement",
+          "start": 44.08,
+          "end": 44.86,
+          "confidence": 0.321
+        },
+        {
+          "text": "inédit",
+          "start": 44.86,
+          "end": 45.54,
+          "confidence": 0.655
+        },
+        {
+          "text": "dans",
+          "start": 45.54,
+          "end": 45.74,
+          "confidence": 0.817
+        },
+        {
+          "text": "l'histoire",
+          "start": 45.74,
+          "end": 46.02,
+          "confidence": 0.824
+        },
+        {
+          "text": "de",
+          "start": 46.02,
+          "end": 46.14,
+          "confidence": 0.983
+        },
+        {
+          "text": "l'humanité.",
+          "start": 46.14,
+          "end": 46.58,
+          "confidence": 0.99
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 2804,
+      "start": 47.06,
+      "end": 48.76,
+      "text": " Mais ça s'assoulait d'une autre interrogation.",
+      "tokens": [
+        51290,
+        6313,
+        2788,
+        262,
+        6,
+        640,
+        263,
+        35235,
+        274,
+        6,
+        2613,
+        15081,
+        24871,
+        399,
+        13,
+        51402
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4256427271836469,
+      "compression_ratio": 1.7156549520766773,
+      "no_speech_prob": 0.12921307981014252,
+      "confidence": 0.717,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 47.06,
+          "end": 47.24,
+          "confidence": 0.928
+        },
+        {
+          "text": "ça",
+          "start": 47.24,
+          "end": 47.48,
+          "confidence": 0.75
+        },
+        {
+          "text": "s'assoulait",
+          "start": 47.48,
+          "end": 47.84,
+          "confidence": 0.616
+        },
+        {
+          "text": "d'une",
+          "start": 47.84,
+          "end": 48.08,
+          "confidence": 0.674
+        },
+        {
+          "text": "autre",
+          "start": 48.08,
+          "end": 48.18,
+          "confidence": 0.964
+        },
+        {
+          "text": "interrogation.",
+          "start": 48.18,
+          "end": 48.76,
+          "confidence": 0.855
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 2804,
+      "start": 49.42,
+      "end": 54.93,
+      "text": " Est-ce que le fait que cette objet soit inédit un d'huits que notre rapport a lui est aussi un rapport",
+      "tokens": [
+        51402,
+        4410,
+        12,
+        384,
+        631,
+        476,
+        3887,
+        631,
+        5550,
+        14964,
+        12703,
+        294,
+        7811,
+        270,
+        517,
+        274,
+        6,
+        12086,
+        1208,
+        631,
+        10349,
+        18018,
+        257,
+        8783,
+        871,
+        6212,
+        517,
+        18018,
+        51710
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4256427271836469,
+      "compression_ratio": 1.7156549520766773,
+      "no_speech_prob": 0.12921307981014252,
+      "confidence": 0.704,
+      "words": [
+        {
+          "text": "Est-ce",
+          "start": 49.42,
+          "end": 49.7,
+          "confidence": 0.919
+        },
+        {
+          "text": "que",
+          "start": 49.7,
+          "end": 49.74,
+          "confidence": 0.99
+        },
+        {
+          "text": "le",
+          "start": 49.74,
+          "end": 49.82,
+          "confidence": 0.871
+        },
+        {
+          "text": "fait",
+          "start": 49.82,
+          "end": 50.02,
+          "confidence": 0.945
+        },
+        {
+          "text": "que",
+          "start": 50.02,
+          "end": 50.16,
+          "confidence": 0.923
+        },
+        {
+          "text": "cette",
+          "start": 50.16,
+          "end": 50.3,
+          "confidence": 0.943
+        },
+        {
+          "text": "objet",
+          "start": 50.3,
+          "end": 50.64,
+          "confidence": 0.963
+        },
+        {
+          "text": "soit",
+          "start": 50.64,
+          "end": 51.1,
+          "confidence": 0.99
+        },
+        {
+          "text": "inédit",
+          "start": 51.1,
+          "end": 51.82,
+          "confidence": 0.928
+        },
+        {
+          "text": "un",
+          "start": 51.82,
+          "end": 52.08,
+          "confidence": 0.511
+        },
+        {
+          "text": "d'huits",
+          "start": 52.08,
+          "end": 52.34,
+          "confidence": 0.246
+        },
+        {
+          "text": "que",
+          "start": 52.34,
+          "end": 52.44,
+          "confidence": 0.974
+        },
+        {
+          "text": "notre",
+          "start": 52.44,
+          "end": 52.66,
+          "confidence": 0.992
+        },
+        {
+          "text": "rapport",
+          "start": 52.66,
+          "end": 53.24,
+          "confidence": 0.779
+        },
+        {
+          "text": "a",
+          "start": 53.24,
+          "end": 53.5,
+          "confidence": 0.57
+        },
+        {
+          "text": "lui",
+          "start": 53.5,
+          "end": 53.7,
+          "confidence": 0.701
+        },
+        {
+          "text": "est",
+          "start": 53.7,
+          "end": 54.04,
+          "confidence": 0.879
+        },
+        {
+          "text": "aussi",
+          "start": 54.04,
+          "end": 54.52,
+          "confidence": 0.815
+        },
+        {
+          "text": "un",
+          "start": 54.52,
+          "end": 54.7,
+          "confidence": 0.48
+        },
+        {
+          "text": "rapport",
+          "start": 54.7,
+          "end": 54.93,
+          "confidence": 0.952
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 2804,
+      "start": 54.93,
+      "end": 55.88,
+      "text": " inédit ?",
+      "tokens": [
+        51710,
+        294,
+        7811,
+        270,
+        2506,
+        51760
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4256427271836469,
+      "compression_ratio": 1.7156549520766773,
+      "no_speech_prob": 0.12921307981014252,
+      "confidence": 0.86,
+      "words": [
+        {
+          "text": "inédit ?",
+          "start": 54.93,
+          "end": 55.88,
+          "confidence": 0.86
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 5596,
+      "start": 55.96,
+      "end": 59.36,
+      "text": " Est-ce que le rapport qu'on a au sein de foi n'est comparable à celui qu'on entretenait",
+      "tokens": [
+        50364,
+        4410,
+        12,
+        384,
+        631,
+        476,
+        18018,
+        421,
+        6,
+        266,
+        257,
+        1609,
+        6195,
+        368,
+        6901,
+        297,
+        6,
+        377,
+        25323,
+        1531,
+        22829,
+        421,
+        6,
+        266,
+        3962,
+        1147,
+        1001,
+        50530
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6293370928083147,
+      "compression_ratio": 1.5749128919860627,
+      "no_speech_prob": 0.21948836743831635,
+      "confidence": 0.62,
+      "words": [
+        {
+          "text": "Est-ce",
+          "start": 55.96,
+          "end": 56.38,
+          "confidence": 0.553
+        },
+        {
+          "text": "que",
+          "start": 56.38,
+          "end": 56.44,
+          "confidence": 0.892
+        },
+        {
+          "text": "le",
+          "start": 56.44,
+          "end": 56.58,
+          "confidence": 0.982
+        },
+        {
+          "text": "rapport",
+          "start": 56.58,
+          "end": 56.9,
+          "confidence": 0.999
+        },
+        {
+          "text": "qu'on",
+          "start": 56.9,
+          "end": 57.14,
+          "confidence": 0.902
+        },
+        {
+          "text": "a",
+          "start": 57.14,
+          "end": 57.2,
+          "confidence": 0.959
+        },
+        {
+          "text": "au",
+          "start": 57.2,
+          "end": 57.28,
+          "confidence": 0.273
+        },
+        {
+          "text": "sein",
+          "start": 57.28,
+          "end": 57.42,
+          "confidence": 0.17
+        },
+        {
+          "text": "de",
+          "start": 57.42,
+          "end": 57.56,
+          "confidence": 0.229
+        },
+        {
+          "text": "foi",
+          "start": 57.56,
+          "end": 57.58,
+          "confidence": 0.121
+        },
+        {
+          "text": "n'est",
+          "start": 57.58,
+          "end": 57.78,
+          "confidence": 0.79
+        },
+        {
+          "text": "comparable",
+          "start": 57.78,
+          "end": 58.28,
+          "confidence": 0.547
+        },
+        {
+          "text": "à",
+          "start": 58.28,
+          "end": 58.48,
+          "confidence": 0.934
+        },
+        {
+          "text": "celui",
+          "start": 58.48,
+          "end": 58.7,
+          "confidence": 0.851
+        },
+        {
+          "text": "qu'on",
+          "start": 58.7,
+          "end": 58.94,
+          "confidence": 0.926
+        },
+        {
+          "text": "entretenait",
+          "start": 58.94,
+          "end": 59.36,
+          "confidence": 0.56
+        }
+      ]
+    },
+    {
+      "id": 17,
+      "seek": 5596,
+      "start": 59.36,
+      "end": 63.14,
+      "text": " à d'autres objectes techniques comme la voiture ou le téléphone ?",
+      "tokens": [
+        50530,
+        1531,
+        274,
+        6,
+        16752,
+        2657,
+        279,
+        7512,
+        5173,
+        635,
+        38859,
+        2820,
+        476,
+        47159,
+        2506,
+        50714
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6293370928083147,
+      "compression_ratio": 1.5749128919860627,
+      "no_speech_prob": 0.21948836743831635,
+      "confidence": 0.756,
+      "words": [
+        {
+          "text": "à",
+          "start": 59.36,
+          "end": 59.44,
+          "confidence": 0.951
+        },
+        {
+          "text": "d'autres",
+          "start": 59.44,
+          "end": 59.68,
+          "confidence": 0.857
+        },
+        {
+          "text": "objectes",
+          "start": 59.68,
+          "end": 60.02,
+          "confidence": 0.507
+        },
+        {
+          "text": "techniques",
+          "start": 60.02,
+          "end": 60.44,
+          "confidence": 0.462
+        },
+        {
+          "text": "comme",
+          "start": 60.44,
+          "end": 61.04,
+          "confidence": 0.639
+        },
+        {
+          "text": "la",
+          "start": 61.04,
+          "end": 61.52,
+          "confidence": 0.905
+        },
+        {
+          "text": "voiture",
+          "start": 61.52,
+          "end": 61.86,
+          "confidence": 0.946
+        },
+        {
+          "text": "ou",
+          "start": 61.86,
+          "end": 62.46,
+          "confidence": 0.755
+        },
+        {
+          "text": "le",
+          "start": 62.46,
+          "end": 62.68,
+          "confidence": 0.913
+        },
+        {
+          "text": "téléphone ?",
+          "start": 62.68,
+          "end": 63.14,
+          "confidence": 0.983
+        }
+      ]
+    },
+    {
+      "id": 18,
+      "seek": 5596,
+      "start": 65.4,
+      "end": 66.16,
+      "text": " Il n'y a pas d'équivalent.",
+      "tokens": [
+        50714,
+        4416,
+        297,
+        6,
+        88,
+        257,
+        1736,
+        274,
+        6,
+        20183,
+        3576,
+        317,
+        13,
+        50872
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6293370928083147,
+      "compression_ratio": 1.5749128919860627,
+      "no_speech_prob": 0.21948836743831635,
+      "confidence": 0.881,
+      "words": [
+        {
+          "text": "Il",
+          "start": 65.4,
+          "end": 65.5,
+          "confidence": 0.901
+        },
+        {
+          "text": "n'y",
+          "start": 65.5,
+          "end": 65.54,
+          "confidence": 0.86
+        },
+        {
+          "text": "a",
+          "start": 65.54,
+          "end": 65.56,
+          "confidence": 0.962
+        },
+        {
+          "text": "pas",
+          "start": 65.56,
+          "end": 65.68,
+          "confidence": 0.998
+        },
+        {
+          "text": "d'équivalent.",
+          "start": 65.68,
+          "end": 66.16,
+          "confidence": 0.852
+        }
+      ]
+    },
+    {
+      "id": 19,
+      "seek": 5596,
+      "start": 66.16,
+      "end": 69.92,
+      "text": " On s'est espèrent de nous voter dans la relation à l'objet.",
+      "tokens": [
+        50872,
+        1282,
+        262,
+        6,
+        377,
+        7089,
+        1462,
+        1753,
+        368,
+        4666,
+        21722,
+        2680,
+        635,
+        9721,
+        1531,
+        287,
+        6,
+        996,
+        7108,
+        13,
+        51058
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6293370928083147,
+      "compression_ratio": 1.5749128919860627,
+      "no_speech_prob": 0.21948836743831635,
+      "confidence": 0.501,
+      "words": [
+        {
+          "text": "On",
+          "start": 66.16,
+          "end": 67.08,
+          "confidence": 0.302
+        },
+        {
+          "text": "s'est",
+          "start": 67.08,
+          "end": 67.3,
+          "confidence": 0.563
+        },
+        {
+          "text": "espèrent",
+          "start": 67.3,
+          "end": 67.62,
+          "confidence": 0.134
+        },
+        {
+          "text": "de",
+          "start": 67.62,
+          "end": 67.66,
+          "confidence": 0.99
+        },
+        {
+          "text": "nous",
+          "start": 67.66,
+          "end": 67.84,
+          "confidence": 0.763
+        },
+        {
+          "text": "voter",
+          "start": 67.84,
+          "end": 68.36,
+          "confidence": 0.181
+        },
+        {
+          "text": "dans",
+          "start": 68.36,
+          "end": 68.86,
+          "confidence": 0.82
+        },
+        {
+          "text": "la",
+          "start": 68.86,
+          "end": 68.96,
+          "confidence": 0.617
+        },
+        {
+          "text": "relation",
+          "start": 68.96,
+          "end": 69.24,
+          "confidence": 0.949
+        },
+        {
+          "text": "à",
+          "start": 69.24,
+          "end": 69.42,
+          "confidence": 0.75
+        },
+        {
+          "text": "l'objet.",
+          "start": 69.42,
+          "end": 69.92,
+          "confidence": 0.887
+        }
+      ]
+    },
+    {
+      "id": 20,
+      "seek": 5596,
+      "start": 70.2,
+      "end": 71.22,
+      "text": " C'est facilement éterricion.",
+      "tokens": [
+        51058,
+        383,
+        6,
+        377,
+        23670,
+        518,
+        1136,
+        391,
+        1341,
+        313,
+        13,
+        51122
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6293370928083147,
+      "compression_ratio": 1.5749128919860627,
+      "no_speech_prob": 0.21948836743831635,
+      "confidence": 0.441,
+      "words": [
+        {
+          "text": "C'est",
+          "start": 70.2,
+          "end": 70.34,
+          "confidence": 0.895
+        },
+        {
+          "text": "facilement",
+          "start": 70.34,
+          "end": 70.7,
+          "confidence": 0.562
+        },
+        {
+          "text": "éterricion.",
+          "start": 70.7,
+          "end": 71.22,
+          "confidence": 0.23
+        }
+      ]
+    },
+    {
+      "id": 21,
+      "seek": 5596,
+      "start": 71.64,
+      "end": 76.97,
+      "text": " Parce que la passion de l'utilisateur et ses affices a dépendance, cette objet d'un lieu",
+      "tokens": [
+        51122,
+        20429,
+        631,
+        635,
+        5418,
+        368,
+        287,
+        6,
+        20835,
+        271,
+        15540,
+        1030,
+        5385,
+        2096,
+        1473,
+        257,
+        45768,
+        719,
+        11,
+        5550,
+        14964,
+        274,
+        6,
+        409,
+        26036,
+        51416
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6293370928083147,
+      "compression_ratio": 1.5749128919860627,
+      "no_speech_prob": 0.21948836743831635,
+      "confidence": 0.457,
+      "words": [
+        {
+          "text": "Parce",
+          "start": 71.64,
+          "end": 71.94,
+          "confidence": 0.679
+        },
+        {
+          "text": "que",
+          "start": 71.94,
+          "end": 72.32,
+          "confidence": 0.566
+        },
+        {
+          "text": "la",
+          "start": 72.32,
+          "end": 72.56,
+          "confidence": 0.336
+        },
+        {
+          "text": "passion",
+          "start": 72.56,
+          "end": 72.9,
+          "confidence": 0.267
+        },
+        {
+          "text": "de",
+          "start": 72.9,
+          "end": 73.24,
+          "confidence": 0.365
+        },
+        {
+          "text": "l'utilisateur",
+          "start": 73.24,
+          "end": 74.82,
+          "confidence": 0.499
+        },
+        {
+          "text": "et",
+          "start": 74.82,
+          "end": 74.92,
+          "confidence": 0.45
+        },
+        {
+          "text": "ses",
+          "start": 74.92,
+          "end": 75.04,
+          "confidence": 0.095
+        },
+        {
+          "text": "affices",
+          "start": 75.04,
+          "end": 75.24,
+          "confidence": 0.303
+        },
+        {
+          "text": "a",
+          "start": 75.24,
+          "end": 75.38,
+          "confidence": 0.59
+        },
+        {
+          "text": "dépendance,",
+          "start": 75.38,
+          "end": 76.06,
+          "confidence": 0.559
+        },
+        {
+          "text": "cette",
+          "start": 76.32,
+          "end": 76.34,
+          "confidence": 0.401
+        },
+        {
+          "text": "objet",
+          "start": 76.34,
+          "end": 76.54,
+          "confidence": 0.924
+        },
+        {
+          "text": "d'un",
+          "start": 76.54,
+          "end": 76.92,
+          "confidence": 0.783
+        },
+        {
+          "text": "lieu",
+          "start": 76.92,
+          "end": 76.97,
+          "confidence": 0.307
+        }
+      ]
+    },
+    {
+      "id": 22,
+      "seek": 5596,
+      "start": 76.97,
+      "end": 82.15,
+      "text": " en fait, une espèce de relation de médiation avec le monde qui rendent encore avec",
+      "tokens": [
+        51416,
+        465,
+        3887,
+        11,
+        2251,
+        7089,
+        30236,
+        368,
+        9721,
+        368,
+        42436,
+        399,
+        4163,
+        476,
+        10431,
+        1956,
+        6125,
+        317,
+        10122,
+        4163,
+        51671
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6293370928083147,
+      "compression_ratio": 1.5749128919860627,
+      "no_speech_prob": 0.21948836743831635,
+      "confidence": 0.746,
+      "words": [
+        {
+          "text": "en",
+          "start": 76.97,
+          "end": 77.2,
+          "confidence": 0.767
+        },
+        {
+          "text": "fait,",
+          "start": 77.2,
+          "end": 77.32,
+          "confidence": 0.944
+        },
+        {
+          "text": "une",
+          "start": 77.46,
+          "end": 77.48,
+          "confidence": 0.696
+        },
+        {
+          "text": "espèce",
+          "start": 77.48,
+          "end": 77.9,
+          "confidence": 0.97
+        },
+        {
+          "text": "de",
+          "start": 77.9,
+          "end": 78.08,
+          "confidence": 0.994
+        },
+        {
+          "text": "relation",
+          "start": 78.08,
+          "end": 78.5,
+          "confidence": 0.826
+        },
+        {
+          "text": "de",
+          "start": 78.5,
+          "end": 78.94,
+          "confidence": 0.72
+        },
+        {
+          "text": "médiation",
+          "start": 78.94,
+          "end": 79.5,
+          "confidence": 0.881
+        },
+        {
+          "text": "avec",
+          "start": 79.5,
+          "end": 79.74,
+          "confidence": 0.968
+        },
+        {
+          "text": "le",
+          "start": 79.74,
+          "end": 79.94,
+          "confidence": 0.986
+        },
+        {
+          "text": "monde",
+          "start": 79.94,
+          "end": 80.44,
+          "confidence": 0.906
+        },
+        {
+          "text": "qui",
+          "start": 80.44,
+          "end": 81.14,
+          "confidence": 0.825
+        },
+        {
+          "text": "rendent",
+          "start": 81.14,
+          "end": 81.8,
+          "confidence": 0.584
+        },
+        {
+          "text": "encore",
+          "start": 81.8,
+          "end": 81.98,
+          "confidence": 0.198
+        },
+        {
+          "text": "avec",
+          "start": 81.98,
+          "end": 82.15,
+          "confidence": 0.486
+        }
+      ]
+    },
+    {
+      "id": 23,
+      "seek": 8210,
+      "start": 82.15,
+      "end": 83.44,
+      "text": " la maille de celles formes de rogeur.",
+      "tokens": [
+        50364,
+        635,
+        463,
+        3409,
+        368,
+        2815,
+        279,
+        1254,
+        279,
+        368,
+        744,
+        432,
+        374,
+        13,
+        50440
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.45904387403654573,
+      "compression_ratio": 1.6159169550173011,
+      "no_speech_prob": 0.2066797912120819,
+      "confidence": 0.465,
+      "words": [
+        {
+          "text": "la",
+          "start": 82.15,
+          "end": 82.22,
+          "confidence": 0.648
+        },
+        {
+          "text": "maille",
+          "start": 82.22,
+          "end": 82.4,
+          "confidence": 0.136
+        },
+        {
+          "text": "de",
+          "start": 82.4,
+          "end": 82.48,
+          "confidence": 0.585
+        },
+        {
+          "text": "celles",
+          "start": 82.48,
+          "end": 82.74,
+          "confidence": 0.561
+        },
+        {
+          "text": "formes",
+          "start": 82.74,
+          "end": 82.96,
+          "confidence": 0.78
+        },
+        {
+          "text": "de",
+          "start": 82.96,
+          "end": 83.0,
+          "confidence": 0.936
+        },
+        {
+          "text": "rogeur.",
+          "start": 83.0,
+          "end": 83.44,
+          "confidence": 0.433
+        }
+      ]
+    },
+    {
+      "id": 24,
+      "seek": 8210,
+      "start": 83.98,
+      "end": 87.86,
+      "text": " Donc, à objets inédits, rapport inédits.",
+      "tokens": [
+        50440,
+        7477,
+        11,
+        1531,
+        1111,
+        25349,
+        294,
+        7811,
+        1208,
+        11,
+        18018,
+        294,
+        7811,
+        1208,
+        13,
+        50640
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.45904387403654573,
+      "compression_ratio": 1.6159169550173011,
+      "no_speech_prob": 0.2066797912120819,
+      "confidence": 0.745,
+      "words": [
+        {
+          "text": "Donc,",
+          "start": 83.98,
+          "end": 84.46,
+          "confidence": 0.833
+        },
+        {
+          "text": "à",
+          "start": 84.56,
+          "end": 84.96,
+          "confidence": 0.696
+        },
+        {
+          "text": "objets",
+          "start": 84.96,
+          "end": 85.44,
+          "confidence": 0.526
+        },
+        {
+          "text": "inédits,",
+          "start": 85.44,
+          "end": 86.24,
+          "confidence": 0.701
+        },
+        {
+          "text": "rapport",
+          "start": 86.32,
+          "end": 86.92,
+          "confidence": 0.944
+        },
+        {
+          "text": "inédits.",
+          "start": 86.92,
+          "end": 87.86,
+          "confidence": 0.908
+        }
+      ]
+    },
+    {
+      "id": 25,
+      "seek": 8210,
+      "start": 88.1,
+      "end": 94.2,
+      "text": " Et, ce rapport, si j'en prends Nicolas, frère caractérisée par un mélange de dépendance",
+      "tokens": [
+        50640,
+        3790,
+        11,
+        1769,
+        18018,
+        11,
+        1511,
+        361,
+        6,
+        268,
+        46750,
+        38268,
+        11,
+        431,
+        4212,
+        1032,
+        578,
+        4198,
+        50027,
+        971,
+        517,
+        41953,
+        933,
+        368,
+        45768,
+        719,
+        50972
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.45904387403654573,
+      "compression_ratio": 1.6159169550173011,
+      "no_speech_prob": 0.2066797912120819,
+      "confidence": 0.669,
+      "words": [
+        {
+          "text": "Et,",
+          "start": 88.1,
+          "end": 88.3,
+          "confidence": 0.865
+        },
+        {
+          "text": "ce",
+          "start": 88.58,
+          "end": 88.84,
+          "confidence": 0.277
+        },
+        {
+          "text": "rapport,",
+          "start": 88.84,
+          "end": 89.28,
+          "confidence": 0.998
+        },
+        {
+          "text": "si",
+          "start": 89.38,
+          "end": 89.56,
+          "confidence": 0.933
+        },
+        {
+          "text": "j'en",
+          "start": 89.56,
+          "end": 89.74,
+          "confidence": 0.78
+        },
+        {
+          "text": "prends",
+          "start": 89.74,
+          "end": 89.92,
+          "confidence": 0.307
+        },
+        {
+          "text": "Nicolas,",
+          "start": 89.92,
+          "end": 90.22,
+          "confidence": 0.65
+        },
+        {
+          "text": "frère",
+          "start": 90.78,
+          "end": 91.1,
+          "confidence": 0.431
+        },
+        {
+          "text": "caractérisée",
+          "start": 91.1,
+          "end": 91.8,
+          "confidence": 0.595
+        },
+        {
+          "text": "par",
+          "start": 91.8,
+          "end": 92.14,
+          "confidence": 0.907
+        },
+        {
+          "text": "un",
+          "start": 92.14,
+          "end": 92.34,
+          "confidence": 0.989
+        },
+        {
+          "text": "mélange",
+          "start": 92.34,
+          "end": 92.98,
+          "confidence": 0.92
+        },
+        {
+          "text": "de",
+          "start": 92.98,
+          "end": 93.24,
+          "confidence": 0.842
+        },
+        {
+          "text": "dépendance",
+          "start": 93.24,
+          "end": 94.2,
+          "confidence": 0.675
+        }
+      ]
+    },
+    {
+      "id": 26,
+      "seek": 8210,
+      "start": 94.36,
+      "end": 95.08,
+      "text": " et de rogeur.",
+      "tokens": [
+        50972,
+        1030,
+        368,
+        744,
+        432,
+        374,
+        13,
+        51022
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.45904387403654573,
+      "compression_ratio": 1.6159169550173011,
+      "no_speech_prob": 0.2066797912120819,
+      "confidence": 0.851,
+      "words": [
+        {
+          "text": "et",
+          "start": 94.36,
+          "end": 94.52,
+          "confidence": 0.97
+        },
+        {
+          "text": "de",
+          "start": 94.52,
+          "end": 94.64,
+          "confidence": 0.996
+        },
+        {
+          "text": "rogeur.",
+          "start": 94.64,
+          "end": 95.08,
+          "confidence": 0.773
+        }
+      ]
+    },
+    {
+      "id": 27,
+      "seek": 8210,
+      "start": 96.3,
+      "end": 100.48,
+      "text": " Bon, en vrai, il faudrait remonter très, très filmant tout l'histoire des objectes",
+      "tokens": [
+        51022,
+        7368,
+        11,
+        465,
+        17815,
+        11,
+        1930,
+        38694,
+        8645,
+        890,
+        41806,
+        5732,
+        11,
+        5732,
+        2007,
+        394,
+        3486,
+        287,
+        6,
+        29093,
+        730,
+        2657,
+        279,
+        51286
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.45904387403654573,
+      "compression_ratio": 1.6159169550173011,
+      "no_speech_prob": 0.2066797912120819,
+      "confidence": 0.752,
+      "words": [
+        {
+          "text": "Bon,",
+          "start": 96.3,
+          "end": 96.32,
+          "confidence": 0.6
+        },
+        {
+          "text": "en",
+          "start": 96.36,
+          "end": 96.58,
+          "confidence": 0.918
+        },
+        {
+          "text": "vrai,",
+          "start": 96.58,
+          "end": 96.92,
+          "confidence": 0.992
+        },
+        {
+          "text": "il",
+          "start": 97.14,
+          "end": 97.18,
+          "confidence": 0.987
+        },
+        {
+          "text": "faudrait",
+          "start": 97.18,
+          "end": 97.56,
+          "confidence": 0.933
+        },
+        {
+          "text": "remonter",
+          "start": 97.56,
+          "end": 98.08,
+          "confidence": 0.61
+        },
+        {
+          "text": "très,",
+          "start": 98.08,
+          "end": 98.56,
+          "confidence": 0.975
+        },
+        {
+          "text": "très",
+          "start": 98.56,
+          "end": 98.86,
+          "confidence": 0.986
+        },
+        {
+          "text": "filmant",
+          "start": 98.86,
+          "end": 99.42,
+          "confidence": 0.409
+        },
+        {
+          "text": "tout",
+          "start": 99.42,
+          "end": 99.68,
+          "confidence": 0.348
+        },
+        {
+          "text": "l'histoire",
+          "start": 99.68,
+          "end": 100.08,
+          "confidence": 0.876
+        },
+        {
+          "text": "des",
+          "start": 100.08,
+          "end": 100.22,
+          "confidence": 0.957
+        },
+        {
+          "text": "objectes",
+          "start": 100.22,
+          "end": 100.48,
+          "confidence": 0.842
+        }
+      ]
+    },
+    {
+      "id": 28,
+      "seek": 8210,
+      "start": 100.48,
+      "end": 105.24,
+      "text": " techniques et de leur infertion dans nos vieux pour déterminer si ce rapport est totalement",
+      "tokens": [
+        51286,
+        7512,
+        1030,
+        368,
+        9580,
+        1536,
+        911,
+        313,
+        2680,
+        3269,
+        4941,
+        2449,
+        2016,
+        2795,
+        29725,
+        260,
+        1511,
+        1769,
+        18018,
+        871,
+        45203,
+        51530
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.45904387403654573,
+      "compression_ratio": 1.6159169550173011,
+      "no_speech_prob": 0.2066797912120819,
+      "confidence": 0.614,
+      "words": [
+        {
+          "text": "techniques",
+          "start": 100.48,
+          "end": 101.0,
+          "confidence": 0.952
+        },
+        {
+          "text": "et",
+          "start": 101.0,
+          "end": 101.58,
+          "confidence": 0.943
+        },
+        {
+          "text": "de",
+          "start": 101.58,
+          "end": 101.72,
+          "confidence": 0.975
+        },
+        {
+          "text": "leur",
+          "start": 101.72,
+          "end": 101.8,
+          "confidence": 0.803
+        },
+        {
+          "text": "infertion",
+          "start": 101.8,
+          "end": 102.34,
+          "confidence": 0.382
+        },
+        {
+          "text": "dans",
+          "start": 102.34,
+          "end": 102.5,
+          "confidence": 0.297
+        },
+        {
+          "text": "nos",
+          "start": 102.5,
+          "end": 102.68,
+          "confidence": 0.419
+        },
+        {
+          "text": "vieux",
+          "start": 102.68,
+          "end": 103.08,
+          "confidence": 0.386
+        },
+        {
+          "text": "pour",
+          "start": 103.08,
+          "end": 103.1,
+          "confidence": 0.281
+        },
+        {
+          "text": "déterminer",
+          "start": 103.1,
+          "end": 103.64,
+          "confidence": 0.976
+        },
+        {
+          "text": "si",
+          "start": 103.64,
+          "end": 103.8,
+          "confidence": 0.367
+        },
+        {
+          "text": "ce",
+          "start": 103.8,
+          "end": 103.92,
+          "confidence": 0.983
+        },
+        {
+          "text": "rapport",
+          "start": 103.92,
+          "end": 104.22,
+          "confidence": 0.998
+        },
+        {
+          "text": "est",
+          "start": 104.22,
+          "end": 104.88,
+          "confidence": 0.942
+        },
+        {
+          "text": "totalement",
+          "start": 104.88,
+          "end": 105.24,
+          "confidence": 0.907
+        }
+      ]
+    },
+    {
+      "id": 29,
+      "seek": 8210,
+      "start": 105.24,
+      "end": 106.1,
+      "text": " inédit.",
+      "tokens": [
+        51530,
+        294,
+        7811,
+        270,
+        13,
+        51580
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.45904387403654573,
+      "compression_ratio": 1.6159169550173011,
+      "no_speech_prob": 0.2066797912120819,
+      "confidence": 0.939,
+      "words": [
+        {
+          "text": "inédit.",
+          "start": 105.24,
+          "end": 106.1,
+          "confidence": 0.939
+        }
+      ]
+    },
+    {
+      "id": 30,
+      "seek": 8210,
+      "start": 106.16,
+      "end": 109.44,
+      "text": " Mais j'ai l'impression comme ça que Nicolas se trompe pas vraiment.",
+      "tokens": [
+        51580,
+        6313,
+        361,
+        6,
+        1301,
+        287,
+        6,
+        36107,
+        5173,
+        2788,
+        631,
+        38268,
+        369,
+        504,
+        298,
+        494,
+        1736,
+        8322,
+        13,
+        51738
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.45904387403654573,
+      "compression_ratio": 1.6159169550173011,
+      "no_speech_prob": 0.2066797912120819,
+      "confidence": 0.811,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 106.16,
+          "end": 106.5,
+          "confidence": 0.721
+        },
+        {
+          "text": "j'ai",
+          "start": 106.5,
+          "end": 106.92,
+          "confidence": 0.91
+        },
+        {
+          "text": "l'impression",
+          "start": 106.92,
+          "end": 107.34,
+          "confidence": 0.956
+        },
+        {
+          "text": "comme",
+          "start": 107.34,
+          "end": 107.58,
+          "confidence": 0.7
+        },
+        {
+          "text": "ça",
+          "start": 107.58,
+          "end": 107.74,
+          "confidence": 0.953
+        },
+        {
+          "text": "que",
+          "start": 107.74,
+          "end": 108.06,
+          "confidence": 0.941
+        },
+        {
+          "text": "Nicolas",
+          "start": 108.06,
+          "end": 108.46,
+          "confidence": 0.994
+        },
+        {
+          "text": "se",
+          "start": 108.46,
+          "end": 108.68,
+          "confidence": 0.716
+        },
+        {
+          "text": "trompe",
+          "start": 108.68,
+          "end": 109.02,
+          "confidence": 0.54
+        },
+        {
+          "text": "pas",
+          "start": 109.02,
+          "end": 109.16,
+          "confidence": 0.886
+        },
+        {
+          "text": "vraiment.",
+          "start": 109.16,
+          "end": 109.44,
+          "confidence": 0.963
+        }
+      ]
+    },
+    {
+      "id": 31,
+      "seek": 8210,
+      "start": 109.92,
+      "end": 110.86,
+      "text": " Pour autant, je sache.",
+      "tokens": [
+        51738,
+        8732,
+        34081,
+        11,
+        1506,
+        262,
+        6000,
+        13,
+        51808
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.45904387403654573,
+      "compression_ratio": 1.6159169550173011,
+      "no_speech_prob": 0.2066797912120819,
+      "confidence": 0.6,
+      "words": [
+        {
+          "text": "Pour",
+          "start": 109.92,
+          "end": 110.1,
+          "confidence": 0.49
+        },
+        {
+          "text": "autant,",
+          "start": 110.1,
+          "end": 110.28,
+          "confidence": 0.75
+        },
+        {
+          "text": "je",
+          "start": 110.42,
+          "end": 110.48,
+          "confidence": 0.931
+        },
+        {
+          "text": "sache.",
+          "start": 110.48,
+          "end": 110.86,
+          "confidence": 0.477
+        }
+      ]
+    },
+    {
+      "id": 32,
+      "seek": 11098,
+      "start": 111.04,
+      "end": 115.0,
+      "text": " Il y a eu plein de discussions autour de la voiture ou même du téléphone.",
+      "tokens": [
+        50364,
+        4416,
+        288,
+        257,
+        2228,
+        21088,
+        368,
+        11088,
+        30249,
+        368,
+        635,
+        38859,
+        2820,
+        5698,
+        1581,
+        47159,
+        13,
+        50568
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.44320285092493533,
+      "compression_ratio": 1.7050847457627119,
+      "no_speech_prob": 0.15390530228614807,
+      "confidence": 0.821,
+      "words": [
+        {
+          "text": "Il",
+          "start": 111.04,
+          "end": 111.2,
+          "confidence": 0.905
+        },
+        {
+          "text": "y",
+          "start": 111.2,
+          "end": 111.3,
+          "confidence": 0.934
+        },
+        {
+          "text": "a",
+          "start": 111.3,
+          "end": 111.56,
+          "confidence": 0.893
+        },
+        {
+          "text": "eu",
+          "start": 111.56,
+          "end": 111.6,
+          "confidence": 0.839
+        },
+        {
+          "text": "plein",
+          "start": 111.6,
+          "end": 111.88,
+          "confidence": 0.776
+        },
+        {
+          "text": "de",
+          "start": 111.88,
+          "end": 112.12,
+          "confidence": 0.944
+        },
+        {
+          "text": "discussions",
+          "start": 112.12,
+          "end": 112.6,
+          "confidence": 0.681
+        },
+        {
+          "text": "autour",
+          "start": 112.6,
+          "end": 113.04,
+          "confidence": 0.978
+        },
+        {
+          "text": "de",
+          "start": 113.04,
+          "end": 113.48,
+          "confidence": 0.975
+        },
+        {
+          "text": "la",
+          "start": 113.48,
+          "end": 113.56,
+          "confidence": 0.966
+        },
+        {
+          "text": "voiture",
+          "start": 113.56,
+          "end": 113.88,
+          "confidence": 0.983
+        },
+        {
+          "text": "ou",
+          "start": 113.88,
+          "end": 114.14,
+          "confidence": 0.66
+        },
+        {
+          "text": "même",
+          "start": 114.14,
+          "end": 114.34,
+          "confidence": 0.99
+        },
+        {
+          "text": "du",
+          "start": 114.34,
+          "end": 114.64,
+          "confidence": 0.283
+        },
+        {
+          "text": "téléphone.",
+          "start": 114.64,
+          "end": 115.0,
+          "confidence": 0.986
+        }
+      ]
+    },
+    {
+      "id": 33,
+      "seek": 11098,
+      "start": 115.52,
+      "end": 119.51,
+      "text": " Mais, la dépense n'était pas du même mort, donc le rejet n'en plus n'était pas du même",
+      "tokens": [
+        50568,
+        6313,
+        11,
+        635,
+        27998,
+        1288,
+        297,
+        6,
+        9743,
+        1736,
+        1581,
+        5698,
+        6599,
+        11,
+        5926,
+        476,
+        319,
+        7108,
+        297,
+        6,
+        268,
+        1804,
+        297,
+        6,
+        9743,
+        1736,
+        1581,
+        5698,
+        50790
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.44320285092493533,
+      "compression_ratio": 1.7050847457627119,
+      "no_speech_prob": 0.15390530228614807,
+      "confidence": 0.701,
+      "words": [
+        {
+          "text": "Mais,",
+          "start": 115.52,
+          "end": 115.82,
+          "confidence": 0.983
+        },
+        {
+          "text": "la",
+          "start": 115.9,
+          "end": 116.0,
+          "confidence": 0.961
+        },
+        {
+          "text": "dépense",
+          "start": 116.0,
+          "end": 116.42,
+          "confidence": 0.616
+        },
+        {
+          "text": "n'était",
+          "start": 116.42,
+          "end": 116.82,
+          "confidence": 0.955
+        },
+        {
+          "text": "pas",
+          "start": 116.82,
+          "end": 117.04,
+          "confidence": 0.994
+        },
+        {
+          "text": "du",
+          "start": 117.04,
+          "end": 117.2,
+          "confidence": 0.958
+        },
+        {
+          "text": "même",
+          "start": 117.2,
+          "end": 117.38,
+          "confidence": 0.929
+        },
+        {
+          "text": "mort,",
+          "start": 117.38,
+          "end": 117.58,
+          "confidence": 0.686
+        },
+        {
+          "text": "donc",
+          "start": 117.7,
+          "end": 118.02,
+          "confidence": 0.932
+        },
+        {
+          "text": "le",
+          "start": 118.02,
+          "end": 118.34,
+          "confidence": 0.95
+        },
+        {
+          "text": "rejet",
+          "start": 118.34,
+          "end": 118.64,
+          "confidence": 0.57
+        },
+        {
+          "text": "n'en",
+          "start": 118.64,
+          "end": 118.82,
+          "confidence": 0.429
+        },
+        {
+          "text": "plus",
+          "start": 118.82,
+          "end": 118.96,
+          "confidence": 0.055
+        },
+        {
+          "text": "n'était",
+          "start": 118.96,
+          "end": 119.16,
+          "confidence": 0.973
+        },
+        {
+          "text": "pas",
+          "start": 119.16,
+          "end": 119.32,
+          "confidence": 0.993
+        },
+        {
+          "text": "du",
+          "start": 119.32,
+          "end": 119.42,
+          "confidence": 0.823
+        },
+        {
+          "text": "même",
+          "start": 119.42,
+          "end": 119.51,
+          "confidence": 0.79
+        }
+      ]
+    },
+    {
+      "id": 34,
+      "seek": 11098,
+      "start": 119.51,
+      "end": 119.72,
+      "text": " mort.",
+      "tokens": [
+        50790,
+        6599,
+        13,
+        50840
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.44320285092493533,
+      "compression_ratio": 1.7050847457627119,
+      "no_speech_prob": 0.15390530228614807,
+      "confidence": 0.639,
+      "words": [
+        {
+          "text": "mort.",
+          "start": 119.51,
+          "end": 119.72,
+          "confidence": 0.639
+        }
+      ]
+    },
+    {
+      "id": 35,
+      "seek": 11098,
+      "start": 120.04,
+      "end": 121.24,
+      "text": " On peut adorer sa bagnure.",
+      "tokens": [
+        50840,
+        1282,
+        5977,
+        614,
+        17618,
+        601,
+        3411,
+        77,
+        540,
+        13,
+        50890
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.44320285092493533,
+      "compression_ratio": 1.7050847457627119,
+      "no_speech_prob": 0.15390530228614807,
+      "confidence": 0.615,
+      "words": [
+        {
+          "text": "On",
+          "start": 120.04,
+          "end": 120.22,
+          "confidence": 0.981
+        },
+        {
+          "text": "peut",
+          "start": 120.22,
+          "end": 120.36,
+          "confidence": 0.988
+        },
+        {
+          "text": "adorer",
+          "start": 120.36,
+          "end": 120.7,
+          "confidence": 0.859
+        },
+        {
+          "text": "sa",
+          "start": 120.7,
+          "end": 120.88,
+          "confidence": 0.918
+        },
+        {
+          "text": "bagnure.",
+          "start": 120.88,
+          "end": 121.24,
+          "confidence": 0.314
+        }
+      ]
+    },
+    {
+      "id": 36,
+      "seek": 11098,
+      "start": 121.38,
+      "end": 123.06,
+      "text": " On a par besoin pour plein de choses.",
+      "tokens": [
+        50890,
+        1282,
+        257,
+        971,
+        19207,
+        2016,
+        21088,
+        368,
+        14488,
+        13,
+        50972
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.44320285092493533,
+      "compression_ratio": 1.7050847457627119,
+      "no_speech_prob": 0.15390530228614807,
+      "confidence": 0.722,
+      "words": [
+        {
+          "text": "On",
+          "start": 121.38,
+          "end": 121.56,
+          "confidence": 0.897
+        },
+        {
+          "text": "a",
+          "start": 121.56,
+          "end": 121.64,
+          "confidence": 0.656
+        },
+        {
+          "text": "par",
+          "start": 121.64,
+          "end": 121.8,
+          "confidence": 0.161
+        },
+        {
+          "text": "besoin",
+          "start": 121.8,
+          "end": 122.12,
+          "confidence": 0.947
+        },
+        {
+          "text": "pour",
+          "start": 122.12,
+          "end": 122.5,
+          "confidence": 0.976
+        },
+        {
+          "text": "plein",
+          "start": 122.5,
+          "end": 122.72,
+          "confidence": 0.857
+        },
+        {
+          "text": "de",
+          "start": 122.72,
+          "end": 122.8,
+          "confidence": 0.993
+        },
+        {
+          "text": "choses.",
+          "start": 122.8,
+          "end": 123.06,
+          "confidence": 0.989
+        }
+      ]
+    },
+    {
+      "id": 37,
+      "seek": 11098,
+      "start": 123.36,
+      "end": 126.46,
+      "text": " Et là, le soir, quand on va se coucher, on la laisse.",
+      "tokens": [
+        50972,
+        3790,
+        3684,
+        11,
+        476,
+        27105,
+        11,
+        6932,
+        322,
+        2773,
+        369,
+        1384,
+        6759,
+        11,
+        322,
+        635,
+        30969,
+        13,
+        51142
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.44320285092493533,
+      "compression_ratio": 1.7050847457627119,
+      "no_speech_prob": 0.15390530228614807,
+      "confidence": 0.835,
+      "words": [
+        {
+          "text": "Et",
+          "start": 123.36,
+          "end": 123.5,
+          "confidence": 0.606
+        },
+        {
+          "text": "là,",
+          "start": 123.5,
+          "end": 123.76,
+          "confidence": 0.498
+        },
+        {
+          "text": "le",
+          "start": 123.82,
+          "end": 124.06,
+          "confidence": 0.986
+        },
+        {
+          "text": "soir,",
+          "start": 124.06,
+          "end": 124.42,
+          "confidence": 0.971
+        },
+        {
+          "text": "quand",
+          "start": 124.84,
+          "end": 124.96,
+          "confidence": 0.787
+        },
+        {
+          "text": "on",
+          "start": 124.96,
+          "end": 125.06,
+          "confidence": 0.988
+        },
+        {
+          "text": "va",
+          "start": 125.06,
+          "end": 125.18,
+          "confidence": 0.966
+        },
+        {
+          "text": "se",
+          "start": 125.18,
+          "end": 125.26,
+          "confidence": 0.869
+        },
+        {
+          "text": "coucher,",
+          "start": 125.26,
+          "end": 125.6,
+          "confidence": 0.804
+        },
+        {
+          "text": "on",
+          "start": 125.82,
+          "end": 126.06,
+          "confidence": 0.98
+        },
+        {
+          "text": "la",
+          "start": 126.06,
+          "end": 126.2,
+          "confidence": 0.811
+        },
+        {
+          "text": "laisse.",
+          "start": 126.2,
+          "end": 126.46,
+          "confidence": 0.985
+        }
+      ]
+    },
+    {
+      "id": 38,
+      "seek": 11098,
+      "start": 127.06,
+      "end": 130.1,
+      "text": " On la pade en la main quand on est colis, qu'on n'a même pas au chiot.",
+      "tokens": [
+        51142,
+        1282,
+        635,
+        280,
+        762,
+        465,
+        635,
+        2135,
+        6932,
+        322,
+        871,
+        1173,
+        271,
+        11,
+        421,
+        6,
+        266,
+        297,
+        6,
+        64,
+        5698,
+        1736,
+        1609,
+        417,
+        6471,
+        13,
+        51334
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.44320285092493533,
+      "compression_ratio": 1.7050847457627119,
+      "no_speech_prob": 0.15390530228614807,
+      "confidence": 0.542,
+      "words": [
+        {
+          "text": "On",
+          "start": 127.06,
+          "end": 127.32,
+          "confidence": 0.605
+        },
+        {
+          "text": "la",
+          "start": 127.32,
+          "end": 127.5,
+          "confidence": 0.35
+        },
+        {
+          "text": "pade",
+          "start": 127.5,
+          "end": 127.72,
+          "confidence": 0.18
+        },
+        {
+          "text": "en",
+          "start": 127.72,
+          "end": 127.88,
+          "confidence": 0.775
+        },
+        {
+          "text": "la",
+          "start": 127.88,
+          "end": 128.04,
+          "confidence": 0.795
+        },
+        {
+          "text": "main",
+          "start": 128.04,
+          "end": 128.3,
+          "confidence": 0.971
+        },
+        {
+          "text": "quand",
+          "start": 128.3,
+          "end": 128.46,
+          "confidence": 0.483
+        },
+        {
+          "text": "on",
+          "start": 128.46,
+          "end": 128.62,
+          "confidence": 0.994
+        },
+        {
+          "text": "est",
+          "start": 128.62,
+          "end": 128.74,
+          "confidence": 0.714
+        },
+        {
+          "text": "colis,",
+          "start": 128.74,
+          "end": 129.12,
+          "confidence": 0.501
+        },
+        {
+          "text": "qu'on",
+          "start": 129.22,
+          "end": 129.32,
+          "confidence": 0.777
+        },
+        {
+          "text": "n'a",
+          "start": 129.32,
+          "end": 129.42,
+          "confidence": 0.439
+        },
+        {
+          "text": "même",
+          "start": 129.42,
+          "end": 129.56,
+          "confidence": 0.324
+        },
+        {
+          "text": "pas",
+          "start": 129.56,
+          "end": 129.74,
+          "confidence": 1.0
+        },
+        {
+          "text": "au",
+          "start": 129.74,
+          "end": 129.88,
+          "confidence": 0.64
+        },
+        {
+          "text": "chiot.",
+          "start": 129.88,
+          "end": 130.1,
+          "confidence": 0.514
+        }
+      ]
+    },
+    {
+      "id": 39,
+      "seek": 11098,
+      "start": 130.94,
+      "end": 135.32,
+      "text": " On pouvait être émervé par son mome qui occupeait la ligne de téléphone pendant une heure",
+      "tokens": [
+        51334,
+        1282,
+        45913,
+        7418,
+        1136,
+        936,
+        15797,
+        971,
+        1872,
+        275,
+        423,
+        1956,
+        2678,
+        84,
+        494,
+        1001,
+        635,
+        34207,
+        368,
+        47159,
+        17338,
+        2251,
+        30027,
+        51574
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.44320285092493533,
+      "compression_ratio": 1.7050847457627119,
+      "no_speech_prob": 0.15390530228614807,
+      "confidence": 0.656,
+      "words": [
+        {
+          "text": "On",
+          "start": 130.94,
+          "end": 131.04,
+          "confidence": 0.99
+        },
+        {
+          "text": "pouvait",
+          "start": 131.04,
+          "end": 131.28,
+          "confidence": 0.588
+        },
+        {
+          "text": "être",
+          "start": 131.28,
+          "end": 131.6,
+          "confidence": 0.446
+        },
+        {
+          "text": "émervé",
+          "start": 131.6,
+          "end": 132.24,
+          "confidence": 0.725
+        },
+        {
+          "text": "par",
+          "start": 132.24,
+          "end": 132.5,
+          "confidence": 0.848
+        },
+        {
+          "text": "son",
+          "start": 132.5,
+          "end": 132.7,
+          "confidence": 0.445
+        },
+        {
+          "text": "mome",
+          "start": 132.7,
+          "end": 133.08,
+          "confidence": 0.255
+        },
+        {
+          "text": "qui",
+          "start": 133.08,
+          "end": 133.3,
+          "confidence": 0.911
+        },
+        {
+          "text": "occupeait",
+          "start": 133.3,
+          "end": 133.74,
+          "confidence": 0.642
+        },
+        {
+          "text": "la",
+          "start": 133.74,
+          "end": 133.86,
+          "confidence": 0.808
+        },
+        {
+          "text": "ligne",
+          "start": 133.86,
+          "end": 134.02,
+          "confidence": 0.975
+        },
+        {
+          "text": "de",
+          "start": 134.02,
+          "end": 134.24,
+          "confidence": 0.928
+        },
+        {
+          "text": "téléphone",
+          "start": 134.24,
+          "end": 134.56,
+          "confidence": 0.978
+        },
+        {
+          "text": "pendant",
+          "start": 134.56,
+          "end": 134.92,
+          "confidence": 0.901
+        },
+        {
+          "text": "une",
+          "start": 134.92,
+          "end": 135.18,
+          "confidence": 0.811
+        },
+        {
+          "text": "heure",
+          "start": 135.18,
+          "end": 135.32,
+          "confidence": 0.477
+        }
+      ]
+    },
+    {
+      "id": 40,
+      "seek": 11098,
+      "start": 135.32,
+      "end": 137.04,
+      "text": " chaque soir pour discuter avec un copain.",
+      "tokens": [
+        51574,
+        18920,
+        27105,
+        2016,
+        2983,
+        20314,
+        4163,
+        517,
+        2971,
+        491,
+        13,
+        51664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.44320285092493533,
+      "compression_ratio": 1.7050847457627119,
+      "no_speech_prob": 0.15390530228614807,
+      "confidence": 0.955,
+      "words": [
+        {
+          "text": "chaque",
+          "start": 135.32,
+          "end": 135.6,
+          "confidence": 0.99
+        },
+        {
+          "text": "soir",
+          "start": 135.6,
+          "end": 135.8,
+          "confidence": 0.997
+        },
+        {
+          "text": "pour",
+          "start": 135.8,
+          "end": 136.0,
+          "confidence": 0.981
+        },
+        {
+          "text": "discuter",
+          "start": 136.0,
+          "end": 136.34,
+          "confidence": 0.882
+        },
+        {
+          "text": "avec",
+          "start": 136.34,
+          "end": 136.5,
+          "confidence": 0.993
+        },
+        {
+          "text": "un",
+          "start": 136.5,
+          "end": 136.62,
+          "confidence": 0.967
+        },
+        {
+          "text": "copain.",
+          "start": 136.62,
+          "end": 137.04,
+          "confidence": 0.953
+        }
+      ]
+    },
+    {
+      "id": 41,
+      "seek": 13698,
+      "start": 137.32,
+      "end": 141.84,
+      "text": " Mais ça ne ressemble pas à ce qu'on peut ressentir à voir même mome aujourd'hui.",
+      "tokens": [
+        50376,
+        6313,
+        2788,
+        408,
+        725,
+        37227,
+        1736,
+        1531,
+        1769,
+        421,
+        6,
+        266,
+        5977,
+        24689,
+        317,
+        347,
+        1531,
+        10695,
+        5698,
+        275,
+        423,
+        14023,
+        6,
+        10556,
+        13,
+        50606
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5337450312471937,
+      "compression_ratio": 1.6231454005934718,
+      "no_speech_prob": 0.1096271350979805,
+      "confidence": 0.735,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 137.32,
+          "end": 137.52,
+          "confidence": 0.984
+        },
+        {
+          "text": "ça",
+          "start": 137.52,
+          "end": 137.7,
+          "confidence": 0.877
+        },
+        {
+          "text": "ne",
+          "start": 137.7,
+          "end": 137.8,
+          "confidence": 0.672
+        },
+        {
+          "text": "ressemble",
+          "start": 137.8,
+          "end": 138.22,
+          "confidence": 0.731
+        },
+        {
+          "text": "pas",
+          "start": 138.22,
+          "end": 138.76,
+          "confidence": 0.526
+        },
+        {
+          "text": "à",
+          "start": 138.76,
+          "end": 138.94,
+          "confidence": 0.98
+        },
+        {
+          "text": "ce",
+          "start": 138.94,
+          "end": 139.08,
+          "confidence": 0.578
+        },
+        {
+          "text": "qu'on",
+          "start": 139.08,
+          "end": 139.22,
+          "confidence": 0.96
+        },
+        {
+          "text": "peut",
+          "start": 139.22,
+          "end": 139.38,
+          "confidence": 0.547
+        },
+        {
+          "text": "ressentir",
+          "start": 139.38,
+          "end": 140.06,
+          "confidence": 0.888
+        },
+        {
+          "text": "à",
+          "start": 140.06,
+          "end": 140.26,
+          "confidence": 0.437
+        },
+        {
+          "text": "voir",
+          "start": 140.26,
+          "end": 140.54,
+          "confidence": 0.952
+        },
+        {
+          "text": "même",
+          "start": 140.54,
+          "end": 140.96,
+          "confidence": 0.297
+        },
+        {
+          "text": "mome",
+          "start": 140.96,
+          "end": 141.22,
+          "confidence": 0.496
+        },
+        {
+          "text": "aujourd'hui.",
+          "start": 141.22,
+          "end": 141.84,
+          "confidence": 0.961
+        }
+      ]
+    },
+    {
+      "id": 42,
+      "seek": 13698,
+      "start": 141.96,
+      "end": 145.86,
+      "text": " Continuellement avec son smartphone dans la main, comme c'était une sorte de estimateur",
+      "tokens": [
+        50606,
+        14674,
+        31816,
+        4163,
+        1872,
+        13307,
+        2680,
+        635,
+        2135,
+        11,
+        5173,
+        269,
+        6,
+        9743,
+        2251,
+        25559,
+        368,
+        8017,
+        15540,
+        50810
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5337450312471937,
+      "compression_ratio": 1.6231454005934718,
+      "no_speech_prob": 0.1096271350979805,
+      "confidence": 0.663,
+      "words": [
+        {
+          "text": "Continuellement",
+          "start": 141.96,
+          "end": 142.84,
+          "confidence": 0.844
+        },
+        {
+          "text": "avec",
+          "start": 142.84,
+          "end": 143.24,
+          "confidence": 0.646
+        },
+        {
+          "text": "son",
+          "start": 143.24,
+          "end": 143.42,
+          "confidence": 0.864
+        },
+        {
+          "text": "smartphone",
+          "start": 143.42,
+          "end": 143.72,
+          "confidence": 0.447
+        },
+        {
+          "text": "dans",
+          "start": 143.72,
+          "end": 143.92,
+          "confidence": 0.587
+        },
+        {
+          "text": "la",
+          "start": 143.92,
+          "end": 144.0,
+          "confidence": 0.974
+        },
+        {
+          "text": "main,",
+          "start": 144.0,
+          "end": 144.3,
+          "confidence": 0.995
+        },
+        {
+          "text": "comme",
+          "start": 144.42,
+          "end": 144.56,
+          "confidence": 0.895
+        },
+        {
+          "text": "c'était",
+          "start": 144.56,
+          "end": 144.84,
+          "confidence": 0.596
+        },
+        {
+          "text": "une",
+          "start": 144.84,
+          "end": 144.96,
+          "confidence": 0.972
+        },
+        {
+          "text": "sorte",
+          "start": 144.96,
+          "end": 145.1,
+          "confidence": 0.658
+        },
+        {
+          "text": "de",
+          "start": 145.1,
+          "end": 145.4,
+          "confidence": 0.312
+        },
+        {
+          "text": "estimateur",
+          "start": 145.4,
+          "end": 145.86,
+          "confidence": 0.489
+        }
+      ]
+    },
+    {
+      "id": 43,
+      "seek": 13698,
+      "start": 145.96,
+      "end": 149.0,
+      "text": " extère de tomber de lâcher à l'éantrénée, ça m'a eu immédiate.",
+      "tokens": [
+        50810,
+        1279,
+        4212,
+        368,
+        2916,
+        607,
+        368,
+        48835,
+        6759,
+        1531,
+        287,
+        6,
+        526,
+        394,
+        81,
+        3516,
+        3856,
+        11,
+        2788,
+        275,
+        6,
+        64,
+        2228,
+        3397,
+        526,
+        4504,
+        473,
+        13,
+        50954
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5337450312471937,
+      "compression_ratio": 1.6231454005934718,
+      "no_speech_prob": 0.1096271350979805,
+      "confidence": 0.416,
+      "words": [
+        {
+          "text": "extère",
+          "start": 145.96,
+          "end": 146.4,
+          "confidence": 0.371
+        },
+        {
+          "text": "de",
+          "start": 146.4,
+          "end": 146.54,
+          "confidence": 0.254
+        },
+        {
+          "text": "tomber",
+          "start": 146.54,
+          "end": 146.7,
+          "confidence": 0.102
+        },
+        {
+          "text": "de",
+          "start": 146.7,
+          "end": 146.9,
+          "confidence": 0.454
+        },
+        {
+          "text": "lâcher",
+          "start": 146.9,
+          "end": 147.34,
+          "confidence": 0.75
+        },
+        {
+          "text": "à",
+          "start": 147.34,
+          "end": 147.46,
+          "confidence": 0.444
+        },
+        {
+          "text": "l'éantrénée,",
+          "start": 147.46,
+          "end": 147.9,
+          "confidence": 0.491
+        },
+        {
+          "text": "ça",
+          "start": 148.0,
+          "end": 148.02,
+          "confidence": 0.799
+        },
+        {
+          "text": "m'a",
+          "start": 148.02,
+          "end": 148.26,
+          "confidence": 0.531
+        },
+        {
+          "text": "eu",
+          "start": 148.26,
+          "end": 148.44,
+          "confidence": 0.136
+        },
+        {
+          "text": "immédiate.",
+          "start": 148.44,
+          "end": 149.0,
+          "confidence": 0.505
+        }
+      ]
+    },
+    {
+      "id": 44,
+      "seek": 13698,
+      "start": 149.08,
+      "end": 151.98,
+      "text": " Bon, je dis ça pour le mome, mais évidemment, va là, bon aussi.",
+      "tokens": [
+        50954,
+        7368,
+        11,
+        1506,
+        717,
+        2788,
+        2016,
+        476,
+        275,
+        423,
+        11,
+        2420,
+        24724,
+        11,
+        2773,
+        3684,
+        11,
+        4428,
+        6212,
+        13,
+        51126
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5337450312471937,
+      "compression_ratio": 1.6231454005934718,
+      "no_speech_prob": 0.1096271350979805,
+      "confidence": 0.564,
+      "words": [
+        {
+          "text": "Bon,",
+          "start": 149.08,
+          "end": 149.28,
+          "confidence": 0.375
+        },
+        {
+          "text": "je",
+          "start": 149.34,
+          "end": 149.4,
+          "confidence": 0.471
+        },
+        {
+          "text": "dis",
+          "start": 149.4,
+          "end": 149.46,
+          "confidence": 0.324
+        },
+        {
+          "text": "ça",
+          "start": 149.46,
+          "end": 149.64,
+          "confidence": 0.952
+        },
+        {
+          "text": "pour",
+          "start": 149.64,
+          "end": 149.8,
+          "confidence": 0.963
+        },
+        {
+          "text": "le",
+          "start": 149.8,
+          "end": 149.92,
+          "confidence": 0.992
+        },
+        {
+          "text": "mome,",
+          "start": 149.92,
+          "end": 150.12,
+          "confidence": 0.619
+        },
+        {
+          "text": "mais",
+          "start": 150.46,
+          "end": 150.52,
+          "confidence": 0.694
+        },
+        {
+          "text": "évidemment,",
+          "start": 150.52,
+          "end": 151.12,
+          "confidence": 0.776
+        },
+        {
+          "text": "va",
+          "start": 151.26,
+          "end": 151.36,
+          "confidence": 0.388
+        },
+        {
+          "text": "là,",
+          "start": 151.36,
+          "end": 151.46,
+          "confidence": 0.59
+        },
+        {
+          "text": "bon",
+          "start": 151.6,
+          "end": 151.68,
+          "confidence": 0.825
+        },
+        {
+          "text": "aussi.",
+          "start": 151.68,
+          "end": 151.98,
+          "confidence": 0.162
+        }
+      ]
+    },
+    {
+      "id": 45,
+      "seek": 13698,
+      "start": 152.64,
+      "end": 154.64,
+      "text": " Donc, rapport immédiate d'accord.",
+      "tokens": [
+        51126,
+        7477,
+        11,
+        18018,
+        3397,
+        526,
+        4504,
+        473,
+        274,
+        6,
+        19947,
+        13,
+        51248
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5337450312471937,
+      "compression_ratio": 1.6231454005934718,
+      "no_speech_prob": 0.1096271350979805,
+      "confidence": 0.861,
+      "words": [
+        {
+          "text": "Donc,",
+          "start": 152.64,
+          "end": 153.08,
+          "confidence": 0.982
+        },
+        {
+          "text": "rapport",
+          "start": 153.16,
+          "end": 153.58,
+          "confidence": 0.979
+        },
+        {
+          "text": "immédiate",
+          "start": 153.58,
+          "end": 154.28,
+          "confidence": 0.841
+        },
+        {
+          "text": "d'accord.",
+          "start": 154.28,
+          "end": 154.64,
+          "confidence": 0.816
+        }
+      ]
+    },
+    {
+      "id": 46,
+      "seek": 13698,
+      "start": 155.66,
+      "end": 158.36,
+      "text": " Mais pourquoi, à ton impression qu'on en sortira, j'amé?",
+      "tokens": [
+        51248,
+        6313,
+        19934,
+        11,
+        1531,
+        2952,
+        9995,
+        421,
+        6,
+        266,
+        465,
+        26906,
+        64,
+        11,
+        361,
+        6,
+        335,
+        526,
+        30,
+        51440
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5337450312471937,
+      "compression_ratio": 1.6231454005934718,
+      "no_speech_prob": 0.1096271350979805,
+      "confidence": 0.709,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 155.66,
+          "end": 155.88,
+          "confidence": 0.984
+        },
+        {
+          "text": "pourquoi,",
+          "start": 155.88,
+          "end": 156.28,
+          "confidence": 0.897
+        },
+        {
+          "text": "à",
+          "start": 156.38,
+          "end": 156.58,
+          "confidence": 0.837
+        },
+        {
+          "text": "ton",
+          "start": 156.58,
+          "end": 156.7,
+          "confidence": 0.953
+        },
+        {
+          "text": "impression",
+          "start": 156.7,
+          "end": 157.06,
+          "confidence": 0.938
+        },
+        {
+          "text": "qu'on",
+          "start": 157.06,
+          "end": 157.28,
+          "confidence": 0.89
+        },
+        {
+          "text": "en",
+          "start": 157.28,
+          "end": 157.4,
+          "confidence": 0.801
+        },
+        {
+          "text": "sortira,",
+          "start": 157.4,
+          "end": 157.88,
+          "confidence": 0.576
+        },
+        {
+          "text": "j'amé?",
+          "start": 157.96,
+          "end": 158.36,
+          "confidence": 0.464
+        }
+      ]
+    },
+    {
+      "id": 47,
+      "seek": 13698,
+      "start": 159.16,
+      "end": 163.32,
+      "text": " Et puis, il faut en remettre la faute sur les gens qui ont créé cette critique merveilleux",
+      "tokens": [
+        51440,
+        3790,
+        9093,
+        11,
+        1930,
+        8487,
+        465,
+        890,
+        40681,
+        635,
+        2050,
+        1169,
+        1022,
+        1512,
+        10668,
+        1956,
+        6592,
+        15609,
+        526,
+        5550,
+        25673,
+        3551,
+        303,
+        3409,
+        2449,
+        51678
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5337450312471937,
+      "compression_ratio": 1.6231454005934718,
+      "no_speech_prob": 0.1096271350979805,
+      "confidence": 0.714,
+      "words": [
+        {
+          "text": "Et",
+          "start": 159.16,
+          "end": 159.32,
+          "confidence": 0.832
+        },
+        {
+          "text": "puis,",
+          "start": 159.32,
+          "end": 159.46,
+          "confidence": 0.494
+        },
+        {
+          "text": "il",
+          "start": 159.62,
+          "end": 159.64,
+          "confidence": 0.594
+        },
+        {
+          "text": "faut",
+          "start": 159.64,
+          "end": 159.66,
+          "confidence": 0.951
+        },
+        {
+          "text": "en",
+          "start": 159.66,
+          "end": 159.78,
+          "confidence": 0.937
+        },
+        {
+          "text": "remettre",
+          "start": 159.78,
+          "end": 160.14,
+          "confidence": 0.984
+        },
+        {
+          "text": "la",
+          "start": 160.14,
+          "end": 160.42,
+          "confidence": 0.602
+        },
+        {
+          "text": "faute",
+          "start": 160.42,
+          "end": 160.68,
+          "confidence": 0.59
+        },
+        {
+          "text": "sur",
+          "start": 160.68,
+          "end": 160.98,
+          "confidence": 0.966
+        },
+        {
+          "text": "les",
+          "start": 160.98,
+          "end": 161.24,
+          "confidence": 0.828
+        },
+        {
+          "text": "gens",
+          "start": 161.24,
+          "end": 161.46,
+          "confidence": 0.986
+        },
+        {
+          "text": "qui",
+          "start": 161.46,
+          "end": 161.6,
+          "confidence": 0.98
+        },
+        {
+          "text": "ont",
+          "start": 161.6,
+          "end": 161.68,
+          "confidence": 0.95
+        },
+        {
+          "text": "créé",
+          "start": 161.68,
+          "end": 162.3,
+          "confidence": 0.95
+        },
+        {
+          "text": "cette",
+          "start": 162.3,
+          "end": 162.48,
+          "confidence": 0.908
+        },
+        {
+          "text": "critique",
+          "start": 162.48,
+          "end": 162.72,
+          "confidence": 0.032
+        },
+        {
+          "text": "merveilleux",
+          "start": 162.72,
+          "end": 163.32,
+          "confidence": 0.839
+        }
+      ]
+    },
+    {
+      "id": 48,
+      "seek": 13698,
+      "start": 163.32,
+      "end": 165.34,
+      "text": " et diabolique et diabolique par que merveilleux.",
+      "tokens": [
+        51678,
+        1030,
+        1026,
+        14923,
+        1925,
+        1030,
+        1026,
+        14923,
+        1925,
+        971,
+        631,
+        3551,
+        303,
+        3409,
+        2449,
+        13,
+        51778
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5337450312471937,
+      "compression_ratio": 1.6231454005934718,
+      "no_speech_prob": 0.1096271350979805,
+      "confidence": 0.708,
+      "words": [
+        {
+          "text": "et",
+          "start": 163.32,
+          "end": 163.44,
+          "confidence": 0.945
+        },
+        {
+          "text": "diabolique",
+          "start": 163.44,
+          "end": 163.86,
+          "confidence": 0.573
+        },
+        {
+          "text": "et",
+          "start": 163.86,
+          "end": 163.94,
+          "confidence": 0.238
+        },
+        {
+          "text": "diabolique",
+          "start": 163.94,
+          "end": 164.38,
+          "confidence": 0.892
+        },
+        {
+          "text": "par",
+          "start": 164.38,
+          "end": 164.62,
+          "confidence": 0.544
+        },
+        {
+          "text": "que",
+          "start": 164.62,
+          "end": 164.82,
+          "confidence": 0.529
+        },
+        {
+          "text": "merveilleux.",
+          "start": 164.82,
+          "end": 165.34,
+          "confidence": 0.981
+        }
+      ]
+    },
+    {
+      "id": 49,
+      "seek": 16526,
+      "start": 166.9,
+      "end": 168.8,
+      "text": " Les économistes parlent de dépendance du santé.",
+      "tokens": [
+        50410,
+        6965,
+        31171,
+        22368,
+        13734,
+        317,
+        368,
+        45768,
+        719,
+        1581,
+        30068,
+        13,
+        50542
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6644235849380493,
+      "compression_ratio": 1.4761904761904763,
+      "no_speech_prob": 0.1915542334318161,
+      "confidence": 0.765,
+      "words": [
+        {
+          "text": "Les",
+          "start": 166.9,
+          "end": 167.06,
+          "confidence": 0.699
+        },
+        {
+          "text": "économistes",
+          "start": 167.06,
+          "end": 167.52,
+          "confidence": 0.917
+        },
+        {
+          "text": "parlent",
+          "start": 167.52,
+          "end": 167.78,
+          "confidence": 0.793
+        },
+        {
+          "text": "de",
+          "start": 167.78,
+          "end": 167.84,
+          "confidence": 0.813
+        },
+        {
+          "text": "dépendance",
+          "start": 167.84,
+          "end": 168.36,
+          "confidence": 0.698
+        },
+        {
+          "text": "du",
+          "start": 168.36,
+          "end": 168.5,
+          "confidence": 0.963
+        },
+        {
+          "text": "santé.",
+          "start": 168.5,
+          "end": 168.8,
+          "confidence": 0.489
+        }
+      ]
+    },
+    {
+      "id": 50,
+      "seek": 16526,
+      "start": 168.82,
+      "end": 173.42,
+      "text": " Ces vidéos, en fait, on est un santé qui a été étabis, un soit mon termine, en marchand dessus,",
+      "tokens": [
+        50542,
+        28414,
+        25417,
+        11,
+        465,
+        3887,
+        11,
+        322,
+        871,
+        517,
+        30068,
+        1956,
+        257,
+        8862,
+        4823,
+        455,
+        271,
+        11,
+        517,
+        12703,
+        1108,
+        1433,
+        533,
+        11,
+        465,
+        8368,
+        474,
+        30677,
+        11,
+        50784
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6644235849380493,
+      "compression_ratio": 1.4761904761904763,
+      "no_speech_prob": 0.1915542334318161,
+      "confidence": 0.474,
+      "words": [
+        {
+          "text": "Ces",
+          "start": 168.82,
+          "end": 169.14,
+          "confidence": 0.443
+        },
+        {
+          "text": "vidéos,",
+          "start": 169.14,
+          "end": 169.4,
+          "confidence": 0.455
+        },
+        {
+          "text": "en",
+          "start": 169.44,
+          "end": 169.64,
+          "confidence": 0.744
+        },
+        {
+          "text": "fait,",
+          "start": 169.64,
+          "end": 169.66,
+          "confidence": 0.976
+        },
+        {
+          "text": "on",
+          "start": 169.72,
+          "end": 169.74,
+          "confidence": 0.303
+        },
+        {
+          "text": "est",
+          "start": 169.74,
+          "end": 169.9,
+          "confidence": 0.814
+        },
+        {
+          "text": "un",
+          "start": 169.9,
+          "end": 170.48,
+          "confidence": 0.367
+        },
+        {
+          "text": "santé",
+          "start": 170.48,
+          "end": 170.8,
+          "confidence": 0.951
+        },
+        {
+          "text": "qui",
+          "start": 170.8,
+          "end": 170.92,
+          "confidence": 0.835
+        },
+        {
+          "text": "a",
+          "start": 170.92,
+          "end": 171.02,
+          "confidence": 0.819
+        },
+        {
+          "text": "été",
+          "start": 171.02,
+          "end": 171.12,
+          "confidence": 0.994
+        },
+        {
+          "text": "étabis,",
+          "start": 171.12,
+          "end": 171.5,
+          "confidence": 0.343
+        },
+        {
+          "text": "un",
+          "start": 171.76,
+          "end": 171.9,
+          "confidence": 0.236
+        },
+        {
+          "text": "soit",
+          "start": 171.9,
+          "end": 172.16,
+          "confidence": 0.31
+        },
+        {
+          "text": "mon",
+          "start": 172.16,
+          "end": 172.36,
+          "confidence": 0.205
+        },
+        {
+          "text": "termine,",
+          "start": 172.36,
+          "end": 172.72,
+          "confidence": 0.4
+        },
+        {
+          "text": "en",
+          "start": 172.8,
+          "end": 172.82,
+          "confidence": 0.309
+        },
+        {
+          "text": "marchand",
+          "start": 172.82,
+          "end": 173.14,
+          "confidence": 0.816
+        },
+        {
+          "text": "dessus,",
+          "start": 173.14,
+          "end": 173.42,
+          "confidence": 0.201
+        }
+      ]
+    },
+    {
+      "id": 51,
+      "seek": 16526,
+      "start": 173.86,
+      "end": 177.42,
+      "text": " soit des finissants débordes, des finissants, une signalétique.",
+      "tokens": [
+        50784,
+        12703,
+        730,
+        962,
+        891,
+        1719,
+        36529,
+        765,
+        279,
+        11,
+        730,
+        962,
+        891,
+        1719,
+        11,
+        2251,
+        6358,
+        42379,
+        13,
+        50974
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6644235849380493,
+      "compression_ratio": 1.4761904761904763,
+      "no_speech_prob": 0.1915542334318161,
+      "confidence": 0.582,
+      "words": [
+        {
+          "text": "soit",
+          "start": 173.86,
+          "end": 174.4,
+          "confidence": 0.993
+        },
+        {
+          "text": "des",
+          "start": 174.4,
+          "end": 175.2,
+          "confidence": 0.759
+        },
+        {
+          "text": "finissants",
+          "start": 175.2,
+          "end": 175.58,
+          "confidence": 0.436
+        },
+        {
+          "text": "débordes,",
+          "start": 175.58,
+          "end": 175.98,
+          "confidence": 0.467
+        },
+        {
+          "text": "des",
+          "start": 176.14,
+          "end": 176.18,
+          "confidence": 0.222
+        },
+        {
+          "text": "finissants,",
+          "start": 176.18,
+          "end": 176.62,
+          "confidence": 0.961
+        },
+        {
+          "text": "une",
+          "start": 176.66,
+          "end": 176.84,
+          "confidence": 0.75
+        },
+        {
+          "text": "signalétique.",
+          "start": 176.84,
+          "end": 177.42,
+          "confidence": 0.566
+        }
+      ]
+    }
+  ],
+  "language": "fr",
+  "language_probs": {
+    "en": 0.003095489228144288,
+    "zh": 0.0006387902540154755,
+    "de": 0.0005213654367253184,
+    "es": 0.0002621589810587466,
+    "ru": 9.644290548749268e-05,
+    "ko": 0.0004060397914145142,
+    "fr": 0.9878895878791809,
+    "ja": 0.001508620916865766,
+    "pt": 0.0008202229510061443,
+    "tr": 0.00010758983989944682,
+    "pl": 5.243510167929344e-05,
+    "ca": 5.111286554893013e-06,
+    "nl": 0.00018159222963731736,
+    "ar": 0.0003162241482641548,
+    "sv": 5.988276097923517e-05,
+    "it": 0.00041243399027734995,
+    "id": 5.3565827329293825e-06,
+    "hi": 1.899073504318949e-05,
+    "fi": 9.529085787107761e-07,
+    "vi": 1.4905997886671685e-05,
+    "he": 2.2728934709448367e-05,
+    "uk": 6.863543262625171e-07,
+    "el": 1.255210918316152e-05,
+    "ms": 3.63207291229628e-05,
+    "cs": 6.311596735031344e-06,
+    "ro": 1.2261339179531205e-05,
+    "da": 7.264603482326493e-06,
+    "hu": 9.775592843652703e-06,
+    "ta": 7.081414992171631e-07,
+    "no": 1.378579418087611e-05,
+    "th": 2.0533880160655826e-05,
+    "ur": 5.111286554893013e-06,
+    "hr": 9.435073167196606e-08,
+    "bg": 2.3956120003276737e-06,
+    "lt": 3.299109607723949e-08,
+    "la": 0.00038744587800465524,
+    "mi": 5.526619133888744e-06,
+    "ml": 1.522743559689843e-06,
+    "cy": 3.896646012435667e-05,
+    "sk": 3.397700254481606e-07,
+    "te": 1.4386768043550546e-07,
+    "fa": 3.17366993840551e-06,
+    "lv": 2.490298456336859e-08,
+    "bn": 2.2155788883537753e-06,
+    "sr": 3.273435922324097e-08,
+    "az": 4.94362438985263e-07,
+    "sl": 6.347739827106125e-07,
+    "kn": 3.197606801563779e-08,
+    "et": 7.761079245938163e-08,
+    "mk": 1.3515118268969672e-07,
+    "br": 0.0019371077651157975,
+    "eu": 1.2749776033160742e-05,
+    "is": 2.794872102640511e-07,
+    "hy": 1.2623987686311011e-06,
+    "ne": 1.2795857173841796e-07,
+    "mn": 1.9860319753206568e-06,
+    "bs": 8.26162533940078e-08,
+    "kk": 1.891105085860545e-07,
+    "sq": 1.3126870044288808e-06,
+    "sw": 2.2859089767734986e-06,
+    "gl": 1.2357507330307271e-05,
+    "mr": 7.976223770356228e-08,
+    "pa": 6.249327384466596e-07,
+    "si": 2.867172270271112e-06,
+    "km": 2.5158635253319517e-05,
+    "sn": 2.3086862711352296e-05,
+    "yo": 2.3634351236978546e-05,
+    "so": 8.52387884719974e-08,
+    "af": 5.221507990427199e-07,
+    "oc": 0.00014821125660091639,
+    "ka": 2.281108066881643e-07,
+    "be": 1.1584422736632405e-06,
+    "tg": 8.308935761647263e-09,
+    "sd": 1.3864739685232053e-06,
+    "gu": 6.044334810439977e-08,
+    "am": 1.9511351467826898e-07,
+    "yi": 4.581727807817515e-06,
+    "lo": 7.026307002888643e-07,
+    "uz": 2.0319157467696414e-10,
+    "fo": 4.075073320564115e-06,
+    "ht": 0.0001349478989141062,
+    "ps": 2.838884540778963e-07,
+    "tk": 5.8224053356426e-10,
+    "nn": 0.0004747086495626718,
+    "mt": 3.1423587643075734e-07,
+    "sa": 2.4716568987059873e-06,
+    "lb": 4.894851457493132e-08,
+    "my": 6.461271823354764e-06,
+    "bo": 3.052088686672505e-06,
+    "tl": 8.343945978595002e-07,
+    "mg": 1.7280938902075604e-09,
+    "as": 2.3352028222234367e-07,
+    "tt": 2.362024353885772e-09,
+    "haw": 5.988276097923517e-05,
+    "ln": 3.0825005524093285e-05,
+    "ha": 5.3437370084452596e-09,
+    "ba": 5.260104574134061e-10,
+    "jw": 7.394534623017535e-05,
+    "su": 7.896352460790013e-10
+  }
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_fr.cpu/bonjour_vous_allez_bien.mp3.words.json b/tests/expected/tiny_fr.cpu/bonjour_vous_allez_bien.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..adc9890af4a61ebbb4b7beeef62b7b6307ee0338
--- /dev/null
+++ b/tests/expected/tiny_fr.cpu/bonjour_vous_allez_bien.mp3.words.json
@@ -0,0 +1,190 @@
+{
+  "text": " Bonjour! Est-ce que vous allez bien? Bonjour! Bonjour! Est-ce que vous allez bien?",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.46,
+      "end": 0.68,
+      "text": " Bonjour!",
+      "tokens": [
+        25431,
+        2298
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7739177703857422,
+      "compression_ratio": 0.8181818181818182,
+      "no_speech_prob": 0.04250079020857811,
+      "confidence": 0.69,
+      "words": [
+        {
+          "text": "Bonjour!",
+          "start": 0.46,
+          "end": 0.68,
+          "confidence": 0.69
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 148,
+      "start": 1.86,
+      "end": 2.8,
+      "text": " Est-ce que vous allez bien?",
+      "tokens": [
+        50364,
+        4410,
+        12,
+        384,
+        631,
+        2630,
+        18146,
+        3610,
+        2506,
+        50464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4815776131369851,
+      "compression_ratio": 0.7714285714285715,
+      "no_speech_prob": 0.04176269844174385,
+      "confidence": 0.632,
+      "words": [
+        {
+          "text": "Est-ce",
+          "start": 1.86,
+          "end": 2.14,
+          "confidence": 0.548
+        },
+        {
+          "text": "que",
+          "start": 2.14,
+          "end": 2.18,
+          "confidence": 0.848
+        },
+        {
+          "text": "vous",
+          "start": 2.18,
+          "end": 2.34,
+          "confidence": 0.993
+        },
+        {
+          "text": "allez",
+          "start": 2.34,
+          "end": 2.48,
+          "confidence": 0.298
+        },
+        {
+          "text": "bien?",
+          "start": 2.48,
+          "end": 2.8,
+          "confidence": 0.979
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 3148,
+      "start": 32.98,
+      "end": 33.16,
+      "text": " Bonjour!",
+      "tokens": [
+        25431,
+        2298
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.34033950169881183,
+      "compression_ratio": 0.8181818181818182,
+      "no_speech_prob": 0.5495142936706543,
+      "confidence": 0.919,
+      "words": [
+        {
+          "text": "Bonjour!",
+          "start": 32.98,
+          "end": 33.16,
+          "confidence": 0.919
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 3348,
+      "start": 34.4,
+      "end": 34.61,
+      "text": " Bonjour!",
+      "tokens": [
+        25431,
+        2298
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.23644089698791504,
+      "compression_ratio": 0.8181818181818182,
+      "no_speech_prob": 0.40533149242401123,
+      "confidence": 0.331,
+      "words": [
+        {
+          "text": "Bonjour!",
+          "start": 34.4,
+          "end": 34.61,
+          "confidence": 0.331
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 3448,
+      "start": 34.61,
+      "end": 35.34,
+      "text": " Est-ce que vous allez bien?",
+      "tokens": [
+        50364,
+        4410,
+        12,
+        384,
+        631,
+        2630,
+        18146,
+        3610,
+        2506,
+        50464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.17279924045909534,
+      "compression_ratio": 0.7714285714285715,
+      "no_speech_prob": 0.5867945551872253,
+      "confidence": 0.871,
+      "words": [
+        {
+          "text": "Est-ce",
+          "start": 34.61,
+          "end": 34.66,
+          "confidence": 0.741
+        },
+        {
+          "text": "que",
+          "start": 34.66,
+          "end": 34.72,
+          "confidence": 0.979
+        },
+        {
+          "text": "vous",
+          "start": 34.72,
+          "end": 34.86,
+          "confidence": 0.999
+        },
+        {
+          "text": "allez",
+          "start": 34.86,
+          "end": 35.0,
+          "confidence": 0.959
+        },
+        {
+          "text": "bien?",
+          "start": 35.0,
+          "end": 35.34,
+          "confidence": 1.0
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_fr.cpu/radio_short.mp3.words.json b/tests/expected/tiny_fr.cpu/radio_short.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..b1910cc5b3224406e946a7c50d9507d3dfe850fe
--- /dev/null
+++ b/tests/expected/tiny_fr.cpu/radio_short.mp3.words.json
@@ -0,0 +1,104 @@
+{
+  "text": "............",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.08,
+      "end": 0.76,
+      "text": "...",
+      "tokens": [
+        50364,
+        1097,
+        50614
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -1.4265364408493042,
+      "compression_ratio": 0.2727272727272727,
+      "no_speech_prob": 0.5112143754959106,
+      "confidence": 0.224,
+      "words": [
+        {
+          "text": "...",
+          "start": 0.08,
+          "end": 0.76,
+          "confidence": 0.224
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 6000,
+      "start": 60.02,
+      "end": 69.4,
+      "text": "...",
+      "tokens": [
+        50364,
+        1097,
+        51714
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.973953366279602,
+      "compression_ratio": 0.2727272727272727,
+      "no_speech_prob": 0.8780310153961182,
+      "confidence": 0.466,
+      "words": [
+        {
+          "text": "...",
+          "start": 60.02,
+          "end": 69.4,
+          "confidence": 0.466
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 9000,
+      "start": 90.02,
+      "end": 90.24,
+      "text": "...",
+      "tokens": [
+        1097
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.8283956527709961,
+      "compression_ratio": 0.2727272727272727,
+      "no_speech_prob": 0.641629695892334,
+      "confidence": 0.842,
+      "words": [
+        {
+          "text": "...",
+          "start": 90.02,
+          "end": 90.24,
+          "confidence": 0.842
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 10500,
+      "start": 105.04,
+      "end": 117.76,
+      "text": "...",
+      "tokens": [
+        50364,
+        1097,
+        51714
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.728730320930481,
+      "compression_ratio": 0.2727272727272727,
+      "no_speech_prob": 0.25682491064071655,
+      "confidence": 0.764,
+      "words": [
+        {
+          "text": "...",
+          "start": 105.04,
+          "end": 117.76,
+          "confidence": 0.764
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_fr.cpu/smartphone.mp3.words.json b/tests/expected/tiny_fr.cpu/smartphone.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..f90643caf0519b49ba0cbc0381cd8d8ced1f218b
--- /dev/null
+++ b/tests/expected/tiny_fr.cpu/smartphone.mp3.words.json
@@ -0,0 +1,5038 @@
+{
+  "text": " C'est évidence que dit Nicolas. Mais je me l'étais jamais formulé comme ça. Ce qui fait la force du smartphone, c'est pas seulement la cumulation des fonctions, mais la manière dans quelques interagues entraîne. Et il est d'ailleurs, c'est la photo c'est hyper convaincant. Alors évidemment, il faudrait ajouter les interfaces les grand-attêtes qu'il a été beaucoup très souvent ementionné. Mais bon, il faudrait que les profites aussi de 20 ans pendant l'été, les ordinateurs nous ont appris à piquer sur des icônes. C'est ce que le smartphone ajoute le toucher, qui rend le contact plus direct, plus sensible. Et puis, évidemment, il faudrait parler aussi des applications qui permettent de contourner le côté tout flu de la navigation web pour aller directement en but. Bref, tout ça, ce sont les conditions qui permettent de créer cette objet, en Nicolas, dit qu'il est très fondablement inédit dans l'histoire de l'humanité. Mais ça s'assoulait d'une autre interrogation. Est-ce que le fait que cette objet soit inédit un d'huies que notre rapport a lui est aussi un rapport inédit? Je veux dire, est-ce que le rapport qu'on a au sein de foi n'est comparable à celui qu'on entretenait à d'autres objectes techniques comme la voiture ou le téléphone? Il n'y a pas d'équivalent. On s'est espécie de nous voter dans la relation à l'objet. C'est facilement éterréciant parce qu'on a impression de, comme le 10, les utilisateurs et les efforts, elles aident dépendant de cette objet d'un lieu, en fait, une espèce de relation de médiation avec le monde qui rendent un peu avec la même sédiforme de le jeu. Donc, à objets inédits, rapport inédits. Et, ce rapport, si j'en prends Nicolas, frère caractérisée par un mélange de dépenses et de rojets. Bon, en vrai, il faudrait remonter très très finement toute l'histoire des objectes techniques et de leur infération dans le vie pour déterminer si ce rapport est totalement inédit. Mais j'ai l'impression comme ça que Nicolas se trompe pas vraiment. Pour autant, je sache. Il y a eu plein de discussions autour de la voiture ou même du téléphone. Mais la dépense n'était pas du même mort, donc le rejet n'en plus n'était pas du même mort. On peut adorer sa bagnure, en avoir besoin pour plein de choses. Et là, le soir, quand on va se coucher, on la laisse. On l'a pas dans la main, quand on est collis, quand on n'en mène pas au chiot. On pouvait être émervé par son mome qui occupeait la ligne de téléphone pendant une heure chaque soir pour discuter avec un copain. Mais ça ne ressemble pas à ce qu'on peut ressentir à voir même mome aujourd'hui continuuellement avec son smartphone dans la main, comme c'était une sorte de estimateur extère de l'intempis de lâcher à l'éantrénée, ça m'a eu immédiate. Bon, je dis ça pour le mome, mais évidemment, va là pour nos aussi. Donc, rapport immédiate d'accord. Mais pourquoi, à ton impression qu'on en sortira jamais? Et puis, il faut en remettre la faute sur les gens qui ont créé cette route merveilleux et diabolique, qui a dit à bollique par coeur, merveilleux. Les économistes parlent de dépendance du santé. Ces vidéos, en fait, on est un santé qui a été établie, c'est un soit mon termine, soit définissant des beurs, on définisse un signalétique.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.42,
+      "end": 1.38,
+      "text": " C'est évidence que dit Nicolas.",
+      "tokens": [
+        383,
+        6,
+        377,
+        20090,
+        2778,
+        631,
+        6176,
+        38268,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.566579490710216,
+      "compression_ratio": 1.605421686746988,
+      "no_speech_prob": 0.14170263707637787,
+      "confidence": 0.625,
+      "words": [
+        {
+          "text": "C'est",
+          "start": 0.42,
+          "end": 0.66,
+          "confidence": 0.849
+        },
+        {
+          "text": "évidence",
+          "start": 0.66,
+          "end": 0.94,
+          "confidence": 0.368
+        },
+        {
+          "text": "que",
+          "start": 0.94,
+          "end": 1.06,
+          "confidence": 0.883
+        },
+        {
+          "text": "dit",
+          "start": 1.06,
+          "end": 1.16,
+          "confidence": 0.344
+        },
+        {
+          "text": "Nicolas.",
+          "start": 1.16,
+          "end": 1.38,
+          "confidence": 0.921
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 1.66,
+      "end": 3.62,
+      "text": " Mais je me l'étais jamais formulé comme ça.",
+      "tokens": [
+        6313,
+        1506,
+        385,
+        287,
+        6,
+        22824,
+        14540,
+        1254,
+        425,
+        526,
+        5173,
+        2788,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.566579490710216,
+      "compression_ratio": 1.605421686746988,
+      "no_speech_prob": 0.14170263707637787,
+      "confidence": 0.745,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 1.66,
+          "end": 1.9,
+          "confidence": 0.956
+        },
+        {
+          "text": "je",
+          "start": 1.9,
+          "end": 2.18,
+          "confidence": 0.629
+        },
+        {
+          "text": "me",
+          "start": 2.18,
+          "end": 2.3,
+          "confidence": 0.943
+        },
+        {
+          "text": "l'étais",
+          "start": 2.3,
+          "end": 2.54,
+          "confidence": 0.708
+        },
+        {
+          "text": "jamais",
+          "start": 2.54,
+          "end": 2.78,
+          "confidence": 0.962
+        },
+        {
+          "text": "formulé",
+          "start": 2.78,
+          "end": 3.2,
+          "confidence": 0.541
+        },
+        {
+          "text": "comme",
+          "start": 3.2,
+          "end": 3.34,
+          "confidence": 0.975
+        },
+        {
+          "text": "ça.",
+          "start": 3.34,
+          "end": 3.62,
+          "confidence": 0.979
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 4.14,
+      "end": 8.82,
+      "text": " Ce qui fait la force du smartphone, c'est pas seulement la cumulation des fonctions, mais la manière",
+      "tokens": [
+        8257,
+        1956,
+        3887,
+        635,
+        3464,
+        1581,
+        13307,
+        11,
+        269,
+        6,
+        377,
+        1736,
+        27772,
+        635,
+        12713,
+        2776,
+        730,
+        17290,
+        3916,
+        11,
+        2420,
+        635,
+        22267
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.566579490710216,
+      "compression_ratio": 1.605421686746988,
+      "no_speech_prob": 0.14170263707637787,
+      "confidence": 0.762,
+      "words": [
+        {
+          "text": "Ce",
+          "start": 4.14,
+          "end": 4.22,
+          "confidence": 0.39
+        },
+        {
+          "text": "qui",
+          "start": 4.22,
+          "end": 4.34,
+          "confidence": 0.934
+        },
+        {
+          "text": "fait",
+          "start": 4.34,
+          "end": 4.46,
+          "confidence": 0.735
+        },
+        {
+          "text": "la",
+          "start": 4.46,
+          "end": 4.56,
+          "confidence": 0.988
+        },
+        {
+          "text": "force",
+          "start": 4.56,
+          "end": 4.96,
+          "confidence": 0.933
+        },
+        {
+          "text": "du",
+          "start": 4.96,
+          "end": 5.16,
+          "confidence": 0.936
+        },
+        {
+          "text": "smartphone,",
+          "start": 5.16,
+          "end": 5.74,
+          "confidence": 0.909
+        },
+        {
+          "text": "c'est",
+          "start": 5.74,
+          "end": 6.12,
+          "confidence": 0.871
+        },
+        {
+          "text": "pas",
+          "start": 6.12,
+          "end": 6.2,
+          "confidence": 0.982
+        },
+        {
+          "text": "seulement",
+          "start": 6.2,
+          "end": 6.52,
+          "confidence": 0.991
+        },
+        {
+          "text": "la",
+          "start": 6.52,
+          "end": 6.76,
+          "confidence": 0.627
+        },
+        {
+          "text": "cumulation",
+          "start": 6.76,
+          "end": 7.18,
+          "confidence": 0.679
+        },
+        {
+          "text": "des",
+          "start": 7.18,
+          "end": 7.54,
+          "confidence": 0.752
+        },
+        {
+          "text": "fonctions,",
+          "start": 7.54,
+          "end": 8.1,
+          "confidence": 0.826
+        },
+        {
+          "text": "mais",
+          "start": 8.1,
+          "end": 8.42,
+          "confidence": 0.511
+        },
+        {
+          "text": "la",
+          "start": 8.42,
+          "end": 8.58,
+          "confidence": 0.717
+        },
+        {
+          "text": "manière",
+          "start": 8.58,
+          "end": 8.82,
+          "confidence": 0.457
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 8.9,
+      "end": 10.84,
+      "text": " dans quelques interagues entraîne.",
+      "tokens": [
+        2680,
+        16597,
+        728,
+        559,
+        1247,
+        22284,
+        24741,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.566579490710216,
+      "compression_ratio": 1.605421686746988,
+      "no_speech_prob": 0.14170263707637787,
+      "confidence": 0.3,
+      "words": [
+        {
+          "text": "dans",
+          "start": 8.9,
+          "end": 9.04,
+          "confidence": 0.329
+        },
+        {
+          "text": "quelques",
+          "start": 9.04,
+          "end": 9.26,
+          "confidence": 0.282
+        },
+        {
+          "text": "interagues",
+          "start": 9.26,
+          "end": 10.18,
+          "confidence": 0.238
+        },
+        {
+          "text": "entraîne.",
+          "start": 10.18,
+          "end": 10.84,
+          "confidence": 0.421
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 11.04,
+      "end": 12.92,
+      "text": " Et il est d'ailleurs, c'est la photo c'est hyper convaincant.",
+      "tokens": [
+        3790,
+        1930,
+        871,
+        274,
+        6,
+        19400,
+        11,
+        269,
+        6,
+        377,
+        635,
+        5052,
+        269,
+        6,
+        377,
+        9848,
+        3754,
+        491,
+        66,
+        394,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.566579490710216,
+      "compression_ratio": 1.605421686746988,
+      "no_speech_prob": 0.14170263707637787,
+      "confidence": 0.625,
+      "words": [
+        {
+          "text": "Et",
+          "start": 11.04,
+          "end": 11.1,
+          "confidence": 0.394
+        },
+        {
+          "text": "il",
+          "start": 11.1,
+          "end": 11.24,
+          "confidence": 0.128
+        },
+        {
+          "text": "est",
+          "start": 11.24,
+          "end": 11.38,
+          "confidence": 0.237
+        },
+        {
+          "text": "d'ailleurs,",
+          "start": 11.38,
+          "end": 11.62,
+          "confidence": 0.904
+        },
+        {
+          "text": "c'est",
+          "start": 11.62,
+          "end": 11.78,
+          "confidence": 0.879
+        },
+        {
+          "text": "la",
+          "start": 11.78,
+          "end": 11.82,
+          "confidence": 0.968
+        },
+        {
+          "text": "photo",
+          "start": 11.82,
+          "end": 11.92,
+          "confidence": 0.811
+        },
+        {
+          "text": "c'est",
+          "start": 11.92,
+          "end": 12.18,
+          "confidence": 0.792
+        },
+        {
+          "text": "hyper",
+          "start": 12.18,
+          "end": 12.38,
+          "confidence": 0.939
+        },
+        {
+          "text": "convaincant.",
+          "start": 12.38,
+          "end": 12.92,
+          "confidence": 0.494
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 0,
+      "start": 13.26,
+      "end": 18.03,
+      "text": " Alors évidemment, il faudrait ajouter les interfaces les grand-attêtes qu'il a été beaucoup",
+      "tokens": [
+        9946,
+        24724,
+        11,
+        1930,
+        38694,
+        8645,
+        17680,
+        23985,
+        1512,
+        28416,
+        1512,
+        2697,
+        12,
+        1591,
+        38262,
+        421,
+        6,
+        388,
+        257,
+        8862,
+        8796
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.566579490710216,
+      "compression_ratio": 1.605421686746988,
+      "no_speech_prob": 0.14170263707637787,
+      "confidence": 0.553,
+      "words": [
+        {
+          "text": "Alors",
+          "start": 13.26,
+          "end": 13.48,
+          "confidence": 0.904
+        },
+        {
+          "text": "évidemment,",
+          "start": 13.48,
+          "end": 13.92,
+          "confidence": 0.785
+        },
+        {
+          "text": "il",
+          "start": 13.92,
+          "end": 14.4,
+          "confidence": 0.961
+        },
+        {
+          "text": "faudrait",
+          "start": 14.4,
+          "end": 14.76,
+          "confidence": 0.85
+        },
+        {
+          "text": "ajouter",
+          "start": 14.76,
+          "end": 15.38,
+          "confidence": 0.874
+        },
+        {
+          "text": "les",
+          "start": 15.38,
+          "end": 15.62,
+          "confidence": 0.933
+        },
+        {
+          "text": "interfaces",
+          "start": 15.62,
+          "end": 15.86,
+          "confidence": 0.359
+        },
+        {
+          "text": "les",
+          "start": 15.86,
+          "end": 16.5,
+          "confidence": 0.414
+        },
+        {
+          "text": "grand-attêtes",
+          "start": 16.5,
+          "end": 16.94,
+          "confidence": 0.178
+        },
+        {
+          "text": "qu'il",
+          "start": 16.94,
+          "end": 17.18,
+          "confidence": 0.632
+        },
+        {
+          "text": "a",
+          "start": 17.18,
+          "end": 17.24,
+          "confidence": 0.969
+        },
+        {
+          "text": "été",
+          "start": 17.24,
+          "end": 17.5,
+          "confidence": 0.957
+        },
+        {
+          "text": "beaucoup",
+          "start": 17.5,
+          "end": 18.03,
+          "confidence": 0.572
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 0,
+      "start": 18.03,
+      "end": 19.26,
+      "text": " très souvent ementionné.",
+      "tokens": [
+        5732,
+        20847,
+        846,
+        1251,
+        15055,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.566579490710216,
+      "compression_ratio": 1.605421686746988,
+      "no_speech_prob": 0.14170263707637787,
+      "confidence": 0.541,
+      "words": [
+        {
+          "text": "très",
+          "start": 18.03,
+          "end": 18.66,
+          "confidence": 0.959
+        },
+        {
+          "text": "souvent",
+          "start": 18.66,
+          "end": 18.82,
+          "confidence": 0.994
+        },
+        {
+          "text": "ementionné.",
+          "start": 18.82,
+          "end": 19.26,
+          "confidence": 0.365
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 0,
+      "start": 19.86,
+      "end": 23.54,
+      "text": " Mais bon, il faudrait que les profites aussi de 20 ans pendant l'été, les ordinateurs",
+      "tokens": [
+        6313,
+        4428,
+        11,
+        1930,
+        38694,
+        8645,
+        631,
+        1512,
+        1740,
+        3324,
+        6212,
+        368,
+        945,
+        1567,
+        17338,
+        287,
+        6,
+        21210,
+        11,
+        1512,
+        4792,
+        13923,
+        2156
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.566579490710216,
+      "compression_ratio": 1.605421686746988,
+      "no_speech_prob": 0.14170263707637787,
+      "confidence": 0.648,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 19.86,
+          "end": 20.22,
+          "confidence": 0.975
+        },
+        {
+          "text": "bon,",
+          "start": 20.22,
+          "end": 20.56,
+          "confidence": 0.479
+        },
+        {
+          "text": "il",
+          "start": 20.56,
+          "end": 20.6,
+          "confidence": 0.978
+        },
+        {
+          "text": "faudrait",
+          "start": 20.6,
+          "end": 20.74,
+          "confidence": 0.753
+        },
+        {
+          "text": "que",
+          "start": 20.74,
+          "end": 20.92,
+          "confidence": 0.378
+        },
+        {
+          "text": "les",
+          "start": 20.92,
+          "end": 20.98,
+          "confidence": 0.182
+        },
+        {
+          "text": "profites",
+          "start": 20.98,
+          "end": 21.26,
+          "confidence": 0.622
+        },
+        {
+          "text": "aussi",
+          "start": 21.26,
+          "end": 21.7,
+          "confidence": 0.502
+        },
+        {
+          "text": "de",
+          "start": 21.7,
+          "end": 21.84,
+          "confidence": 0.468
+        },
+        {
+          "text": "20",
+          "start": 21.84,
+          "end": 22.08,
+          "confidence": 0.924
+        },
+        {
+          "text": "ans",
+          "start": 22.08,
+          "end": 22.28,
+          "confidence": 0.937
+        },
+        {
+          "text": "pendant",
+          "start": 22.28,
+          "end": 22.46,
+          "confidence": 0.903
+        },
+        {
+          "text": "l'été,",
+          "start": 22.46,
+          "end": 22.96,
+          "confidence": 0.499
+        },
+        {
+          "text": "les",
+          "start": 22.96,
+          "end": 23.04,
+          "confidence": 0.861
+        },
+        {
+          "text": "ordinateurs",
+          "start": 23.04,
+          "end": 23.54,
+          "confidence": 0.934
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 0,
+      "start": 23.58,
+      "end": 25.26,
+      "text": " nous ont appris à piquer sur des icônes.",
+      "tokens": [
+        4666,
+        6592,
+        724,
+        5714,
+        1531,
+        280,
+        23909,
+        1022,
+        730,
+        4376,
+        2851,
+        4081,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.566579490710216,
+      "compression_ratio": 1.605421686746988,
+      "no_speech_prob": 0.14170263707637787,
+      "confidence": 0.663,
+      "words": [
+        {
+          "text": "nous",
+          "start": 23.58,
+          "end": 23.74,
+          "confidence": 0.833
+        },
+        {
+          "text": "ont",
+          "start": 23.74,
+          "end": 23.86,
+          "confidence": 0.976
+        },
+        {
+          "text": "appris",
+          "start": 23.86,
+          "end": 24.06,
+          "confidence": 0.947
+        },
+        {
+          "text": "à",
+          "start": 24.06,
+          "end": 24.24,
+          "confidence": 0.24
+        },
+        {
+          "text": "piquer",
+          "start": 24.24,
+          "end": 24.42,
+          "confidence": 0.45
+        },
+        {
+          "text": "sur",
+          "start": 24.42,
+          "end": 24.68,
+          "confidence": 0.749
+        },
+        {
+          "text": "des",
+          "start": 24.68,
+          "end": 24.8,
+          "confidence": 0.96
+        },
+        {
+          "text": "icônes.",
+          "start": 24.8,
+          "end": 25.26,
+          "confidence": 0.656
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 2556,
+      "start": 25.58,
+      "end": 30.56,
+      "text": " C'est ce que le smartphone ajoute le toucher, qui rend le contact plus direct, plus sensible.",
+      "tokens": [
+        383,
+        6,
+        377,
+        1769,
+        631,
+        476,
+        13307,
+        17680,
+        14040,
+        476,
+        2557,
+        260,
+        11,
+        1956,
+        6125,
+        476,
+        3385,
+        1804,
+        2047,
+        11,
+        1804,
+        25380,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4095459938049316,
+      "compression_ratio": 1.7522658610271904,
+      "no_speech_prob": 0.0006256799097172916,
+      "confidence": 0.643,
+      "words": [
+        {
+          "text": "C'est",
+          "start": 25.58,
+          "end": 25.66,
+          "confidence": 0.449
+        },
+        {
+          "text": "ce",
+          "start": 25.66,
+          "end": 25.72,
+          "confidence": 0.491
+        },
+        {
+          "text": "que",
+          "start": 25.72,
+          "end": 25.94,
+          "confidence": 0.935
+        },
+        {
+          "text": "le",
+          "start": 25.94,
+          "end": 26.6,
+          "confidence": 0.377
+        },
+        {
+          "text": "smartphone",
+          "start": 26.6,
+          "end": 26.86,
+          "confidence": 0.977
+        },
+        {
+          "text": "ajoute",
+          "start": 26.86,
+          "end": 27.42,
+          "confidence": 0.813
+        },
+        {
+          "text": "le",
+          "start": 27.42,
+          "end": 27.64,
+          "confidence": 0.957
+        },
+        {
+          "text": "toucher,",
+          "start": 27.64,
+          "end": 28.06,
+          "confidence": 0.73
+        },
+        {
+          "text": "qui",
+          "start": 28.06,
+          "end": 28.18,
+          "confidence": 0.209
+        },
+        {
+          "text": "rend",
+          "start": 28.18,
+          "end": 28.34,
+          "confidence": 0.877
+        },
+        {
+          "text": "le",
+          "start": 28.34,
+          "end": 28.68,
+          "confidence": 0.991
+        },
+        {
+          "text": "contact",
+          "start": 28.68,
+          "end": 28.96,
+          "confidence": 0.854
+        },
+        {
+          "text": "plus",
+          "start": 28.96,
+          "end": 29.48,
+          "confidence": 0.865
+        },
+        {
+          "text": "direct,",
+          "start": 29.48,
+          "end": 29.96,
+          "confidence": 0.692
+        },
+        {
+          "text": "plus",
+          "start": 29.96,
+          "end": 30.24,
+          "confidence": 0.928
+        },
+        {
+          "text": "sensible.",
+          "start": 30.24,
+          "end": 30.56,
+          "confidence": 0.332
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 2556,
+      "start": 31.04,
+      "end": 34.34,
+      "text": " Et puis, évidemment, il faudrait parler aussi des applications qui permettent de contourner",
+      "tokens": [
+        3790,
+        9093,
+        11,
+        24724,
+        11,
+        1930,
+        38694,
+        8645,
+        16421,
+        6212,
+        730,
+        5821,
+        1956,
+        21540,
+        317,
+        368,
+        21234,
+        1193
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4095459938049316,
+      "compression_ratio": 1.7522658610271904,
+      "no_speech_prob": 0.0006256799097172916,
+      "confidence": 0.827,
+      "words": [
+        {
+          "text": "Et",
+          "start": 31.04,
+          "end": 31.24,
+          "confidence": 0.914
+        },
+        {
+          "text": "puis,",
+          "start": 31.24,
+          "end": 31.34,
+          "confidence": 0.713
+        },
+        {
+          "text": "évidemment,",
+          "start": 31.34,
+          "end": 31.64,
+          "confidence": 0.378
+        },
+        {
+          "text": "il",
+          "start": 31.64,
+          "end": 31.78,
+          "confidence": 0.935
+        },
+        {
+          "text": "faudrait",
+          "start": 31.78,
+          "end": 31.88,
+          "confidence": 0.99
+        },
+        {
+          "text": "parler",
+          "start": 31.88,
+          "end": 32.12,
+          "confidence": 0.882
+        },
+        {
+          "text": "aussi",
+          "start": 32.12,
+          "end": 32.3,
+          "confidence": 0.889
+        },
+        {
+          "text": "des",
+          "start": 32.3,
+          "end": 32.44,
+          "confidence": 0.927
+        },
+        {
+          "text": "applications",
+          "start": 32.44,
+          "end": 32.78,
+          "confidence": 0.839
+        },
+        {
+          "text": "qui",
+          "start": 32.78,
+          "end": 33.16,
+          "confidence": 0.652
+        },
+        {
+          "text": "permettent",
+          "start": 33.16,
+          "end": 33.68,
+          "confidence": 0.951
+        },
+        {
+          "text": "de",
+          "start": 33.68,
+          "end": 33.9,
+          "confidence": 0.952
+        },
+        {
+          "text": "contourner",
+          "start": 33.9,
+          "end": 34.34,
+          "confidence": 0.787
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 2556,
+      "start": 34.34,
+      "end": 37.72,
+      "text": " le côté tout flu de la navigation web pour aller directement en but.",
+      "tokens": [
+        476,
+        18437,
+        3486,
+        5029,
+        368,
+        635,
+        17346,
+        3670,
+        2016,
+        8722,
+        37297,
+        465,
+        457,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4095459938049316,
+      "compression_ratio": 1.7522658610271904,
+      "no_speech_prob": 0.0006256799097172916,
+      "confidence": 0.766,
+      "words": [
+        {
+          "text": "le",
+          "start": 34.34,
+          "end": 34.52,
+          "confidence": 0.989
+        },
+        {
+          "text": "côté",
+          "start": 34.52,
+          "end": 34.72,
+          "confidence": 0.983
+        },
+        {
+          "text": "tout",
+          "start": 34.72,
+          "end": 34.96,
+          "confidence": 0.954
+        },
+        {
+          "text": "flu",
+          "start": 34.96,
+          "end": 35.2,
+          "confidence": 0.548
+        },
+        {
+          "text": "de",
+          "start": 35.2,
+          "end": 35.42,
+          "confidence": 0.248
+        },
+        {
+          "text": "la",
+          "start": 35.42,
+          "end": 35.72,
+          "confidence": 0.902
+        },
+        {
+          "text": "navigation",
+          "start": 35.72,
+          "end": 36.04,
+          "confidence": 0.913
+        },
+        {
+          "text": "web",
+          "start": 36.04,
+          "end": 36.64,
+          "confidence": 0.93
+        },
+        {
+          "text": "pour",
+          "start": 36.64,
+          "end": 36.76,
+          "confidence": 0.746
+        },
+        {
+          "text": "aller",
+          "start": 36.76,
+          "end": 36.94,
+          "confidence": 0.992
+        },
+        {
+          "text": "directement",
+          "start": 36.94,
+          "end": 37.46,
+          "confidence": 0.986
+        },
+        {
+          "text": "en",
+          "start": 37.46,
+          "end": 37.68,
+          "confidence": 0.644
+        },
+        {
+          "text": "but.",
+          "start": 37.68,
+          "end": 37.72,
+          "confidence": 0.689
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 2556,
+      "start": 37.72,
+      "end": 43.06,
+      "text": " Bref, tout ça, ce sont les conditions qui permettent de créer cette objet, en Nicolas,",
+      "tokens": [
+        49957,
+        11,
+        3486,
+        2788,
+        11,
+        1769,
+        4900,
+        1512,
+        4487,
+        1956,
+        21540,
+        317,
+        368,
+        32062,
+        5550,
+        14964,
+        11,
+        465,
+        38268,
+        11
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4095459938049316,
+      "compression_ratio": 1.7522658610271904,
+      "no_speech_prob": 0.0006256799097172916,
+      "confidence": 0.725,
+      "words": [
+        {
+          "text": "Bref,",
+          "start": 37.72,
+          "end": 38.9,
+          "confidence": 0.967
+        },
+        {
+          "text": "tout",
+          "start": 38.9,
+          "end": 38.98,
+          "confidence": 0.786
+        },
+        {
+          "text": "ça,",
+          "start": 38.98,
+          "end": 39.36,
+          "confidence": 0.985
+        },
+        {
+          "text": "ce",
+          "start": 39.36,
+          "end": 39.68,
+          "confidence": 0.929
+        },
+        {
+          "text": "sont",
+          "start": 39.68,
+          "end": 39.84,
+          "confidence": 0.963
+        },
+        {
+          "text": "les",
+          "start": 39.84,
+          "end": 40.06,
+          "confidence": 0.976
+        },
+        {
+          "text": "conditions",
+          "start": 40.06,
+          "end": 40.54,
+          "confidence": 0.96
+        },
+        {
+          "text": "qui",
+          "start": 40.54,
+          "end": 40.9,
+          "confidence": 0.995
+        },
+        {
+          "text": "permettent",
+          "start": 40.9,
+          "end": 41.54,
+          "confidence": 0.986
+        },
+        {
+          "text": "de",
+          "start": 41.54,
+          "end": 41.58,
+          "confidence": 0.989
+        },
+        {
+          "text": "créer",
+          "start": 41.58,
+          "end": 41.92,
+          "confidence": 0.918
+        },
+        {
+          "text": "cette",
+          "start": 41.92,
+          "end": 42.3,
+          "confidence": 0.518
+        },
+        {
+          "text": "objet,",
+          "start": 42.3,
+          "end": 42.7,
+          "confidence": 0.213
+        },
+        {
+          "text": "en",
+          "start": 42.7,
+          "end": 42.8,
+          "confidence": 0.191
+        },
+        {
+          "text": "Nicolas,",
+          "start": 42.8,
+          "end": 43.06,
+          "confidence": 0.508
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 2556,
+      "start": 43.1,
+      "end": 46.48,
+      "text": " dit qu'il est très fondablement inédit dans l'histoire de l'humanité.",
+      "tokens": [
+        6176,
+        421,
+        6,
+        388,
+        871,
+        5732,
+        9557,
+        712,
+        518,
+        294,
+        7811,
+        270,
+        2680,
+        287,
+        6,
+        29093,
+        368,
+        287,
+        6,
+        18796,
+        5066,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4095459938049316,
+      "compression_ratio": 1.7522658610271904,
+      "no_speech_prob": 0.0006256799097172916,
+      "confidence": 0.768,
+      "words": [
+        {
+          "text": "dit",
+          "start": 43.1,
+          "end": 43.52,
+          "confidence": 0.551
+        },
+        {
+          "text": "qu'il",
+          "start": 43.52,
+          "end": 43.68,
+          "confidence": 0.969
+        },
+        {
+          "text": "est",
+          "start": 43.68,
+          "end": 43.8,
+          "confidence": 0.851
+        },
+        {
+          "text": "très",
+          "start": 43.8,
+          "end": 43.94,
+          "confidence": 0.368
+        },
+        {
+          "text": "fondablement",
+          "start": 43.94,
+          "end": 44.68,
+          "confidence": 0.593
+        },
+        {
+          "text": "inédit",
+          "start": 44.68,
+          "end": 45.52,
+          "confidence": 0.66
+        },
+        {
+          "text": "dans",
+          "start": 45.52,
+          "end": 45.74,
+          "confidence": 0.778
+        },
+        {
+          "text": "l'histoire",
+          "start": 45.74,
+          "end": 45.98,
+          "confidence": 0.825
+        },
+        {
+          "text": "de",
+          "start": 45.98,
+          "end": 46.08,
+          "confidence": 0.978
+        },
+        {
+          "text": "l'humanité.",
+          "start": 46.08,
+          "end": 46.48,
+          "confidence": 0.991
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 2556,
+      "start": 47.06,
+      "end": 48.76,
+      "text": " Mais ça s'assoulait d'une autre interrogation.",
+      "tokens": [
+        6313,
+        2788,
+        262,
+        6,
+        640,
+        263,
+        35235,
+        274,
+        6,
+        2613,
+        15081,
+        24871,
+        399,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4095459938049316,
+      "compression_ratio": 1.7522658610271904,
+      "no_speech_prob": 0.0006256799097172916,
+      "confidence": 0.697,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 47.06,
+          "end": 47.16,
+          "confidence": 0.939
+        },
+        {
+          "text": "ça",
+          "start": 47.16,
+          "end": 47.46,
+          "confidence": 0.854
+        },
+        {
+          "text": "s'assoulait",
+          "start": 47.46,
+          "end": 47.78,
+          "confidence": 0.591
+        },
+        {
+          "text": "d'une",
+          "start": 47.78,
+          "end": 48.02,
+          "confidence": 0.619
+        },
+        {
+          "text": "autre",
+          "start": 48.02,
+          "end": 48.14,
+          "confidence": 0.966
+        },
+        {
+          "text": "interrogation.",
+          "start": 48.14,
+          "end": 48.76,
+          "confidence": 0.833
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 2556,
+      "start": 49.26,
+      "end": 54.34,
+      "text": " Est-ce que le fait que cette objet soit inédit un d'huies que notre rapport a lui est aussi",
+      "tokens": [
+        4410,
+        12,
+        384,
+        631,
+        476,
+        3887,
+        631,
+        5550,
+        14964,
+        12703,
+        294,
+        7811,
+        270,
+        517,
+        274,
+        6,
+        12086,
+        530,
+        631,
+        10349,
+        18018,
+        257,
+        8783,
+        871,
+        6212
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4095459938049316,
+      "compression_ratio": 1.7522658610271904,
+      "no_speech_prob": 0.0006256799097172916,
+      "confidence": 0.697,
+      "words": [
+        {
+          "text": "Est-ce",
+          "start": 49.26,
+          "end": 49.7,
+          "confidence": 0.804
+        },
+        {
+          "text": "que",
+          "start": 49.7,
+          "end": 49.74,
+          "confidence": 0.989
+        },
+        {
+          "text": "le",
+          "start": 49.74,
+          "end": 49.78,
+          "confidence": 0.882
+        },
+        {
+          "text": "fait",
+          "start": 49.78,
+          "end": 49.96,
+          "confidence": 0.962
+        },
+        {
+          "text": "que",
+          "start": 49.96,
+          "end": 50.08,
+          "confidence": 0.935
+        },
+        {
+          "text": "cette",
+          "start": 50.08,
+          "end": 50.24,
+          "confidence": 0.95
+        },
+        {
+          "text": "objet",
+          "start": 50.24,
+          "end": 50.5,
+          "confidence": 0.968
+        },
+        {
+          "text": "soit",
+          "start": 50.5,
+          "end": 50.96,
+          "confidence": 0.991
+        },
+        {
+          "text": "inédit",
+          "start": 50.96,
+          "end": 51.78,
+          "confidence": 0.91
+        },
+        {
+          "text": "un",
+          "start": 51.78,
+          "end": 52.06,
+          "confidence": 0.442
+        },
+        {
+          "text": "d'huies",
+          "start": 52.06,
+          "end": 52.32,
+          "confidence": 0.298
+        },
+        {
+          "text": "que",
+          "start": 52.32,
+          "end": 52.4,
+          "confidence": 0.966
+        },
+        {
+          "text": "notre",
+          "start": 52.4,
+          "end": 52.58,
+          "confidence": 0.992
+        },
+        {
+          "text": "rapport",
+          "start": 52.58,
+          "end": 53.1,
+          "confidence": 0.714
+        },
+        {
+          "text": "a",
+          "start": 53.1,
+          "end": 53.44,
+          "confidence": 0.522
+        },
+        {
+          "text": "lui",
+          "start": 53.44,
+          "end": 53.62,
+          "confidence": 0.659
+        },
+        {
+          "text": "est",
+          "start": 53.62,
+          "end": 54.0,
+          "confidence": 0.643
+        },
+        {
+          "text": "aussi",
+          "start": 54.0,
+          "end": 54.34,
+          "confidence": 0.808
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 2556,
+      "start": 54.34,
+      "end": 55.32,
+      "text": " un rapport inédit?",
+      "tokens": [
+        517,
+        18018,
+        294,
+        7811,
+        270,
+        2506
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4095459938049316,
+      "compression_ratio": 1.7522658610271904,
+      "no_speech_prob": 0.0006256799097172916,
+      "confidence": 0.849,
+      "words": [
+        {
+          "text": "un",
+          "start": 54.34,
+          "end": 54.72,
+          "confidence": 0.506
+        },
+        {
+          "text": "rapport",
+          "start": 54.72,
+          "end": 54.94,
+          "confidence": 0.999
+        },
+        {
+          "text": "inédit?",
+          "start": 54.94,
+          "end": 55.32,
+          "confidence": 0.956
+        }
+      ]
+    },
+    {
+      "id": 17,
+      "seek": 5548,
+      "start": 55.6,
+      "end": 58.6,
+      "text": " Je veux dire, est-ce que le rapport qu'on a au sein de foi n'est comparable à celui",
+      "tokens": [
+        2588,
+        16389,
+        1264,
+        11,
+        871,
+        12,
+        384,
+        631,
+        476,
+        18018,
+        421,
+        6,
+        266,
+        257,
+        1609,
+        6195,
+        368,
+        6901,
+        297,
+        6,
+        377,
+        6311,
+        712,
+        1531,
+        22829
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6093524909167556,
+      "compression_ratio": 1.6292834890965733,
+      "no_speech_prob": 6.752492481609806e-05,
+      "confidence": 0.626,
+      "words": [
+        {
+          "text": "Je",
+          "start": 55.6,
+          "end": 55.84,
+          "confidence": 0.335
+        },
+        {
+          "text": "veux",
+          "start": 55.84,
+          "end": 55.94,
+          "confidence": 0.432
+        },
+        {
+          "text": "dire,",
+          "start": 55.94,
+          "end": 56.16,
+          "confidence": 0.992
+        },
+        {
+          "text": "est-ce",
+          "start": 56.16,
+          "end": 56.34,
+          "confidence": 0.951
+        },
+        {
+          "text": "que",
+          "start": 56.34,
+          "end": 56.4,
+          "confidence": 0.973
+        },
+        {
+          "text": "le",
+          "start": 56.4,
+          "end": 56.54,
+          "confidence": 0.987
+        },
+        {
+          "text": "rapport",
+          "start": 56.54,
+          "end": 56.76,
+          "confidence": 0.999
+        },
+        {
+          "text": "qu'on",
+          "start": 56.76,
+          "end": 57.1,
+          "confidence": 0.906
+        },
+        {
+          "text": "a",
+          "start": 57.1,
+          "end": 57.14,
+          "confidence": 0.974
+        },
+        {
+          "text": "au",
+          "start": 57.14,
+          "end": 57.26,
+          "confidence": 0.319
+        },
+        {
+          "text": "sein",
+          "start": 57.26,
+          "end": 57.36,
+          "confidence": 0.244
+        },
+        {
+          "text": "de",
+          "start": 57.36,
+          "end": 57.44,
+          "confidence": 0.177
+        },
+        {
+          "text": "foi",
+          "start": 57.44,
+          "end": 57.54,
+          "confidence": 0.163
+        },
+        {
+          "text": "n'est",
+          "start": 57.54,
+          "end": 57.78,
+          "confidence": 0.777
+        },
+        {
+          "text": "comparable",
+          "start": 57.78,
+          "end": 58.32,
+          "confidence": 0.606
+        },
+        {
+          "text": "à",
+          "start": 58.32,
+          "end": 58.46,
+          "confidence": 0.482
+        },
+        {
+          "text": "celui",
+          "start": 58.46,
+          "end": 58.6,
+          "confidence": 0.831
+        }
+      ]
+    },
+    {
+      "id": 18,
+      "seek": 5548,
+      "start": 58.72,
+      "end": 62.81,
+      "text": " qu'on entretenait à d'autres objectes techniques comme la voiture ou le téléphone?",
+      "tokens": [
+        421,
+        6,
+        266,
+        3962,
+        1147,
+        1001,
+        1531,
+        274,
+        6,
+        16752,
+        2657,
+        279,
+        7512,
+        5173,
+        635,
+        38859,
+        2820,
+        476,
+        47159,
+        2506
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6093524909167556,
+      "compression_ratio": 1.6292834890965733,
+      "no_speech_prob": 6.752492481609806e-05,
+      "confidence": 0.781,
+      "words": [
+        {
+          "text": "qu'on",
+          "start": 58.72,
+          "end": 58.88,
+          "confidence": 0.941
+        },
+        {
+          "text": "entretenait",
+          "start": 58.88,
+          "end": 59.38,
+          "confidence": 0.657
+        },
+        {
+          "text": "à",
+          "start": 59.38,
+          "end": 59.44,
+          "confidence": 0.973
+        },
+        {
+          "text": "d'autres",
+          "start": 59.44,
+          "end": 59.64,
+          "confidence": 0.909
+        },
+        {
+          "text": "objectes",
+          "start": 59.64,
+          "end": 60.02,
+          "confidence": 0.528
+        },
+        {
+          "text": "techniques",
+          "start": 60.02,
+          "end": 60.38,
+          "confidence": 0.547
+        },
+        {
+          "text": "comme",
+          "start": 60.38,
+          "end": 60.86,
+          "confidence": 0.662
+        },
+        {
+          "text": "la",
+          "start": 60.86,
+          "end": 61.46,
+          "confidence": 0.898
+        },
+        {
+          "text": "voiture",
+          "start": 61.46,
+          "end": 61.8,
+          "confidence": 0.954
+        },
+        {
+          "text": "ou",
+          "start": 61.8,
+          "end": 62.32,
+          "confidence": 0.74
+        },
+        {
+          "text": "le",
+          "start": 62.32,
+          "end": 62.6,
+          "confidence": 0.847
+        },
+        {
+          "text": "téléphone?",
+          "start": 62.6,
+          "end": 62.81,
+          "confidence": 0.979
+        }
+      ]
+    },
+    {
+      "id": 19,
+      "seek": 5548,
+      "start": 62.81,
+      "end": 66.07,
+      "text": " Il n'y a pas d'équivalent.",
+      "tokens": [
+        4416,
+        297,
+        6,
+        88,
+        257,
+        1736,
+        274,
+        6,
+        20183,
+        3576,
+        317,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6093524909167556,
+      "compression_ratio": 1.6292834890965733,
+      "no_speech_prob": 6.752492481609806e-05,
+      "confidence": 0.882,
+      "words": [
+        {
+          "text": "Il",
+          "start": 62.81,
+          "end": 65.42,
+          "confidence": 0.866
+        },
+        {
+          "text": "n'y",
+          "start": 65.42,
+          "end": 65.52,
+          "confidence": 0.865
+        },
+        {
+          "text": "a",
+          "start": 65.52,
+          "end": 65.56,
+          "confidence": 0.965
+        },
+        {
+          "text": "pas",
+          "start": 65.56,
+          "end": 65.62,
+          "confidence": 0.998
+        },
+        {
+          "text": "d'équivalent.",
+          "start": 65.62,
+          "end": 66.07,
+          "confidence": 0.858
+        }
+      ]
+    },
+    {
+      "id": 20,
+      "seek": 5548,
+      "start": 66.07,
+      "end": 69.74,
+      "text": " On s'est espécie de nous voter dans la relation à l'objet.",
+      "tokens": [
+        1282,
+        262,
+        6,
+        377,
+        7089,
+        526,
+        4260,
+        368,
+        4666,
+        21722,
+        2680,
+        635,
+        9721,
+        1531,
+        287,
+        6,
+        996,
+        7108,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6093524909167556,
+      "compression_ratio": 1.6292834890965733,
+      "no_speech_prob": 6.752492481609806e-05,
+      "confidence": 0.552,
+      "words": [
+        {
+          "text": "On",
+          "start": 66.07,
+          "end": 67.0,
+          "confidence": 0.29
+        },
+        {
+          "text": "s'est",
+          "start": 67.0,
+          "end": 67.26,
+          "confidence": 0.562
+        },
+        {
+          "text": "espécie",
+          "start": 67.26,
+          "end": 67.46,
+          "confidence": 0.233
+        },
+        {
+          "text": "de",
+          "start": 67.46,
+          "end": 67.58,
+          "confidence": 0.963
+        },
+        {
+          "text": "nous",
+          "start": 67.58,
+          "end": 67.8,
+          "confidence": 0.631
+        },
+        {
+          "text": "voter",
+          "start": 67.8,
+          "end": 68.24,
+          "confidence": 0.241
+        },
+        {
+          "text": "dans",
+          "start": 68.24,
+          "end": 68.68,
+          "confidence": 0.853
+        },
+        {
+          "text": "la",
+          "start": 68.68,
+          "end": 68.88,
+          "confidence": 0.61
+        },
+        {
+          "text": "relation",
+          "start": 68.88,
+          "end": 69.22,
+          "confidence": 0.932
+        },
+        {
+          "text": "à",
+          "start": 69.22,
+          "end": 69.34,
+          "confidence": 0.792
+        },
+        {
+          "text": "l'objet.",
+          "start": 69.34,
+          "end": 69.74,
+          "confidence": 0.889
+        }
+      ]
+    },
+    {
+      "id": 21,
+      "seek": 5548,
+      "start": 70.18,
+      "end": 74.78,
+      "text": " C'est facilement éterréciant parce qu'on a impression de, comme le 10, les utilisateurs",
+      "tokens": [
+        383,
+        6,
+        377,
+        23670,
+        518,
+        1136,
+        391,
+        10521,
+        537,
+        394,
+        6992,
+        421,
+        6,
+        266,
+        257,
+        9995,
+        368,
+        11,
+        5173,
+        476,
+        1266,
+        11,
+        1512,
+        33643,
+        25929
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6093524909167556,
+      "compression_ratio": 1.6292834890965733,
+      "no_speech_prob": 6.752492481609806e-05,
+      "confidence": 0.491,
+      "words": [
+        {
+          "text": "C'est",
+          "start": 70.18,
+          "end": 70.34,
+          "confidence": 0.907
+        },
+        {
+          "text": "facilement",
+          "start": 70.34,
+          "end": 70.72,
+          "confidence": 0.527
+        },
+        {
+          "text": "éterréciant",
+          "start": 70.72,
+          "end": 71.56,
+          "confidence": 0.277
+        },
+        {
+          "text": "parce",
+          "start": 71.56,
+          "end": 71.82,
+          "confidence": 0.298
+        },
+        {
+          "text": "qu'on",
+          "start": 71.82,
+          "end": 72.3,
+          "confidence": 0.775
+        },
+        {
+          "text": "a",
+          "start": 72.3,
+          "end": 72.4,
+          "confidence": 0.563
+        },
+        {
+          "text": "impression",
+          "start": 72.4,
+          "end": 72.74,
+          "confidence": 0.148
+        },
+        {
+          "text": "de,",
+          "start": 72.74,
+          "end": 73.36,
+          "confidence": 0.211
+        },
+        {
+          "text": "comme",
+          "start": 73.36,
+          "end": 73.8,
+          "confidence": 0.843
+        },
+        {
+          "text": "le",
+          "start": 73.8,
+          "end": 73.96,
+          "confidence": 0.9
+        },
+        {
+          "text": "10,",
+          "start": 73.96,
+          "end": 74.28,
+          "confidence": 0.395
+        },
+        {
+          "text": "les",
+          "start": 74.28,
+          "end": 74.32,
+          "confidence": 0.581
+        },
+        {
+          "text": "utilisateurs",
+          "start": 74.32,
+          "end": 74.78,
+          "confidence": 0.745
+        }
+      ]
+    },
+    {
+      "id": 22,
+      "seek": 5548,
+      "start": 74.8,
+      "end": 77.93,
+      "text": " et les efforts, elles aident dépendant de cette objet d'un lieu, en fait, une espèce de",
+      "tokens": [
+        1030,
+        1512,
+        6484,
+        11,
+        23576,
+        257,
+        1078,
+        45768,
+        394,
+        368,
+        5550,
+        14964,
+        274,
+        6,
+        409,
+        26036,
+        11,
+        465,
+        3887,
+        11,
+        2251,
+        7089,
+        30236,
+        368
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6093524909167556,
+      "compression_ratio": 1.6292834890965733,
+      "no_speech_prob": 6.752492481609806e-05,
+      "confidence": 0.464,
+      "words": [
+        {
+          "text": "et",
+          "start": 74.8,
+          "end": 74.92,
+          "confidence": 0.147
+        },
+        {
+          "text": "les",
+          "start": 74.92,
+          "end": 74.96,
+          "confidence": 0.242
+        },
+        {
+          "text": "efforts,",
+          "start": 74.96,
+          "end": 75.22,
+          "confidence": 0.108
+        },
+        {
+          "text": "elles",
+          "start": 75.22,
+          "end": 75.32,
+          "confidence": 0.108
+        },
+        {
+          "text": "aident",
+          "start": 75.32,
+          "end": 75.44,
+          "confidence": 0.289
+        },
+        {
+          "text": "dépendant",
+          "start": 75.44,
+          "end": 76.0,
+          "confidence": 0.576
+        },
+        {
+          "text": "de",
+          "start": 76.0,
+          "end": 76.16,
+          "confidence": 0.301
+        },
+        {
+          "text": "cette",
+          "start": 76.16,
+          "end": 76.2,
+          "confidence": 0.519
+        },
+        {
+          "text": "objet",
+          "start": 76.2,
+          "end": 76.48,
+          "confidence": 0.961
+        },
+        {
+          "text": "d'un",
+          "start": 76.48,
+          "end": 76.86,
+          "confidence": 0.883
+        },
+        {
+          "text": "lieu,",
+          "start": 76.86,
+          "end": 77.06,
+          "confidence": 0.333
+        },
+        {
+          "text": "en",
+          "start": 77.06,
+          "end": 77.18,
+          "confidence": 0.837
+        },
+        {
+          "text": "fait,",
+          "start": 77.18,
+          "end": 77.42,
+          "confidence": 0.958
+        },
+        {
+          "text": "une",
+          "start": 77.42,
+          "end": 77.46,
+          "confidence": 0.57
+        },
+        {
+          "text": "espèce",
+          "start": 77.46,
+          "end": 77.74,
+          "confidence": 0.961
+        },
+        {
+          "text": "de",
+          "start": 77.74,
+          "end": 77.93,
+          "confidence": 0.601
+        }
+      ]
+    },
+    {
+      "id": 23,
+      "seek": 5548,
+      "start": 77.93,
+      "end": 82.98,
+      "text": " relation de médiation avec le monde qui rendent un peu avec la même sédiforme de",
+      "tokens": [
+        9721,
+        368,
+        42436,
+        399,
+        4163,
+        476,
+        10431,
+        1956,
+        6125,
+        317,
+        517,
+        5604,
+        4163,
+        635,
+        5698,
+        262,
+        7811,
+        8629,
+        68,
+        368
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6093524909167556,
+      "compression_ratio": 1.6292834890965733,
+      "no_speech_prob": 6.752492481609806e-05,
+      "confidence": 0.556,
+      "words": [
+        {
+          "text": "relation",
+          "start": 77.93,
+          "end": 78.32,
+          "confidence": 0.839
+        },
+        {
+          "text": "de",
+          "start": 78.32,
+          "end": 78.7,
+          "confidence": 0.723
+        },
+        {
+          "text": "médiation",
+          "start": 78.7,
+          "end": 79.4,
+          "confidence": 0.872
+        },
+        {
+          "text": "avec",
+          "start": 79.4,
+          "end": 79.74,
+          "confidence": 0.964
+        },
+        {
+          "text": "le",
+          "start": 79.74,
+          "end": 79.88,
+          "confidence": 0.985
+        },
+        {
+          "text": "monde",
+          "start": 79.88,
+          "end": 80.24,
+          "confidence": 0.909
+        },
+        {
+          "text": "qui",
+          "start": 80.24,
+          "end": 81.02,
+          "confidence": 0.871
+        },
+        {
+          "text": "rendent",
+          "start": 81.02,
+          "end": 81.74,
+          "confidence": 0.623
+        },
+        {
+          "text": "un",
+          "start": 81.74,
+          "end": 81.84,
+          "confidence": 0.224
+        },
+        {
+          "text": "peu",
+          "start": 81.84,
+          "end": 81.88,
+          "confidence": 0.223
+        },
+        {
+          "text": "avec",
+          "start": 81.88,
+          "end": 82.1,
+          "confidence": 0.863
+        },
+        {
+          "text": "la",
+          "start": 82.1,
+          "end": 82.24,
+          "confidence": 0.565
+        },
+        {
+          "text": "même",
+          "start": 82.24,
+          "end": 82.32,
+          "confidence": 0.384
+        },
+        {
+          "text": "sédiforme",
+          "start": 82.32,
+          "end": 82.86,
+          "confidence": 0.29
+        },
+        {
+          "text": "de",
+          "start": 82.86,
+          "end": 82.98,
+          "confidence": 0.899
+        }
+      ]
+    },
+    {
+      "id": 24,
+      "seek": 8298,
+      "start": 83.0,
+      "end": 87.66,
+      "text": " le jeu. Donc, à objets inédits, rapport inédits.",
+      "tokens": [
+        476,
+        16748,
+        13,
+        7477,
+        11,
+        1531,
+        1111,
+        25349,
+        294,
+        7811,
+        1208,
+        11,
+        18018,
+        294,
+        7811,
+        1208,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4346100035167876,
+      "compression_ratio": 1.5907335907335907,
+      "no_speech_prob": 3.121094050584361e-05,
+      "confidence": 0.614,
+      "words": [
+        {
+          "text": "le",
+          "start": 83.0,
+          "end": 83.12,
+          "confidence": 0.128
+        },
+        {
+          "text": "jeu.",
+          "start": 83.12,
+          "end": 83.64,
+          "confidence": 0.505
+        },
+        {
+          "text": "Donc,",
+          "start": 83.64,
+          "end": 84.48,
+          "confidence": 0.513
+        },
+        {
+          "text": "à",
+          "start": 84.48,
+          "end": 84.86,
+          "confidence": 0.634
+        },
+        {
+          "text": "objets",
+          "start": 84.86,
+          "end": 85.36,
+          "confidence": 0.547
+        },
+        {
+          "text": "inédits,",
+          "start": 85.36,
+          "end": 86.24,
+          "confidence": 0.73
+        },
+        {
+          "text": "rapport",
+          "start": 86.24,
+          "end": 86.62,
+          "confidence": 0.928
+        },
+        {
+          "text": "inédits.",
+          "start": 86.62,
+          "end": 87.66,
+          "confidence": 0.921
+        }
+      ]
+    },
+    {
+      "id": 25,
+      "seek": 8298,
+      "start": 88.08,
+      "end": 93.78,
+      "text": " Et, ce rapport, si j'en prends Nicolas, frère caractérisée par un mélange de dépenses",
+      "tokens": [
+        3790,
+        11,
+        1769,
+        18018,
+        11,
+        1511,
+        361,
+        6,
+        268,
+        46750,
+        38268,
+        11,
+        431,
+        4212,
+        1032,
+        578,
+        4198,
+        50027,
+        971,
+        517,
+        41953,
+        933,
+        368,
+        27998,
+        9085
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4346100035167876,
+      "compression_ratio": 1.5907335907335907,
+      "no_speech_prob": 3.121094050584361e-05,
+      "confidence": 0.624,
+      "words": [
+        {
+          "text": "Et,",
+          "start": 88.08,
+          "end": 88.3,
+          "confidence": 0.87
+        },
+        {
+          "text": "ce",
+          "start": 88.3,
+          "end": 88.8,
+          "confidence": 0.462
+        },
+        {
+          "text": "rapport,",
+          "start": 88.8,
+          "end": 89.28,
+          "confidence": 0.997
+        },
+        {
+          "text": "si",
+          "start": 89.28,
+          "end": 89.56,
+          "confidence": 0.913
+        },
+        {
+          "text": "j'en",
+          "start": 89.56,
+          "end": 89.74,
+          "confidence": 0.771
+        },
+        {
+          "text": "prends",
+          "start": 89.74,
+          "end": 89.84,
+          "confidence": 0.313
+        },
+        {
+          "text": "Nicolas,",
+          "start": 89.84,
+          "end": 90.54,
+          "confidence": 0.358
+        },
+        {
+          "text": "frère",
+          "start": 90.54,
+          "end": 91.06,
+          "confidence": 0.405
+        },
+        {
+          "text": "caractérisée",
+          "start": 91.06,
+          "end": 91.7,
+          "confidence": 0.567
+        },
+        {
+          "text": "par",
+          "start": 91.7,
+          "end": 92.12,
+          "confidence": 0.868
+        },
+        {
+          "text": "un",
+          "start": 92.12,
+          "end": 92.32,
+          "confidence": 0.989
+        },
+        {
+          "text": "mélange",
+          "start": 92.32,
+          "end": 92.96,
+          "confidence": 0.932
+        },
+        {
+          "text": "de",
+          "start": 92.96,
+          "end": 93.24,
+          "confidence": 0.812
+        },
+        {
+          "text": "dépenses",
+          "start": 93.24,
+          "end": 93.78,
+          "confidence": 0.404
+        }
+      ]
+    },
+    {
+      "id": 26,
+      "seek": 8298,
+      "start": 94.36,
+      "end": 94.98,
+      "text": " et de rojets.",
+      "tokens": [
+        1030,
+        368,
+        744,
+        73,
+        1385,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4346100035167876,
+      "compression_ratio": 1.5907335907335907,
+      "no_speech_prob": 3.121094050584361e-05,
+      "confidence": 0.583,
+      "words": [
+        {
+          "text": "et",
+          "start": 94.36,
+          "end": 94.52,
+          "confidence": 0.986
+        },
+        {
+          "text": "de",
+          "start": 94.52,
+          "end": 94.56,
+          "confidence": 0.996
+        },
+        {
+          "text": "rojets.",
+          "start": 94.56,
+          "end": 94.98,
+          "confidence": 0.41
+        }
+      ]
+    },
+    {
+      "id": 27,
+      "seek": 8298,
+      "start": 95.8,
+      "end": 100.4,
+      "text": " Bon, en vrai, il faudrait remonter très très finement toute l'histoire des objectes",
+      "tokens": [
+        7368,
+        11,
+        465,
+        17815,
+        11,
+        1930,
+        38694,
+        8645,
+        890,
+        41806,
+        5732,
+        5732,
+        962,
+        1712,
+        14953,
+        287,
+        6,
+        29093,
+        730,
+        2657,
+        279
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4346100035167876,
+      "compression_ratio": 1.5907335907335907,
+      "no_speech_prob": 3.121094050584361e-05,
+      "confidence": 0.749,
+      "words": [
+        {
+          "text": "Bon,",
+          "start": 95.8,
+          "end": 96.06,
+          "confidence": 0.71
+        },
+        {
+          "text": "en",
+          "start": 96.06,
+          "end": 96.54,
+          "confidence": 0.92
+        },
+        {
+          "text": "vrai,",
+          "start": 96.54,
+          "end": 96.88,
+          "confidence": 0.994
+        },
+        {
+          "text": "il",
+          "start": 96.88,
+          "end": 97.1,
+          "confidence": 0.985
+        },
+        {
+          "text": "faudrait",
+          "start": 97.1,
+          "end": 97.5,
+          "confidence": 0.932
+        },
+        {
+          "text": "remonter",
+          "start": 97.5,
+          "end": 98.02,
+          "confidence": 0.574
+        },
+        {
+          "text": "très",
+          "start": 98.02,
+          "end": 98.46,
+          "confidence": 0.984
+        },
+        {
+          "text": "très",
+          "start": 98.46,
+          "end": 98.76,
+          "confidence": 0.597
+        },
+        {
+          "text": "finement",
+          "start": 98.76,
+          "end": 99.36,
+          "confidence": 0.476
+        },
+        {
+          "text": "toute",
+          "start": 99.36,
+          "end": 99.68,
+          "confidence": 0.367
+        },
+        {
+          "text": "l'histoire",
+          "start": 99.68,
+          "end": 100.02,
+          "confidence": 0.909
+        },
+        {
+          "text": "des",
+          "start": 100.02,
+          "end": 100.2,
+          "confidence": 0.949
+        },
+        {
+          "text": "objectes",
+          "start": 100.2,
+          "end": 100.4,
+          "confidence": 0.805
+        }
+      ]
+    },
+    {
+      "id": 28,
+      "seek": 8298,
+      "start": 100.4,
+      "end": 105.14,
+      "text": " techniques et de leur infération dans le vie pour déterminer si ce rapport est totalement",
+      "tokens": [
+        7512,
+        1030,
+        368,
+        9580,
+        1536,
+        526,
+        2405,
+        2680,
+        476,
+        4941,
+        2016,
+        2795,
+        29725,
+        260,
+        1511,
+        1769,
+        18018,
+        871,
+        45203
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4346100035167876,
+      "compression_ratio": 1.5907335907335907,
+      "no_speech_prob": 3.121094050584361e-05,
+      "confidence": 0.665,
+      "words": [
+        {
+          "text": "techniques",
+          "start": 100.4,
+          "end": 101.02,
+          "confidence": 0.954
+        },
+        {
+          "text": "et",
+          "start": 101.02,
+          "end": 101.52,
+          "confidence": 0.967
+        },
+        {
+          "text": "de",
+          "start": 101.52,
+          "end": 101.64,
+          "confidence": 0.973
+        },
+        {
+          "text": "leur",
+          "start": 101.64,
+          "end": 101.78,
+          "confidence": 0.811
+        },
+        {
+          "text": "infération",
+          "start": 101.78,
+          "end": 102.22,
+          "confidence": 0.227
+        },
+        {
+          "text": "dans",
+          "start": 102.22,
+          "end": 102.46,
+          "confidence": 0.518
+        },
+        {
+          "text": "le",
+          "start": 102.46,
+          "end": 102.54,
+          "confidence": 0.511
+        },
+        {
+          "text": "vie",
+          "start": 102.54,
+          "end": 102.78,
+          "confidence": 0.612
+        },
+        {
+          "text": "pour",
+          "start": 102.78,
+          "end": 103.06,
+          "confidence": 0.933
+        },
+        {
+          "text": "déterminer",
+          "start": 103.06,
+          "end": 103.64,
+          "confidence": 0.954
+        },
+        {
+          "text": "si",
+          "start": 103.64,
+          "end": 103.74,
+          "confidence": 0.488
+        },
+        {
+          "text": "ce",
+          "start": 103.74,
+          "end": 103.86,
+          "confidence": 0.98
+        },
+        {
+          "text": "rapport",
+          "start": 103.86,
+          "end": 104.1,
+          "confidence": 0.997
+        },
+        {
+          "text": "est",
+          "start": 104.1,
+          "end": 104.88,
+          "confidence": 0.942
+        },
+        {
+          "text": "totalement",
+          "start": 104.88,
+          "end": 105.14,
+          "confidence": 0.854
+        }
+      ]
+    },
+    {
+      "id": 29,
+      "seek": 8298,
+      "start": 105.26,
+      "end": 105.78,
+      "text": " inédit.",
+      "tokens": [
+        294,
+        7811,
+        270,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4346100035167876,
+      "compression_ratio": 1.5907335907335907,
+      "no_speech_prob": 3.121094050584361e-05,
+      "confidence": 0.943,
+      "words": [
+        {
+          "text": "inédit.",
+          "start": 105.26,
+          "end": 105.78,
+          "confidence": 0.943
+        }
+      ]
+    },
+    {
+      "id": 30,
+      "seek": 8298,
+      "start": 106.14,
+      "end": 109.36,
+      "text": " Mais j'ai l'impression comme ça que Nicolas se trompe pas vraiment.",
+      "tokens": [
+        6313,
+        361,
+        6,
+        1301,
+        287,
+        6,
+        36107,
+        5173,
+        2788,
+        631,
+        38268,
+        369,
+        504,
+        298,
+        494,
+        1736,
+        8322,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4346100035167876,
+      "compression_ratio": 1.5907335907335907,
+      "no_speech_prob": 3.121094050584361e-05,
+      "confidence": 0.798,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 106.14,
+          "end": 106.34,
+          "confidence": 0.872
+        },
+        {
+          "text": "j'ai",
+          "start": 106.34,
+          "end": 106.9,
+          "confidence": 0.924
+        },
+        {
+          "text": "l'impression",
+          "start": 106.9,
+          "end": 107.28,
+          "confidence": 0.967
+        },
+        {
+          "text": "comme",
+          "start": 107.28,
+          "end": 107.5,
+          "confidence": 0.709
+        },
+        {
+          "text": "ça",
+          "start": 107.5,
+          "end": 107.68,
+          "confidence": 0.955
+        },
+        {
+          "text": "que",
+          "start": 107.68,
+          "end": 107.96,
+          "confidence": 0.91
+        },
+        {
+          "text": "Nicolas",
+          "start": 107.96,
+          "end": 108.36,
+          "confidence": 0.986
+        },
+        {
+          "text": "se",
+          "start": 108.36,
+          "end": 108.66,
+          "confidence": 0.569
+        },
+        {
+          "text": "trompe",
+          "start": 108.66,
+          "end": 109.0,
+          "confidence": 0.532
+        },
+        {
+          "text": "pas",
+          "start": 109.0,
+          "end": 109.1,
+          "confidence": 0.715
+        },
+        {
+          "text": "vraiment.",
+          "start": 109.1,
+          "end": 109.36,
+          "confidence": 0.923
+        }
+      ]
+    },
+    {
+      "id": 31,
+      "seek": 10970,
+      "start": 109.72,
+      "end": 114.26,
+      "text": " Pour autant, je sache. Il y a eu plein de discussions autour de la voiture ou même",
+      "tokens": [
+        8732,
+        34081,
+        11,
+        1506,
+        262,
+        6000,
+        13,
+        4416,
+        288,
+        257,
+        2228,
+        21088,
+        368,
+        11088,
+        30249,
+        368,
+        635,
+        38859,
+        2820,
+        5698
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.394765736144266,
+      "compression_ratio": 1.7249190938511327,
+      "no_speech_prob": 9.048193533089943e-06,
+      "confidence": 0.829,
+      "words": [
+        {
+          "text": "Pour",
+          "start": 109.72,
+          "end": 110.08,
+          "confidence": 0.92
+        },
+        {
+          "text": "autant,",
+          "start": 110.08,
+          "end": 110.36,
+          "confidence": 0.986
+        },
+        {
+          "text": "je",
+          "start": 110.36,
+          "end": 110.4,
+          "confidence": 0.894
+        },
+        {
+          "text": "sache.",
+          "start": 110.4,
+          "end": 110.86,
+          "confidence": 0.531
+        },
+        {
+          "text": "Il",
+          "start": 110.86,
+          "end": 111.16,
+          "confidence": 0.851
+        },
+        {
+          "text": "y",
+          "start": 111.16,
+          "end": 111.22,
+          "confidence": 0.872
+        },
+        {
+          "text": "a",
+          "start": 111.22,
+          "end": 111.28,
+          "confidence": 0.939
+        },
+        {
+          "text": "eu",
+          "start": 111.28,
+          "end": 111.38,
+          "confidence": 0.891
+        },
+        {
+          "text": "plein",
+          "start": 111.38,
+          "end": 111.76,
+          "confidence": 0.833
+        },
+        {
+          "text": "de",
+          "start": 111.76,
+          "end": 112.04,
+          "confidence": 0.94
+        },
+        {
+          "text": "discussions",
+          "start": 112.04,
+          "end": 112.46,
+          "confidence": 0.711
+        },
+        {
+          "text": "autour",
+          "start": 112.46,
+          "end": 112.96,
+          "confidence": 0.97
+        },
+        {
+          "text": "de",
+          "start": 112.96,
+          "end": 113.46,
+          "confidence": 0.952
+        },
+        {
+          "text": "la",
+          "start": 113.46,
+          "end": 113.5,
+          "confidence": 0.955
+        },
+        {
+          "text": "voiture",
+          "start": 113.5,
+          "end": 113.8,
+          "confidence": 0.983
+        },
+        {
+          "text": "ou",
+          "start": 113.8,
+          "end": 114.02,
+          "confidence": 0.523
+        },
+        {
+          "text": "même",
+          "start": 114.02,
+          "end": 114.26,
+          "confidence": 0.963
+        }
+      ]
+    },
+    {
+      "id": 32,
+      "seek": 10970,
+      "start": 114.42,
+      "end": 118.76,
+      "text": " du téléphone. Mais la dépense n'était pas du même mort, donc le rejet n'en",
+      "tokens": [
+        1581,
+        47159,
+        13,
+        6313,
+        635,
+        27998,
+        1288,
+        297,
+        6,
+        9743,
+        1736,
+        1581,
+        5698,
+        6599,
+        11,
+        5926,
+        476,
+        319,
+        7108,
+        297,
+        6,
+        268
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.394765736144266,
+      "compression_ratio": 1.7249190938511327,
+      "no_speech_prob": 9.048193533089943e-06,
+      "confidence": 0.732,
+      "words": [
+        {
+          "text": "du",
+          "start": 114.42,
+          "end": 114.6,
+          "confidence": 0.677
+        },
+        {
+          "text": "téléphone.",
+          "start": 114.6,
+          "end": 115.16,
+          "confidence": 0.983
+        },
+        {
+          "text": "Mais",
+          "start": 115.16,
+          "end": 115.72,
+          "confidence": 0.649
+        },
+        {
+          "text": "la",
+          "start": 115.72,
+          "end": 116.0,
+          "confidence": 0.809
+        },
+        {
+          "text": "dépense",
+          "start": 116.0,
+          "end": 116.38,
+          "confidence": 0.766
+        },
+        {
+          "text": "n'était",
+          "start": 116.38,
+          "end": 116.62,
+          "confidence": 0.952
+        },
+        {
+          "text": "pas",
+          "start": 116.62,
+          "end": 117.02,
+          "confidence": 0.994
+        },
+        {
+          "text": "du",
+          "start": 117.02,
+          "end": 117.16,
+          "confidence": 0.98
+        },
+        {
+          "text": "même",
+          "start": 117.16,
+          "end": 117.32,
+          "confidence": 0.944
+        },
+        {
+          "text": "mort,",
+          "start": 117.32,
+          "end": 117.66,
+          "confidence": 0.519
+        },
+        {
+          "text": "donc",
+          "start": 117.66,
+          "end": 117.78,
+          "confidence": 0.871
+        },
+        {
+          "text": "le",
+          "start": 117.78,
+          "end": 118.32,
+          "confidence": 0.932
+        },
+        {
+          "text": "rejet",
+          "start": 118.32,
+          "end": 118.62,
+          "confidence": 0.524
+        },
+        {
+          "text": "n'en",
+          "start": 118.62,
+          "end": 118.76,
+          "confidence": 0.472
+        }
+      ]
+    },
+    {
+      "id": 33,
+      "seek": 10970,
+      "start": 118.76,
+      "end": 119.66,
+      "text": " plus n'était pas du même mort.",
+      "tokens": [
+        1804,
+        297,
+        6,
+        9743,
+        1736,
+        1581,
+        5698,
+        6599,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.394765736144266,
+      "compression_ratio": 1.7249190938511327,
+      "no_speech_prob": 9.048193533089943e-06,
+      "confidence": 0.853,
+      "words": [
+        {
+          "text": "plus",
+          "start": 118.76,
+          "end": 118.9,
+          "confidence": 0.313
+        },
+        {
+          "text": "n'était",
+          "start": 118.9,
+          "end": 119.1,
+          "confidence": 0.973
+        },
+        {
+          "text": "pas",
+          "start": 119.1,
+          "end": 119.26,
+          "confidence": 0.998
+        },
+        {
+          "text": "du",
+          "start": 119.26,
+          "end": 119.36,
+          "confidence": 0.988
+        },
+        {
+          "text": "même",
+          "start": 119.36,
+          "end": 119.5,
+          "confidence": 0.999
+        },
+        {
+          "text": "mort.",
+          "start": 119.5,
+          "end": 119.66,
+          "confidence": 0.984
+        }
+      ]
+    },
+    {
+      "id": 34,
+      "seek": 10970,
+      "start": 120.06,
+      "end": 122.94,
+      "text": " On peut adorer sa bagnure, en avoir besoin pour plein de choses.",
+      "tokens": [
+        1282,
+        5977,
+        614,
+        17618,
+        601,
+        3411,
+        77,
+        540,
+        11,
+        465,
+        10853,
+        19207,
+        2016,
+        21088,
+        368,
+        14488,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.394765736144266,
+      "compression_ratio": 1.7249190938511327,
+      "no_speech_prob": 9.048193533089943e-06,
+      "confidence": 0.753,
+      "words": [
+        {
+          "text": "On",
+          "start": 120.06,
+          "end": 120.22,
+          "confidence": 0.969
+        },
+        {
+          "text": "peut",
+          "start": 120.22,
+          "end": 120.32,
+          "confidence": 0.988
+        },
+        {
+          "text": "adorer",
+          "start": 120.32,
+          "end": 120.64,
+          "confidence": 0.854
+        },
+        {
+          "text": "sa",
+          "start": 120.64,
+          "end": 120.86,
+          "confidence": 0.918
+        },
+        {
+          "text": "bagnure,",
+          "start": 120.86,
+          "end": 121.38,
+          "confidence": 0.368
+        },
+        {
+          "text": "en",
+          "start": 121.38,
+          "end": 121.52,
+          "confidence": 0.56
+        },
+        {
+          "text": "avoir",
+          "start": 121.52,
+          "end": 121.66,
+          "confidence": 0.969
+        },
+        {
+          "text": "besoin",
+          "start": 121.66,
+          "end": 122.08,
+          "confidence": 0.997
+        },
+        {
+          "text": "pour",
+          "start": 122.08,
+          "end": 122.34,
+          "confidence": 0.92
+        },
+        {
+          "text": "plein",
+          "start": 122.34,
+          "end": 122.64,
+          "confidence": 0.9
+        },
+        {
+          "text": "de",
+          "start": 122.64,
+          "end": 122.78,
+          "confidence": 0.993
+        },
+        {
+          "text": "choses.",
+          "start": 122.78,
+          "end": 122.94,
+          "confidence": 0.994
+        }
+      ]
+    },
+    {
+      "id": 35,
+      "seek": 10970,
+      "start": 123.36,
+      "end": 126.38,
+      "text": " Et là, le soir, quand on va se coucher, on la laisse.",
+      "tokens": [
+        3790,
+        3684,
+        11,
+        476,
+        27105,
+        11,
+        6932,
+        322,
+        2773,
+        369,
+        1384,
+        6759,
+        11,
+        322,
+        635,
+        30969,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.394765736144266,
+      "compression_ratio": 1.7249190938511327,
+      "no_speech_prob": 9.048193533089943e-06,
+      "confidence": 0.826,
+      "words": [
+        {
+          "text": "Et",
+          "start": 123.36,
+          "end": 123.48,
+          "confidence": 0.557
+        },
+        {
+          "text": "là,",
+          "start": 123.48,
+          "end": 123.66,
+          "confidence": 0.527
+        },
+        {
+          "text": "le",
+          "start": 123.66,
+          "end": 124.02,
+          "confidence": 0.986
+        },
+        {
+          "text": "soir,",
+          "start": 124.02,
+          "end": 124.5,
+          "confidence": 0.966
+        },
+        {
+          "text": "quand",
+          "start": 124.5,
+          "end": 124.9,
+          "confidence": 0.774
+        },
+        {
+          "text": "on",
+          "start": 124.9,
+          "end": 125.02,
+          "confidence": 0.986
+        },
+        {
+          "text": "va",
+          "start": 125.02,
+          "end": 125.1,
+          "confidence": 0.968
+        },
+        {
+          "text": "se",
+          "start": 125.1,
+          "end": 125.2,
+          "confidence": 0.862
+        },
+        {
+          "text": "coucher,",
+          "start": 125.2,
+          "end": 125.64,
+          "confidence": 0.791
+        },
+        {
+          "text": "on",
+          "start": 125.64,
+          "end": 126.04,
+          "confidence": 0.974
+        },
+        {
+          "text": "la",
+          "start": 126.04,
+          "end": 126.12,
+          "confidence": 0.783
+        },
+        {
+          "text": "laisse.",
+          "start": 126.12,
+          "end": 126.38,
+          "confidence": 0.981
+        }
+      ]
+    },
+    {
+      "id": 36,
+      "seek": 10970,
+      "start": 127.06,
+      "end": 130.0,
+      "text": " On l'a pas dans la main, quand on est collis, quand on n'en mène pas au chiot.",
+      "tokens": [
+        1282,
+        287,
+        6,
+        64,
+        1736,
+        2680,
+        635,
+        2135,
+        11,
+        6932,
+        322,
+        871,
+        1263,
+        271,
+        11,
+        6932,
+        322,
+        297,
+        6,
+        268,
+        275,
+        18832,
+        1736,
+        1609,
+        417,
+        6471,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.394765736144266,
+      "compression_ratio": 1.7249190938511327,
+      "no_speech_prob": 9.048193533089943e-06,
+      "confidence": 0.66,
+      "words": [
+        {
+          "text": "On",
+          "start": 127.06,
+          "end": 127.3,
+          "confidence": 0.742
+        },
+        {
+          "text": "l'a",
+          "start": 127.3,
+          "end": 127.46,
+          "confidence": 0.714
+        },
+        {
+          "text": "pas",
+          "start": 127.46,
+          "end": 127.64,
+          "confidence": 0.99
+        },
+        {
+          "text": "dans",
+          "start": 127.64,
+          "end": 127.82,
+          "confidence": 0.967
+        },
+        {
+          "text": "la",
+          "start": 127.82,
+          "end": 127.94,
+          "confidence": 0.956
+        },
+        {
+          "text": "main,",
+          "start": 127.94,
+          "end": 128.3,
+          "confidence": 0.978
+        },
+        {
+          "text": "quand",
+          "start": 128.3,
+          "end": 128.44,
+          "confidence": 0.967
+        },
+        {
+          "text": "on",
+          "start": 128.44,
+          "end": 128.6,
+          "confidence": 0.993
+        },
+        {
+          "text": "est",
+          "start": 128.6,
+          "end": 128.66,
+          "confidence": 0.602
+        },
+        {
+          "text": "collis,",
+          "start": 128.66,
+          "end": 129.2,
+          "confidence": 0.346
+        },
+        {
+          "text": "quand",
+          "start": 129.2,
+          "end": 129.24,
+          "confidence": 0.524
+        },
+        {
+          "text": "on",
+          "start": 129.24,
+          "end": 129.32,
+          "confidence": 0.991
+        },
+        {
+          "text": "n'en",
+          "start": 129.32,
+          "end": 129.38,
+          "confidence": 0.537
+        },
+        {
+          "text": "mène",
+          "start": 129.38,
+          "end": 129.56,
+          "confidence": 0.434
+        },
+        {
+          "text": "pas",
+          "start": 129.56,
+          "end": 129.72,
+          "confidence": 0.998
+        },
+        {
+          "text": "au",
+          "start": 129.72,
+          "end": 129.82,
+          "confidence": 0.811
+        },
+        {
+          "text": "chiot.",
+          "start": 129.82,
+          "end": 130.0,
+          "confidence": 0.473
+        }
+      ]
+    },
+    {
+      "id": 37,
+      "seek": 10970,
+      "start": 130.88,
+      "end": 135.1,
+      "text": " On pouvait être émervé par son mome qui occupeait la ligne de téléphone pendant une",
+      "tokens": [
+        1282,
+        45913,
+        7418,
+        1136,
+        936,
+        15797,
+        971,
+        1872,
+        275,
+        423,
+        1956,
+        2678,
+        84,
+        494,
+        1001,
+        635,
+        34207,
+        368,
+        47159,
+        17338,
+        2251
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.394765736144266,
+      "compression_ratio": 1.7249190938511327,
+      "no_speech_prob": 9.048193533089943e-06,
+      "confidence": 0.672,
+      "words": [
+        {
+          "text": "On",
+          "start": 130.88,
+          "end": 131.0,
+          "confidence": 0.991
+        },
+        {
+          "text": "pouvait",
+          "start": 131.0,
+          "end": 131.24,
+          "confidence": 0.532
+        },
+        {
+          "text": "être",
+          "start": 131.24,
+          "end": 131.7,
+          "confidence": 0.545
+        },
+        {
+          "text": "émervé",
+          "start": 131.7,
+          "end": 132.2,
+          "confidence": 0.725
+        },
+        {
+          "text": "par",
+          "start": 132.2,
+          "end": 132.42,
+          "confidence": 0.82
+        },
+        {
+          "text": "son",
+          "start": 132.42,
+          "end": 132.68,
+          "confidence": 0.448
+        },
+        {
+          "text": "mome",
+          "start": 132.68,
+          "end": 133.04,
+          "confidence": 0.261
+        },
+        {
+          "text": "qui",
+          "start": 133.04,
+          "end": 133.26,
+          "confidence": 0.901
+        },
+        {
+          "text": "occupeait",
+          "start": 133.26,
+          "end": 133.72,
+          "confidence": 0.641
+        },
+        {
+          "text": "la",
+          "start": 133.72,
+          "end": 133.8,
+          "confidence": 0.8
+        },
+        {
+          "text": "ligne",
+          "start": 133.8,
+          "end": 134.0,
+          "confidence": 0.976
+        },
+        {
+          "text": "de",
+          "start": 134.0,
+          "end": 134.14,
+          "confidence": 0.964
+        },
+        {
+          "text": "téléphone",
+          "start": 134.14,
+          "end": 134.44,
+          "confidence": 0.977
+        },
+        {
+          "text": "pendant",
+          "start": 134.44,
+          "end": 134.8,
+          "confidence": 0.92
+        },
+        {
+          "text": "une",
+          "start": 134.8,
+          "end": 135.1,
+          "confidence": 0.838
+        }
+      ]
+    },
+    {
+      "id": 38,
+      "seek": 10970,
+      "start": 135.1,
+      "end": 136.84,
+      "text": " heure chaque soir pour discuter avec un copain.",
+      "tokens": [
+        30027,
+        18920,
+        27105,
+        2016,
+        2983,
+        20314,
+        4163,
+        517,
+        2971,
+        491,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.394765736144266,
+      "compression_ratio": 1.7249190938511327,
+      "no_speech_prob": 9.048193533089943e-06,
+      "confidence": 0.922,
+      "words": [
+        {
+          "text": "heure",
+          "start": 135.1,
+          "end": 135.36,
+          "confidence": 0.701
+        },
+        {
+          "text": "chaque",
+          "start": 135.36,
+          "end": 135.52,
+          "confidence": 0.957
+        },
+        {
+          "text": "soir",
+          "start": 135.52,
+          "end": 135.76,
+          "confidence": 0.997
+        },
+        {
+          "text": "pour",
+          "start": 135.76,
+          "end": 135.94,
+          "confidence": 0.983
+        },
+        {
+          "text": "discuter",
+          "start": 135.94,
+          "end": 136.26,
+          "confidence": 0.882
+        },
+        {
+          "text": "avec",
+          "start": 136.26,
+          "end": 136.44,
+          "confidence": 0.993
+        },
+        {
+          "text": "un",
+          "start": 136.44,
+          "end": 136.6,
+          "confidence": 0.976
+        },
+        {
+          "text": "copain.",
+          "start": 136.6,
+          "end": 136.84,
+          "confidence": 0.948
+        }
+      ]
+    },
+    {
+      "id": 39,
+      "seek": 13702,
+      "start": 137.26,
+      "end": 141.8,
+      "text": " Mais ça ne ressemble pas à ce qu'on peut ressentir à voir même mome aujourd'hui",
+      "tokens": [
+        6313,
+        2788,
+        408,
+        725,
+        37227,
+        1736,
+        1531,
+        1769,
+        421,
+        6,
+        266,
+        5977,
+        24689,
+        317,
+        347,
+        1531,
+        10695,
+        5698,
+        275,
+        423,
+        14023,
+        6,
+        10556
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5734858703613281,
+      "compression_ratio": 1.5562700964630225,
+      "no_speech_prob": 3.1260256037057843e-06,
+      "confidence": 0.716,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 137.26,
+          "end": 137.52,
+          "confidence": 0.967
+        },
+        {
+          "text": "ça",
+          "start": 137.52,
+          "end": 137.6,
+          "confidence": 0.859
+        },
+        {
+          "text": "ne",
+          "start": 137.6,
+          "end": 137.68,
+          "confidence": 0.681
+        },
+        {
+          "text": "ressemble",
+          "start": 137.68,
+          "end": 138.14,
+          "confidence": 0.743
+        },
+        {
+          "text": "pas",
+          "start": 138.14,
+          "end": 138.66,
+          "confidence": 0.524
+        },
+        {
+          "text": "à",
+          "start": 138.66,
+          "end": 138.94,
+          "confidence": 0.978
+        },
+        {
+          "text": "ce",
+          "start": 138.94,
+          "end": 139.02,
+          "confidence": 0.605
+        },
+        {
+          "text": "qu'on",
+          "start": 139.02,
+          "end": 139.16,
+          "confidence": 0.961
+        },
+        {
+          "text": "peut",
+          "start": 139.16,
+          "end": 139.3,
+          "confidence": 0.586
+        },
+        {
+          "text": "ressentir",
+          "start": 139.3,
+          "end": 140.04,
+          "confidence": 0.898
+        },
+        {
+          "text": "à",
+          "start": 140.04,
+          "end": 140.24,
+          "confidence": 0.352
+        },
+        {
+          "text": "voir",
+          "start": 140.24,
+          "end": 140.48,
+          "confidence": 0.918
+        },
+        {
+          "text": "même",
+          "start": 140.48,
+          "end": 140.86,
+          "confidence": 0.324
+        },
+        {
+          "text": "mome",
+          "start": 140.86,
+          "end": 141.18,
+          "confidence": 0.374
+        },
+        {
+          "text": "aujourd'hui",
+          "start": 141.18,
+          "end": 141.8,
+          "confidence": 0.949
+        }
+      ]
+    },
+    {
+      "id": 40,
+      "seek": 13702,
+      "start": 141.92,
+      "end": 145.76,
+      "text": " continuuellement avec son smartphone dans la main, comme c'était une sorte de estimateur",
+      "tokens": [
+        2993,
+        31816,
+        4163,
+        1872,
+        13307,
+        2680,
+        635,
+        2135,
+        11,
+        5173,
+        269,
+        6,
+        9743,
+        2251,
+        25559,
+        368,
+        8017,
+        15540
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5734858703613281,
+      "compression_ratio": 1.5562700964630225,
+      "no_speech_prob": 3.1260256037057843e-06,
+      "confidence": 0.584,
+      "words": [
+        {
+          "text": "continuuellement",
+          "start": 141.92,
+          "end": 142.8,
+          "confidence": 0.327
+        },
+        {
+          "text": "avec",
+          "start": 142.8,
+          "end": 143.18,
+          "confidence": 0.903
+        },
+        {
+          "text": "son",
+          "start": 143.18,
+          "end": 143.36,
+          "confidence": 0.866
+        },
+        {
+          "text": "smartphone",
+          "start": 143.36,
+          "end": 143.64,
+          "confidence": 0.467
+        },
+        {
+          "text": "dans",
+          "start": 143.64,
+          "end": 143.92,
+          "confidence": 0.554
+        },
+        {
+          "text": "la",
+          "start": 143.92,
+          "end": 144.0,
+          "confidence": 0.972
+        },
+        {
+          "text": "main,",
+          "start": 144.0,
+          "end": 144.26,
+          "confidence": 0.997
+        },
+        {
+          "text": "comme",
+          "start": 144.26,
+          "end": 144.52,
+          "confidence": 0.95
+        },
+        {
+          "text": "c'était",
+          "start": 144.52,
+          "end": 144.78,
+          "confidence": 0.574
+        },
+        {
+          "text": "une",
+          "start": 144.78,
+          "end": 144.94,
+          "confidence": 0.971
+        },
+        {
+          "text": "sorte",
+          "start": 144.94,
+          "end": 145.1,
+          "confidence": 0.642
+        },
+        {
+          "text": "de",
+          "start": 145.1,
+          "end": 145.18,
+          "confidence": 0.268
+        },
+        {
+          "text": "estimateur",
+          "start": 145.18,
+          "end": 145.76,
+          "confidence": 0.415
+        }
+      ]
+    },
+    {
+      "id": 41,
+      "seek": 13702,
+      "start": 145.94,
+      "end": 148.88,
+      "text": " extère de l'intempis de lâcher à l'éantrénée, ça m'a eu immédiate.",
+      "tokens": [
+        1279,
+        4212,
+        368,
+        287,
+        6,
+        686,
+        15970,
+        271,
+        368,
+        48835,
+        6759,
+        1531,
+        287,
+        6,
+        526,
+        394,
+        81,
+        3516,
+        3856,
+        11,
+        2788,
+        275,
+        6,
+        64,
+        2228,
+        3397,
+        526,
+        4504,
+        473,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5734858703613281,
+      "compression_ratio": 1.5562700964630225,
+      "no_speech_prob": 3.1260256037057843e-06,
+      "confidence": 0.401,
+      "words": [
+        {
+          "text": "extère",
+          "start": 145.94,
+          "end": 146.38,
+          "confidence": 0.357
+        },
+        {
+          "text": "de",
+          "start": 146.38,
+          "end": 146.46,
+          "confidence": 0.253
+        },
+        {
+          "text": "l'intempis",
+          "start": 146.46,
+          "end": 146.7,
+          "confidence": 0.153
+        },
+        {
+          "text": "de",
+          "start": 146.7,
+          "end": 146.9,
+          "confidence": 0.858
+        },
+        {
+          "text": "lâcher",
+          "start": 146.9,
+          "end": 147.32,
+          "confidence": 0.824
+        },
+        {
+          "text": "à",
+          "start": 147.32,
+          "end": 147.44,
+          "confidence": 0.494
+        },
+        {
+          "text": "l'éantrénée,",
+          "start": 147.44,
+          "end": 147.94,
+          "confidence": 0.476
+        },
+        {
+          "text": "ça",
+          "start": 147.94,
+          "end": 148.0,
+          "confidence": 0.772
+        },
+        {
+          "text": "m'a",
+          "start": 148.0,
+          "end": 148.26,
+          "confidence": 0.532
+        },
+        {
+          "text": "eu",
+          "start": 148.26,
+          "end": 148.42,
+          "confidence": 0.181
+        },
+        {
+          "text": "immédiate.",
+          "start": 148.42,
+          "end": 148.88,
+          "confidence": 0.537
+        }
+      ]
+    },
+    {
+      "id": 42,
+      "seek": 13702,
+      "start": 149.08,
+      "end": 152.02,
+      "text": " Bon, je dis ça pour le mome, mais évidemment, va là pour nos aussi.",
+      "tokens": [
+        7368,
+        11,
+        1506,
+        717,
+        2788,
+        2016,
+        476,
+        275,
+        423,
+        11,
+        2420,
+        24724,
+        11,
+        2773,
+        3684,
+        2016,
+        3269,
+        6212,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5734858703613281,
+      "compression_ratio": 1.5562700964630225,
+      "no_speech_prob": 3.1260256037057843e-06,
+      "confidence": 0.529,
+      "words": [
+        {
+          "text": "Bon,",
+          "start": 149.08,
+          "end": 149.3,
+          "confidence": 0.285
+        },
+        {
+          "text": "je",
+          "start": 149.3,
+          "end": 149.34,
+          "confidence": 0.425
+        },
+        {
+          "text": "dis",
+          "start": 149.34,
+          "end": 149.42,
+          "confidence": 0.316
+        },
+        {
+          "text": "ça",
+          "start": 149.42,
+          "end": 149.62,
+          "confidence": 0.953
+        },
+        {
+          "text": "pour",
+          "start": 149.62,
+          "end": 149.72,
+          "confidence": 0.971
+        },
+        {
+          "text": "le",
+          "start": 149.72,
+          "end": 149.82,
+          "confidence": 0.993
+        },
+        {
+          "text": "mome,",
+          "start": 149.82,
+          "end": 150.24,
+          "confidence": 0.575
+        },
+        {
+          "text": "mais",
+          "start": 150.24,
+          "end": 150.44,
+          "confidence": 0.713
+        },
+        {
+          "text": "évidemment,",
+          "start": 150.44,
+          "end": 151.1,
+          "confidence": 0.775
+        },
+        {
+          "text": "va",
+          "start": 151.1,
+          "end": 151.28,
+          "confidence": 0.381
+        },
+        {
+          "text": "là",
+          "start": 151.28,
+          "end": 151.42,
+          "confidence": 0.633
+        },
+        {
+          "text": "pour",
+          "start": 151.42,
+          "end": 151.62,
+          "confidence": 0.398
+        },
+        {
+          "text": "nos",
+          "start": 151.62,
+          "end": 151.7,
+          "confidence": 0.807
+        },
+        {
+          "text": "aussi.",
+          "start": 151.7,
+          "end": 152.02,
+          "confidence": 0.145
+        }
+      ]
+    },
+    {
+      "id": 43,
+      "seek": 13702,
+      "start": 152.66,
+      "end": 154.4,
+      "text": " Donc, rapport immédiate d'accord.",
+      "tokens": [
+        7477,
+        11,
+        18018,
+        3397,
+        526,
+        4504,
+        473,
+        274,
+        6,
+        19947,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5734858703613281,
+      "compression_ratio": 1.5562700964630225,
+      "no_speech_prob": 3.1260256037057843e-06,
+      "confidence": 0.851,
+      "words": [
+        {
+          "text": "Donc,",
+          "start": 152.66,
+          "end": 153.0,
+          "confidence": 0.985
+        },
+        {
+          "text": "rapport",
+          "start": 153.0,
+          "end": 153.42,
+          "confidence": 0.977
+        },
+        {
+          "text": "immédiate",
+          "start": 153.42,
+          "end": 154.26,
+          "confidence": 0.825
+        },
+        {
+          "text": "d'accord.",
+          "start": 154.26,
+          "end": 154.4,
+          "confidence": 0.806
+        }
+      ]
+    },
+    {
+      "id": 44,
+      "seek": 13702,
+      "start": 154.4,
+      "end": 157.95,
+      "text": " Mais pourquoi, à ton impression qu'on en sortira jamais?",
+      "tokens": [
+        6313,
+        19934,
+        11,
+        1531,
+        2952,
+        9995,
+        421,
+        6,
+        266,
+        465,
+        26906,
+        64,
+        14540,
+        30
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5734858703613281,
+      "compression_ratio": 1.5562700964630225,
+      "no_speech_prob": 3.1260256037057843e-06,
+      "confidence": 0.791,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 154.4,
+          "end": 155.9,
+          "confidence": 0.984
+        },
+        {
+          "text": "pourquoi,",
+          "start": 155.9,
+          "end": 156.36,
+          "confidence": 0.959
+        },
+        {
+          "text": "à",
+          "start": 156.36,
+          "end": 156.48,
+          "confidence": 0.821
+        },
+        {
+          "text": "ton",
+          "start": 156.48,
+          "end": 156.66,
+          "confidence": 0.952
+        },
+        {
+          "text": "impression",
+          "start": 156.66,
+          "end": 156.96,
+          "confidence": 0.932
+        },
+        {
+          "text": "qu'on",
+          "start": 156.96,
+          "end": 157.28,
+          "confidence": 0.906
+        },
+        {
+          "text": "en",
+          "start": 157.28,
+          "end": 157.34,
+          "confidence": 0.789
+        },
+        {
+          "text": "sortira",
+          "start": 157.34,
+          "end": 157.84,
+          "confidence": 0.543
+        },
+        {
+          "text": "jamais?",
+          "start": 157.84,
+          "end": 157.95,
+          "confidence": 0.503
+        }
+      ]
+    },
+    {
+      "id": 45,
+      "seek": 13702,
+      "start": 157.95,
+      "end": 162.37,
+      "text": " Et puis, il faut en remettre la faute sur les gens qui ont créé cette",
+      "tokens": [
+        3790,
+        9093,
+        11,
+        1930,
+        8487,
+        465,
+        890,
+        40681,
+        635,
+        2050,
+        1169,
+        1022,
+        1512,
+        10668,
+        1956,
+        6592,
+        15609,
+        526,
+        5550
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5734858703613281,
+      "compression_ratio": 1.5562700964630225,
+      "no_speech_prob": 3.1260256037057843e-06,
+      "confidence": 0.82,
+      "words": [
+        {
+          "text": "Et",
+          "start": 157.95,
+          "end": 159.26,
+          "confidence": 0.838
+        },
+        {
+          "text": "puis,",
+          "start": 159.26,
+          "end": 159.58,
+          "confidence": 0.481
+        },
+        {
+          "text": "il",
+          "start": 159.58,
+          "end": 159.62,
+          "confidence": 0.665
+        },
+        {
+          "text": "faut",
+          "start": 159.62,
+          "end": 159.66,
+          "confidence": 0.942
+        },
+        {
+          "text": "en",
+          "start": 159.66,
+          "end": 159.72,
+          "confidence": 0.925
+        },
+        {
+          "text": "remettre",
+          "start": 159.72,
+          "end": 160.1,
+          "confidence": 0.985
+        },
+        {
+          "text": "la",
+          "start": 160.1,
+          "end": 160.28,
+          "confidence": 0.702
+        },
+        {
+          "text": "faute",
+          "start": 160.28,
+          "end": 160.62,
+          "confidence": 0.55
+        },
+        {
+          "text": "sur",
+          "start": 160.62,
+          "end": 160.9,
+          "confidence": 0.954
+        },
+        {
+          "text": "les",
+          "start": 160.9,
+          "end": 161.22,
+          "confidence": 0.81
+        },
+        {
+          "text": "gens",
+          "start": 161.22,
+          "end": 161.42,
+          "confidence": 0.985
+        },
+        {
+          "text": "qui",
+          "start": 161.42,
+          "end": 161.58,
+          "confidence": 0.981
+        },
+        {
+          "text": "ont",
+          "start": 161.58,
+          "end": 161.62,
+          "confidence": 0.955
+        },
+        {
+          "text": "créé",
+          "start": 161.62,
+          "end": 162.3,
+          "confidence": 0.957
+        },
+        {
+          "text": "cette",
+          "start": 162.3,
+          "end": 162.37,
+          "confidence": 0.9
+        }
+      ]
+    },
+    {
+      "id": 46,
+      "seek": 16228,
+      "start": 162.37,
+      "end": 165.3,
+      "text": " route merveilleux et diabolique, qui a dit à bollique par coeur, merveilleux.",
+      "tokens": [
+        7955,
+        3551,
+        303,
+        3409,
+        2449,
+        1030,
+        33227,
+        401,
+        1925,
+        11,
+        1956,
+        257,
+        6176,
+        1531,
+        748,
+        285,
+        1925,
+        971,
+        45781,
+        11,
+        3551,
+        303,
+        3409,
+        2449,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7643054464588994,
+      "compression_ratio": 1.544041450777202,
+      "no_speech_prob": 3.89045562769752e-05,
+      "confidence": 0.397,
+      "words": [
+        {
+          "text": "route",
+          "start": 162.37,
+          "end": 162.6,
+          "confidence": 0.076
+        },
+        {
+          "text": "merveilleux",
+          "start": 162.6,
+          "end": 163.3,
+          "confidence": 0.635
+        },
+        {
+          "text": "et",
+          "start": 163.3,
+          "end": 163.42,
+          "confidence": 0.837
+        },
+        {
+          "text": "diabolique,",
+          "start": 163.42,
+          "end": 163.82,
+          "confidence": 0.328
+        },
+        {
+          "text": "qui",
+          "start": 163.82,
+          "end": 163.9,
+          "confidence": 0.365
+        },
+        {
+          "text": "a",
+          "start": 163.9,
+          "end": 163.98,
+          "confidence": 0.054
+        },
+        {
+          "text": "dit",
+          "start": 163.98,
+          "end": 164.06,
+          "confidence": 0.085
+        },
+        {
+          "text": "à",
+          "start": 164.06,
+          "end": 164.1,
+          "confidence": 0.433
+        },
+        {
+          "text": "bollique",
+          "start": 164.1,
+          "end": 164.3,
+          "confidence": 0.297
+        },
+        {
+          "text": "par",
+          "start": 164.3,
+          "end": 164.52,
+          "confidence": 0.634
+        },
+        {
+          "text": "coeur,",
+          "start": 164.52,
+          "end": 164.78,
+          "confidence": 0.361
+        },
+        {
+          "text": "merveilleux.",
+          "start": 164.78,
+          "end": 165.3,
+          "confidence": 0.982
+        }
+      ]
+    },
+    {
+      "id": 47,
+      "seek": 16228,
+      "start": 167.36,
+      "end": 168.7,
+      "text": " Les économistes parlent de dépendance du santé.",
+      "tokens": [
+        6965,
+        31171,
+        22368,
+        13734,
+        317,
+        368,
+        45768,
+        719,
+        1581,
+        30068,
+        13
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7643054464588994,
+      "compression_ratio": 1.544041450777202,
+      "no_speech_prob": 3.89045562769752e-05,
+      "confidence": 0.748,
+      "words": [
+        {
+          "text": "Les",
+          "start": 167.36,
+          "end": 167.4,
+          "confidence": 0.513
+        },
+        {
+          "text": "économistes",
+          "start": 167.4,
+          "end": 167.5,
+          "confidence": 0.937
+        },
+        {
+          "text": "parlent",
+          "start": 167.5,
+          "end": 167.78,
+          "confidence": 0.806
+        },
+        {
+          "text": "de",
+          "start": 167.78,
+          "end": 167.82,
+          "confidence": 0.855
+        },
+        {
+          "text": "dépendance",
+          "start": 167.82,
+          "end": 168.32,
+          "confidence": 0.758
+        },
+        {
+          "text": "du",
+          "start": 168.32,
+          "end": 168.5,
+          "confidence": 0.979
+        },
+        {
+          "text": "santé.",
+          "start": 168.5,
+          "end": 168.7,
+          "confidence": 0.389
+        }
+      ]
+    },
+    {
+      "id": 48,
+      "seek": 16228,
+      "start": 168.84,
+      "end": 172.66,
+      "text": " Ces vidéos, en fait, on est un santé qui a été établie, c'est un soit mon termine,",
+      "tokens": [
+        28414,
+        25417,
+        11,
+        465,
+        3887,
+        11,
+        322,
+        871,
+        517,
+        30068,
+        1956,
+        257,
+        8862,
+        4823,
+        455,
+        6302,
+        11,
+        269,
+        6,
+        377,
+        517,
+        12703,
+        1108,
+        1433,
+        533,
+        11
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7643054464588994,
+      "compression_ratio": 1.544041450777202,
+      "no_speech_prob": 3.89045562769752e-05,
+      "confidence": 0.487,
+      "words": [
+        {
+          "text": "Ces",
+          "start": 168.84,
+          "end": 169.14,
+          "confidence": 0.531
+        },
+        {
+          "text": "vidéos,",
+          "start": 169.14,
+          "end": 169.5,
+          "confidence": 0.725
+        },
+        {
+          "text": "en",
+          "start": 169.5,
+          "end": 169.62,
+          "confidence": 0.757
+        },
+        {
+          "text": "fait,",
+          "start": 169.62,
+          "end": 169.68,
+          "confidence": 0.974
+        },
+        {
+          "text": "on",
+          "start": 169.68,
+          "end": 169.74,
+          "confidence": 0.306
+        },
+        {
+          "text": "est",
+          "start": 169.74,
+          "end": 169.86,
+          "confidence": 0.82
+        },
+        {
+          "text": "un",
+          "start": 169.86,
+          "end": 170.16,
+          "confidence": 0.245
+        },
+        {
+          "text": "santé",
+          "start": 170.16,
+          "end": 170.72,
+          "confidence": 0.943
+        },
+        {
+          "text": "qui",
+          "start": 170.72,
+          "end": 170.88,
+          "confidence": 0.839
+        },
+        {
+          "text": "a",
+          "start": 170.88,
+          "end": 170.96,
+          "confidence": 0.533
+        },
+        {
+          "text": "été",
+          "start": 170.96,
+          "end": 171.08,
+          "confidence": 0.992
+        },
+        {
+          "text": "établie,",
+          "start": 171.08,
+          "end": 171.6,
+          "confidence": 0.316
+        },
+        {
+          "text": "c'est",
+          "start": 171.6,
+          "end": 171.74,
+          "confidence": 0.55
+        },
+        {
+          "text": "un",
+          "start": 171.74,
+          "end": 171.88,
+          "confidence": 0.651
+        },
+        {
+          "text": "soit",
+          "start": 171.88,
+          "end": 172.12,
+          "confidence": 0.284
+        },
+        {
+          "text": "mon",
+          "start": 172.12,
+          "end": 172.28,
+          "confidence": 0.225
+        },
+        {
+          "text": "termine,",
+          "start": 172.28,
+          "end": 172.66,
+          "confidence": 0.288
+        }
+      ]
+    },
+    {
+      "id": 49,
+      "seek": 17312,
+      "start": 173.14,
+      "end": 177.42,
+      "text": " soit définissant des beurs, on définisse un signalétique.",
+      "tokens": [
+        50364,
+        12703,
+        40763,
+        29492,
+        730,
+        312,
+        2156,
+        11,
+        322,
+        40763,
+        7746,
+        517,
+        6358,
+        42379,
+        13,
+        51436
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9428024291992188,
+      "compression_ratio": 1.0169491525423728,
+      "no_speech_prob": 6.687085260637105e-05,
+      "confidence": 0.403,
+      "words": [
+        {
+          "text": "soit",
+          "start": 173.14,
+          "end": 174.04,
+          "confidence": 0.127
+        },
+        {
+          "text": "définissant",
+          "start": 174.04,
+          "end": 175.5,
+          "confidence": 0.58
+        },
+        {
+          "text": "des",
+          "start": 175.5,
+          "end": 175.68,
+          "confidence": 0.813
+        },
+        {
+          "text": "beurs,",
+          "start": 175.68,
+          "end": 175.96,
+          "confidence": 0.378
+        },
+        {
+          "text": "on",
+          "start": 175.96,
+          "end": 176.04,
+          "confidence": 0.165
+        },
+        {
+          "text": "définisse",
+          "start": 176.04,
+          "end": 176.42,
+          "confidence": 0.536
+        },
+        {
+          "text": "un",
+          "start": 176.42,
+          "end": 176.6,
+          "confidence": 0.266
+        },
+        {
+          "text": "signalétique.",
+          "start": 176.6,
+          "end": 177.42,
+          "confidence": 0.544
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_fr/bonjour.wav.words.json b/tests/expected/tiny_fr/bonjour.wav.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..6d1d63b947661bb29dbb3d480d85dc90a4e6c115
--- /dev/null
+++ b/tests/expected/tiny_fr/bonjour.wav.words.json
@@ -0,0 +1,32 @@
+{
+  "text": " Bonjour !",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.14,
+      "end": 0.96,
+      "text": " Bonjour !",
+      "tokens": [
+        50364,
+        25431,
+        2298,
+        50414
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6977285861968994,
+      "compression_ratio": 0.5294117647058824,
+      "no_speech_prob": 0.019094161689281464,
+      "confidence": 0.829,
+      "words": [
+        {
+          "text": "Bonjour !",
+          "start": 0.14,
+          "end": 0.96,
+          "confidence": 0.829
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_fr/bonjour_vous_allez_bien.mp3.words.json b/tests/expected/tiny_fr/bonjour_vous_allez_bien.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..56d4282f71080f7d429dd75ef057267e85842e42
--- /dev/null
+++ b/tests/expected/tiny_fr/bonjour_vous_allez_bien.mp3.words.json
@@ -0,0 +1,162 @@
+{
+  "text": " Bonjour ! Est-ce que vous allez bien ? Bonjour ! Esque vous allez bien !",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.44,
+      "end": 1.44,
+      "text": " Bonjour !",
+      "tokens": [
+        50364,
+        25431,
+        2298,
+        50438
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7721260706583659,
+      "compression_ratio": 0.8260869565217391,
+      "no_speech_prob": 0.04302893579006195,
+      "confidence": 0.688,
+      "words": [
+        {
+          "text": "Bonjour !",
+          "start": 0.44,
+          "end": 1.44,
+          "confidence": 0.688
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 1.88,
+      "end": 3.12,
+      "text": " Est-ce que vous allez bien ?",
+      "tokens": [
+        50438,
+        4410,
+        12,
+        384,
+        631,
+        2630,
+        18146,
+        3610,
+        2506,
+        50538
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.7721260706583659,
+      "compression_ratio": 0.8260869565217391,
+      "no_speech_prob": 0.04302893579006195,
+      "confidence": 0.68,
+      "words": [
+        {
+          "text": "Est-ce",
+          "start": 1.88,
+          "end": 2.2,
+          "confidence": 0.667
+        },
+        {
+          "text": "que",
+          "start": 2.2,
+          "end": 2.24,
+          "confidence": 0.873
+        },
+        {
+          "text": "vous",
+          "start": 2.24,
+          "end": 2.36,
+          "confidence": 0.993
+        },
+        {
+          "text": "allez",
+          "start": 2.36,
+          "end": 2.56,
+          "confidence": 0.268
+        },
+        {
+          "text": "bien ?",
+          "start": 2.56,
+          "end": 3.12,
+          "confidence": 0.973
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 3000,
+      "start": 32.98,
+      "end": 33.48,
+      "text": " Bonjour !",
+      "tokens": [
+        50364,
+        25431,
+        2298,
+        50514
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9276708456186148,
+      "compression_ratio": 0.8048780487804879,
+      "no_speech_prob": 0.3543654680252075,
+      "confidence": 0.533,
+      "words": [
+        {
+          "text": "Bonjour !",
+          "start": 32.98,
+          "end": 33.48,
+          "confidence": 0.533
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 3000,
+      "start": 34.42,
+      "end": 35.48,
+      "text": " Esque vous allez bien !",
+      "tokens": [
+        50514,
+        2313,
+        1077,
+        2630,
+        18146,
+        3610,
+        2298,
+        50614
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.9276708456186148,
+      "compression_ratio": 0.8048780487804879,
+      "no_speech_prob": 0.3543654680252075,
+      "confidence": 0.484,
+      "words": [
+        {
+          "text": "Esque",
+          "start": 34.42,
+          "end": 34.76,
+          "confidence": 0.186
+        },
+        {
+          "text": "vous",
+          "start": 34.76,
+          "end": 34.9,
+          "confidence": 0.982
+        },
+        {
+          "text": "allez",
+          "start": 34.9,
+          "end": 35.08,
+          "confidence": 0.781
+        },
+        {
+          "text": "bien !",
+          "start": 35.08,
+          "end": 35.48,
+          "confidence": 0.998
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_fr/empty.mp3.words.json b/tests/expected/tiny_fr/empty.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..cd4c337f3962718881cc93300e57e4f7d05feedb
--- /dev/null
+++ b/tests/expected/tiny_fr/empty.mp3.words.json
@@ -0,0 +1,5 @@
+{
+  "text": "",
+  "segments": [],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_fr/gaenswein15.mp3.words.json b/tests/expected/tiny_fr/gaenswein15.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..5bcf408187d102ee5d53ff99f31d8daa29e14bdc
--- /dev/null
+++ b/tests/expected/tiny_fr/gaenswein15.mp3.words.json
@@ -0,0 +1,71 @@
+{
+  "text": " Leur de l'Ontario est de la",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 20.14,
+      "end": 24.68,
+      "text": " Leur de l'Ontario est de la",
+      "tokens": [
+        50364,
+        1456,
+        374,
+        368,
+        287,
+        6,
+        46,
+        580,
+        4912,
+        871,
+        368,
+        635,
+        51571
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -1.7974119186401367,
+      "compression_ratio": 0.84375,
+      "no_speech_prob": 0.04553895816206932,
+      "confidence": 0.152,
+      "words": [
+        {
+          "text": "Leur",
+          "start": 20.14,
+          "end": 20.16,
+          "confidence": 0.055
+        },
+        {
+          "text": "de",
+          "start": 20.16,
+          "end": 20.18,
+          "confidence": 0.11
+        },
+        {
+          "text": "l'Ontario",
+          "start": 20.18,
+          "end": 24.62,
+          "confidence": 0.309
+        },
+        {
+          "text": "est",
+          "start": 24.62,
+          "end": 24.64,
+          "confidence": 0.128
+        },
+        {
+          "text": "de",
+          "start": 24.64,
+          "end": 24.66,
+          "confidence": 0.063
+        },
+        {
+          "text": "la",
+          "start": 24.66,
+          "end": 24.68,
+          "confidence": 0.133
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_fr/gloria.mp3.words.json b/tests/expected/tiny_fr/gloria.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..5889dee1fb218b037b23960a5c1bf352861a0323
--- /dev/null
+++ b/tests/expected/tiny_fr/gloria.mp3.words.json
@@ -0,0 +1,1584 @@
+{
+  "text": " Je suis très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 1.34,
+      "end": 29.98,
+      "text": " Je suis très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très très",
+      "tokens": [
+        50364,
+        2588,
+        7624,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732,
+        5732
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.3070239596896701,
+      "compression_ratio": 43.0,
+      "no_speech_prob": 0.11146047711372375,
+      "confidence": 0.734,
+      "words": [
+        {
+          "text": "Je",
+          "start": 1.34,
+          "end": 5.76,
+          "confidence": 0.043
+        },
+        {
+          "text": "suis",
+          "start": 5.76,
+          "end": 5.92,
+          "confidence": 0.156
+        },
+        {
+          "text": "très",
+          "start": 5.92,
+          "end": 6.2,
+          "confidence": 0.053
+        },
+        {
+          "text": "très",
+          "start": 6.2,
+          "end": 10.56,
+          "confidence": 0.106
+        },
+        {
+          "text": "très",
+          "start": 10.56,
+          "end": 11.22,
+          "confidence": 0.159
+        },
+        {
+          "text": "très",
+          "start": 11.22,
+          "end": 11.34,
+          "confidence": 0.186
+        },
+        {
+          "text": "très",
+          "start": 11.34,
+          "end": 11.36,
+          "confidence": 0.201
+        },
+        {
+          "text": "très",
+          "start": 11.36,
+          "end": 11.38,
+          "confidence": 0.228
+        },
+        {
+          "text": "très",
+          "start": 11.38,
+          "end": 11.4,
+          "confidence": 0.255
+        },
+        {
+          "text": "très",
+          "start": 11.4,
+          "end": 11.42,
+          "confidence": 0.281
+        },
+        {
+          "text": "très",
+          "start": 11.42,
+          "end": 11.44,
+          "confidence": 0.322
+        },
+        {
+          "text": "très",
+          "start": 11.44,
+          "end": 11.46,
+          "confidence": 0.382
+        },
+        {
+          "text": "très",
+          "start": 11.46,
+          "end": 11.48,
+          "confidence": 0.457
+        },
+        {
+          "text": "très",
+          "start": 11.48,
+          "end": 11.5,
+          "confidence": 0.537
+        },
+        {
+          "text": "très",
+          "start": 11.5,
+          "end": 11.52,
+          "confidence": 0.592
+        },
+        {
+          "text": "très",
+          "start": 11.52,
+          "end": 11.54,
+          "confidence": 0.634
+        },
+        {
+          "text": "très",
+          "start": 11.54,
+          "end": 11.56,
+          "confidence": 0.67
+        },
+        {
+          "text": "très",
+          "start": 11.56,
+          "end": 11.58,
+          "confidence": 0.69
+        },
+        {
+          "text": "très",
+          "start": 11.58,
+          "end": 11.6,
+          "confidence": 0.704
+        },
+        {
+          "text": "très",
+          "start": 11.6,
+          "end": 11.62,
+          "confidence": 0.719
+        },
+        {
+          "text": "très",
+          "start": 11.62,
+          "end": 11.64,
+          "confidence": 0.723
+        },
+        {
+          "text": "très",
+          "start": 11.64,
+          "end": 11.66,
+          "confidence": 0.735
+        },
+        {
+          "text": "très",
+          "start": 11.66,
+          "end": 11.68,
+          "confidence": 0.74
+        },
+        {
+          "text": "très",
+          "start": 11.68,
+          "end": 11.7,
+          "confidence": 0.75
+        },
+        {
+          "text": "très",
+          "start": 11.7,
+          "end": 11.72,
+          "confidence": 0.752
+        },
+        {
+          "text": "très",
+          "start": 11.72,
+          "end": 11.74,
+          "confidence": 0.751
+        },
+        {
+          "text": "très",
+          "start": 11.74,
+          "end": 11.76,
+          "confidence": 0.754
+        },
+        {
+          "text": "très",
+          "start": 11.76,
+          "end": 11.78,
+          "confidence": 0.755
+        },
+        {
+          "text": "très",
+          "start": 11.78,
+          "end": 11.8,
+          "confidence": 0.761
+        },
+        {
+          "text": "très",
+          "start": 11.8,
+          "end": 11.82,
+          "confidence": 0.76
+        },
+        {
+          "text": "très",
+          "start": 11.82,
+          "end": 11.84,
+          "confidence": 0.76
+        },
+        {
+          "text": "très",
+          "start": 11.84,
+          "end": 11.86,
+          "confidence": 0.766
+        },
+        {
+          "text": "très",
+          "start": 11.86,
+          "end": 11.88,
+          "confidence": 0.769
+        },
+        {
+          "text": "très",
+          "start": 11.88,
+          "end": 11.9,
+          "confidence": 0.769
+        },
+        {
+          "text": "très",
+          "start": 11.9,
+          "end": 11.92,
+          "confidence": 0.768
+        },
+        {
+          "text": "très",
+          "start": 11.92,
+          "end": 11.94,
+          "confidence": 0.77
+        },
+        {
+          "text": "très",
+          "start": 11.94,
+          "end": 11.96,
+          "confidence": 0.772
+        },
+        {
+          "text": "très",
+          "start": 11.96,
+          "end": 11.98,
+          "confidence": 0.775
+        },
+        {
+          "text": "très",
+          "start": 11.98,
+          "end": 12.0,
+          "confidence": 0.776
+        },
+        {
+          "text": "très",
+          "start": 12.0,
+          "end": 12.02,
+          "confidence": 0.776
+        },
+        {
+          "text": "très",
+          "start": 12.02,
+          "end": 12.8,
+          "confidence": 0.779
+        },
+        {
+          "text": "très",
+          "start": 12.8,
+          "end": 13.7,
+          "confidence": 0.782
+        },
+        {
+          "text": "très",
+          "start": 13.7,
+          "end": 13.72,
+          "confidence": 0.786
+        },
+        {
+          "text": "très",
+          "start": 13.72,
+          "end": 14.74,
+          "confidence": 0.781
+        },
+        {
+          "text": "très",
+          "start": 14.74,
+          "end": 14.76,
+          "confidence": 0.779
+        },
+        {
+          "text": "très",
+          "start": 14.76,
+          "end": 14.96,
+          "confidence": 0.784
+        },
+        {
+          "text": "très",
+          "start": 14.96,
+          "end": 14.98,
+          "confidence": 0.784
+        },
+        {
+          "text": "très",
+          "start": 14.98,
+          "end": 15.94,
+          "confidence": 0.785
+        },
+        {
+          "text": "très",
+          "start": 15.94,
+          "end": 15.96,
+          "confidence": 0.787
+        },
+        {
+          "text": "très",
+          "start": 15.96,
+          "end": 15.98,
+          "confidence": 0.787
+        },
+        {
+          "text": "très",
+          "start": 15.98,
+          "end": 16.0,
+          "confidence": 0.791
+        },
+        {
+          "text": "très",
+          "start": 16.0,
+          "end": 16.02,
+          "confidence": 0.79
+        },
+        {
+          "text": "très",
+          "start": 16.02,
+          "end": 16.04,
+          "confidence": 0.788
+        },
+        {
+          "text": "très",
+          "start": 16.04,
+          "end": 16.06,
+          "confidence": 0.788
+        },
+        {
+          "text": "très",
+          "start": 16.06,
+          "end": 16.08,
+          "confidence": 0.787
+        },
+        {
+          "text": "très",
+          "start": 16.08,
+          "end": 17.54,
+          "confidence": 0.793
+        },
+        {
+          "text": "très",
+          "start": 17.54,
+          "end": 17.56,
+          "confidence": 0.791
+        },
+        {
+          "text": "très",
+          "start": 17.56,
+          "end": 17.58,
+          "confidence": 0.793
+        },
+        {
+          "text": "très",
+          "start": 17.58,
+          "end": 17.6,
+          "confidence": 0.794
+        },
+        {
+          "text": "très",
+          "start": 17.6,
+          "end": 17.62,
+          "confidence": 0.798
+        },
+        {
+          "text": "très",
+          "start": 17.62,
+          "end": 17.64,
+          "confidence": 0.795
+        },
+        {
+          "text": "très",
+          "start": 17.64,
+          "end": 17.66,
+          "confidence": 0.796
+        },
+        {
+          "text": "très",
+          "start": 17.66,
+          "end": 17.68,
+          "confidence": 0.796
+        },
+        {
+          "text": "très",
+          "start": 17.68,
+          "end": 17.7,
+          "confidence": 0.799
+        },
+        {
+          "text": "très",
+          "start": 17.7,
+          "end": 17.72,
+          "confidence": 0.801
+        },
+        {
+          "text": "très",
+          "start": 17.72,
+          "end": 17.74,
+          "confidence": 0.804
+        },
+        {
+          "text": "très",
+          "start": 17.74,
+          "end": 17.76,
+          "confidence": 0.803
+        },
+        {
+          "text": "très",
+          "start": 17.76,
+          "end": 17.78,
+          "confidence": 0.801
+        },
+        {
+          "text": "très",
+          "start": 17.78,
+          "end": 17.8,
+          "confidence": 0.805
+        },
+        {
+          "text": "très",
+          "start": 17.8,
+          "end": 17.82,
+          "confidence": 0.806
+        },
+        {
+          "text": "très",
+          "start": 17.82,
+          "end": 17.84,
+          "confidence": 0.808
+        },
+        {
+          "text": "très",
+          "start": 17.84,
+          "end": 17.86,
+          "confidence": 0.811
+        },
+        {
+          "text": "très",
+          "start": 17.86,
+          "end": 17.88,
+          "confidence": 0.814
+        },
+        {
+          "text": "très",
+          "start": 17.88,
+          "end": 17.9,
+          "confidence": 0.817
+        },
+        {
+          "text": "très",
+          "start": 17.9,
+          "end": 17.92,
+          "confidence": 0.819
+        },
+        {
+          "text": "très",
+          "start": 17.92,
+          "end": 17.94,
+          "confidence": 0.82
+        },
+        {
+          "text": "très",
+          "start": 17.94,
+          "end": 17.96,
+          "confidence": 0.823
+        },
+        {
+          "text": "très",
+          "start": 17.96,
+          "end": 17.98,
+          "confidence": 0.823
+        },
+        {
+          "text": "très",
+          "start": 17.98,
+          "end": 19.34,
+          "confidence": 0.827
+        },
+        {
+          "text": "très",
+          "start": 19.34,
+          "end": 19.36,
+          "confidence": 0.828
+        },
+        {
+          "text": "très",
+          "start": 19.36,
+          "end": 19.38,
+          "confidence": 0.835
+        },
+        {
+          "text": "très",
+          "start": 19.38,
+          "end": 19.4,
+          "confidence": 0.836
+        },
+        {
+          "text": "très",
+          "start": 19.4,
+          "end": 19.42,
+          "confidence": 0.839
+        },
+        {
+          "text": "très",
+          "start": 19.42,
+          "end": 19.44,
+          "confidence": 0.838
+        },
+        {
+          "text": "très",
+          "start": 19.44,
+          "end": 19.46,
+          "confidence": 0.841
+        },
+        {
+          "text": "très",
+          "start": 19.46,
+          "end": 19.48,
+          "confidence": 0.841
+        },
+        {
+          "text": "très",
+          "start": 19.48,
+          "end": 19.5,
+          "confidence": 0.843
+        },
+        {
+          "text": "très",
+          "start": 19.5,
+          "end": 19.52,
+          "confidence": 0.844
+        },
+        {
+          "text": "très",
+          "start": 19.52,
+          "end": 19.54,
+          "confidence": 0.848
+        },
+        {
+          "text": "très",
+          "start": 19.54,
+          "end": 19.56,
+          "confidence": 0.849
+        },
+        {
+          "text": "très",
+          "start": 19.56,
+          "end": 19.58,
+          "confidence": 0.848
+        },
+        {
+          "text": "très",
+          "start": 19.58,
+          "end": 19.6,
+          "confidence": 0.849
+        },
+        {
+          "text": "très",
+          "start": 19.6,
+          "end": 19.62,
+          "confidence": 0.852
+        },
+        {
+          "text": "très",
+          "start": 19.62,
+          "end": 19.64,
+          "confidence": 0.851
+        },
+        {
+          "text": "très",
+          "start": 19.64,
+          "end": 20.06,
+          "confidence": 0.852
+        },
+        {
+          "text": "très",
+          "start": 20.06,
+          "end": 20.14,
+          "confidence": 0.854
+        },
+        {
+          "text": "très",
+          "start": 20.14,
+          "end": 20.16,
+          "confidence": 0.854
+        },
+        {
+          "text": "très",
+          "start": 20.16,
+          "end": 20.18,
+          "confidence": 0.857
+        },
+        {
+          "text": "très",
+          "start": 20.18,
+          "end": 20.2,
+          "confidence": 0.857
+        },
+        {
+          "text": "très",
+          "start": 20.2,
+          "end": 20.22,
+          "confidence": 0.858
+        },
+        {
+          "text": "très",
+          "start": 20.22,
+          "end": 20.56,
+          "confidence": 0.859
+        },
+        {
+          "text": "très",
+          "start": 20.56,
+          "end": 20.58,
+          "confidence": 0.858
+        },
+        {
+          "text": "très",
+          "start": 20.58,
+          "end": 20.6,
+          "confidence": 0.86
+        },
+        {
+          "text": "très",
+          "start": 20.6,
+          "end": 20.62,
+          "confidence": 0.861
+        },
+        {
+          "text": "très",
+          "start": 20.62,
+          "end": 20.64,
+          "confidence": 0.864
+        },
+        {
+          "text": "très",
+          "start": 20.64,
+          "end": 20.66,
+          "confidence": 0.866
+        },
+        {
+          "text": "très",
+          "start": 20.66,
+          "end": 20.68,
+          "confidence": 0.866
+        },
+        {
+          "text": "très",
+          "start": 20.68,
+          "end": 20.7,
+          "confidence": 0.866
+        },
+        {
+          "text": "très",
+          "start": 20.7,
+          "end": 20.72,
+          "confidence": 0.862
+        },
+        {
+          "text": "très",
+          "start": 20.72,
+          "end": 20.74,
+          "confidence": 0.863
+        },
+        {
+          "text": "très",
+          "start": 20.74,
+          "end": 20.76,
+          "confidence": 0.864
+        },
+        {
+          "text": "très",
+          "start": 20.76,
+          "end": 20.78,
+          "confidence": 0.864
+        },
+        {
+          "text": "très",
+          "start": 20.78,
+          "end": 20.8,
+          "confidence": 0.862
+        },
+        {
+          "text": "très",
+          "start": 20.8,
+          "end": 20.82,
+          "confidence": 0.861
+        },
+        {
+          "text": "très",
+          "start": 20.82,
+          "end": 20.84,
+          "confidence": 0.863
+        },
+        {
+          "text": "très",
+          "start": 20.84,
+          "end": 20.86,
+          "confidence": 0.862
+        },
+        {
+          "text": "très",
+          "start": 20.86,
+          "end": 20.88,
+          "confidence": 0.859
+        },
+        {
+          "text": "très",
+          "start": 20.88,
+          "end": 20.9,
+          "confidence": 0.855
+        },
+        {
+          "text": "très",
+          "start": 20.9,
+          "end": 20.92,
+          "confidence": 0.858
+        },
+        {
+          "text": "très",
+          "start": 20.92,
+          "end": 20.94,
+          "confidence": 0.856
+        },
+        {
+          "text": "très",
+          "start": 20.94,
+          "end": 20.96,
+          "confidence": 0.853
+        },
+        {
+          "text": "très",
+          "start": 20.96,
+          "end": 20.98,
+          "confidence": 0.849
+        },
+        {
+          "text": "très",
+          "start": 20.98,
+          "end": 21.0,
+          "confidence": 0.851
+        },
+        {
+          "text": "très",
+          "start": 21.0,
+          "end": 21.02,
+          "confidence": 0.853
+        },
+        {
+          "text": "très",
+          "start": 21.02,
+          "end": 21.04,
+          "confidence": 0.853
+        },
+        {
+          "text": "très",
+          "start": 21.04,
+          "end": 21.06,
+          "confidence": 0.848
+        },
+        {
+          "text": "très",
+          "start": 21.06,
+          "end": 21.08,
+          "confidence": 0.849
+        },
+        {
+          "text": "très",
+          "start": 21.08,
+          "end": 21.1,
+          "confidence": 0.851
+        },
+        {
+          "text": "très",
+          "start": 21.1,
+          "end": 21.12,
+          "confidence": 0.845
+        },
+        {
+          "text": "très",
+          "start": 21.12,
+          "end": 21.14,
+          "confidence": 0.849
+        },
+        {
+          "text": "très",
+          "start": 21.14,
+          "end": 21.16,
+          "confidence": 0.851
+        },
+        {
+          "text": "très",
+          "start": 21.16,
+          "end": 21.18,
+          "confidence": 0.851
+        },
+        {
+          "text": "très",
+          "start": 21.18,
+          "end": 21.2,
+          "confidence": 0.85
+        },
+        {
+          "text": "très",
+          "start": 21.2,
+          "end": 21.22,
+          "confidence": 0.847
+        },
+        {
+          "text": "très",
+          "start": 21.22,
+          "end": 21.24,
+          "confidence": 0.846
+        },
+        {
+          "text": "très",
+          "start": 21.24,
+          "end": 21.26,
+          "confidence": 0.843
+        },
+        {
+          "text": "très",
+          "start": 21.26,
+          "end": 21.28,
+          "confidence": 0.844
+        },
+        {
+          "text": "très",
+          "start": 21.28,
+          "end": 21.3,
+          "confidence": 0.846
+        },
+        {
+          "text": "très",
+          "start": 21.3,
+          "end": 21.32,
+          "confidence": 0.838
+        },
+        {
+          "text": "très",
+          "start": 21.32,
+          "end": 21.34,
+          "confidence": 0.842
+        },
+        {
+          "text": "très",
+          "start": 21.34,
+          "end": 21.36,
+          "confidence": 0.841
+        },
+        {
+          "text": "très",
+          "start": 21.36,
+          "end": 21.38,
+          "confidence": 0.845
+        },
+        {
+          "text": "très",
+          "start": 21.38,
+          "end": 21.4,
+          "confidence": 0.839
+        },
+        {
+          "text": "très",
+          "start": 21.4,
+          "end": 21.42,
+          "confidence": 0.833
+        },
+        {
+          "text": "très",
+          "start": 21.42,
+          "end": 21.44,
+          "confidence": 0.826
+        },
+        {
+          "text": "très",
+          "start": 21.44,
+          "end": 21.46,
+          "confidence": 0.824
+        },
+        {
+          "text": "très",
+          "start": 21.46,
+          "end": 21.48,
+          "confidence": 0.824
+        },
+        {
+          "text": "très",
+          "start": 21.48,
+          "end": 21.5,
+          "confidence": 0.821
+        },
+        {
+          "text": "très",
+          "start": 21.5,
+          "end": 21.52,
+          "confidence": 0.823
+        },
+        {
+          "text": "très",
+          "start": 21.52,
+          "end": 21.54,
+          "confidence": 0.821
+        },
+        {
+          "text": "très",
+          "start": 21.54,
+          "end": 21.56,
+          "confidence": 0.827
+        },
+        {
+          "text": "très",
+          "start": 21.56,
+          "end": 21.58,
+          "confidence": 0.819
+        },
+        {
+          "text": "très",
+          "start": 21.58,
+          "end": 21.6,
+          "confidence": 0.816
+        },
+        {
+          "text": "très",
+          "start": 21.6,
+          "end": 21.62,
+          "confidence": 0.815
+        },
+        {
+          "text": "très",
+          "start": 21.62,
+          "end": 21.64,
+          "confidence": 0.815
+        },
+        {
+          "text": "très",
+          "start": 21.64,
+          "end": 21.66,
+          "confidence": 0.819
+        },
+        {
+          "text": "très",
+          "start": 21.66,
+          "end": 21.68,
+          "confidence": 0.811
+        },
+        {
+          "text": "très",
+          "start": 21.68,
+          "end": 21.7,
+          "confidence": 0.821
+        },
+        {
+          "text": "très",
+          "start": 21.7,
+          "end": 21.72,
+          "confidence": 0.811
+        },
+        {
+          "text": "très",
+          "start": 21.72,
+          "end": 21.74,
+          "confidence": 0.816
+        },
+        {
+          "text": "très",
+          "start": 21.74,
+          "end": 21.76,
+          "confidence": 0.819
+        },
+        {
+          "text": "très",
+          "start": 21.76,
+          "end": 21.78,
+          "confidence": 0.812
+        },
+        {
+          "text": "très",
+          "start": 21.78,
+          "end": 21.8,
+          "confidence": 0.815
+        },
+        {
+          "text": "très",
+          "start": 21.8,
+          "end": 21.82,
+          "confidence": 0.813
+        },
+        {
+          "text": "très",
+          "start": 21.82,
+          "end": 21.84,
+          "confidence": 0.811
+        },
+        {
+          "text": "très",
+          "start": 21.84,
+          "end": 21.86,
+          "confidence": 0.809
+        },
+        {
+          "text": "très",
+          "start": 21.86,
+          "end": 21.88,
+          "confidence": 0.802
+        },
+        {
+          "text": "très",
+          "start": 21.88,
+          "end": 21.9,
+          "confidence": 0.802
+        },
+        {
+          "text": "très",
+          "start": 21.9,
+          "end": 21.92,
+          "confidence": 0.798
+        },
+        {
+          "text": "très",
+          "start": 21.92,
+          "end": 21.94,
+          "confidence": 0.792
+        },
+        {
+          "text": "très",
+          "start": 21.94,
+          "end": 21.96,
+          "confidence": 0.802
+        },
+        {
+          "text": "très",
+          "start": 21.96,
+          "end": 21.98,
+          "confidence": 0.784
+        },
+        {
+          "text": "très",
+          "start": 21.98,
+          "end": 22.0,
+          "confidence": 0.78
+        },
+        {
+          "text": "très",
+          "start": 22.0,
+          "end": 22.02,
+          "confidence": 0.782
+        },
+        {
+          "text": "très",
+          "start": 22.02,
+          "end": 22.04,
+          "confidence": 0.783
+        },
+        {
+          "text": "très",
+          "start": 22.04,
+          "end": 22.06,
+          "confidence": 0.777
+        },
+        {
+          "text": "très",
+          "start": 22.06,
+          "end": 22.08,
+          "confidence": 0.778
+        },
+        {
+          "text": "très",
+          "start": 22.08,
+          "end": 22.1,
+          "confidence": 0.787
+        },
+        {
+          "text": "très",
+          "start": 22.1,
+          "end": 22.12,
+          "confidence": 0.789
+        },
+        {
+          "text": "très",
+          "start": 22.12,
+          "end": 22.14,
+          "confidence": 0.788
+        },
+        {
+          "text": "très",
+          "start": 22.14,
+          "end": 22.16,
+          "confidence": 0.788
+        },
+        {
+          "text": "très",
+          "start": 22.16,
+          "end": 22.18,
+          "confidence": 0.784
+        },
+        {
+          "text": "très",
+          "start": 22.18,
+          "end": 22.2,
+          "confidence": 0.777
+        },
+        {
+          "text": "très",
+          "start": 22.2,
+          "end": 22.22,
+          "confidence": 0.783
+        },
+        {
+          "text": "très",
+          "start": 22.22,
+          "end": 22.24,
+          "confidence": 0.793
+        },
+        {
+          "text": "très",
+          "start": 22.24,
+          "end": 22.26,
+          "confidence": 0.794
+        },
+        {
+          "text": "très",
+          "start": 22.26,
+          "end": 22.28,
+          "confidence": 0.782
+        },
+        {
+          "text": "très",
+          "start": 22.28,
+          "end": 22.3,
+          "confidence": 0.788
+        },
+        {
+          "text": "très",
+          "start": 22.3,
+          "end": 22.32,
+          "confidence": 0.787
+        },
+        {
+          "text": "très",
+          "start": 22.32,
+          "end": 22.34,
+          "confidence": 0.782
+        },
+        {
+          "text": "très",
+          "start": 22.34,
+          "end": 22.36,
+          "confidence": 0.781
+        },
+        {
+          "text": "très",
+          "start": 22.36,
+          "end": 22.38,
+          "confidence": 0.788
+        },
+        {
+          "text": "très",
+          "start": 22.38,
+          "end": 22.4,
+          "confidence": 0.775
+        },
+        {
+          "text": "très",
+          "start": 22.4,
+          "end": 22.42,
+          "confidence": 0.777
+        },
+        {
+          "text": "très",
+          "start": 22.42,
+          "end": 22.44,
+          "confidence": 0.778
+        },
+        {
+          "text": "très",
+          "start": 22.44,
+          "end": 22.46,
+          "confidence": 0.77
+        },
+        {
+          "text": "très",
+          "start": 22.46,
+          "end": 22.48,
+          "confidence": 0.768
+        },
+        {
+          "text": "très",
+          "start": 22.48,
+          "end": 22.5,
+          "confidence": 0.768
+        },
+        {
+          "text": "très",
+          "start": 22.5,
+          "end": 22.52,
+          "confidence": 0.775
+        },
+        {
+          "text": "très",
+          "start": 22.52,
+          "end": 22.54,
+          "confidence": 0.763
+        },
+        {
+          "text": "très",
+          "start": 22.54,
+          "end": 22.56,
+          "confidence": 0.768
+        },
+        {
+          "text": "très",
+          "start": 22.56,
+          "end": 22.58,
+          "confidence": 0.759
+        },
+        {
+          "text": "très",
+          "start": 22.58,
+          "end": 22.6,
+          "confidence": 0.771
+        },
+        {
+          "text": "très",
+          "start": 22.6,
+          "end": 22.62,
+          "confidence": 0.764
+        },
+        {
+          "text": "très",
+          "start": 22.62,
+          "end": 22.64,
+          "confidence": 0.763
+        },
+        {
+          "text": "très",
+          "start": 22.64,
+          "end": 22.66,
+          "confidence": 0.772
+        },
+        {
+          "text": "très",
+          "start": 22.66,
+          "end": 22.68,
+          "confidence": 0.774
+        },
+        {
+          "text": "très",
+          "start": 22.68,
+          "end": 22.7,
+          "confidence": 0.764
+        },
+        {
+          "text": "très",
+          "start": 22.7,
+          "end": 22.72,
+          "confidence": 0.763
+        },
+        {
+          "text": "très",
+          "start": 22.72,
+          "end": 22.74,
+          "confidence": 0.755
+        },
+        {
+          "text": "très",
+          "start": 22.74,
+          "end": 22.76,
+          "confidence": 0.766
+        },
+        {
+          "text": "très",
+          "start": 22.76,
+          "end": 22.78,
+          "confidence": 0.766
+        },
+        {
+          "text": "très",
+          "start": 22.78,
+          "end": 22.8,
+          "confidence": 0.759
+        },
+        {
+          "text": "très",
+          "start": 22.8,
+          "end": 22.82,
+          "confidence": 0.768
+        },
+        {
+          "text": "très",
+          "start": 22.82,
+          "end": 23.04,
+          "confidence": 0.762
+        },
+        {
+          "text": "très",
+          "start": 23.04,
+          "end": 23.06,
+          "confidence": 0.764
+        },
+        {
+          "text": "très",
+          "start": 23.06,
+          "end": 23.08,
+          "confidence": 0.775
+        },
+        {
+          "text": "très",
+          "start": 23.08,
+          "end": 23.1,
+          "confidence": 0.785
+        },
+        {
+          "text": "très",
+          "start": 23.1,
+          "end": 23.5,
+          "confidence": 0.783
+        },
+        {
+          "text": "très",
+          "start": 23.5,
+          "end": 23.52,
+          "confidence": 0.792
+        },
+        {
+          "text": "très",
+          "start": 23.52,
+          "end": 23.54,
+          "confidence": 0.822
+        },
+        {
+          "text": "très",
+          "start": 23.54,
+          "end": 26.7,
+          "confidence": 0.791
+        },
+        {
+          "text": "très",
+          "start": 26.7,
+          "end": 29.98,
+          "confidence": 0.775
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_fr/laugh1.mp3.words.json b/tests/expected/tiny_fr/laugh1.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..eb2fd3f9aad12383bae10efd67b83d1b964fe781
--- /dev/null
+++ b/tests/expected/tiny_fr/laugh1.mp3.words.json
@@ -0,0 +1,81 @@
+{
+  "text": " Je vais vous donner un peu de temps.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.18,
+      "end": 1.72,
+      "text": " Je vais vous donner un peu de temps.",
+      "tokens": [
+        50364,
+        2588,
+        9369,
+        2630,
+        20882,
+        517,
+        5604,
+        368,
+        8827,
+        13,
+        50464
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -1.8613839149475098,
+      "compression_ratio": 0.8181818181818182,
+      "no_speech_prob": 0.4180056154727936,
+      "confidence": 0.103,
+      "words": [
+        {
+          "text": "Je",
+          "start": 0.18,
+          "end": 0.82,
+          "confidence": 0.066
+        },
+        {
+          "text": "vais",
+          "start": 0.82,
+          "end": 1.04,
+          "confidence": 0.128
+        },
+        {
+          "text": "vous",
+          "start": 1.04,
+          "end": 1.06,
+          "confidence": 0.075
+        },
+        {
+          "text": "donner",
+          "start": 1.06,
+          "end": 1.26,
+          "confidence": 0.048
+        },
+        {
+          "text": "un",
+          "start": 1.26,
+          "end": 1.66,
+          "confidence": 0.144
+        },
+        {
+          "text": "peu",
+          "start": 1.66,
+          "end": 1.68,
+          "confidence": 0.091
+        },
+        {
+          "text": "de",
+          "start": 1.68,
+          "end": 1.7,
+          "confidence": 0.625
+        },
+        {
+          "text": "temps.",
+          "start": 1.7,
+          "end": 1.72,
+          "confidence": 0.053
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_fr/laugh2.mp3.words.json b/tests/expected/tiny_fr/laugh2.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..f1d7d6f65ef571345c23b4098d89aad0a0ce1517
--- /dev/null
+++ b/tests/expected/tiny_fr/laugh2.mp3.words.json
@@ -0,0 +1,31 @@
+{
+  "text": " ...",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.18,
+      "end": 0.66,
+      "text": " ...",
+      "tokens": [
+        50364,
+        1097,
+        50414
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -1.2521450519561768,
+      "compression_ratio": 0.2727272727272727,
+      "no_speech_prob": 0.5721203088760376,
+      "confidence": 0.088,
+      "words": [
+        {
+          "text": "...",
+          "start": 0.18,
+          "end": 0.66,
+          "confidence": 0.088
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_fr/punctuations.mp3.words.json b/tests/expected/tiny_fr/punctuations.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..1f16958b6309f821036a0f5a21562201b9249ac3
--- /dev/null
+++ b/tests/expected/tiny_fr/punctuations.mp3.words.json
@@ -0,0 +1,71 @@
+{
+  "text": " Dima, est ce que l'on vole ?",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.42,
+      "end": 2.58,
+      "text": " Dima, est ce que l'on vole ?",
+      "tokens": [
+        50364,
+        413,
+        4775,
+        11,
+        871,
+        1769,
+        631,
+        287,
+        6,
+        266,
+        49877,
+        2506,
+        50494
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.8432660784040179,
+      "compression_ratio": 0.7777777777777778,
+      "no_speech_prob": 0.0010773586109280586,
+      "confidence": 0.456,
+      "words": [
+        {
+          "text": "Dima,",
+          "start": 0.42,
+          "end": 0.84,
+          "confidence": 0.247
+        },
+        {
+          "text": "est",
+          "start": 1.2,
+          "end": 1.4,
+          "confidence": 0.93
+        },
+        {
+          "text": "ce",
+          "start": 1.4,
+          "end": 1.56,
+          "confidence": 0.587
+        },
+        {
+          "text": "que",
+          "start": 1.56,
+          "end": 1.68,
+          "confidence": 0.916
+        },
+        {
+          "text": "l'on",
+          "start": 1.68,
+          "end": 2.02,
+          "confidence": 0.481
+        },
+        {
+          "text": "vole ?",
+          "start": 2.02,
+          "end": 2.58,
+          "confidence": 0.249
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_fr/radio_short.mp3.words.json b/tests/expected/tiny_fr/radio_short.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..89ebc4084194b018f68524608248adb9cce76c01
--- /dev/null
+++ b/tests/expected/tiny_fr/radio_short.mp3.words.json
@@ -0,0 +1,106 @@
+{
+  "text": " ... ... ... ...",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.44,
+      "end": 1.46,
+      "text": " ...",
+      "tokens": [
+        50364,
+        1097,
+        50614
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -1.4211220741271973,
+      "compression_ratio": 0.2727272727272727,
+      "no_speech_prob": 0.5096546411514282,
+      "confidence": 0.224,
+      "words": [
+        {
+          "text": "...",
+          "start": 0.44,
+          "end": 1.46,
+          "confidence": 0.224
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 6000,
+      "start": 60.0,
+      "end": 69.42,
+      "text": " ...",
+      "tokens": [
+        50364,
+        1097,
+        51714
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.965636134147644,
+      "compression_ratio": 0.2727272727272727,
+      "no_speech_prob": 0.8783581256866455,
+      "confidence": 0.464,
+      "words": [
+        {
+          "text": "...",
+          "start": 60.0,
+          "end": 69.42,
+          "confidence": 0.464
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 9000,
+      "start": 105.48,
+      "end": 105.5,
+      "text": " ...",
+      "tokens": [
+        50364,
+        1097,
+        51114
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.8222528457641601,
+      "compression_ratio": 0.2727272727272727,
+      "no_speech_prob": 0.640861988067627,
+      "confidence": 0.842,
+      "words": [
+        {
+          "text": "...",
+          "start": 105.48,
+          "end": 105.5,
+          "confidence": 0.842
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 10500,
+      "start": 106.84,
+      "end": 108.62,
+      "text": " ...",
+      "tokens": [
+        50414,
+        1097,
+        50864
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.923416793346405,
+      "compression_ratio": 0.2727272727272727,
+      "no_speech_prob": 0.8327455520629883,
+      "confidence": 0.47,
+      "words": [
+        {
+          "text": "...",
+          "start": 106.84,
+          "end": 108.62,
+          "confidence": 0.47
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/tiny_fr/smartphone.mp3.words.json b/tests/expected/tiny_fr/smartphone.mp3.words.json
new file mode 100644
index 0000000000000000000000000000000000000000..2cc965cbb861935e22aec7bb1065ee2edbc145c8
--- /dev/null
+++ b/tests/expected/tiny_fr/smartphone.mp3.words.json
@@ -0,0 +1,5091 @@
+{
+  "text": " C'est évidence que dit Nicolas, mais je me l'étais jamais formulé comme ça. Ce qui fait la force du smartphone, c'est pas seulement la cumulation des fonctions, mais la manière dans quelques interagues entraîne. Et il est d'ailleurs, c'est la photo c'est hyper convaincant. Alors évidemment, il faudrait ajouter les interfaces les grand-attachilles à été beaucoup très souvent mentionnées. Mais bon, il faudrait que les profites aussi de 20 ans pendant l'été, les ordinateurs nous ont appris à piquer sur des icônes, sauf que, alors le smartphone ajoute le toucher, qui rend le contact plus direct, plus sensible. Et puis, évidemment, il faudrait parler aussi des applications qui permettent de contourner le côté tout flu de la navigation web pour aller directement en but. Bref, tout ça, ce sont les conditions qui permettent de créer cette objet, en Nicolas, dit qu'il est très symbolablement inédit dans l'histoire de l'humanité. Mais ça s'assoulait d'une autre interrogation. Est-ce que le fait que cette objet soit inédit un d'huits que notre rapport a lui est aussi un rapport inédit ? Est-ce que le rapport qu'on a au sein de foi n'est comparable à celui qu'on entretenait à d'autres objectes techniques comme la voiture ou le téléphone ? Il n'y a pas d'équivalent. On s'est espèrent de nous voter dans la relation à l'objet. C'est facilement éterricion. Parce que la passion de l'utilisateur et ses affices a dépendance, cette objet d'un lieu en fait, une espèce de relation de médiation avec le monde qui rendent encore avec la maille de celles formes de rogeur. Donc, à objets inédits, rapport inédits. Et, ce rapport, si j'en prends Nicolas, frère caractérisée par un mélange de dépendance et de rogeur. Bon, en vrai, il faudrait remonter très, très filmant tout l'histoire des objectes techniques et de leur infertion dans nos vieux pour déterminer si ce rapport est totalement inédit. Mais j'ai l'impression comme ça que Nicolas se trompe pas vraiment. Pour autant, je sache. Il y a eu plein de discussions autour de la voiture ou même du téléphone. Mais, la dépense n'était pas du même mort, donc le rejet n'en plus n'était pas du même mort. On peut adorer sa bagnure. On a par besoin pour plein de choses. Et là, le soir, quand on va se coucher, on la laisse. On la pade en la main quand on est colis, qu'on n'a même pas au chiot. On pouvait être émervé par son mome qui occupeait la ligne de téléphone pendant une heure chaque soir pour discuter avec un copain. Mais ça ne ressemble pas à ce qu'on peut ressentir à voir même mome aujourd'hui. Continuellement avec son smartphone dans la main, comme c'était une sorte de estimateur extère de tomber de lâcher à l'éantrénée, ça m'a eu immédiate. Bon, je dis ça pour le mome, mais évidemment, va là, bon aussi. Donc, rapport immédiate d'accord. Mais pourquoi, à ton impression qu'on en sortira, j'amé? Et puis, il faut en remettre la faute sur les gens qui ont créé cette critique merveilleux et diabolique et diabolique par que merveilleux. Les économistes parlent de dépendance du santé. Ces vidéos, en fait, on est un santé qui a été étabis, un soit mon termine, en marchand dessus, soit des finissants débordes, des finissants, une signalétique.",
+  "segments": [
+    {
+      "id": 0,
+      "seek": 0,
+      "start": 0.42,
+      "end": 3.66,
+      "text": " C'est évidence que dit Nicolas, mais je me l'étais jamais formulé comme ça.",
+      "tokens": [
+        50364,
+        383,
+        6,
+        377,
+        20090,
+        2778,
+        631,
+        6176,
+        38268,
+        11,
+        2420,
+        1506,
+        385,
+        287,
+        6,
+        22824,
+        14540,
+        49990,
+        526,
+        5173,
+        2788,
+        13,
+        50545
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5389881480823864,
+      "compression_ratio": 1.6505681818181819,
+      "no_speech_prob": 0.14073368906974792,
+      "confidence": 0.709,
+      "words": [
+        {
+          "text": "C'est",
+          "start": 0.42,
+          "end": 0.68,
+          "confidence": 0.849
+        },
+        {
+          "text": "évidence",
+          "start": 0.68,
+          "end": 0.94,
+          "confidence": 0.368
+        },
+        {
+          "text": "que",
+          "start": 0.94,
+          "end": 1.08,
+          "confidence": 0.883
+        },
+        {
+          "text": "dit",
+          "start": 1.08,
+          "end": 1.2,
+          "confidence": 0.343
+        },
+        {
+          "text": "Nicolas,",
+          "start": 1.2,
+          "end": 1.44,
+          "confidence": 0.921
+        },
+        {
+          "text": "mais",
+          "start": 1.88,
+          "end": 2.14,
+          "confidence": 0.914
+        },
+        {
+          "text": "je",
+          "start": 2.14,
+          "end": 2.26,
+          "confidence": 0.778
+        },
+        {
+          "text": "me",
+          "start": 2.26,
+          "end": 2.34,
+          "confidence": 0.954
+        },
+        {
+          "text": "l'étais",
+          "start": 2.34,
+          "end": 2.58,
+          "confidence": 0.72
+        },
+        {
+          "text": "jamais",
+          "start": 2.58,
+          "end": 2.86,
+          "confidence": 0.946
+        },
+        {
+          "text": "formulé",
+          "start": 2.86,
+          "end": 3.26,
+          "confidence": 0.53
+        },
+        {
+          "text": "comme",
+          "start": 3.26,
+          "end": 3.46,
+          "confidence": 0.968
+        },
+        {
+          "text": "ça.",
+          "start": 3.46,
+          "end": 3.66,
+          "confidence": 0.96
+        }
+      ]
+    },
+    {
+      "id": 1,
+      "seek": 0,
+      "start": 4.14,
+      "end": 8.9,
+      "text": " Ce qui fait la force du smartphone, c'est pas seulement la cumulation des fonctions, mais la manière",
+      "tokens": [
+        50545,
+        8257,
+        1956,
+        3887,
+        635,
+        3464,
+        1581,
+        13307,
+        11,
+        269,
+        6,
+        377,
+        1736,
+        27772,
+        635,
+        12713,
+        2776,
+        730,
+        17290,
+        3916,
+        11,
+        2420,
+        635,
+        22267,
+        50806
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5389881480823864,
+      "compression_ratio": 1.6505681818181819,
+      "no_speech_prob": 0.14073368906974792,
+      "confidence": 0.789,
+      "words": [
+        {
+          "text": "Ce",
+          "start": 4.14,
+          "end": 4.26,
+          "confidence": 0.392
+        },
+        {
+          "text": "qui",
+          "start": 4.26,
+          "end": 4.38,
+          "confidence": 0.94
+        },
+        {
+          "text": "fait",
+          "start": 4.38,
+          "end": 4.56,
+          "confidence": 0.732
+        },
+        {
+          "text": "la",
+          "start": 4.56,
+          "end": 4.72,
+          "confidence": 0.988
+        },
+        {
+          "text": "force",
+          "start": 4.72,
+          "end": 5.02,
+          "confidence": 0.93
+        },
+        {
+          "text": "du",
+          "start": 5.02,
+          "end": 5.2,
+          "confidence": 0.938
+        },
+        {
+          "text": "smartphone,",
+          "start": 5.2,
+          "end": 5.58,
+          "confidence": 0.909
+        },
+        {
+          "text": "c'est",
+          "start": 5.9,
+          "end": 6.2,
+          "confidence": 0.947
+        },
+        {
+          "text": "pas",
+          "start": 6.2,
+          "end": 6.26,
+          "confidence": 0.983
+        },
+        {
+          "text": "seulement",
+          "start": 6.26,
+          "end": 6.6,
+          "confidence": 0.993
+        },
+        {
+          "text": "la",
+          "start": 6.6,
+          "end": 6.8,
+          "confidence": 0.633
+        },
+        {
+          "text": "cumulation",
+          "start": 6.8,
+          "end": 7.34,
+          "confidence": 0.689
+        },
+        {
+          "text": "des",
+          "start": 7.34,
+          "end": 7.56,
+          "confidence": 0.792
+        },
+        {
+          "text": "fonctions,",
+          "start": 7.56,
+          "end": 8.14,
+          "confidence": 0.834
+        },
+        {
+          "text": "mais",
+          "start": 8.38,
+          "end": 8.5,
+          "confidence": 0.668
+        },
+        {
+          "text": "la",
+          "start": 8.5,
+          "end": 8.62,
+          "confidence": 0.719
+        },
+        {
+          "text": "manière",
+          "start": 8.62,
+          "end": 8.9,
+          "confidence": 0.498
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "seek": 0,
+      "start": 8.9,
+      "end": 10.98,
+      "text": " dans quelques interagues entraîne.",
+      "tokens": [
+        50806,
+        2680,
+        16597,
+        728,
+        559,
+        1247,
+        22284,
+        24741,
+        13,
+        50906
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5389881480823864,
+      "compression_ratio": 1.6505681818181819,
+      "no_speech_prob": 0.14073368906974792,
+      "confidence": 0.303,
+      "words": [
+        {
+          "text": "dans",
+          "start": 8.9,
+          "end": 9.06,
+          "confidence": 0.284
+        },
+        {
+          "text": "quelques",
+          "start": 9.06,
+          "end": 9.28,
+          "confidence": 0.281
+        },
+        {
+          "text": "interagues",
+          "start": 9.28,
+          "end": 10.38,
+          "confidence": 0.246
+        },
+        {
+          "text": "entraîne.",
+          "start": 10.38,
+          "end": 10.98,
+          "confidence": 0.446
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "seek": 0,
+      "start": 11.0,
+      "end": 12.96,
+      "text": " Et il est d'ailleurs, c'est la photo c'est hyper convaincant.",
+      "tokens": [
+        50906,
+        3790,
+        1930,
+        871,
+        274,
+        6,
+        19400,
+        11,
+        269,
+        6,
+        377,
+        635,
+        5052,
+        269,
+        6,
+        377,
+        9848,
+        3754,
+        491,
+        66,
+        394,
+        13,
+        51006
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5389881480823864,
+      "compression_ratio": 1.6505681818181819,
+      "no_speech_prob": 0.14073368906974792,
+      "confidence": 0.63,
+      "words": [
+        {
+          "text": "Et",
+          "start": 11.0,
+          "end": 11.12,
+          "confidence": 0.36
+        },
+        {
+          "text": "il",
+          "start": 11.12,
+          "end": 11.28,
+          "confidence": 0.144
+        },
+        {
+          "text": "est",
+          "start": 11.28,
+          "end": 11.38,
+          "confidence": 0.241
+        },
+        {
+          "text": "d'ailleurs,",
+          "start": 11.38,
+          "end": 11.6,
+          "confidence": 0.904
+        },
+        {
+          "text": "c'est",
+          "start": 11.7,
+          "end": 11.78,
+          "confidence": 0.886
+        },
+        {
+          "text": "la",
+          "start": 11.78,
+          "end": 11.8,
+          "confidence": 0.969
+        },
+        {
+          "text": "photo",
+          "start": 11.8,
+          "end": 12.02,
+          "confidence": 0.809
+        },
+        {
+          "text": "c'est",
+          "start": 12.02,
+          "end": 12.26,
+          "confidence": 0.785
+        },
+        {
+          "text": "hyper",
+          "start": 12.26,
+          "end": 12.46,
+          "confidence": 0.938
+        },
+        {
+          "text": "convaincant.",
+          "start": 12.46,
+          "end": 12.96,
+          "confidence": 0.51
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "seek": 0,
+      "start": 13.3,
+      "end": 18.8,
+      "text": " Alors évidemment, il faudrait ajouter les interfaces les grand-attachilles à été beaucoup très souvent",
+      "tokens": [
+        51006,
+        9946,
+        24724,
+        11,
+        1930,
+        38694,
+        8645,
+        17680,
+        23985,
+        1512,
+        28416,
+        1512,
+        2697,
+        12,
+        1591,
+        608,
+        14835,
+        1531,
+        8862,
+        8796,
+        5732,
+        20847,
+        51306
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5389881480823864,
+      "compression_ratio": 1.6505681818181819,
+      "no_speech_prob": 0.14073368906974792,
+      "confidence": 0.532,
+      "words": [
+        {
+          "text": "Alors",
+          "start": 13.3,
+          "end": 13.56,
+          "confidence": 0.894
+        },
+        {
+          "text": "évidemment,",
+          "start": 13.56,
+          "end": 13.82,
+          "confidence": 0.778
+        },
+        {
+          "text": "il",
+          "start": 14.38,
+          "end": 14.4,
+          "confidence": 0.964
+        },
+        {
+          "text": "faudrait",
+          "start": 14.4,
+          "end": 14.76,
+          "confidence": 0.856
+        },
+        {
+          "text": "ajouter",
+          "start": 14.76,
+          "end": 15.38,
+          "confidence": 0.883
+        },
+        {
+          "text": "les",
+          "start": 15.38,
+          "end": 15.6,
+          "confidence": 0.934
+        },
+        {
+          "text": "interfaces",
+          "start": 15.6,
+          "end": 16.0,
+          "confidence": 0.38
+        },
+        {
+          "text": "les",
+          "start": 16.0,
+          "end": 16.5,
+          "confidence": 0.463
+        },
+        {
+          "text": "grand-attachilles",
+          "start": 16.5,
+          "end": 17.16,
+          "confidence": 0.213
+        },
+        {
+          "text": "à",
+          "start": 17.16,
+          "end": 17.32,
+          "confidence": 0.406
+        },
+        {
+          "text": "été",
+          "start": 17.32,
+          "end": 17.72,
+          "confidence": 0.894
+        },
+        {
+          "text": "beaucoup",
+          "start": 17.72,
+          "end": 18.28,
+          "confidence": 0.797
+        },
+        {
+          "text": "très",
+          "start": 18.28,
+          "end": 18.64,
+          "confidence": 0.493
+        },
+        {
+          "text": "souvent",
+          "start": 18.64,
+          "end": 18.8,
+          "confidence": 0.822
+        }
+      ]
+    },
+    {
+      "id": 5,
+      "seek": 0,
+      "start": 18.8,
+      "end": 19.84,
+      "text": " mentionnées.",
+      "tokens": [
+        51306,
+        2152,
+        77,
+        6836,
+        13,
+        51356
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5389881480823864,
+      "compression_ratio": 1.6505681818181819,
+      "no_speech_prob": 0.14073368906974792,
+      "confidence": 0.626,
+      "words": [
+        {
+          "text": "mentionnées.",
+          "start": 18.8,
+          "end": 19.84,
+          "confidence": 0.626
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "seek": 0,
+      "start": 20.02,
+      "end": 23.58,
+      "text": " Mais bon, il faudrait que les profites aussi de 20 ans pendant l'été, les ordinateurs",
+      "tokens": [
+        51356,
+        6313,
+        4428,
+        11,
+        1930,
+        38694,
+        8645,
+        631,
+        1512,
+        1740,
+        3324,
+        6212,
+        368,
+        945,
+        1567,
+        17338,
+        287,
+        6,
+        21210,
+        11,
+        1512,
+        4792,
+        13923,
+        2156,
+        51543
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5389881480823864,
+      "compression_ratio": 1.6505681818181819,
+      "no_speech_prob": 0.14073368906974792,
+      "confidence": 0.658,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 20.02,
+          "end": 20.26,
+          "confidence": 0.98
+        },
+        {
+          "text": "bon,",
+          "start": 20.26,
+          "end": 20.46,
+          "confidence": 0.568
+        },
+        {
+          "text": "il",
+          "start": 20.6,
+          "end": 20.68,
+          "confidence": 0.975
+        },
+        {
+          "text": "faudrait",
+          "start": 20.68,
+          "end": 20.78,
+          "confidence": 0.771
+        },
+        {
+          "text": "que",
+          "start": 20.78,
+          "end": 20.92,
+          "confidence": 0.388
+        },
+        {
+          "text": "les",
+          "start": 20.92,
+          "end": 20.96,
+          "confidence": 0.22
+        },
+        {
+          "text": "profites",
+          "start": 20.96,
+          "end": 21.36,
+          "confidence": 0.57
+        },
+        {
+          "text": "aussi",
+          "start": 21.36,
+          "end": 21.72,
+          "confidence": 0.52
+        },
+        {
+          "text": "de",
+          "start": 21.72,
+          "end": 21.92,
+          "confidence": 0.492
+        },
+        {
+          "text": "20",
+          "start": 21.92,
+          "end": 22.14,
+          "confidence": 0.915
+        },
+        {
+          "text": "ans",
+          "start": 22.14,
+          "end": 22.32,
+          "confidence": 0.942
+        },
+        {
+          "text": "pendant",
+          "start": 22.32,
+          "end": 22.52,
+          "confidence": 0.916
+        },
+        {
+          "text": "l'été,",
+          "start": 22.52,
+          "end": 22.86,
+          "confidence": 0.48
+        },
+        {
+          "text": "les",
+          "start": 22.98,
+          "end": 23.1,
+          "confidence": 0.903
+        },
+        {
+          "text": "ordinateurs",
+          "start": 23.1,
+          "end": 23.58,
+          "confidence": 0.946
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "seek": 0,
+      "start": 23.58,
+      "end": 28.07,
+      "text": " nous ont appris à piquer sur des icônes, sauf que, alors le smartphone ajoute le toucher,",
+      "tokens": [
+        51543,
+        4666,
+        6592,
+        724,
+        5714,
+        1531,
+        280,
+        23909,
+        1022,
+        730,
+        4376,
+        2851,
+        4081,
+        11,
+        601,
+        2947,
+        631,
+        11,
+        11246,
+        476,
+        13307,
+        17680,
+        14040,
+        476,
+        2557,
+        260,
+        11,
+        51766
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5389881480823864,
+      "compression_ratio": 1.6505681818181819,
+      "no_speech_prob": 0.14073368906974792,
+      "confidence": 0.656,
+      "words": [
+        {
+          "text": "nous",
+          "start": 23.58,
+          "end": 23.78,
+          "confidence": 0.767
+        },
+        {
+          "text": "ont",
+          "start": 23.78,
+          "end": 23.9,
+          "confidence": 0.98
+        },
+        {
+          "text": "appris",
+          "start": 23.9,
+          "end": 24.12,
+          "confidence": 0.952
+        },
+        {
+          "text": "à",
+          "start": 24.12,
+          "end": 24.26,
+          "confidence": 0.34
+        },
+        {
+          "text": "piquer",
+          "start": 24.26,
+          "end": 24.54,
+          "confidence": 0.449
+        },
+        {
+          "text": "sur",
+          "start": 24.54,
+          "end": 24.72,
+          "confidence": 0.816
+        },
+        {
+          "text": "des",
+          "start": 24.72,
+          "end": 24.9,
+          "confidence": 0.96
+        },
+        {
+          "text": "icônes,",
+          "start": 24.9,
+          "end": 25.56,
+          "confidence": 0.599
+        },
+        {
+          "text": "sauf",
+          "start": 25.64,
+          "end": 25.8,
+          "confidence": 0.522
+        },
+        {
+          "text": "que,",
+          "start": 25.8,
+          "end": 26.36,
+          "confidence": 0.915
+        },
+        {
+          "text": "alors",
+          "start": 26.36,
+          "end": 26.58,
+          "confidence": 0.396
+        },
+        {
+          "text": "le",
+          "start": 26.58,
+          "end": 26.72,
+          "confidence": 0.824
+        },
+        {
+          "text": "smartphone",
+          "start": 26.72,
+          "end": 27.0,
+          "confidence": 0.977
+        },
+        {
+          "text": "ajoute",
+          "start": 27.0,
+          "end": 27.5,
+          "confidence": 0.674
+        },
+        {
+          "text": "le",
+          "start": 27.5,
+          "end": 27.62,
+          "confidence": 0.552
+        },
+        {
+          "text": "toucher,",
+          "start": 27.62,
+          "end": 28.07,
+          "confidence": 0.631
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "seek": 2804,
+      "start": 28.07,
+      "end": 30.6,
+      "text": " qui rend le contact plus direct, plus sensible.",
+      "tokens": [
+        50364,
+        1956,
+        6125,
+        476,
+        3385,
+        1804,
+        2047,
+        11,
+        1804,
+        25380,
+        13,
+        50496
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4256427271836469,
+      "compression_ratio": 1.7156549520766773,
+      "no_speech_prob": 0.12921307981014252,
+      "confidence": 0.742,
+      "words": [
+        {
+          "text": "qui",
+          "start": 28.07,
+          "end": 28.26,
+          "confidence": 0.305
+        },
+        {
+          "text": "rend",
+          "start": 28.26,
+          "end": 28.5,
+          "confidence": 0.763
+        },
+        {
+          "text": "le",
+          "start": 28.5,
+          "end": 28.72,
+          "confidence": 0.988
+        },
+        {
+          "text": "contact",
+          "start": 28.72,
+          "end": 29.06,
+          "confidence": 0.817
+        },
+        {
+          "text": "plus",
+          "start": 29.06,
+          "end": 29.48,
+          "confidence": 0.84
+        },
+        {
+          "text": "direct,",
+          "start": 29.48,
+          "end": 30.02,
+          "confidence": 0.944
+        },
+        {
+          "text": "plus",
+          "start": 30.18,
+          "end": 30.24,
+          "confidence": 0.992
+        },
+        {
+          "text": "sensible.",
+          "start": 30.24,
+          "end": 30.6,
+          "confidence": 0.618
+        }
+      ]
+    },
+    {
+      "id": 9,
+      "seek": 2804,
+      "start": 31.1,
+      "end": 34.76,
+      "text": " Et puis, évidemment, il faudrait parler aussi des applications qui permettent de contourner le côté",
+      "tokens": [
+        50496,
+        3790,
+        9093,
+        11,
+        24724,
+        11,
+        1930,
+        38694,
+        8645,
+        16421,
+        6212,
+        730,
+        5821,
+        1956,
+        21540,
+        317,
+        368,
+        21234,
+        1193,
+        476,
+        18437,
+        50698
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4256427271836469,
+      "compression_ratio": 1.7156549520766773,
+      "no_speech_prob": 0.12921307981014252,
+      "confidence": 0.777,
+      "words": [
+        {
+          "text": "Et",
+          "start": 31.1,
+          "end": 31.24,
+          "confidence": 0.949
+        },
+        {
+          "text": "puis,",
+          "start": 31.24,
+          "end": 31.36,
+          "confidence": 0.721
+        },
+        {
+          "text": "évidemment,",
+          "start": 31.42,
+          "end": 31.62,
+          "confidence": 0.213
+        },
+        {
+          "text": "il",
+          "start": 31.7,
+          "end": 31.76,
+          "confidence": 0.959
+        },
+        {
+          "text": "faudrait",
+          "start": 31.76,
+          "end": 31.94,
+          "confidence": 0.994
+        },
+        {
+          "text": "parler",
+          "start": 31.94,
+          "end": 32.14,
+          "confidence": 0.847
+        },
+        {
+          "text": "aussi",
+          "start": 32.14,
+          "end": 32.36,
+          "confidence": 0.925
+        },
+        {
+          "text": "des",
+          "start": 32.36,
+          "end": 32.46,
+          "confidence": 0.921
+        },
+        {
+          "text": "applications",
+          "start": 32.46,
+          "end": 32.88,
+          "confidence": 0.857
+        },
+        {
+          "text": "qui",
+          "start": 32.88,
+          "end": 33.2,
+          "confidence": 0.663
+        },
+        {
+          "text": "permettent",
+          "start": 33.2,
+          "end": 33.8,
+          "confidence": 0.952
+        },
+        {
+          "text": "de",
+          "start": 33.8,
+          "end": 33.96,
+          "confidence": 0.951
+        },
+        {
+          "text": "contourner",
+          "start": 33.96,
+          "end": 34.4,
+          "confidence": 0.721
+        },
+        {
+          "text": "le",
+          "start": 34.4,
+          "end": 34.52,
+          "confidence": 0.654
+        },
+        {
+          "text": "côté",
+          "start": 34.52,
+          "end": 34.76,
+          "confidence": 0.641
+        }
+      ]
+    },
+    {
+      "id": 10,
+      "seek": 2804,
+      "start": 34.8,
+      "end": 37.86,
+      "text": " tout flu de la navigation web pour aller directement en but.",
+      "tokens": [
+        50698,
+        3486,
+        5029,
+        368,
+        635,
+        17346,
+        3670,
+        2016,
+        8722,
+        37297,
+        465,
+        457,
+        13,
+        50860
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4256427271836469,
+      "compression_ratio": 1.7156549520766773,
+      "no_speech_prob": 0.12921307981014252,
+      "confidence": 0.735,
+      "words": [
+        {
+          "text": "tout",
+          "start": 34.8,
+          "end": 35.04,
+          "confidence": 0.945
+        },
+        {
+          "text": "flu",
+          "start": 35.04,
+          "end": 35.32,
+          "confidence": 0.484
+        },
+        {
+          "text": "de",
+          "start": 35.32,
+          "end": 35.64,
+          "confidence": 0.35
+        },
+        {
+          "text": "la",
+          "start": 35.64,
+          "end": 35.78,
+          "confidence": 0.921
+        },
+        {
+          "text": "navigation",
+          "start": 35.78,
+          "end": 36.24,
+          "confidence": 0.903
+        },
+        {
+          "text": "web",
+          "start": 36.24,
+          "end": 36.64,
+          "confidence": 0.913
+        },
+        {
+          "text": "pour",
+          "start": 36.64,
+          "end": 36.84,
+          "confidence": 0.57
+        },
+        {
+          "text": "aller",
+          "start": 36.84,
+          "end": 37.06,
+          "confidence": 0.991
+        },
+        {
+          "text": "directement",
+          "start": 37.06,
+          "end": 37.48,
+          "confidence": 0.981
+        },
+        {
+          "text": "en",
+          "start": 37.48,
+          "end": 37.7,
+          "confidence": 0.654
+        },
+        {
+          "text": "but.",
+          "start": 37.7,
+          "end": 37.86,
+          "confidence": 0.768
+        }
+      ]
+    },
+    {
+      "id": 11,
+      "seek": 2804,
+      "start": 38.78,
+      "end": 43.12,
+      "text": " Bref, tout ça, ce sont les conditions qui permettent de créer cette objet, en Nicolas,",
+      "tokens": [
+        50860,
+        49957,
+        11,
+        3486,
+        2788,
+        11,
+        1769,
+        4900,
+        1512,
+        4487,
+        1956,
+        21540,
+        317,
+        368,
+        32062,
+        5550,
+        14964,
+        11,
+        465,
+        38268,
+        11,
+        51121
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4256427271836469,
+      "compression_ratio": 1.7156549520766773,
+      "no_speech_prob": 0.12921307981014252,
+      "confidence": 0.737,
+      "words": [
+        {
+          "text": "Bref,",
+          "start": 38.78,
+          "end": 38.8,
+          "confidence": 0.972
+        },
+        {
+          "text": "tout",
+          "start": 38.84,
+          "end": 39.04,
+          "confidence": 0.817
+        },
+        {
+          "text": "ça,",
+          "start": 39.04,
+          "end": 39.46,
+          "confidence": 0.984
+        },
+        {
+          "text": "ce",
+          "start": 39.54,
+          "end": 39.76,
+          "confidence": 0.905
+        },
+        {
+          "text": "sont",
+          "start": 39.76,
+          "end": 39.96,
+          "confidence": 0.98
+        },
+        {
+          "text": "les",
+          "start": 39.96,
+          "end": 40.1,
+          "confidence": 0.982
+        },
+        {
+          "text": "conditions",
+          "start": 40.1,
+          "end": 40.64,
+          "confidence": 0.956
+        },
+        {
+          "text": "qui",
+          "start": 40.64,
+          "end": 40.96,
+          "confidence": 0.995
+        },
+        {
+          "text": "permettent",
+          "start": 40.96,
+          "end": 41.58,
+          "confidence": 0.994
+        },
+        {
+          "text": "de",
+          "start": 41.58,
+          "end": 41.64,
+          "confidence": 0.993
+        },
+        {
+          "text": "créer",
+          "start": 41.64,
+          "end": 42.08,
+          "confidence": 0.91
+        },
+        {
+          "text": "cette",
+          "start": 42.08,
+          "end": 42.34,
+          "confidence": 0.473
+        },
+        {
+          "text": "objet,",
+          "start": 42.34,
+          "end": 42.64,
+          "confidence": 0.235
+        },
+        {
+          "text": "en",
+          "start": 42.7,
+          "end": 42.84,
+          "confidence": 0.221
+        },
+        {
+          "text": "Nicolas,",
+          "start": 42.84,
+          "end": 43.12,
+          "confidence": 0.537
+        }
+      ]
+    },
+    {
+      "id": 12,
+      "seek": 2804,
+      "start": 43.12,
+      "end": 46.58,
+      "text": " dit qu'il est très symbolablement inédit dans l'histoire de l'humanité.",
+      "tokens": [
+        51121,
+        6176,
+        421,
+        6,
+        388,
+        871,
+        5732,
+        5986,
+        712,
+        518,
+        294,
+        7811,
+        270,
+        2680,
+        287,
+        6,
+        29093,
+        368,
+        287,
+        6,
+        18796,
+        5066,
+        13,
+        51290
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4256427271836469,
+      "compression_ratio": 1.7156549520766773,
+      "no_speech_prob": 0.12921307981014252,
+      "confidence": 0.717,
+      "words": [
+        {
+          "text": "dit",
+          "start": 43.12,
+          "end": 43.56,
+          "confidence": 0.696
+        },
+        {
+          "text": "qu'il",
+          "start": 43.56,
+          "end": 43.76,
+          "confidence": 0.958
+        },
+        {
+          "text": "est",
+          "start": 43.76,
+          "end": 43.9,
+          "confidence": 0.849
+        },
+        {
+          "text": "très",
+          "start": 43.9,
+          "end": 44.08,
+          "confidence": 0.443
+        },
+        {
+          "text": "symbolablement",
+          "start": 44.08,
+          "end": 44.86,
+          "confidence": 0.321
+        },
+        {
+          "text": "inédit",
+          "start": 44.86,
+          "end": 45.54,
+          "confidence": 0.655
+        },
+        {
+          "text": "dans",
+          "start": 45.54,
+          "end": 45.74,
+          "confidence": 0.817
+        },
+        {
+          "text": "l'histoire",
+          "start": 45.74,
+          "end": 46.02,
+          "confidence": 0.824
+        },
+        {
+          "text": "de",
+          "start": 46.02,
+          "end": 46.14,
+          "confidence": 0.983
+        },
+        {
+          "text": "l'humanité.",
+          "start": 46.14,
+          "end": 46.58,
+          "confidence": 0.99
+        }
+      ]
+    },
+    {
+      "id": 13,
+      "seek": 2804,
+      "start": 47.06,
+      "end": 48.76,
+      "text": " Mais ça s'assoulait d'une autre interrogation.",
+      "tokens": [
+        51290,
+        6313,
+        2788,
+        262,
+        6,
+        640,
+        263,
+        35235,
+        274,
+        6,
+        2613,
+        15081,
+        24871,
+        399,
+        13,
+        51402
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4256427271836469,
+      "compression_ratio": 1.7156549520766773,
+      "no_speech_prob": 0.12921307981014252,
+      "confidence": 0.717,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 47.06,
+          "end": 47.24,
+          "confidence": 0.928
+        },
+        {
+          "text": "ça",
+          "start": 47.24,
+          "end": 47.48,
+          "confidence": 0.75
+        },
+        {
+          "text": "s'assoulait",
+          "start": 47.48,
+          "end": 47.84,
+          "confidence": 0.616
+        },
+        {
+          "text": "d'une",
+          "start": 47.84,
+          "end": 48.08,
+          "confidence": 0.674
+        },
+        {
+          "text": "autre",
+          "start": 48.08,
+          "end": 48.18,
+          "confidence": 0.964
+        },
+        {
+          "text": "interrogation.",
+          "start": 48.18,
+          "end": 48.76,
+          "confidence": 0.855
+        }
+      ]
+    },
+    {
+      "id": 14,
+      "seek": 2804,
+      "start": 49.42,
+      "end": 54.93,
+      "text": " Est-ce que le fait que cette objet soit inédit un d'huits que notre rapport a lui est aussi un rapport",
+      "tokens": [
+        51402,
+        4410,
+        12,
+        384,
+        631,
+        476,
+        3887,
+        631,
+        5550,
+        14964,
+        12703,
+        294,
+        7811,
+        270,
+        517,
+        274,
+        6,
+        12086,
+        1208,
+        631,
+        10349,
+        18018,
+        257,
+        8783,
+        871,
+        6212,
+        517,
+        18018,
+        51710
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4256427271836469,
+      "compression_ratio": 1.7156549520766773,
+      "no_speech_prob": 0.12921307981014252,
+      "confidence": 0.704,
+      "words": [
+        {
+          "text": "Est-ce",
+          "start": 49.42,
+          "end": 49.7,
+          "confidence": 0.919
+        },
+        {
+          "text": "que",
+          "start": 49.7,
+          "end": 49.74,
+          "confidence": 0.99
+        },
+        {
+          "text": "le",
+          "start": 49.74,
+          "end": 49.82,
+          "confidence": 0.871
+        },
+        {
+          "text": "fait",
+          "start": 49.82,
+          "end": 50.02,
+          "confidence": 0.945
+        },
+        {
+          "text": "que",
+          "start": 50.02,
+          "end": 50.16,
+          "confidence": 0.923
+        },
+        {
+          "text": "cette",
+          "start": 50.16,
+          "end": 50.3,
+          "confidence": 0.943
+        },
+        {
+          "text": "objet",
+          "start": 50.3,
+          "end": 50.64,
+          "confidence": 0.963
+        },
+        {
+          "text": "soit",
+          "start": 50.64,
+          "end": 51.1,
+          "confidence": 0.99
+        },
+        {
+          "text": "inédit",
+          "start": 51.1,
+          "end": 51.82,
+          "confidence": 0.928
+        },
+        {
+          "text": "un",
+          "start": 51.82,
+          "end": 52.08,
+          "confidence": 0.511
+        },
+        {
+          "text": "d'huits",
+          "start": 52.08,
+          "end": 52.34,
+          "confidence": 0.246
+        },
+        {
+          "text": "que",
+          "start": 52.34,
+          "end": 52.44,
+          "confidence": 0.974
+        },
+        {
+          "text": "notre",
+          "start": 52.44,
+          "end": 52.66,
+          "confidence": 0.992
+        },
+        {
+          "text": "rapport",
+          "start": 52.66,
+          "end": 53.24,
+          "confidence": 0.779
+        },
+        {
+          "text": "a",
+          "start": 53.24,
+          "end": 53.5,
+          "confidence": 0.57
+        },
+        {
+          "text": "lui",
+          "start": 53.5,
+          "end": 53.7,
+          "confidence": 0.701
+        },
+        {
+          "text": "est",
+          "start": 53.7,
+          "end": 54.04,
+          "confidence": 0.879
+        },
+        {
+          "text": "aussi",
+          "start": 54.04,
+          "end": 54.52,
+          "confidence": 0.815
+        },
+        {
+          "text": "un",
+          "start": 54.52,
+          "end": 54.7,
+          "confidence": 0.48
+        },
+        {
+          "text": "rapport",
+          "start": 54.7,
+          "end": 54.93,
+          "confidence": 0.952
+        }
+      ]
+    },
+    {
+      "id": 15,
+      "seek": 2804,
+      "start": 54.93,
+      "end": 55.88,
+      "text": " inédit ?",
+      "tokens": [
+        51710,
+        294,
+        7811,
+        270,
+        2506,
+        51760
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.4256427271836469,
+      "compression_ratio": 1.7156549520766773,
+      "no_speech_prob": 0.12921307981014252,
+      "confidence": 0.86,
+      "words": [
+        {
+          "text": "inédit ?",
+          "start": 54.93,
+          "end": 55.88,
+          "confidence": 0.86
+        }
+      ]
+    },
+    {
+      "id": 16,
+      "seek": 5596,
+      "start": 55.96,
+      "end": 59.36,
+      "text": " Est-ce que le rapport qu'on a au sein de foi n'est comparable à celui qu'on entretenait",
+      "tokens": [
+        50364,
+        4410,
+        12,
+        384,
+        631,
+        476,
+        18018,
+        421,
+        6,
+        266,
+        257,
+        1609,
+        6195,
+        368,
+        6901,
+        297,
+        6,
+        377,
+        25323,
+        1531,
+        22829,
+        421,
+        6,
+        266,
+        3962,
+        1147,
+        1001,
+        50530
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6293370928083147,
+      "compression_ratio": 1.5749128919860627,
+      "no_speech_prob": 0.21948836743831635,
+      "confidence": 0.62,
+      "words": [
+        {
+          "text": "Est-ce",
+          "start": 55.96,
+          "end": 56.38,
+          "confidence": 0.553
+        },
+        {
+          "text": "que",
+          "start": 56.38,
+          "end": 56.44,
+          "confidence": 0.892
+        },
+        {
+          "text": "le",
+          "start": 56.44,
+          "end": 56.58,
+          "confidence": 0.982
+        },
+        {
+          "text": "rapport",
+          "start": 56.58,
+          "end": 56.9,
+          "confidence": 0.999
+        },
+        {
+          "text": "qu'on",
+          "start": 56.9,
+          "end": 57.14,
+          "confidence": 0.902
+        },
+        {
+          "text": "a",
+          "start": 57.14,
+          "end": 57.2,
+          "confidence": 0.959
+        },
+        {
+          "text": "au",
+          "start": 57.2,
+          "end": 57.28,
+          "confidence": 0.273
+        },
+        {
+          "text": "sein",
+          "start": 57.28,
+          "end": 57.42,
+          "confidence": 0.17
+        },
+        {
+          "text": "de",
+          "start": 57.42,
+          "end": 57.56,
+          "confidence": 0.229
+        },
+        {
+          "text": "foi",
+          "start": 57.56,
+          "end": 57.58,
+          "confidence": 0.121
+        },
+        {
+          "text": "n'est",
+          "start": 57.58,
+          "end": 57.78,
+          "confidence": 0.79
+        },
+        {
+          "text": "comparable",
+          "start": 57.78,
+          "end": 58.28,
+          "confidence": 0.547
+        },
+        {
+          "text": "à",
+          "start": 58.28,
+          "end": 58.48,
+          "confidence": 0.934
+        },
+        {
+          "text": "celui",
+          "start": 58.48,
+          "end": 58.7,
+          "confidence": 0.851
+        },
+        {
+          "text": "qu'on",
+          "start": 58.7,
+          "end": 58.94,
+          "confidence": 0.926
+        },
+        {
+          "text": "entretenait",
+          "start": 58.94,
+          "end": 59.36,
+          "confidence": 0.56
+        }
+      ]
+    },
+    {
+      "id": 17,
+      "seek": 5596,
+      "start": 59.36,
+      "end": 63.14,
+      "text": " à d'autres objectes techniques comme la voiture ou le téléphone ?",
+      "tokens": [
+        50530,
+        1531,
+        274,
+        6,
+        16752,
+        2657,
+        279,
+        7512,
+        5173,
+        635,
+        38859,
+        2820,
+        476,
+        47159,
+        2506,
+        50714
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6293370928083147,
+      "compression_ratio": 1.5749128919860627,
+      "no_speech_prob": 0.21948836743831635,
+      "confidence": 0.756,
+      "words": [
+        {
+          "text": "à",
+          "start": 59.36,
+          "end": 59.44,
+          "confidence": 0.951
+        },
+        {
+          "text": "d'autres",
+          "start": 59.44,
+          "end": 59.68,
+          "confidence": 0.857
+        },
+        {
+          "text": "objectes",
+          "start": 59.68,
+          "end": 60.02,
+          "confidence": 0.507
+        },
+        {
+          "text": "techniques",
+          "start": 60.02,
+          "end": 60.44,
+          "confidence": 0.462
+        },
+        {
+          "text": "comme",
+          "start": 60.44,
+          "end": 61.04,
+          "confidence": 0.639
+        },
+        {
+          "text": "la",
+          "start": 61.04,
+          "end": 61.52,
+          "confidence": 0.905
+        },
+        {
+          "text": "voiture",
+          "start": 61.52,
+          "end": 61.86,
+          "confidence": 0.946
+        },
+        {
+          "text": "ou",
+          "start": 61.86,
+          "end": 62.46,
+          "confidence": 0.755
+        },
+        {
+          "text": "le",
+          "start": 62.46,
+          "end": 62.68,
+          "confidence": 0.913
+        },
+        {
+          "text": "téléphone ?",
+          "start": 62.68,
+          "end": 63.14,
+          "confidence": 0.983
+        }
+      ]
+    },
+    {
+      "id": 18,
+      "seek": 5596,
+      "start": 65.4,
+      "end": 66.16,
+      "text": " Il n'y a pas d'équivalent.",
+      "tokens": [
+        50714,
+        4416,
+        297,
+        6,
+        88,
+        257,
+        1736,
+        274,
+        6,
+        20183,
+        3576,
+        317,
+        13,
+        50872
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6293370928083147,
+      "compression_ratio": 1.5749128919860627,
+      "no_speech_prob": 0.21948836743831635,
+      "confidence": 0.881,
+      "words": [
+        {
+          "text": "Il",
+          "start": 65.4,
+          "end": 65.5,
+          "confidence": 0.901
+        },
+        {
+          "text": "n'y",
+          "start": 65.5,
+          "end": 65.54,
+          "confidence": 0.86
+        },
+        {
+          "text": "a",
+          "start": 65.54,
+          "end": 65.56,
+          "confidence": 0.962
+        },
+        {
+          "text": "pas",
+          "start": 65.56,
+          "end": 65.68,
+          "confidence": 0.998
+        },
+        {
+          "text": "d'équivalent.",
+          "start": 65.68,
+          "end": 66.16,
+          "confidence": 0.852
+        }
+      ]
+    },
+    {
+      "id": 19,
+      "seek": 5596,
+      "start": 66.16,
+      "end": 69.92,
+      "text": " On s'est espèrent de nous voter dans la relation à l'objet.",
+      "tokens": [
+        50872,
+        1282,
+        262,
+        6,
+        377,
+        7089,
+        1462,
+        1753,
+        368,
+        4666,
+        21722,
+        2680,
+        635,
+        9721,
+        1531,
+        287,
+        6,
+        996,
+        7108,
+        13,
+        51058
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6293370928083147,
+      "compression_ratio": 1.5749128919860627,
+      "no_speech_prob": 0.21948836743831635,
+      "confidence": 0.501,
+      "words": [
+        {
+          "text": "On",
+          "start": 66.16,
+          "end": 67.08,
+          "confidence": 0.302
+        },
+        {
+          "text": "s'est",
+          "start": 67.08,
+          "end": 67.3,
+          "confidence": 0.563
+        },
+        {
+          "text": "espèrent",
+          "start": 67.3,
+          "end": 67.62,
+          "confidence": 0.134
+        },
+        {
+          "text": "de",
+          "start": 67.62,
+          "end": 67.66,
+          "confidence": 0.99
+        },
+        {
+          "text": "nous",
+          "start": 67.66,
+          "end": 67.84,
+          "confidence": 0.763
+        },
+        {
+          "text": "voter",
+          "start": 67.84,
+          "end": 68.36,
+          "confidence": 0.181
+        },
+        {
+          "text": "dans",
+          "start": 68.36,
+          "end": 68.86,
+          "confidence": 0.82
+        },
+        {
+          "text": "la",
+          "start": 68.86,
+          "end": 68.96,
+          "confidence": 0.617
+        },
+        {
+          "text": "relation",
+          "start": 68.96,
+          "end": 69.24,
+          "confidence": 0.949
+        },
+        {
+          "text": "à",
+          "start": 69.24,
+          "end": 69.42,
+          "confidence": 0.75
+        },
+        {
+          "text": "l'objet.",
+          "start": 69.42,
+          "end": 69.92,
+          "confidence": 0.887
+        }
+      ]
+    },
+    {
+      "id": 20,
+      "seek": 5596,
+      "start": 70.2,
+      "end": 71.22,
+      "text": " C'est facilement éterricion.",
+      "tokens": [
+        51058,
+        383,
+        6,
+        377,
+        23670,
+        518,
+        1136,
+        391,
+        1341,
+        313,
+        13,
+        51122
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6293370928083147,
+      "compression_ratio": 1.5749128919860627,
+      "no_speech_prob": 0.21948836743831635,
+      "confidence": 0.441,
+      "words": [
+        {
+          "text": "C'est",
+          "start": 70.2,
+          "end": 70.34,
+          "confidence": 0.895
+        },
+        {
+          "text": "facilement",
+          "start": 70.34,
+          "end": 70.7,
+          "confidence": 0.562
+        },
+        {
+          "text": "éterricion.",
+          "start": 70.7,
+          "end": 71.22,
+          "confidence": 0.23
+        }
+      ]
+    },
+    {
+      "id": 21,
+      "seek": 5596,
+      "start": 71.64,
+      "end": 76.97,
+      "text": " Parce que la passion de l'utilisateur et ses affices a dépendance, cette objet d'un lieu",
+      "tokens": [
+        51122,
+        20429,
+        631,
+        635,
+        5418,
+        368,
+        287,
+        6,
+        20835,
+        271,
+        15540,
+        1030,
+        5385,
+        2096,
+        1473,
+        257,
+        45768,
+        719,
+        11,
+        5550,
+        14964,
+        274,
+        6,
+        409,
+        26036,
+        51416
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6293370928083147,
+      "compression_ratio": 1.5749128919860627,
+      "no_speech_prob": 0.21948836743831635,
+      "confidence": 0.457,
+      "words": [
+        {
+          "text": "Parce",
+          "start": 71.64,
+          "end": 71.94,
+          "confidence": 0.679
+        },
+        {
+          "text": "que",
+          "start": 71.94,
+          "end": 72.32,
+          "confidence": 0.566
+        },
+        {
+          "text": "la",
+          "start": 72.32,
+          "end": 72.56,
+          "confidence": 0.336
+        },
+        {
+          "text": "passion",
+          "start": 72.56,
+          "end": 72.9,
+          "confidence": 0.267
+        },
+        {
+          "text": "de",
+          "start": 72.9,
+          "end": 73.24,
+          "confidence": 0.365
+        },
+        {
+          "text": "l'utilisateur",
+          "start": 73.24,
+          "end": 74.82,
+          "confidence": 0.499
+        },
+        {
+          "text": "et",
+          "start": 74.82,
+          "end": 74.92,
+          "confidence": 0.45
+        },
+        {
+          "text": "ses",
+          "start": 74.92,
+          "end": 75.04,
+          "confidence": 0.095
+        },
+        {
+          "text": "affices",
+          "start": 75.04,
+          "end": 75.24,
+          "confidence": 0.303
+        },
+        {
+          "text": "a",
+          "start": 75.24,
+          "end": 75.38,
+          "confidence": 0.59
+        },
+        {
+          "text": "dépendance,",
+          "start": 75.38,
+          "end": 76.06,
+          "confidence": 0.559
+        },
+        {
+          "text": "cette",
+          "start": 76.32,
+          "end": 76.34,
+          "confidence": 0.401
+        },
+        {
+          "text": "objet",
+          "start": 76.34,
+          "end": 76.54,
+          "confidence": 0.924
+        },
+        {
+          "text": "d'un",
+          "start": 76.54,
+          "end": 76.92,
+          "confidence": 0.783
+        },
+        {
+          "text": "lieu",
+          "start": 76.92,
+          "end": 76.97,
+          "confidence": 0.307
+        }
+      ]
+    },
+    {
+      "id": 22,
+      "seek": 5596,
+      "start": 76.97,
+      "end": 82.15,
+      "text": " en fait, une espèce de relation de médiation avec le monde qui rendent encore avec",
+      "tokens": [
+        51416,
+        465,
+        3887,
+        11,
+        2251,
+        7089,
+        30236,
+        368,
+        9721,
+        368,
+        42436,
+        399,
+        4163,
+        476,
+        10431,
+        1956,
+        6125,
+        317,
+        10122,
+        4163,
+        51671
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6293370928083147,
+      "compression_ratio": 1.5749128919860627,
+      "no_speech_prob": 0.21948836743831635,
+      "confidence": 0.746,
+      "words": [
+        {
+          "text": "en",
+          "start": 76.97,
+          "end": 77.2,
+          "confidence": 0.767
+        },
+        {
+          "text": "fait,",
+          "start": 77.2,
+          "end": 77.32,
+          "confidence": 0.944
+        },
+        {
+          "text": "une",
+          "start": 77.46,
+          "end": 77.48,
+          "confidence": 0.696
+        },
+        {
+          "text": "espèce",
+          "start": 77.48,
+          "end": 77.9,
+          "confidence": 0.97
+        },
+        {
+          "text": "de",
+          "start": 77.9,
+          "end": 78.08,
+          "confidence": 0.994
+        },
+        {
+          "text": "relation",
+          "start": 78.08,
+          "end": 78.5,
+          "confidence": 0.826
+        },
+        {
+          "text": "de",
+          "start": 78.5,
+          "end": 78.94,
+          "confidence": 0.72
+        },
+        {
+          "text": "médiation",
+          "start": 78.94,
+          "end": 79.5,
+          "confidence": 0.881
+        },
+        {
+          "text": "avec",
+          "start": 79.5,
+          "end": 79.74,
+          "confidence": 0.968
+        },
+        {
+          "text": "le",
+          "start": 79.74,
+          "end": 79.94,
+          "confidence": 0.986
+        },
+        {
+          "text": "monde",
+          "start": 79.94,
+          "end": 80.44,
+          "confidence": 0.906
+        },
+        {
+          "text": "qui",
+          "start": 80.44,
+          "end": 81.14,
+          "confidence": 0.825
+        },
+        {
+          "text": "rendent",
+          "start": 81.14,
+          "end": 81.8,
+          "confidence": 0.584
+        },
+        {
+          "text": "encore",
+          "start": 81.8,
+          "end": 81.98,
+          "confidence": 0.198
+        },
+        {
+          "text": "avec",
+          "start": 81.98,
+          "end": 82.15,
+          "confidence": 0.486
+        }
+      ]
+    },
+    {
+      "id": 23,
+      "seek": 8210,
+      "start": 82.15,
+      "end": 83.44,
+      "text": " la maille de celles formes de rogeur.",
+      "tokens": [
+        50364,
+        635,
+        463,
+        3409,
+        368,
+        2815,
+        279,
+        1254,
+        279,
+        368,
+        744,
+        432,
+        374,
+        13,
+        50440
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.45904387403654573,
+      "compression_ratio": 1.6159169550173011,
+      "no_speech_prob": 0.2066797912120819,
+      "confidence": 0.465,
+      "words": [
+        {
+          "text": "la",
+          "start": 82.15,
+          "end": 82.22,
+          "confidence": 0.648
+        },
+        {
+          "text": "maille",
+          "start": 82.22,
+          "end": 82.4,
+          "confidence": 0.136
+        },
+        {
+          "text": "de",
+          "start": 82.4,
+          "end": 82.48,
+          "confidence": 0.585
+        },
+        {
+          "text": "celles",
+          "start": 82.48,
+          "end": 82.74,
+          "confidence": 0.561
+        },
+        {
+          "text": "formes",
+          "start": 82.74,
+          "end": 82.96,
+          "confidence": 0.78
+        },
+        {
+          "text": "de",
+          "start": 82.96,
+          "end": 83.0,
+          "confidence": 0.936
+        },
+        {
+          "text": "rogeur.",
+          "start": 83.0,
+          "end": 83.44,
+          "confidence": 0.433
+        }
+      ]
+    },
+    {
+      "id": 24,
+      "seek": 8210,
+      "start": 83.98,
+      "end": 87.86,
+      "text": " Donc, à objets inédits, rapport inédits.",
+      "tokens": [
+        50440,
+        7477,
+        11,
+        1531,
+        1111,
+        25349,
+        294,
+        7811,
+        1208,
+        11,
+        18018,
+        294,
+        7811,
+        1208,
+        13,
+        50640
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.45904387403654573,
+      "compression_ratio": 1.6159169550173011,
+      "no_speech_prob": 0.2066797912120819,
+      "confidence": 0.745,
+      "words": [
+        {
+          "text": "Donc,",
+          "start": 83.98,
+          "end": 84.46,
+          "confidence": 0.833
+        },
+        {
+          "text": "à",
+          "start": 84.56,
+          "end": 84.96,
+          "confidence": 0.696
+        },
+        {
+          "text": "objets",
+          "start": 84.96,
+          "end": 85.44,
+          "confidence": 0.526
+        },
+        {
+          "text": "inédits,",
+          "start": 85.44,
+          "end": 86.24,
+          "confidence": 0.701
+        },
+        {
+          "text": "rapport",
+          "start": 86.32,
+          "end": 86.92,
+          "confidence": 0.944
+        },
+        {
+          "text": "inédits.",
+          "start": 86.92,
+          "end": 87.86,
+          "confidence": 0.908
+        }
+      ]
+    },
+    {
+      "id": 25,
+      "seek": 8210,
+      "start": 88.1,
+      "end": 94.2,
+      "text": " Et, ce rapport, si j'en prends Nicolas, frère caractérisée par un mélange de dépendance",
+      "tokens": [
+        50640,
+        3790,
+        11,
+        1769,
+        18018,
+        11,
+        1511,
+        361,
+        6,
+        268,
+        46750,
+        38268,
+        11,
+        431,
+        4212,
+        1032,
+        578,
+        4198,
+        50027,
+        971,
+        517,
+        41953,
+        933,
+        368,
+        45768,
+        719,
+        50972
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.45904387403654573,
+      "compression_ratio": 1.6159169550173011,
+      "no_speech_prob": 0.2066797912120819,
+      "confidence": 0.669,
+      "words": [
+        {
+          "text": "Et,",
+          "start": 88.1,
+          "end": 88.3,
+          "confidence": 0.865
+        },
+        {
+          "text": "ce",
+          "start": 88.58,
+          "end": 88.84,
+          "confidence": 0.277
+        },
+        {
+          "text": "rapport,",
+          "start": 88.84,
+          "end": 89.28,
+          "confidence": 0.998
+        },
+        {
+          "text": "si",
+          "start": 89.38,
+          "end": 89.56,
+          "confidence": 0.933
+        },
+        {
+          "text": "j'en",
+          "start": 89.56,
+          "end": 89.74,
+          "confidence": 0.78
+        },
+        {
+          "text": "prends",
+          "start": 89.74,
+          "end": 89.92,
+          "confidence": 0.307
+        },
+        {
+          "text": "Nicolas,",
+          "start": 89.92,
+          "end": 90.22,
+          "confidence": 0.65
+        },
+        {
+          "text": "frère",
+          "start": 90.78,
+          "end": 91.1,
+          "confidence": 0.431
+        },
+        {
+          "text": "caractérisée",
+          "start": 91.1,
+          "end": 91.8,
+          "confidence": 0.595
+        },
+        {
+          "text": "par",
+          "start": 91.8,
+          "end": 92.14,
+          "confidence": 0.907
+        },
+        {
+          "text": "un",
+          "start": 92.14,
+          "end": 92.34,
+          "confidence": 0.989
+        },
+        {
+          "text": "mélange",
+          "start": 92.34,
+          "end": 92.98,
+          "confidence": 0.92
+        },
+        {
+          "text": "de",
+          "start": 92.98,
+          "end": 93.24,
+          "confidence": 0.842
+        },
+        {
+          "text": "dépendance",
+          "start": 93.24,
+          "end": 94.2,
+          "confidence": 0.675
+        }
+      ]
+    },
+    {
+      "id": 26,
+      "seek": 8210,
+      "start": 94.36,
+      "end": 95.08,
+      "text": " et de rogeur.",
+      "tokens": [
+        50972,
+        1030,
+        368,
+        744,
+        432,
+        374,
+        13,
+        51022
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.45904387403654573,
+      "compression_ratio": 1.6159169550173011,
+      "no_speech_prob": 0.2066797912120819,
+      "confidence": 0.851,
+      "words": [
+        {
+          "text": "et",
+          "start": 94.36,
+          "end": 94.52,
+          "confidence": 0.97
+        },
+        {
+          "text": "de",
+          "start": 94.52,
+          "end": 94.64,
+          "confidence": 0.996
+        },
+        {
+          "text": "rogeur.",
+          "start": 94.64,
+          "end": 95.08,
+          "confidence": 0.773
+        }
+      ]
+    },
+    {
+      "id": 27,
+      "seek": 8210,
+      "start": 96.3,
+      "end": 100.48,
+      "text": " Bon, en vrai, il faudrait remonter très, très filmant tout l'histoire des objectes",
+      "tokens": [
+        51022,
+        7368,
+        11,
+        465,
+        17815,
+        11,
+        1930,
+        38694,
+        8645,
+        890,
+        41806,
+        5732,
+        11,
+        5732,
+        2007,
+        394,
+        3486,
+        287,
+        6,
+        29093,
+        730,
+        2657,
+        279,
+        51286
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.45904387403654573,
+      "compression_ratio": 1.6159169550173011,
+      "no_speech_prob": 0.2066797912120819,
+      "confidence": 0.752,
+      "words": [
+        {
+          "text": "Bon,",
+          "start": 96.3,
+          "end": 96.32,
+          "confidence": 0.6
+        },
+        {
+          "text": "en",
+          "start": 96.36,
+          "end": 96.58,
+          "confidence": 0.918
+        },
+        {
+          "text": "vrai,",
+          "start": 96.58,
+          "end": 96.92,
+          "confidence": 0.992
+        },
+        {
+          "text": "il",
+          "start": 97.14,
+          "end": 97.18,
+          "confidence": 0.987
+        },
+        {
+          "text": "faudrait",
+          "start": 97.18,
+          "end": 97.56,
+          "confidence": 0.933
+        },
+        {
+          "text": "remonter",
+          "start": 97.56,
+          "end": 98.08,
+          "confidence": 0.61
+        },
+        {
+          "text": "très,",
+          "start": 98.08,
+          "end": 98.56,
+          "confidence": 0.975
+        },
+        {
+          "text": "très",
+          "start": 98.56,
+          "end": 98.86,
+          "confidence": 0.986
+        },
+        {
+          "text": "filmant",
+          "start": 98.86,
+          "end": 99.42,
+          "confidence": 0.409
+        },
+        {
+          "text": "tout",
+          "start": 99.42,
+          "end": 99.68,
+          "confidence": 0.348
+        },
+        {
+          "text": "l'histoire",
+          "start": 99.68,
+          "end": 100.08,
+          "confidence": 0.876
+        },
+        {
+          "text": "des",
+          "start": 100.08,
+          "end": 100.22,
+          "confidence": 0.957
+        },
+        {
+          "text": "objectes",
+          "start": 100.22,
+          "end": 100.48,
+          "confidence": 0.842
+        }
+      ]
+    },
+    {
+      "id": 28,
+      "seek": 8210,
+      "start": 100.48,
+      "end": 105.24,
+      "text": " techniques et de leur infertion dans nos vieux pour déterminer si ce rapport est totalement",
+      "tokens": [
+        51286,
+        7512,
+        1030,
+        368,
+        9580,
+        1536,
+        911,
+        313,
+        2680,
+        3269,
+        4941,
+        2449,
+        2016,
+        2795,
+        29725,
+        260,
+        1511,
+        1769,
+        18018,
+        871,
+        45203,
+        51530
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.45904387403654573,
+      "compression_ratio": 1.6159169550173011,
+      "no_speech_prob": 0.2066797912120819,
+      "confidence": 0.614,
+      "words": [
+        {
+          "text": "techniques",
+          "start": 100.48,
+          "end": 101.0,
+          "confidence": 0.952
+        },
+        {
+          "text": "et",
+          "start": 101.0,
+          "end": 101.58,
+          "confidence": 0.943
+        },
+        {
+          "text": "de",
+          "start": 101.58,
+          "end": 101.72,
+          "confidence": 0.975
+        },
+        {
+          "text": "leur",
+          "start": 101.72,
+          "end": 101.8,
+          "confidence": 0.803
+        },
+        {
+          "text": "infertion",
+          "start": 101.8,
+          "end": 102.34,
+          "confidence": 0.382
+        },
+        {
+          "text": "dans",
+          "start": 102.34,
+          "end": 102.5,
+          "confidence": 0.297
+        },
+        {
+          "text": "nos",
+          "start": 102.5,
+          "end": 102.68,
+          "confidence": 0.419
+        },
+        {
+          "text": "vieux",
+          "start": 102.68,
+          "end": 103.08,
+          "confidence": 0.386
+        },
+        {
+          "text": "pour",
+          "start": 103.08,
+          "end": 103.1,
+          "confidence": 0.281
+        },
+        {
+          "text": "déterminer",
+          "start": 103.1,
+          "end": 103.64,
+          "confidence": 0.976
+        },
+        {
+          "text": "si",
+          "start": 103.64,
+          "end": 103.8,
+          "confidence": 0.367
+        },
+        {
+          "text": "ce",
+          "start": 103.8,
+          "end": 103.92,
+          "confidence": 0.983
+        },
+        {
+          "text": "rapport",
+          "start": 103.92,
+          "end": 104.22,
+          "confidence": 0.998
+        },
+        {
+          "text": "est",
+          "start": 104.22,
+          "end": 104.88,
+          "confidence": 0.942
+        },
+        {
+          "text": "totalement",
+          "start": 104.88,
+          "end": 105.24,
+          "confidence": 0.907
+        }
+      ]
+    },
+    {
+      "id": 29,
+      "seek": 8210,
+      "start": 105.24,
+      "end": 106.1,
+      "text": " inédit.",
+      "tokens": [
+        51530,
+        294,
+        7811,
+        270,
+        13,
+        51580
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.45904387403654573,
+      "compression_ratio": 1.6159169550173011,
+      "no_speech_prob": 0.2066797912120819,
+      "confidence": 0.939,
+      "words": [
+        {
+          "text": "inédit.",
+          "start": 105.24,
+          "end": 106.1,
+          "confidence": 0.939
+        }
+      ]
+    },
+    {
+      "id": 30,
+      "seek": 8210,
+      "start": 106.16,
+      "end": 109.44,
+      "text": " Mais j'ai l'impression comme ça que Nicolas se trompe pas vraiment.",
+      "tokens": [
+        51580,
+        6313,
+        361,
+        6,
+        1301,
+        287,
+        6,
+        36107,
+        5173,
+        2788,
+        631,
+        38268,
+        369,
+        504,
+        298,
+        494,
+        1736,
+        8322,
+        13,
+        51738
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.45904387403654573,
+      "compression_ratio": 1.6159169550173011,
+      "no_speech_prob": 0.2066797912120819,
+      "confidence": 0.811,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 106.16,
+          "end": 106.5,
+          "confidence": 0.721
+        },
+        {
+          "text": "j'ai",
+          "start": 106.5,
+          "end": 106.92,
+          "confidence": 0.91
+        },
+        {
+          "text": "l'impression",
+          "start": 106.92,
+          "end": 107.34,
+          "confidence": 0.956
+        },
+        {
+          "text": "comme",
+          "start": 107.34,
+          "end": 107.58,
+          "confidence": 0.7
+        },
+        {
+          "text": "ça",
+          "start": 107.58,
+          "end": 107.74,
+          "confidence": 0.953
+        },
+        {
+          "text": "que",
+          "start": 107.74,
+          "end": 108.06,
+          "confidence": 0.941
+        },
+        {
+          "text": "Nicolas",
+          "start": 108.06,
+          "end": 108.46,
+          "confidence": 0.994
+        },
+        {
+          "text": "se",
+          "start": 108.46,
+          "end": 108.68,
+          "confidence": 0.716
+        },
+        {
+          "text": "trompe",
+          "start": 108.68,
+          "end": 109.02,
+          "confidence": 0.54
+        },
+        {
+          "text": "pas",
+          "start": 109.02,
+          "end": 109.16,
+          "confidence": 0.886
+        },
+        {
+          "text": "vraiment.",
+          "start": 109.16,
+          "end": 109.44,
+          "confidence": 0.963
+        }
+      ]
+    },
+    {
+      "id": 31,
+      "seek": 8210,
+      "start": 109.92,
+      "end": 110.86,
+      "text": " Pour autant, je sache.",
+      "tokens": [
+        51738,
+        8732,
+        34081,
+        11,
+        1506,
+        262,
+        6000,
+        13,
+        51808
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.45904387403654573,
+      "compression_ratio": 1.6159169550173011,
+      "no_speech_prob": 0.2066797912120819,
+      "confidence": 0.6,
+      "words": [
+        {
+          "text": "Pour",
+          "start": 109.92,
+          "end": 110.1,
+          "confidence": 0.49
+        },
+        {
+          "text": "autant,",
+          "start": 110.1,
+          "end": 110.28,
+          "confidence": 0.75
+        },
+        {
+          "text": "je",
+          "start": 110.42,
+          "end": 110.48,
+          "confidence": 0.931
+        },
+        {
+          "text": "sache.",
+          "start": 110.48,
+          "end": 110.86,
+          "confidence": 0.477
+        }
+      ]
+    },
+    {
+      "id": 32,
+      "seek": 11098,
+      "start": 111.04,
+      "end": 115.0,
+      "text": " Il y a eu plein de discussions autour de la voiture ou même du téléphone.",
+      "tokens": [
+        50364,
+        4416,
+        288,
+        257,
+        2228,
+        21088,
+        368,
+        11088,
+        30249,
+        368,
+        635,
+        38859,
+        2820,
+        5698,
+        1581,
+        47159,
+        13,
+        50568
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.44320285092493533,
+      "compression_ratio": 1.7050847457627119,
+      "no_speech_prob": 0.15390530228614807,
+      "confidence": 0.821,
+      "words": [
+        {
+          "text": "Il",
+          "start": 111.04,
+          "end": 111.2,
+          "confidence": 0.905
+        },
+        {
+          "text": "y",
+          "start": 111.2,
+          "end": 111.3,
+          "confidence": 0.934
+        },
+        {
+          "text": "a",
+          "start": 111.3,
+          "end": 111.56,
+          "confidence": 0.893
+        },
+        {
+          "text": "eu",
+          "start": 111.56,
+          "end": 111.6,
+          "confidence": 0.839
+        },
+        {
+          "text": "plein",
+          "start": 111.6,
+          "end": 111.88,
+          "confidence": 0.776
+        },
+        {
+          "text": "de",
+          "start": 111.88,
+          "end": 112.12,
+          "confidence": 0.944
+        },
+        {
+          "text": "discussions",
+          "start": 112.12,
+          "end": 112.6,
+          "confidence": 0.681
+        },
+        {
+          "text": "autour",
+          "start": 112.6,
+          "end": 113.04,
+          "confidence": 0.978
+        },
+        {
+          "text": "de",
+          "start": 113.04,
+          "end": 113.48,
+          "confidence": 0.975
+        },
+        {
+          "text": "la",
+          "start": 113.48,
+          "end": 113.56,
+          "confidence": 0.966
+        },
+        {
+          "text": "voiture",
+          "start": 113.56,
+          "end": 113.88,
+          "confidence": 0.983
+        },
+        {
+          "text": "ou",
+          "start": 113.88,
+          "end": 114.14,
+          "confidence": 0.66
+        },
+        {
+          "text": "même",
+          "start": 114.14,
+          "end": 114.34,
+          "confidence": 0.99
+        },
+        {
+          "text": "du",
+          "start": 114.34,
+          "end": 114.64,
+          "confidence": 0.283
+        },
+        {
+          "text": "téléphone.",
+          "start": 114.64,
+          "end": 115.0,
+          "confidence": 0.986
+        }
+      ]
+    },
+    {
+      "id": 33,
+      "seek": 11098,
+      "start": 115.52,
+      "end": 119.51,
+      "text": " Mais, la dépense n'était pas du même mort, donc le rejet n'en plus n'était pas du même",
+      "tokens": [
+        50568,
+        6313,
+        11,
+        635,
+        27998,
+        1288,
+        297,
+        6,
+        9743,
+        1736,
+        1581,
+        5698,
+        6599,
+        11,
+        5926,
+        476,
+        319,
+        7108,
+        297,
+        6,
+        268,
+        1804,
+        297,
+        6,
+        9743,
+        1736,
+        1581,
+        5698,
+        50790
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.44320285092493533,
+      "compression_ratio": 1.7050847457627119,
+      "no_speech_prob": 0.15390530228614807,
+      "confidence": 0.701,
+      "words": [
+        {
+          "text": "Mais,",
+          "start": 115.52,
+          "end": 115.82,
+          "confidence": 0.983
+        },
+        {
+          "text": "la",
+          "start": 115.9,
+          "end": 116.0,
+          "confidence": 0.961
+        },
+        {
+          "text": "dépense",
+          "start": 116.0,
+          "end": 116.42,
+          "confidence": 0.616
+        },
+        {
+          "text": "n'était",
+          "start": 116.42,
+          "end": 116.82,
+          "confidence": 0.955
+        },
+        {
+          "text": "pas",
+          "start": 116.82,
+          "end": 117.04,
+          "confidence": 0.994
+        },
+        {
+          "text": "du",
+          "start": 117.04,
+          "end": 117.2,
+          "confidence": 0.958
+        },
+        {
+          "text": "même",
+          "start": 117.2,
+          "end": 117.38,
+          "confidence": 0.929
+        },
+        {
+          "text": "mort,",
+          "start": 117.38,
+          "end": 117.58,
+          "confidence": 0.686
+        },
+        {
+          "text": "donc",
+          "start": 117.7,
+          "end": 118.02,
+          "confidence": 0.932
+        },
+        {
+          "text": "le",
+          "start": 118.02,
+          "end": 118.34,
+          "confidence": 0.95
+        },
+        {
+          "text": "rejet",
+          "start": 118.34,
+          "end": 118.64,
+          "confidence": 0.57
+        },
+        {
+          "text": "n'en",
+          "start": 118.64,
+          "end": 118.82,
+          "confidence": 0.429
+        },
+        {
+          "text": "plus",
+          "start": 118.82,
+          "end": 118.96,
+          "confidence": 0.055
+        },
+        {
+          "text": "n'était",
+          "start": 118.96,
+          "end": 119.16,
+          "confidence": 0.973
+        },
+        {
+          "text": "pas",
+          "start": 119.16,
+          "end": 119.32,
+          "confidence": 0.993
+        },
+        {
+          "text": "du",
+          "start": 119.32,
+          "end": 119.42,
+          "confidence": 0.823
+        },
+        {
+          "text": "même",
+          "start": 119.42,
+          "end": 119.51,
+          "confidence": 0.79
+        }
+      ]
+    },
+    {
+      "id": 34,
+      "seek": 11098,
+      "start": 119.51,
+      "end": 119.72,
+      "text": " mort.",
+      "tokens": [
+        50790,
+        6599,
+        13,
+        50840
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.44320285092493533,
+      "compression_ratio": 1.7050847457627119,
+      "no_speech_prob": 0.15390530228614807,
+      "confidence": 0.639,
+      "words": [
+        {
+          "text": "mort.",
+          "start": 119.51,
+          "end": 119.72,
+          "confidence": 0.639
+        }
+      ]
+    },
+    {
+      "id": 35,
+      "seek": 11098,
+      "start": 120.04,
+      "end": 121.24,
+      "text": " On peut adorer sa bagnure.",
+      "tokens": [
+        50840,
+        1282,
+        5977,
+        614,
+        17618,
+        601,
+        3411,
+        77,
+        540,
+        13,
+        50890
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.44320285092493533,
+      "compression_ratio": 1.7050847457627119,
+      "no_speech_prob": 0.15390530228614807,
+      "confidence": 0.615,
+      "words": [
+        {
+          "text": "On",
+          "start": 120.04,
+          "end": 120.22,
+          "confidence": 0.981
+        },
+        {
+          "text": "peut",
+          "start": 120.22,
+          "end": 120.36,
+          "confidence": 0.988
+        },
+        {
+          "text": "adorer",
+          "start": 120.36,
+          "end": 120.7,
+          "confidence": 0.859
+        },
+        {
+          "text": "sa",
+          "start": 120.7,
+          "end": 120.88,
+          "confidence": 0.918
+        },
+        {
+          "text": "bagnure.",
+          "start": 120.88,
+          "end": 121.24,
+          "confidence": 0.314
+        }
+      ]
+    },
+    {
+      "id": 36,
+      "seek": 11098,
+      "start": 121.38,
+      "end": 123.06,
+      "text": " On a par besoin pour plein de choses.",
+      "tokens": [
+        50890,
+        1282,
+        257,
+        971,
+        19207,
+        2016,
+        21088,
+        368,
+        14488,
+        13,
+        50972
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.44320285092493533,
+      "compression_ratio": 1.7050847457627119,
+      "no_speech_prob": 0.15390530228614807,
+      "confidence": 0.722,
+      "words": [
+        {
+          "text": "On",
+          "start": 121.38,
+          "end": 121.56,
+          "confidence": 0.897
+        },
+        {
+          "text": "a",
+          "start": 121.56,
+          "end": 121.64,
+          "confidence": 0.656
+        },
+        {
+          "text": "par",
+          "start": 121.64,
+          "end": 121.8,
+          "confidence": 0.161
+        },
+        {
+          "text": "besoin",
+          "start": 121.8,
+          "end": 122.12,
+          "confidence": 0.947
+        },
+        {
+          "text": "pour",
+          "start": 122.12,
+          "end": 122.5,
+          "confidence": 0.976
+        },
+        {
+          "text": "plein",
+          "start": 122.5,
+          "end": 122.72,
+          "confidence": 0.857
+        },
+        {
+          "text": "de",
+          "start": 122.72,
+          "end": 122.8,
+          "confidence": 0.993
+        },
+        {
+          "text": "choses.",
+          "start": 122.8,
+          "end": 123.06,
+          "confidence": 0.989
+        }
+      ]
+    },
+    {
+      "id": 37,
+      "seek": 11098,
+      "start": 123.36,
+      "end": 126.46,
+      "text": " Et là, le soir, quand on va se coucher, on la laisse.",
+      "tokens": [
+        50972,
+        3790,
+        3684,
+        11,
+        476,
+        27105,
+        11,
+        6932,
+        322,
+        2773,
+        369,
+        1384,
+        6759,
+        11,
+        322,
+        635,
+        30969,
+        13,
+        51142
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.44320285092493533,
+      "compression_ratio": 1.7050847457627119,
+      "no_speech_prob": 0.15390530228614807,
+      "confidence": 0.835,
+      "words": [
+        {
+          "text": "Et",
+          "start": 123.36,
+          "end": 123.5,
+          "confidence": 0.606
+        },
+        {
+          "text": "là,",
+          "start": 123.5,
+          "end": 123.76,
+          "confidence": 0.498
+        },
+        {
+          "text": "le",
+          "start": 123.82,
+          "end": 124.06,
+          "confidence": 0.986
+        },
+        {
+          "text": "soir,",
+          "start": 124.06,
+          "end": 124.42,
+          "confidence": 0.971
+        },
+        {
+          "text": "quand",
+          "start": 124.84,
+          "end": 124.96,
+          "confidence": 0.787
+        },
+        {
+          "text": "on",
+          "start": 124.96,
+          "end": 125.06,
+          "confidence": 0.988
+        },
+        {
+          "text": "va",
+          "start": 125.06,
+          "end": 125.18,
+          "confidence": 0.966
+        },
+        {
+          "text": "se",
+          "start": 125.18,
+          "end": 125.26,
+          "confidence": 0.869
+        },
+        {
+          "text": "coucher,",
+          "start": 125.26,
+          "end": 125.6,
+          "confidence": 0.804
+        },
+        {
+          "text": "on",
+          "start": 125.82,
+          "end": 126.06,
+          "confidence": 0.98
+        },
+        {
+          "text": "la",
+          "start": 126.06,
+          "end": 126.2,
+          "confidence": 0.811
+        },
+        {
+          "text": "laisse.",
+          "start": 126.2,
+          "end": 126.46,
+          "confidence": 0.985
+        }
+      ]
+    },
+    {
+      "id": 38,
+      "seek": 11098,
+      "start": 127.06,
+      "end": 130.1,
+      "text": " On la pade en la main quand on est colis, qu'on n'a même pas au chiot.",
+      "tokens": [
+        51142,
+        1282,
+        635,
+        280,
+        762,
+        465,
+        635,
+        2135,
+        6932,
+        322,
+        871,
+        1173,
+        271,
+        11,
+        421,
+        6,
+        266,
+        297,
+        6,
+        64,
+        5698,
+        1736,
+        1609,
+        417,
+        6471,
+        13,
+        51334
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.44320285092493533,
+      "compression_ratio": 1.7050847457627119,
+      "no_speech_prob": 0.15390530228614807,
+      "confidence": 0.542,
+      "words": [
+        {
+          "text": "On",
+          "start": 127.06,
+          "end": 127.32,
+          "confidence": 0.605
+        },
+        {
+          "text": "la",
+          "start": 127.32,
+          "end": 127.5,
+          "confidence": 0.35
+        },
+        {
+          "text": "pade",
+          "start": 127.5,
+          "end": 127.72,
+          "confidence": 0.18
+        },
+        {
+          "text": "en",
+          "start": 127.72,
+          "end": 127.88,
+          "confidence": 0.775
+        },
+        {
+          "text": "la",
+          "start": 127.88,
+          "end": 128.04,
+          "confidence": 0.795
+        },
+        {
+          "text": "main",
+          "start": 128.04,
+          "end": 128.3,
+          "confidence": 0.971
+        },
+        {
+          "text": "quand",
+          "start": 128.3,
+          "end": 128.46,
+          "confidence": 0.483
+        },
+        {
+          "text": "on",
+          "start": 128.46,
+          "end": 128.62,
+          "confidence": 0.994
+        },
+        {
+          "text": "est",
+          "start": 128.62,
+          "end": 128.74,
+          "confidence": 0.714
+        },
+        {
+          "text": "colis,",
+          "start": 128.74,
+          "end": 129.12,
+          "confidence": 0.501
+        },
+        {
+          "text": "qu'on",
+          "start": 129.22,
+          "end": 129.32,
+          "confidence": 0.777
+        },
+        {
+          "text": "n'a",
+          "start": 129.32,
+          "end": 129.42,
+          "confidence": 0.439
+        },
+        {
+          "text": "même",
+          "start": 129.42,
+          "end": 129.56,
+          "confidence": 0.324
+        },
+        {
+          "text": "pas",
+          "start": 129.56,
+          "end": 129.74,
+          "confidence": 1.0
+        },
+        {
+          "text": "au",
+          "start": 129.74,
+          "end": 129.88,
+          "confidence": 0.64
+        },
+        {
+          "text": "chiot.",
+          "start": 129.88,
+          "end": 130.1,
+          "confidence": 0.514
+        }
+      ]
+    },
+    {
+      "id": 39,
+      "seek": 11098,
+      "start": 130.94,
+      "end": 135.32,
+      "text": " On pouvait être émervé par son mome qui occupeait la ligne de téléphone pendant une heure",
+      "tokens": [
+        51334,
+        1282,
+        45913,
+        7418,
+        1136,
+        936,
+        15797,
+        971,
+        1872,
+        275,
+        423,
+        1956,
+        2678,
+        84,
+        494,
+        1001,
+        635,
+        34207,
+        368,
+        47159,
+        17338,
+        2251,
+        30027,
+        51574
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.44320285092493533,
+      "compression_ratio": 1.7050847457627119,
+      "no_speech_prob": 0.15390530228614807,
+      "confidence": 0.656,
+      "words": [
+        {
+          "text": "On",
+          "start": 130.94,
+          "end": 131.04,
+          "confidence": 0.99
+        },
+        {
+          "text": "pouvait",
+          "start": 131.04,
+          "end": 131.28,
+          "confidence": 0.588
+        },
+        {
+          "text": "être",
+          "start": 131.28,
+          "end": 131.6,
+          "confidence": 0.446
+        },
+        {
+          "text": "émervé",
+          "start": 131.6,
+          "end": 132.24,
+          "confidence": 0.725
+        },
+        {
+          "text": "par",
+          "start": 132.24,
+          "end": 132.5,
+          "confidence": 0.848
+        },
+        {
+          "text": "son",
+          "start": 132.5,
+          "end": 132.7,
+          "confidence": 0.445
+        },
+        {
+          "text": "mome",
+          "start": 132.7,
+          "end": 133.08,
+          "confidence": 0.255
+        },
+        {
+          "text": "qui",
+          "start": 133.08,
+          "end": 133.3,
+          "confidence": 0.911
+        },
+        {
+          "text": "occupeait",
+          "start": 133.3,
+          "end": 133.74,
+          "confidence": 0.642
+        },
+        {
+          "text": "la",
+          "start": 133.74,
+          "end": 133.86,
+          "confidence": 0.808
+        },
+        {
+          "text": "ligne",
+          "start": 133.86,
+          "end": 134.02,
+          "confidence": 0.975
+        },
+        {
+          "text": "de",
+          "start": 134.02,
+          "end": 134.24,
+          "confidence": 0.928
+        },
+        {
+          "text": "téléphone",
+          "start": 134.24,
+          "end": 134.56,
+          "confidence": 0.978
+        },
+        {
+          "text": "pendant",
+          "start": 134.56,
+          "end": 134.92,
+          "confidence": 0.901
+        },
+        {
+          "text": "une",
+          "start": 134.92,
+          "end": 135.18,
+          "confidence": 0.811
+        },
+        {
+          "text": "heure",
+          "start": 135.18,
+          "end": 135.32,
+          "confidence": 0.477
+        }
+      ]
+    },
+    {
+      "id": 40,
+      "seek": 11098,
+      "start": 135.32,
+      "end": 137.04,
+      "text": " chaque soir pour discuter avec un copain.",
+      "tokens": [
+        51574,
+        18920,
+        27105,
+        2016,
+        2983,
+        20314,
+        4163,
+        517,
+        2971,
+        491,
+        13,
+        51664
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.44320285092493533,
+      "compression_ratio": 1.7050847457627119,
+      "no_speech_prob": 0.15390530228614807,
+      "confidence": 0.955,
+      "words": [
+        {
+          "text": "chaque",
+          "start": 135.32,
+          "end": 135.6,
+          "confidence": 0.99
+        },
+        {
+          "text": "soir",
+          "start": 135.6,
+          "end": 135.8,
+          "confidence": 0.997
+        },
+        {
+          "text": "pour",
+          "start": 135.8,
+          "end": 136.0,
+          "confidence": 0.981
+        },
+        {
+          "text": "discuter",
+          "start": 136.0,
+          "end": 136.34,
+          "confidence": 0.882
+        },
+        {
+          "text": "avec",
+          "start": 136.34,
+          "end": 136.5,
+          "confidence": 0.993
+        },
+        {
+          "text": "un",
+          "start": 136.5,
+          "end": 136.62,
+          "confidence": 0.967
+        },
+        {
+          "text": "copain.",
+          "start": 136.62,
+          "end": 137.04,
+          "confidence": 0.953
+        }
+      ]
+    },
+    {
+      "id": 41,
+      "seek": 13698,
+      "start": 137.32,
+      "end": 141.84,
+      "text": " Mais ça ne ressemble pas à ce qu'on peut ressentir à voir même mome aujourd'hui.",
+      "tokens": [
+        50376,
+        6313,
+        2788,
+        408,
+        725,
+        37227,
+        1736,
+        1531,
+        1769,
+        421,
+        6,
+        266,
+        5977,
+        24689,
+        317,
+        347,
+        1531,
+        10695,
+        5698,
+        275,
+        423,
+        14023,
+        6,
+        10556,
+        13,
+        50606
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5337450312471937,
+      "compression_ratio": 1.6231454005934718,
+      "no_speech_prob": 0.1096271350979805,
+      "confidence": 0.735,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 137.32,
+          "end": 137.52,
+          "confidence": 0.984
+        },
+        {
+          "text": "ça",
+          "start": 137.52,
+          "end": 137.7,
+          "confidence": 0.877
+        },
+        {
+          "text": "ne",
+          "start": 137.7,
+          "end": 137.8,
+          "confidence": 0.672
+        },
+        {
+          "text": "ressemble",
+          "start": 137.8,
+          "end": 138.22,
+          "confidence": 0.731
+        },
+        {
+          "text": "pas",
+          "start": 138.22,
+          "end": 138.76,
+          "confidence": 0.526
+        },
+        {
+          "text": "à",
+          "start": 138.76,
+          "end": 138.94,
+          "confidence": 0.98
+        },
+        {
+          "text": "ce",
+          "start": 138.94,
+          "end": 139.08,
+          "confidence": 0.578
+        },
+        {
+          "text": "qu'on",
+          "start": 139.08,
+          "end": 139.22,
+          "confidence": 0.96
+        },
+        {
+          "text": "peut",
+          "start": 139.22,
+          "end": 139.38,
+          "confidence": 0.547
+        },
+        {
+          "text": "ressentir",
+          "start": 139.38,
+          "end": 140.06,
+          "confidence": 0.888
+        },
+        {
+          "text": "à",
+          "start": 140.06,
+          "end": 140.26,
+          "confidence": 0.437
+        },
+        {
+          "text": "voir",
+          "start": 140.26,
+          "end": 140.54,
+          "confidence": 0.952
+        },
+        {
+          "text": "même",
+          "start": 140.54,
+          "end": 140.96,
+          "confidence": 0.297
+        },
+        {
+          "text": "mome",
+          "start": 140.96,
+          "end": 141.22,
+          "confidence": 0.496
+        },
+        {
+          "text": "aujourd'hui.",
+          "start": 141.22,
+          "end": 141.84,
+          "confidence": 0.961
+        }
+      ]
+    },
+    {
+      "id": 42,
+      "seek": 13698,
+      "start": 141.96,
+      "end": 145.86,
+      "text": " Continuellement avec son smartphone dans la main, comme c'était une sorte de estimateur",
+      "tokens": [
+        50606,
+        14674,
+        31816,
+        4163,
+        1872,
+        13307,
+        2680,
+        635,
+        2135,
+        11,
+        5173,
+        269,
+        6,
+        9743,
+        2251,
+        25559,
+        368,
+        8017,
+        15540,
+        50810
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5337450312471937,
+      "compression_ratio": 1.6231454005934718,
+      "no_speech_prob": 0.1096271350979805,
+      "confidence": 0.663,
+      "words": [
+        {
+          "text": "Continuellement",
+          "start": 141.96,
+          "end": 142.84,
+          "confidence": 0.844
+        },
+        {
+          "text": "avec",
+          "start": 142.84,
+          "end": 143.24,
+          "confidence": 0.646
+        },
+        {
+          "text": "son",
+          "start": 143.24,
+          "end": 143.42,
+          "confidence": 0.864
+        },
+        {
+          "text": "smartphone",
+          "start": 143.42,
+          "end": 143.72,
+          "confidence": 0.447
+        },
+        {
+          "text": "dans",
+          "start": 143.72,
+          "end": 143.92,
+          "confidence": 0.587
+        },
+        {
+          "text": "la",
+          "start": 143.92,
+          "end": 144.0,
+          "confidence": 0.974
+        },
+        {
+          "text": "main,",
+          "start": 144.0,
+          "end": 144.3,
+          "confidence": 0.995
+        },
+        {
+          "text": "comme",
+          "start": 144.42,
+          "end": 144.56,
+          "confidence": 0.895
+        },
+        {
+          "text": "c'était",
+          "start": 144.56,
+          "end": 144.84,
+          "confidence": 0.596
+        },
+        {
+          "text": "une",
+          "start": 144.84,
+          "end": 144.96,
+          "confidence": 0.972
+        },
+        {
+          "text": "sorte",
+          "start": 144.96,
+          "end": 145.1,
+          "confidence": 0.658
+        },
+        {
+          "text": "de",
+          "start": 145.1,
+          "end": 145.4,
+          "confidence": 0.312
+        },
+        {
+          "text": "estimateur",
+          "start": 145.4,
+          "end": 145.86,
+          "confidence": 0.489
+        }
+      ]
+    },
+    {
+      "id": 43,
+      "seek": 13698,
+      "start": 145.96,
+      "end": 149.0,
+      "text": " extère de tomber de lâcher à l'éantrénée, ça m'a eu immédiate.",
+      "tokens": [
+        50810,
+        1279,
+        4212,
+        368,
+        2916,
+        607,
+        368,
+        48835,
+        6759,
+        1531,
+        287,
+        6,
+        526,
+        394,
+        81,
+        3516,
+        3856,
+        11,
+        2788,
+        275,
+        6,
+        64,
+        2228,
+        3397,
+        526,
+        4504,
+        473,
+        13,
+        50954
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5337450312471937,
+      "compression_ratio": 1.6231454005934718,
+      "no_speech_prob": 0.1096271350979805,
+      "confidence": 0.416,
+      "words": [
+        {
+          "text": "extère",
+          "start": 145.96,
+          "end": 146.4,
+          "confidence": 0.371
+        },
+        {
+          "text": "de",
+          "start": 146.4,
+          "end": 146.54,
+          "confidence": 0.254
+        },
+        {
+          "text": "tomber",
+          "start": 146.54,
+          "end": 146.7,
+          "confidence": 0.102
+        },
+        {
+          "text": "de",
+          "start": 146.7,
+          "end": 146.9,
+          "confidence": 0.454
+        },
+        {
+          "text": "lâcher",
+          "start": 146.9,
+          "end": 147.34,
+          "confidence": 0.75
+        },
+        {
+          "text": "à",
+          "start": 147.34,
+          "end": 147.46,
+          "confidence": 0.444
+        },
+        {
+          "text": "l'éantrénée,",
+          "start": 147.46,
+          "end": 147.9,
+          "confidence": 0.491
+        },
+        {
+          "text": "ça",
+          "start": 148.0,
+          "end": 148.02,
+          "confidence": 0.799
+        },
+        {
+          "text": "m'a",
+          "start": 148.02,
+          "end": 148.26,
+          "confidence": 0.531
+        },
+        {
+          "text": "eu",
+          "start": 148.26,
+          "end": 148.44,
+          "confidence": 0.136
+        },
+        {
+          "text": "immédiate.",
+          "start": 148.44,
+          "end": 149.0,
+          "confidence": 0.505
+        }
+      ]
+    },
+    {
+      "id": 44,
+      "seek": 13698,
+      "start": 149.08,
+      "end": 151.98,
+      "text": " Bon, je dis ça pour le mome, mais évidemment, va là, bon aussi.",
+      "tokens": [
+        50954,
+        7368,
+        11,
+        1506,
+        717,
+        2788,
+        2016,
+        476,
+        275,
+        423,
+        11,
+        2420,
+        24724,
+        11,
+        2773,
+        3684,
+        11,
+        4428,
+        6212,
+        13,
+        51126
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5337450312471937,
+      "compression_ratio": 1.6231454005934718,
+      "no_speech_prob": 0.1096271350979805,
+      "confidence": 0.564,
+      "words": [
+        {
+          "text": "Bon,",
+          "start": 149.08,
+          "end": 149.28,
+          "confidence": 0.375
+        },
+        {
+          "text": "je",
+          "start": 149.34,
+          "end": 149.4,
+          "confidence": 0.471
+        },
+        {
+          "text": "dis",
+          "start": 149.4,
+          "end": 149.46,
+          "confidence": 0.324
+        },
+        {
+          "text": "ça",
+          "start": 149.46,
+          "end": 149.64,
+          "confidence": 0.952
+        },
+        {
+          "text": "pour",
+          "start": 149.64,
+          "end": 149.8,
+          "confidence": 0.963
+        },
+        {
+          "text": "le",
+          "start": 149.8,
+          "end": 149.92,
+          "confidence": 0.992
+        },
+        {
+          "text": "mome,",
+          "start": 149.92,
+          "end": 150.12,
+          "confidence": 0.619
+        },
+        {
+          "text": "mais",
+          "start": 150.46,
+          "end": 150.52,
+          "confidence": 0.694
+        },
+        {
+          "text": "évidemment,",
+          "start": 150.52,
+          "end": 151.12,
+          "confidence": 0.776
+        },
+        {
+          "text": "va",
+          "start": 151.26,
+          "end": 151.36,
+          "confidence": 0.388
+        },
+        {
+          "text": "là,",
+          "start": 151.36,
+          "end": 151.46,
+          "confidence": 0.59
+        },
+        {
+          "text": "bon",
+          "start": 151.6,
+          "end": 151.68,
+          "confidence": 0.825
+        },
+        {
+          "text": "aussi.",
+          "start": 151.68,
+          "end": 151.98,
+          "confidence": 0.162
+        }
+      ]
+    },
+    {
+      "id": 45,
+      "seek": 13698,
+      "start": 152.64,
+      "end": 154.64,
+      "text": " Donc, rapport immédiate d'accord.",
+      "tokens": [
+        51126,
+        7477,
+        11,
+        18018,
+        3397,
+        526,
+        4504,
+        473,
+        274,
+        6,
+        19947,
+        13,
+        51248
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5337450312471937,
+      "compression_ratio": 1.6231454005934718,
+      "no_speech_prob": 0.1096271350979805,
+      "confidence": 0.861,
+      "words": [
+        {
+          "text": "Donc,",
+          "start": 152.64,
+          "end": 153.08,
+          "confidence": 0.982
+        },
+        {
+          "text": "rapport",
+          "start": 153.16,
+          "end": 153.58,
+          "confidence": 0.979
+        },
+        {
+          "text": "immédiate",
+          "start": 153.58,
+          "end": 154.28,
+          "confidence": 0.841
+        },
+        {
+          "text": "d'accord.",
+          "start": 154.28,
+          "end": 154.64,
+          "confidence": 0.816
+        }
+      ]
+    },
+    {
+      "id": 46,
+      "seek": 13698,
+      "start": 155.66,
+      "end": 158.36,
+      "text": " Mais pourquoi, à ton impression qu'on en sortira, j'amé?",
+      "tokens": [
+        51248,
+        6313,
+        19934,
+        11,
+        1531,
+        2952,
+        9995,
+        421,
+        6,
+        266,
+        465,
+        26906,
+        64,
+        11,
+        361,
+        6,
+        335,
+        526,
+        30,
+        51440
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5337450312471937,
+      "compression_ratio": 1.6231454005934718,
+      "no_speech_prob": 0.1096271350979805,
+      "confidence": 0.709,
+      "words": [
+        {
+          "text": "Mais",
+          "start": 155.66,
+          "end": 155.88,
+          "confidence": 0.984
+        },
+        {
+          "text": "pourquoi,",
+          "start": 155.88,
+          "end": 156.28,
+          "confidence": 0.897
+        },
+        {
+          "text": "à",
+          "start": 156.38,
+          "end": 156.58,
+          "confidence": 0.837
+        },
+        {
+          "text": "ton",
+          "start": 156.58,
+          "end": 156.7,
+          "confidence": 0.953
+        },
+        {
+          "text": "impression",
+          "start": 156.7,
+          "end": 157.06,
+          "confidence": 0.938
+        },
+        {
+          "text": "qu'on",
+          "start": 157.06,
+          "end": 157.28,
+          "confidence": 0.89
+        },
+        {
+          "text": "en",
+          "start": 157.28,
+          "end": 157.4,
+          "confidence": 0.801
+        },
+        {
+          "text": "sortira,",
+          "start": 157.4,
+          "end": 157.88,
+          "confidence": 0.576
+        },
+        {
+          "text": "j'amé?",
+          "start": 157.96,
+          "end": 158.36,
+          "confidence": 0.464
+        }
+      ]
+    },
+    {
+      "id": 47,
+      "seek": 13698,
+      "start": 159.16,
+      "end": 163.32,
+      "text": " Et puis, il faut en remettre la faute sur les gens qui ont créé cette critique merveilleux",
+      "tokens": [
+        51440,
+        3790,
+        9093,
+        11,
+        1930,
+        8487,
+        465,
+        890,
+        40681,
+        635,
+        2050,
+        1169,
+        1022,
+        1512,
+        10668,
+        1956,
+        6592,
+        15609,
+        526,
+        5550,
+        25673,
+        3551,
+        303,
+        3409,
+        2449,
+        51678
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5337450312471937,
+      "compression_ratio": 1.6231454005934718,
+      "no_speech_prob": 0.1096271350979805,
+      "confidence": 0.714,
+      "words": [
+        {
+          "text": "Et",
+          "start": 159.16,
+          "end": 159.32,
+          "confidence": 0.832
+        },
+        {
+          "text": "puis,",
+          "start": 159.32,
+          "end": 159.46,
+          "confidence": 0.494
+        },
+        {
+          "text": "il",
+          "start": 159.62,
+          "end": 159.64,
+          "confidence": 0.594
+        },
+        {
+          "text": "faut",
+          "start": 159.64,
+          "end": 159.66,
+          "confidence": 0.951
+        },
+        {
+          "text": "en",
+          "start": 159.66,
+          "end": 159.78,
+          "confidence": 0.937
+        },
+        {
+          "text": "remettre",
+          "start": 159.78,
+          "end": 160.14,
+          "confidence": 0.984
+        },
+        {
+          "text": "la",
+          "start": 160.14,
+          "end": 160.42,
+          "confidence": 0.602
+        },
+        {
+          "text": "faute",
+          "start": 160.42,
+          "end": 160.68,
+          "confidence": 0.59
+        },
+        {
+          "text": "sur",
+          "start": 160.68,
+          "end": 160.98,
+          "confidence": 0.966
+        },
+        {
+          "text": "les",
+          "start": 160.98,
+          "end": 161.24,
+          "confidence": 0.828
+        },
+        {
+          "text": "gens",
+          "start": 161.24,
+          "end": 161.46,
+          "confidence": 0.986
+        },
+        {
+          "text": "qui",
+          "start": 161.46,
+          "end": 161.6,
+          "confidence": 0.98
+        },
+        {
+          "text": "ont",
+          "start": 161.6,
+          "end": 161.68,
+          "confidence": 0.95
+        },
+        {
+          "text": "créé",
+          "start": 161.68,
+          "end": 162.3,
+          "confidence": 0.95
+        },
+        {
+          "text": "cette",
+          "start": 162.3,
+          "end": 162.48,
+          "confidence": 0.908
+        },
+        {
+          "text": "critique",
+          "start": 162.48,
+          "end": 162.72,
+          "confidence": 0.032
+        },
+        {
+          "text": "merveilleux",
+          "start": 162.72,
+          "end": 163.32,
+          "confidence": 0.839
+        }
+      ]
+    },
+    {
+      "id": 48,
+      "seek": 13698,
+      "start": 163.32,
+      "end": 165.34,
+      "text": " et diabolique et diabolique par que merveilleux.",
+      "tokens": [
+        51678,
+        1030,
+        1026,
+        14923,
+        1925,
+        1030,
+        1026,
+        14923,
+        1925,
+        971,
+        631,
+        3551,
+        303,
+        3409,
+        2449,
+        13,
+        51778
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.5337450312471937,
+      "compression_ratio": 1.6231454005934718,
+      "no_speech_prob": 0.1096271350979805,
+      "confidence": 0.708,
+      "words": [
+        {
+          "text": "et",
+          "start": 163.32,
+          "end": 163.44,
+          "confidence": 0.945
+        },
+        {
+          "text": "diabolique",
+          "start": 163.44,
+          "end": 163.86,
+          "confidence": 0.573
+        },
+        {
+          "text": "et",
+          "start": 163.86,
+          "end": 163.94,
+          "confidence": 0.238
+        },
+        {
+          "text": "diabolique",
+          "start": 163.94,
+          "end": 164.38,
+          "confidence": 0.892
+        },
+        {
+          "text": "par",
+          "start": 164.38,
+          "end": 164.62,
+          "confidence": 0.544
+        },
+        {
+          "text": "que",
+          "start": 164.62,
+          "end": 164.82,
+          "confidence": 0.529
+        },
+        {
+          "text": "merveilleux.",
+          "start": 164.82,
+          "end": 165.34,
+          "confidence": 0.981
+        }
+      ]
+    },
+    {
+      "id": 49,
+      "seek": 16526,
+      "start": 166.9,
+      "end": 168.8,
+      "text": " Les économistes parlent de dépendance du santé.",
+      "tokens": [
+        50410,
+        6965,
+        31171,
+        22368,
+        13734,
+        317,
+        368,
+        45768,
+        719,
+        1581,
+        30068,
+        13,
+        50542
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6644235849380493,
+      "compression_ratio": 1.4761904761904763,
+      "no_speech_prob": 0.1915542334318161,
+      "confidence": 0.765,
+      "words": [
+        {
+          "text": "Les",
+          "start": 166.9,
+          "end": 167.06,
+          "confidence": 0.699
+        },
+        {
+          "text": "économistes",
+          "start": 167.06,
+          "end": 167.52,
+          "confidence": 0.917
+        },
+        {
+          "text": "parlent",
+          "start": 167.52,
+          "end": 167.78,
+          "confidence": 0.793
+        },
+        {
+          "text": "de",
+          "start": 167.78,
+          "end": 167.84,
+          "confidence": 0.813
+        },
+        {
+          "text": "dépendance",
+          "start": 167.84,
+          "end": 168.36,
+          "confidence": 0.698
+        },
+        {
+          "text": "du",
+          "start": 168.36,
+          "end": 168.5,
+          "confidence": 0.963
+        },
+        {
+          "text": "santé.",
+          "start": 168.5,
+          "end": 168.8,
+          "confidence": 0.489
+        }
+      ]
+    },
+    {
+      "id": 50,
+      "seek": 16526,
+      "start": 168.82,
+      "end": 173.42,
+      "text": " Ces vidéos, en fait, on est un santé qui a été étabis, un soit mon termine, en marchand dessus,",
+      "tokens": [
+        50542,
+        28414,
+        25417,
+        11,
+        465,
+        3887,
+        11,
+        322,
+        871,
+        517,
+        30068,
+        1956,
+        257,
+        8862,
+        4823,
+        455,
+        271,
+        11,
+        517,
+        12703,
+        1108,
+        1433,
+        533,
+        11,
+        465,
+        8368,
+        474,
+        30677,
+        11,
+        50784
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6644235849380493,
+      "compression_ratio": 1.4761904761904763,
+      "no_speech_prob": 0.1915542334318161,
+      "confidence": 0.474,
+      "words": [
+        {
+          "text": "Ces",
+          "start": 168.82,
+          "end": 169.14,
+          "confidence": 0.443
+        },
+        {
+          "text": "vidéos,",
+          "start": 169.14,
+          "end": 169.4,
+          "confidence": 0.455
+        },
+        {
+          "text": "en",
+          "start": 169.44,
+          "end": 169.64,
+          "confidence": 0.744
+        },
+        {
+          "text": "fait,",
+          "start": 169.64,
+          "end": 169.66,
+          "confidence": 0.976
+        },
+        {
+          "text": "on",
+          "start": 169.72,
+          "end": 169.74,
+          "confidence": 0.303
+        },
+        {
+          "text": "est",
+          "start": 169.74,
+          "end": 169.9,
+          "confidence": 0.814
+        },
+        {
+          "text": "un",
+          "start": 169.9,
+          "end": 170.48,
+          "confidence": 0.367
+        },
+        {
+          "text": "santé",
+          "start": 170.48,
+          "end": 170.8,
+          "confidence": 0.951
+        },
+        {
+          "text": "qui",
+          "start": 170.8,
+          "end": 170.92,
+          "confidence": 0.835
+        },
+        {
+          "text": "a",
+          "start": 170.92,
+          "end": 171.02,
+          "confidence": 0.819
+        },
+        {
+          "text": "été",
+          "start": 171.02,
+          "end": 171.12,
+          "confidence": 0.994
+        },
+        {
+          "text": "étabis,",
+          "start": 171.12,
+          "end": 171.5,
+          "confidence": 0.343
+        },
+        {
+          "text": "un",
+          "start": 171.76,
+          "end": 171.9,
+          "confidence": 0.236
+        },
+        {
+          "text": "soit",
+          "start": 171.9,
+          "end": 172.16,
+          "confidence": 0.31
+        },
+        {
+          "text": "mon",
+          "start": 172.16,
+          "end": 172.36,
+          "confidence": 0.205
+        },
+        {
+          "text": "termine,",
+          "start": 172.36,
+          "end": 172.72,
+          "confidence": 0.4
+        },
+        {
+          "text": "en",
+          "start": 172.8,
+          "end": 172.82,
+          "confidence": 0.309
+        },
+        {
+          "text": "marchand",
+          "start": 172.82,
+          "end": 173.14,
+          "confidence": 0.816
+        },
+        {
+          "text": "dessus,",
+          "start": 173.14,
+          "end": 173.42,
+          "confidence": 0.201
+        }
+      ]
+    },
+    {
+      "id": 51,
+      "seek": 16526,
+      "start": 173.86,
+      "end": 177.42,
+      "text": " soit des finissants débordes, des finissants, une signalétique.",
+      "tokens": [
+        50784,
+        12703,
+        730,
+        962,
+        891,
+        1719,
+        36529,
+        765,
+        279,
+        11,
+        730,
+        962,
+        891,
+        1719,
+        11,
+        2251,
+        6358,
+        42379,
+        13,
+        50974
+      ],
+      "temperature": 0.0,
+      "avg_logprob": -0.6644235849380493,
+      "compression_ratio": 1.4761904761904763,
+      "no_speech_prob": 0.1915542334318161,
+      "confidence": 0.582,
+      "words": [
+        {
+          "text": "soit",
+          "start": 173.86,
+          "end": 174.4,
+          "confidence": 0.993
+        },
+        {
+          "text": "des",
+          "start": 174.4,
+          "end": 175.2,
+          "confidence": 0.759
+        },
+        {
+          "text": "finissants",
+          "start": 175.2,
+          "end": 175.58,
+          "confidence": 0.436
+        },
+        {
+          "text": "débordes,",
+          "start": 175.58,
+          "end": 175.98,
+          "confidence": 0.467
+        },
+        {
+          "text": "des",
+          "start": 176.14,
+          "end": 176.18,
+          "confidence": 0.222
+        },
+        {
+          "text": "finissants,",
+          "start": 176.18,
+          "end": 176.62,
+          "confidence": 0.961
+        },
+        {
+          "text": "une",
+          "start": 176.66,
+          "end": 176.84,
+          "confidence": 0.75
+        },
+        {
+          "text": "signalétique.",
+          "start": 176.84,
+          "end": 177.42,
+          "confidence": 0.566
+        }
+      ]
+    }
+  ],
+  "language": "fr"
+}
\ No newline at end of file
diff --git a/tests/expected/verbose.cpu/accurate.auto_bonjour_vous_allez_bien.mp3.stdout b/tests/expected/verbose.cpu/accurate.auto_bonjour_vous_allez_bien.mp3.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..532d5eaf637389f5cfdbecc58823d2ccd29cfacb
--- /dev/null
+++ b/tests/expected/verbose.cpu/accurate.auto_bonjour_vous_allez_bien.mp3.stdout
@@ -0,0 +1,11 @@
+[00:00.460 --> 00:00.780] Боже
+[00:00.780 --> 00:01.980] улыл!
+[00:02.020 --> 00:02.260] Таков
+[00:02.260 --> 00:02.400] уже
+[00:02.400 --> 00:02.460] на
+[00:02.460 --> 00:02.800] меня!
+[00:32.980 --> 00:33.280] Боже
+[00:33.280 --> 00:33.800] улыл!
+[00:34.400 --> 00:34.800] Эскому
+[00:34.800 --> 00:34.960] за
+[00:34.960 --> 00:35.260] меня!
diff --git a/tests/expected/verbose.cpu/accurate.fr_bonjour_vous_allez_bien.mp3.stdout b/tests/expected/verbose.cpu/accurate.fr_bonjour_vous_allez_bien.mp3.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..bbe59141c7bb85cc4567ff0ac51949b691aea753
--- /dev/null
+++ b/tests/expected/verbose.cpu/accurate.fr_bonjour_vous_allez_bien.mp3.stdout
@@ -0,0 +1,13 @@
+[00:00.460 --> 00:00.680] Bonjour!
+[00:01.860 --> 00:02.140] Est-ce
+[00:02.140 --> 00:02.180] que
+[00:02.180 --> 00:02.340] vous
+[00:02.340 --> 00:02.480] allez
+[00:02.480 --> 00:02.800] bien?
+[00:32.980 --> 00:33.160] Bonjour!
+[00:34.400 --> 00:34.610] Bonjour!
+[00:34.610 --> 00:34.660] Est-ce
+[00:34.660 --> 00:34.720] que
+[00:34.720 --> 00:34.860] vous
+[00:34.860 --> 00:35.000] allez
+[00:35.000 --> 00:35.340] bien?
diff --git a/tests/expected/verbose.cpu/efficient.auto_bonjour_vous_allez_bien.mp3.stdout b/tests/expected/verbose.cpu/efficient.auto_bonjour_vous_allez_bien.mp3.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..532d5eaf637389f5cfdbecc58823d2ccd29cfacb
--- /dev/null
+++ b/tests/expected/verbose.cpu/efficient.auto_bonjour_vous_allez_bien.mp3.stdout
@@ -0,0 +1,11 @@
+[00:00.460 --> 00:00.780] Боже
+[00:00.780 --> 00:01.980] улыл!
+[00:02.020 --> 00:02.260] Таков
+[00:02.260 --> 00:02.400] уже
+[00:02.400 --> 00:02.460] на
+[00:02.460 --> 00:02.800] меня!
+[00:32.980 --> 00:33.280] Боже
+[00:33.280 --> 00:33.800] улыл!
+[00:34.400 --> 00:34.800] Эскому
+[00:34.800 --> 00:34.960] за
+[00:34.960 --> 00:35.260] меня!
diff --git a/tests/expected/verbose.cpu/efficient.fr_bonjour_vous_allez_bien.mp3.stdout b/tests/expected/verbose.cpu/efficient.fr_bonjour_vous_allez_bien.mp3.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..bbe59141c7bb85cc4567ff0ac51949b691aea753
--- /dev/null
+++ b/tests/expected/verbose.cpu/efficient.fr_bonjour_vous_allez_bien.mp3.stdout
@@ -0,0 +1,13 @@
+[00:00.460 --> 00:00.680] Bonjour!
+[00:01.860 --> 00:02.140] Est-ce
+[00:02.140 --> 00:02.180] que
+[00:02.180 --> 00:02.340] vous
+[00:02.340 --> 00:02.480] allez
+[00:02.480 --> 00:02.800] bien?
+[00:32.980 --> 00:33.160] Bonjour!
+[00:34.400 --> 00:34.610] Bonjour!
+[00:34.610 --> 00:34.660] Est-ce
+[00:34.660 --> 00:34.720] que
+[00:34.720 --> 00:34.860] vous
+[00:34.860 --> 00:35.000] allez
+[00:35.000 --> 00:35.340] bien?
diff --git a/tests/expected/verbose.cpu/hf_bonjour.wav.stdout b/tests/expected/verbose.cpu/hf_bonjour.wav.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..99635535fd87302067c97ce13d42f2988dacdd83
--- /dev/null
+++ b/tests/expected/verbose.cpu/hf_bonjour.wav.stdout
@@ -0,0 +1,3 @@
+Detecting language using up to the first 30 seconds. Use `--language` to specify the language
+Detected language: French
+[00:00.120 --> 00:00.640] Bonjour.
diff --git a/tests/expected/verbose/accurate.auto_bonjour_vous_allez_bien.mp3.stdout b/tests/expected/verbose/accurate.auto_bonjour_vous_allez_bien.mp3.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..6bfee4b97e33192bc46f69994bddcd817c220226
--- /dev/null
+++ b/tests/expected/verbose/accurate.auto_bonjour_vous_allez_bien.mp3.stdout
@@ -0,0 +1,10 @@
+Detecting language using up to the first 30 seconds. Use `--language` to specify the language
+Detected language: Russian
+[00:00.440 --> 00:00.860] Боже
+[00:00.860 --> 00:01.880] улыл!
+[00:01.880 --> 00:02.300] Эскому
+[00:02.300 --> 00:03.140] зарегиан!
+[00:32.980 --> 00:33.360] Боже
+[00:33.360 --> 00:34.020] улыл!
+[00:34.420 --> 00:34.840] Эскому
+[00:34.840 --> 00:35.720] зарегиан!
diff --git a/tests/expected/verbose/accurate.fr_bonjour_vous_allez_bien.mp3.stdout b/tests/expected/verbose/accurate.fr_bonjour_vous_allez_bien.mp3.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..ec0d882ef119c14b9da62584ee57728eab7691fd
--- /dev/null
+++ b/tests/expected/verbose/accurate.fr_bonjour_vous_allez_bien.mp3.stdout
@@ -0,0 +1,11 @@
+[00:00.440 --> 00:01.440] Bonjour !
+[00:01.880 --> 00:02.200] Est-ce
+[00:02.200 --> 00:02.240] que
+[00:02.240 --> 00:02.360] vous
+[00:02.360 --> 00:02.560] allez
+[00:02.560 --> 00:03.120] bien ?
+[00:32.980 --> 00:33.480] Bonjour !
+[00:34.420 --> 00:34.760] Esque
+[00:34.760 --> 00:34.900] vous
+[00:34.900 --> 00:35.080] allez
+[00:35.080 --> 00:35.480] bien !
diff --git a/tests/expected/verbose/efficient.auto_bonjour_vous_allez_bien.mp3.stdout b/tests/expected/verbose/efficient.auto_bonjour_vous_allez_bien.mp3.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..6bfee4b97e33192bc46f69994bddcd817c220226
--- /dev/null
+++ b/tests/expected/verbose/efficient.auto_bonjour_vous_allez_bien.mp3.stdout
@@ -0,0 +1,10 @@
+Detecting language using up to the first 30 seconds. Use `--language` to specify the language
+Detected language: Russian
+[00:00.440 --> 00:00.860] Боже
+[00:00.860 --> 00:01.880] улыл!
+[00:01.880 --> 00:02.300] Эскому
+[00:02.300 --> 00:03.140] зарегиан!
+[00:32.980 --> 00:33.360] Боже
+[00:33.360 --> 00:34.020] улыл!
+[00:34.420 --> 00:34.840] Эскому
+[00:34.840 --> 00:35.720] зарегиан!
diff --git a/tests/expected/verbose/efficient.fr_bonjour_vous_allez_bien.mp3.stdout b/tests/expected/verbose/efficient.fr_bonjour_vous_allez_bien.mp3.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..ec0d882ef119c14b9da62584ee57728eab7691fd
--- /dev/null
+++ b/tests/expected/verbose/efficient.fr_bonjour_vous_allez_bien.mp3.stdout
@@ -0,0 +1,11 @@
+[00:00.440 --> 00:01.440] Bonjour !
+[00:01.880 --> 00:02.200] Est-ce
+[00:02.200 --> 00:02.240] que
+[00:02.240 --> 00:02.360] vous
+[00:02.360 --> 00:02.560] allez
+[00:02.560 --> 00:03.120] bien ?
+[00:32.980 --> 00:33.480] Bonjour !
+[00:34.420 --> 00:34.760] Esque
+[00:34.760 --> 00:34.900] vous
+[00:34.900 --> 00:35.080] allez
+[00:35.080 --> 00:35.480] bien !
diff --git a/tests/expected/verbose/hf_bonjour.wav.stdout b/tests/expected/verbose/hf_bonjour.wav.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..99635535fd87302067c97ce13d42f2988dacdd83
--- /dev/null
+++ b/tests/expected/verbose/hf_bonjour.wav.stdout
@@ -0,0 +1,3 @@
+Detecting language using up to the first 30 seconds. Use `--language` to specify the language
+Detected language: French
+[00:00.120 --> 00:00.640] Bonjour.
diff --git a/tests/expected/verbose/vad_auditok_words.wav.stdout b/tests/expected/verbose/vad_auditok_words.wav.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..f0d2d990dc8c2da3adf9a47ec88b0fbfac0c7af1
--- /dev/null
+++ b/tests/expected/verbose/vad_auditok_words.wav.stdout
@@ -0,0 +1,8 @@
+[00:00.750 --> 00:01.470] settlement,
+[00:02.950 --> 00:03.670] Kentucky,
+[00:05.770 --> 00:06.290] causing
+[00:07.900 --> 00:08.950] damage,
+[00:10.900 --> 00:11.700] President,
+[00:14.200 --> 00:14.780] expansion,
+[00:17.120 --> 00:17.760] hospital,
+[00:20.730 --> 00:21.330] devastated.
diff --git a/tests/expected/verbose/vad_silero3.0_words.wav.stdout b/tests/expected/verbose/vad_silero3.0_words.wav.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..79e9f6107b1e48c0323c7fcfd843f9f3a9bf1be9
--- /dev/null
+++ b/tests/expected/verbose/vad_silero3.0_words.wav.stdout
@@ -0,0 +1,8 @@
+[00:00.760 --> 00:01.480] settlement,
+[00:02.890 --> 00:03.670] Kentucky,
+[00:05.710 --> 00:06.270] causing
+[00:07.850 --> 00:08.930] damage,
+[00:10.940 --> 00:11.700] president,
+[00:14.200 --> 00:14.780] expansion,
+[00:17.120 --> 00:17.780] hospital,
+[00:20.140 --> 00:21.380] devastated.
diff --git a/tests/expected/verbose/vad_silero3.1_words.wav.stdout b/tests/expected/verbose/vad_silero3.1_words.wav.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..54b0fd0716a5eed94c6a92c3ea372b879cec5401
--- /dev/null
+++ b/tests/expected/verbose/vad_silero3.1_words.wav.stdout
@@ -0,0 +1,8 @@
+[00:00.760 --> 00:01.480] settlement,
+[00:02.920 --> 00:03.660] Kentucky,
+[00:05.760 --> 00:06.260] causing
+[00:07.850 --> 00:08.940] damage,
+[00:10.840 --> 00:11.700] president,
+[00:14.190 --> 00:14.770] expansion,
+[00:17.130 --> 00:17.750] hospital,
+[00:21.200 --> 00:21.380] devastated.
diff --git a/tests/expected/verbose/vad_words.wav.stdout b/tests/expected/verbose/vad_words.wav.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..5dbf58fc48651f530a5a99a116062ab15fe66aeb
--- /dev/null
+++ b/tests/expected/verbose/vad_words.wav.stdout
@@ -0,0 +1,8 @@
+[00:00.760 --> 00:01.460] settlement,
+[00:02.900 --> 00:03.680] Kentucky,
+[00:05.710 --> 00:06.270] causing
+[00:07.890 --> 00:08.940] damage,
+[00:10.930 --> 00:11.690] president,
+[00:14.070 --> 00:14.770] expansion,
+[00:17.140 --> 00:17.780] hospital,
+[00:20.730 --> 00:21.370] devastated.
diff --git a/tests/json_schema.json b/tests/json_schema.json
new file mode 100644
index 0000000000000000000000000000000000000000..63dfcc6e7ac6247c85d515442d144d744109fc12
--- /dev/null
+++ b/tests/json_schema.json
@@ -0,0 +1,41 @@
+{
+    "type": "object",
+    "properties": {
+        "text": {"type": "string"},
+        "segments": {
+            "type": "array",
+            "items": {
+                "type": "object",
+                "properties": {
+                    "id": {"type": "integer", "minimum":0},
+                    "start": {"type": "number", "minimum":0},
+                    "end": {"type": "number", "minimum":0},
+                    "text": {"type": "string"},
+                    "tokens": {
+                        "type": "array",
+                        "items": {"type": "integer", "minimum": 0, "maximum": 51864}
+                    },
+                    "temperature": {"type": "number", "minimum":0, "maximum":1},
+                    "avg_logprob": {"type": "number", "maximum":0},
+                    "compression_ratio": {"type": "number", "minimum":0},
+                    "no_speech_prob": {"type": "number", "minimum":0, "maximum":1},
+                    "confidence": {"type": "number", "minimum":0, "maximum":1},
+                    "words": {
+                        "type": "array",
+                        "items": {
+                            "type": "object",
+                            "properties": {
+                                "text": {"type": "string"},
+                                "start": {"type": "number", "minimum":0},
+                                "end": {"type": "number", "minimum":0},
+                                "confidence": {"type": "number", "minimum":0, "maximum":1}
+                            }
+                        }
+                    }
+                }
+            },
+            "minItems": 0,
+            "uniqueItems": true
+        }
+    }
+}
diff --git a/tests/run_tests.py b/tests/run_tests.py
new file mode 100644
index 0000000000000000000000000000000000000000..0b202b69af065c478fc99607b012ccec40cf5580
--- /dev/null
+++ b/tests/run_tests.py
@@ -0,0 +1,48 @@
+import sys
+import unittest
+
+from test_transcribe import *
+import test_transcribe
+
+if __name__ == '__main__':
+
+    # Handle several ways of generating expected outputs
+    if "--long" in sys.argv:
+        test_transcribe.SKIP_LONG_TEST_IF_CPU = False
+        sys.argv.remove("--long")
+    if "--generate" in sys.argv:
+        test_transcribe.FAIL_IF_REFERENCE_NOT_FOUND = False
+        sys.argv.remove("--generate")
+    if "--generate_device" in sys.argv:
+        test_transcribe.GENERATE_DEVICE_DEPENDENT = True
+        test_transcribe.FAIL_IF_REFERENCE_NOT_FOUND = False
+        sys.argv.remove("--generate_device")
+    if "--generate_new" in sys.argv:
+        test_transcribe.GENERATE_NEW_ONLY = True
+        test_transcribe.FAIL_IF_REFERENCE_NOT_FOUND = False
+        sys.argv.remove("--generate_new")
+    if "--generate_all" in sys.argv:
+        test_transcribe.GENERATE_ALL = True
+        test_transcribe.FAIL_IF_REFERENCE_NOT_FOUND = False
+        sys.argv.remove("--generate_all")
+
+    # Pass options to whisper_timestamped CLI
+    args = sys.argv[1:]
+    for i, arg in enumerate(args):
+        if arg not in [
+            "-h", "--help",
+            "-v", "--verbose",
+            "--locals",
+            "-q", "--quiet",
+            "-f", "--failfast",
+            "-c", "--catch",
+            "-b", "--buffer",
+            "-k",
+        ] \
+        and not arg.startswith("Test") \
+        and (i==0 or args[i-1] not in ["-k"]) \
+        and (arg.startswith("-") or (i>0 and args[i-1].startswith("-"))):
+            test_transcribe.CMD_OPTIONS.append(arg)
+            sys.argv.remove(arg)
+
+    unittest.main()
diff --git a/tests/test_transcribe.py b/tests/test_transcribe.py
new file mode 100644
index 0000000000000000000000000000000000000000..d16830e6f4d767695da430692757d71f5253de16
--- /dev/null
+++ b/tests/test_transcribe.py
@@ -0,0 +1,880 @@
+__author__ = "Jérôme Louradour"
+__credits__ = ["Jérôme Louradour"]
+__license__ = "GPLv3"
+
+import unittest
+import sys
+import os
+import subprocess
+import shutil
+import tempfile
+import json
+import torch
+import jsonschema
+
+FAIL_IF_REFERENCE_NOT_FOUND = True
+GENERATE_NEW_ONLY = False
+GENERATE_ALL = False
+GENERATE_DEVICE_DEPENDENT = False
+SKIP_LONG_TEST_IF_CPU = True
+CMD_OPTIONS = []
+
+
+class TestHelper(unittest.TestCase):
+
+    def skipLongTests(self):
+        return SKIP_LONG_TEST_IF_CPU and not torch.cuda.is_available()
+
+    def setUp(self):
+        self.maxDiff = None
+        self.createdReferences = []
+
+    def tearDown(self):
+        if GENERATE_ALL or GENERATE_NEW_ONLY or not FAIL_IF_REFERENCE_NOT_FOUND or GENERATE_DEVICE_DEPENDENT:
+            if len(self.createdReferences) > 0:
+                print("WARNING: Created references: " +
+                      ", ".join(self.createdReferences).replace(self.get_data_path()+"/", ""))
+        else:
+            self.assertEqual(self.createdReferences, [], "Created references: " +
+                             ", ".join(self.createdReferences).replace(self.get_data_path()+"/", ""))
+
+    def get_main_path(self, fn=None, check=False):
+        return self._get_path("whisper_timestamped", fn, check=check)
+
+    def get_output_path(self, fn=None):
+        if fn == None:
+            return tempfile.gettempdir()
+        return os.path.join(tempfile.gettempdir(), fn + self._extra_cmd_options())
+
+    def get_expected_path(self, fn=None, check=False):
+        return self._get_path("tests/expected" + self._extra_cmd_options(), fn, check=check)
+    
+    def _extra_cmd_options(self):
+        s = "".join([f.replace("-","").strip() for f in CMD_OPTIONS])
+        if s:
+            return "." + s
+        return ""
+
+    def get_data_files(self, files=None, excluded_by_default=["apollo11.mp3", "music.mp4", "arabic.mp3", "japanese.mp3", "empty.wav", "words.wav"]):
+        if files == None:
+            files = os.listdir(self.get_data_path())
+            files = [f for f in files if f not in excluded_by_default and not f.endswith("json")]
+            files = sorted(files)
+        return [self.get_data_path(fn) for fn in files]
+
+    def get_generated_files(self, input_filename, output_path, extensions):
+        for ext in extensions:
+            yield os.path.join(output_path, os.path.basename(input_filename) + "." + ext.lstrip("."))
+
+    def main_script(self, pyscript = "transcribe.py", exename = "whisper_timestamped"):
+        main_script = self.get_main_path(pyscript, check=False)
+        if not os.path.exists(main_script):
+            main_script = exename
+        return main_script
+
+    def assertRun(self, cmd):
+        if isinstance(cmd, str):
+            return self.assertRun(cmd.split())
+        curdir = os.getcwd()
+        os.chdir(tempfile.gettempdir())
+        if cmd[0].endswith(".py"):
+            cmd = [sys.executable] + cmd
+        print("Running:", " ".join(cmd))
+        p = subprocess.Popen(cmd,
+                             # Otherwise ".local" path might be missing
+                             env=dict(
+                                 os.environ, PYTHONPATH=os.pathsep.join(sys.path)),
+                             stdout=subprocess.PIPE, stderr=subprocess.PIPE
+                             )
+        os.chdir(curdir)
+        (stdout, stderr) = p.communicate()
+        self.assertEqual(p.returncode, 0, msg=stderr.decode("utf-8"))
+        return (stdout.decode("utf-8"), stderr.decode("utf-8"))
+
+    def assertNonRegression(self, content, reference, string_is_file=True):
+        """
+        Check that a file/folder is the same as a reference file/folder.
+        """
+        if isinstance(content, dict):
+            # Make a temporary file
+            with tempfile.NamedTemporaryFile(mode="w", suffix=".json", encoding="utf8", delete=False) as f:
+                json.dump(content, f, indent=2, ensure_ascii=False)
+                content = f.name
+            res = self.assertNonRegression(f.name, reference)
+            os.remove(f.name)
+            return res
+        elif not isinstance(content, str):
+            raise ValueError(f"Invalid content type: {type(content)}")
+
+        if not string_is_file:
+            with tempfile.NamedTemporaryFile(mode="w", suffix=".txt", encoding="utf8", delete=False) as f:
+                f.write(content)
+                content = f.name 
+            res = self.assertNonRegression(f.name, reference)
+            os.remove(f.name)
+            return res
+
+        self.assertTrue(os.path.exists(content), f"Missing file: {content}")
+        is_file = os.path.isfile(reference) if os.path.exists(reference) else os.path.isfile(content)
+
+        reference = self.get_expected_path(
+            reference, check=FAIL_IF_REFERENCE_NOT_FOUND)
+        if not os.path.exists(reference) or ((GENERATE_ALL or GENERATE_DEVICE_DEPENDENT) and reference not in self.createdReferences):
+            dirname = os.path.dirname(reference)
+            if not os.path.isdir(dirname):
+                os.makedirs(dirname)
+            if is_file:
+                shutil.copyfile(content, reference)
+            else:
+                shutil.copytree(content, reference)
+            self.createdReferences.append(reference)
+
+        if is_file:
+            self.assertTrue(os.path.isfile(content))
+            self._check_file_non_regression(content, reference)
+        else:
+            self.assertTrue(os.path.isdir(content))
+            for root, dirs, files in os.walk(content):
+                for f in files:
+                    f_ref = os.path.join(reference, f)
+                    self.assertTrue(os.path.isfile(f_ref),
+                                    f"Additional file: {f}")
+                    self._check_file_non_regression(
+                        os.path.join(root, f), f_ref)
+            for root, dirs, files in os.walk(reference):
+                for f in files:
+                    f = os.path.join(content, f)
+                    self.assertTrue(os.path.isfile(f), f"Missing file: {f}")
+
+    def get_data_path(self, fn=None, check=True):
+        return self._get_path("tests/data", fn, check)
+
+    def _get_path(self, prefix, fn=None, check=True):
+        path = os.path.join(
+            os.path.dirname(os.path.dirname(__file__)),
+            prefix
+        )
+        if fn:
+            path = os.path.join(path, fn)
+        if check:
+            self.assertTrue(os.path.exists(path), f"Cannot find {path}")
+        return path
+
+    def _check_file_non_regression(self, file, reference):
+        if file.endswith(".json"):
+            with open(file) as f:
+                content = json.load(f)
+            with open(reference) as f:
+                reference_content = json.load(f)
+            if "language" in content and "language" in reference_content:
+                content["language"] = self.norm_language(content["language"])
+                reference_content["language"] = self.norm_language(reference_content["language"])
+            self.assertClose(content, reference_content,
+                             msg=f"File {file} does not match reference {reference}")
+            return
+        with open(file) as f:
+            content = f.readlines()
+        with open(reference) as f:
+            reference_content = f.readlines()
+        self.assertEqual(content, reference_content,
+                         msg=f"File {file} does not match reference {reference}")
+
+    def assertClose(self, obj1, obj2, msg=None):
+        return self.assertEqual(self.loose(obj1), self.loose(obj2), msg=msg)
+
+    def loose(self, obj):
+        # Return an approximative value of an object
+        if isinstance(obj, list):
+            return [self.loose(a) for a in obj]
+        if isinstance(obj, float):
+            f = round(obj, 1)
+            return 0.0 if f == -0.0 else f
+        if isinstance(obj, dict):
+            return {k: self.loose(v) for k, v in obj.items()}
+        if isinstance(obj, tuple):
+            return tuple(self.loose(list(obj)))
+        if isinstance(obj, set):
+            return self.loose(list(obj), "set")
+        return obj
+
+    def get_audio_duration(self, audio_file):
+        # Get the duration in sec *without introducing additional dependencies*
+        import whisper
+        return len(whisper.load_audio(audio_file)) / whisper.audio.SAMPLE_RATE
+
+    def get_device_str(self):
+        import torch
+        return "cpu" if not torch.cuda.is_available() else "cuda"
+
+    def norm_language(self, language):
+        # Cheap custom stuff to avoid importing everything
+        return {
+            "japanese": "ja",
+        }.get(language.lower(), language)
+
+
+class TestHelperCli(TestHelper):
+
+    json_schema = None
+
+    def _test_cli_(self, opts, name, files=None, extensions=["words.json"], prefix=None, one_per_call=True, device_specific=None):
+        """
+        Test command line
+        opts: list of options
+        name: name of the test
+        files: list of files to process
+        extensions: list of extensions to check, or None to test the stdout
+        prefix: prefix to add to the reference files
+        one_per_call: if True, each file is processed separately, otherwise all files are processed by a single process
+        """
+
+        opts = opts + CMD_OPTIONS
+
+        output_dir = self.get_output_path(name)
+
+        input_filenames = self.get_data_files(files)
+
+        for i, input_filename in enumerate(input_filenames):
+
+            # Butterfly effect: Results are different depending on the device for long files
+            duration = self.get_audio_duration(input_filename)
+            if device_specific is None:
+                device_dependent = duration > 60 or (duration > 30 and "tiny_fr" in name) or ("empty" in input_filename and "medium_auto" in name)
+            else:
+                device_dependent = device_specific
+            name_ = name
+            if device_dependent and self.get_device_str() != "cuda":
+                name_ += f".{self.get_device_str()}"
+
+            def ref_name(output_filename):
+                return name_ + "/" + (f"{prefix}_" if prefix else "") + os.path.basename(output_filename)
+            generic_name = ref_name(input_filename + ".*")
+
+            if GENERATE_DEVICE_DEPENDENT and not device_dependent:
+                print("Skipping non-regression test", generic_name)
+                continue
+
+            if GENERATE_NEW_ONLY and min([os.path.exists(self.get_expected_path(ref_name(output_filename)))
+                                          for output_filename in self.get_generated_files(input_filename, output_dir, extensions=extensions)]
+                                         ):
+                print("Skipping non-regression test", generic_name)
+                continue
+
+            print("Running non-regression test", generic_name)
+
+            if one_per_call or i == 0:
+                if one_per_call:
+                    (stdout, stderr) = self.assertRun([self.main_script(), input_filename, "--output_dir", output_dir, *opts])
+                else:
+                    (stdout, stderr) = self.assertRun([self.main_script(), *input_filenames, "--output_dir", output_dir, *opts])
+                print(stdout)
+                print(stderr)
+
+            output_json = self.get_generated_files(input_filename, output_dir, extensions=["words.json"]).__next__()
+            if os.path.isfile(output_json):
+                self.check_json(output_json)
+
+            if extensions is None:
+                output_filename = list(self.get_generated_files(input_filename, output_dir, extensions=["stdout"]))[0]
+                self.assertNonRegression(stdout, ref_name(output_filename), string_is_file=False)
+            else:
+                for output_filename in self.get_generated_files(input_filename, output_dir, extensions=extensions):
+                    self.assertNonRegression(output_filename, ref_name(output_filename))
+
+
+        shutil.rmtree(output_dir, ignore_errors=True)
+
+    def check_json(self, json_file):
+        with open(json_file) as f:
+            content = json.load(f)
+
+        if self.json_schema is None:
+            schema_file = os.path.join(os.path.dirname(__file__), "json_schema.json")
+            self.assertTrue(os.path.isfile(schema_file), msg=f"Schema file {schema_file} not found")
+            self.json_schema = json.load(open(schema_file))
+
+        jsonschema.validate(instance=content, schema=self.json_schema)
+
+
+
+class TestTranscribeTiny(TestHelperCli):
+
+    def test_cli_tiny_auto(self):
+        self._test_cli_(
+            ["--model", "tiny"],
+            "tiny_auto",
+        )
+
+    def test_cli_tiny_fr(self):
+        self._test_cli_(
+            ["--model", "tiny", "--language", "fr"],
+            "tiny_fr",
+        )
+
+
+class TestTranscribeMedium(TestHelperCli):
+
+    def test_cli_medium_auto(self):
+        self._test_cli_(
+            ["--model", "medium"],
+            "medium_auto",
+        )
+
+    def test_cli_medium_fr(self):
+        self._test_cli_(
+            ["--model", "medium", "--language", "fr"],
+            "medium_fr",
+        )
+
+
+class TestTranscribeNaive(TestHelperCli):
+
+    def test_naive(self):
+
+        self._test_cli_(
+            ["--model", "small", "--language", "en", "--efficient", "--naive"],
+            "naive",
+            files=["apollo11.mp3"],
+            prefix="naive",
+        )
+
+        self._test_cli_(
+            ["--model", "small", "--language", "en", "--accurate"],
+            "naive",
+            files=["apollo11.mp3"],
+            prefix="accurate",
+        )
+
+    def test_stucked_segments(self):
+        self._test_cli_(
+            ["--model", "tiny"],
+            "corner_cases",
+            files=["apollo11.mp3"],
+            prefix="accurate.tiny",
+        )
+
+
+class TestTranscribeCornerCases(TestHelperCli):
+
+    def test_stucked_lm(self):
+        if self.skipLongTests():
+            return
+
+        self._test_cli_(
+            ["--model", "small", "--language", "en", "--efficient"],
+            "corner_cases",
+            files=["apollo11.mp3"],
+            prefix="stucked_lm",
+        )
+
+    def test_punctuation_only(self):
+
+        # When there is only a punctuation detected in a segment, it could cause issue #24
+        self._test_cli_(
+            ["--model", "medium.en", "--efficient", "--punctuations", "False"],
+            "corner_cases",
+            files=["empty.wav"],
+            prefix="issue24",
+        )
+
+    def test_temperature(self):
+
+        self._test_cli_(
+            ["--model", "small", "--language", "English",
+                "--condition", "False", "--temperature", "0.1", "--efficient"],
+            "corner_cases",
+            files=["apollo11.mp3"],
+            prefix="random.nocond",
+        )
+
+        if self.skipLongTests():
+            return
+
+        self._test_cli_(
+            ["--model", "small", "--language", "en", "--temperature", "0.2", "--efficient"],
+            "corner_cases",
+            files=["apollo11.mp3"],
+            prefix="random",
+        )
+
+    def test_not_conditioned(self):
+
+        if not os.path.exists(self.get_data_path("music.mp4", check=False)):
+            return
+        if self.skipLongTests():
+            return
+
+        self._test_cli_(
+            ["--model", "medium", "--language", "en", "--condition", "False", "--efficient"],
+            "corner_cases",
+            files=["music.mp4"],
+            prefix="nocond",
+        )
+
+        self._test_cli_(
+            ["--model", "medium", "--language", "en",
+                "--condition", "False", "--temperature", "0.4", "--efficient"],
+            "corner_cases",
+            files=["music.mp4"],
+            prefix="nocond.random",
+        )
+
+    def test_large(self):
+        if self.skipLongTests():
+            return
+
+        self._test_cli_(
+            ["--model", "large-v2", "--language", "en",
+                "--condition", "False", "--temperature", "0.4", "--efficient"],
+            "corner_cases",
+            files=["apollo11.mp3"],
+            prefix="large",
+        )
+
+        if os.path.exists(self.get_data_path("arabic.mp3", check=False)):
+            self._test_cli_(
+                ["--model", "large-v2", "--language", "Arabic", "--efficient"],
+                "corner_cases",
+                files=["arabic.mp3"]
+            )
+
+    def test_gloria(self):
+
+        for model in ["medium", "large-v2"]:
+            for dec in ["efficient", "accurate"]:
+                self._test_cli_(
+                    ["--model", model, "--language", "en", "--" + dec],
+                    "corner_cases",
+                    files=["gloria.mp3"],
+                    prefix=model + "." + dec,
+                )
+
+class TestTranscribeMonolingual(TestHelperCli):
+
+    def test_monolingual_tiny(self):
+
+        files = ["bonjour_vous_allez_bien.mp3"]
+
+        self._test_cli_(
+            ["--model", "tiny.en", "--efficient"],
+            "tiny.en",
+            files=files,
+            prefix="efficient",
+        )
+
+        self._test_cli_(
+            ["--model", "tiny.en", "--accurate"],
+            "tiny.en",
+            files=files,
+            prefix="accurate",
+        )
+
+        self._test_cli_(
+            ["--model", "tiny.en", "--condition", "False", "--efficient"],
+            "tiny.en",
+            files=files,
+            prefix="nocond",
+        )
+
+    def test_monolingual_small(self):
+
+        if os.path.exists(self.get_data_path("arabic.mp3", check=False)):
+            self._test_cli_(
+                ["--model", "small.en", "--condition", "True", "--efficient"],
+                "small.en",
+                files=["arabic.mp3"],
+                device_specific=True,
+            )
+
+
+class TestTranscribeWithVad(TestHelperCli):
+
+    def test_vad_default(self):
+        self._test_cli_(
+                ["--model", "tiny", "--accurate", "--language", "en", "--vad", "True", "--verbose", "True"],
+                "verbose",
+                files=["words.wav"],
+                prefix="vad",
+                extensions=None,
+            )
+
+    def test_vad_custom_silero(self):
+        self._test_cli_(
+                ["--model", "tiny", "--accurate", "--language", "en", "--vad", "silero:v3.1", "--verbose", "True"],
+                "verbose",
+                files=["words.wav"],
+                prefix="vad_silero3.1",
+                extensions=None,
+            )
+        self._test_cli_(
+                ["--model", "tiny", "--accurate", "--language", "en", "--vad", "silero:v3.0", "--verbose", "True"],
+                "verbose",
+                files=["words.wav"],
+                prefix="vad_silero3.0",
+                extensions=None,
+            )
+
+    def test_vad_custom_auditok(self):
+        self._test_cli_(
+                ["--model", "tiny", "--language", "en", "--vad", "auditok", "--verbose", "True"],
+                "verbose",
+                files=["words.wav"],
+                prefix="vad_auditok",
+                extensions=None,
+            )
+
+
+class TestTranscribeUnspacedLanguage(TestHelperCli):
+
+    def test_japanese(self):
+
+        self._test_cli_(
+            ["--model", "tiny", "--efficient"],
+            "tiny_auto",
+            files=["japanese.mp3"],
+            device_specific=True,
+        )
+
+        self._test_cli_(
+            ["--model", "tiny", "--language", "Japanese", "--efficient"],
+            "tiny_auto",
+            files=["japanese.mp3"],
+            prefix="jp",
+            device_specific=True,
+        )
+
+        self._test_cli_(
+            ["--model", "tiny", "--accurate"],
+            "tiny_auto",
+            files=["japanese.mp3"],
+            prefix="accurate",
+            device_specific=True,
+        )
+
+        self._test_cli_(
+            ["--model", "tiny", "--language", "Japanese", "--accurate"],
+            "tiny_auto",
+            files=["japanese.mp3"],
+            prefix="accurate_jp",
+            device_specific=True,
+        )
+
+class TestTranscribeFormats(TestHelperCli):
+
+    def test_cli_outputs(self):
+        files = ["punctuations.mp3", "bonjour.wav"]
+        extensions = ["txt", "srt", "vtt", "words.srt", "words.vtt",
+                      "words.json", "csv", "words.csv", "tsv", "words.tsv"]
+        opts = ["--model", "medium", "--language", "fr"]
+
+        # An audio / model combination that produces coma
+        self._test_cli_(
+            opts,
+            "punctuations_yes",
+            files=files,
+            extensions=extensions,
+            one_per_call=False,
+        )
+        self._test_cli_(
+            opts + ["--punctuations", "False"],
+            "punctuations_no",
+            files=files,
+            extensions=extensions,
+            one_per_call=False,
+        )
+
+    def test_verbose(self):
+
+        files = ["bonjour_vous_allez_bien.mp3"]
+        opts = ["--model", "tiny", "--verbose", "True"]
+
+        self._test_cli_(
+            ["--efficient", *opts],
+            "verbose", files=files, extensions=None,
+            prefix="efficient.auto",
+            device_specific=True,
+        )
+
+        self._test_cli_(
+            ["--language", "fr", "--efficient", *opts],
+            "verbose", files=files, extensions=None,
+            prefix="efficient.fr",
+            device_specific=True,
+        )
+
+        self._test_cli_(
+            opts,
+            "verbose", files=files, extensions=None,
+            prefix="accurate.auto",
+            device_specific=True,
+        )
+
+        self._test_cli_(
+            ["--language", "fr", *opts],
+            "verbose", files=files, extensions=None,
+            prefix="accurate.fr",
+            device_specific=True,
+        )
+
+class TestMakeSubtitles(TestHelper):
+
+    def test_make_subtitles(self):
+
+        main_script = self.main_script("make_subtitles.py", "whisper_timestamped_make_subtitles")
+
+        inputs = [
+            self.get_data_path("smartphone.mp3.words.json"),
+            self.get_data_path("no_punctuations.mp3.words.json", check=True),
+            self.get_data_path("yes_punctuations.mp3.words.json", check=True),
+        ]
+
+        for i, input in enumerate(inputs):
+            filename = os.path.basename(input).replace(".words.json", "")
+            for len in 6, 20, 50:
+                output_dir = self.get_output_path()
+                self.assertRun([main_script, 
+                    input if i > 0 else self.get_data_path(), output_dir,
+                    "--max_length", str(len),
+                ])
+                for format in "vtt", "srt",:
+                    output_file = os.path.join(output_dir, f"{filename}.{format}")
+                    self.assertTrue(os.path.isfile(output_file), msg=f"File {output_file} not found")
+                    expected_file = f"split_subtitles/{filename.split('_')[-1]}_{len}.{format}"
+                    self.assertNonRegression(output_file, expected_file)
+                    os.remove(output_file)
+                    self.assertRun([main_script, 
+                        input, output_file,
+                        "--max_length", str(len),
+                    ])
+                    self.assertTrue(os.path.isfile(output_file), msg=f"File {output_file} not found")
+                    self.assertNonRegression(output_file, expected_file)
+
+class TestHuggingFaceModel(TestHelperCli):
+
+    def test_hugging_face_model(self):
+
+        self._test_cli_(
+            ["--model", "qanastek/whisper-tiny-french-cased", "--verbose", "True"],
+            "verbose", files=["bonjour.wav"], extensions=None,
+            prefix="hf",
+            device_specific=True,
+        )
+
+# "ZZZ" to run this test at last (because it will fill the CUDA with some memory)
+class TestZZZPythonImport(TestHelper):
+
+    def test_python_import(self):
+
+        try:
+            import whisper_timestamped
+        except ModuleNotFoundError:
+            sys.path.append(os.path.realpath(
+                os.path.dirname(os.path.dirname(__file__))))
+            import whisper_timestamped
+
+        # Test version
+        version = whisper_timestamped.__version__
+        self.assertTrue(isinstance(version, str))
+
+        (stdout, sterr) = self.assertRun([self.main_script(), "-v"])
+        self.assertEqual(stdout.strip(), version)
+
+        model = whisper_timestamped.load_model("tiny")
+
+        # Check processing of different files
+        for filename in "bonjour.wav", "laugh1.mp3", "laugh2.mp3":
+            res = whisper_timestamped.transcribe(
+                model, self.get_data_path(filename))
+            if self._can_generate_reference():
+                self.assertNonRegression(res, f"tiny_auto/{filename}.words.json")
+
+        for filename in "bonjour.wav", "laugh1.mp3", "laugh2.mp3":
+            res = whisper_timestamped.transcribe(
+                model, self.get_data_path(filename), language="fr")
+            if self._can_generate_reference():
+                self.assertNonRegression(res, f"tiny_fr/{filename}.words.json")
+
+    def _can_generate_reference(self):
+        return not GENERATE_DEVICE_DEPENDENT or self.get_device_str() != "cpu"
+
+    def test_split_tokens(self):
+
+        import whisper
+        whisperversion = whisper.__version__
+
+        import whisper_timestamped as whisper
+        from whisper_timestamped.transcribe import split_tokens_on_spaces
+
+        tokenizer = whisper.tokenizer.get_tokenizer(True, language=None)
+
+        # 220 means space
+        tokens = [50364, 220, 6455, 11, 2232, 11, 286, 2041, 11, 2232, 11, 8660,
+                  291, 808, 493, 220, 365, 11, 220, 445, 718, 505, 458, 13, 220, 50714]
+
+        self.assertEqual(
+            split_tokens_on_spaces(tokens, tokenizer),
+            (['<|0.00|>', 'So,', 'uh,', 'I', 'guess,', 'uh,', 'wherever', 'you', 'come', 'up', 'with,', 'just', 'let', 'us', 'know.', '<|7.00|>'],
+                [['<|0.00|>'],
+                [' ', 'So', ','],
+                [' uh', ','],
+                [' I'],
+                [' guess', ','],
+                [' uh', ','],
+                [' wherever'],
+                [' you'],
+                [' come'],
+                [' up'],
+                [' ', ' with', ','],
+                [' ', ' just'],
+                [' let'],
+                [' us'],
+                [' know', '.', ' '],
+                ['<|7.00|>']],
+             [[50364],
+                [220, 6455, 11],
+                [2232, 11],
+                [286],
+                [2041, 11],
+                [2232, 11],
+                [8660],
+                [291],
+                [808],
+                [493],
+                [220, 365, 11],
+                [220, 445],
+                [718],
+                [505],
+                [458, 13, 220],
+                [50714]
+              ])
+        )
+
+        tokens = [50366, 314, 6, 11771, 17134, 11, 4666, 11, 1022, 220, 875, 2557, 68, 11, 6992, 631, 269, 6, 377, 220, 409, 7282, 1956, 871, 566, 2707, 394, 1956, 256, 622, 8208, 631, 8208, 871, 517, 7282, 1956, 5977, 7418, 371, 1004, 306, 580, 11, 5977, 12, 9498, 9505, 84, 6, 50416]
+        self.assertEqual(
+            split_tokens_on_spaces(tokens, tokenizer),
+                (
+                ['<|0.04|>', "T'façon,", 'nous,', 'sur', 'la', 'touche,', 'parce', 'que', "c'est", 'un', 'sport', 'qui', 'est', 'important', 'qui', 'tue', 'deux', 'que', 'deux', 'est', 'un', 'sport', 'qui', 'peut', 'être', 'violent,', 'peut-être', "qu'", '<|1.04|>'],
+                [['<|0.04|>'],
+                 [' T', "'", 'fa', 'çon', ','],
+                    [' nous', ','],
+                    [' sur'],
+                    [' ', 'la'],
+                    [' touch', 'e', ','],
+                    [' parce'],
+                    [' que'],
+                    [' c', "'", 'est'],
+                    [' ', 'un'],
+                    [' sport'],
+                    [' qui'],
+                    [' est'],
+                    [' im', 'port', 'ant'],
+                    [' qui'],
+                    [' t', 'ue'],
+                    [' deux'],
+                    [' que'],
+                    [' deux'],
+                    [' est'],
+                    [' un'],
+                    [' sport'],
+                    [' qui'],
+                    [' peut'],
+                    [' être'],
+                    [' v', 'io', 'le', 'nt', ','],
+                    [' peut', '-', 'être'],
+                    [' q', 'u', "'"],
+                    ['<|1.04|>']],
+                [[50366],
+                 [314, 6, 11771, 17134, 11],
+                    [4666, 11],
+                    [1022],
+                    [220, 875],
+                    [2557, 68, 11],
+                    [6992],
+                    [631],
+                    [269, 6, 377],
+                    [220, 409],
+                    [7282],
+                    [1956],
+                    [871],
+                    [566, 2707, 394],
+                    [1956],
+                    [256, 622],
+                    [8208],
+                    [631],
+                    [8208],
+                    [871],
+                    [517],
+                    [7282],
+                    [1956],
+                    [5977],
+                    [7418],
+                    [371, 1004, 306, 580, 11],
+                    [5977, 12, 9498],
+                    [9505, 84, 6],
+                    [50416]]
+            )
+        )
+
+        tokens = [50364, 220, 220, 6455, 11, 220, 220, 2232, 220, 220, 11, 220, 50714]
+        self.assertEqual(
+            split_tokens_on_spaces(tokens, tokenizer),
+            (['<|0.00|>', 'So,', 'uh', ',', '<|7.00|>'],
+            [['<|0.00|>'],
+            [' ', ' ', 'So', ','],
+            [' ', ' ', ' uh'],
+            [' ', ' ', ',', ' '],
+            ['<|7.00|>']],
+            [[50364], [220, 220, 6455, 11], [220, 220, 2232], [220, 220, 11, 220], [50714]]
+            )
+        )
+
+        # Careful with the double spaces at the end...
+        tokens = [50364, 220, 220, 6455, 11, 220, 220, 2232, 220, 220, 11, 220, 220, 50714]
+        self.assertEqual(
+            split_tokens_on_spaces(tokens, tokenizer),
+            (['<|0.00|>', 'So,', 'uh', ',', '', '<|7.00|>'],
+            [['<|0.00|>'],
+            [' ', ' ', 'So', ','],
+            [' ', ' ', ' uh'],
+            [' ', ' ', ','],
+            [' ', ' '],
+            ['<|7.00|>']],
+            [[50364], [220, 220, 6455, 11], [220, 220, 2232], [220, 220, 11], [220, 220], [50714]]
+            )
+        )
+
+        # Tokens that could be removed
+        tokens = [50364, 6024, 95, 8848, 7649, 8717, 38251, 11703, 3224, 51864]
+        self.assertEqual(
+            split_tokens_on_spaces(tokens, tokenizer),
+            (['<|0.00|>', 'الآذان', 'نسمّه', '<|30.00|>'],
+                [['<|0.00|>'], ['', ' الآ', 'ذ', 'ان'], [' ن', 'سم', 'ّ', 'ه'], ['<|30.00|>']],
+                [[50364], [6024, 95, 8848, 7649], [8717, 38251, 11703, 3224], [51864]]
+            )
+        )
+
+        # issue #61
+        # Special tokens that are not timestamps
+        tokens = [50414, 805, 12, 17, 50299, 11, 568, 12, 18, 12, 21, 11, 502, 12, 17, 12, 51464]
+        # 50299 is "<|te|>" and appears as ""
+        te = ""
+        self.assertEqual(
+            split_tokens_on_spaces(tokens, tokenizer),
+            (['<|1.00|>', f'3-2{te},', '2-3-6,', '1-2-', '<|22.00|>'],
+             [['<|1.00|>'], [' 3', '-', '2', f'{te}', ','], [' 2', '-', '3', '-','6', ','], [' 1', '-', '2', '-'], ['<|22.00|>']],
+             [[50414], [805, 12, 17, 50299, 11], [568, 12, 18, 12, 21, 11], [502, 12, 17, 12], [51464]])
+        )
+
+        tokenizer = whisper.tokenizer.get_tokenizer(False, language="en")
+
+        # Just a punctuation character
+        tokens = [50363, 764, 51813]
+
+        _dot = "." if whisperversion < "20230314" else " ."
+        self.assertEqual(
+            split_tokens_on_spaces(tokens, tokenizer),
+            (['<|0.00|>', ".", '<|29.00|>'],
+                [['<|0.00|>'], [_dot], ['<|29.00|>']],
+                [[50363], [764], [51813]]
+            )
+        )
diff --git a/whisper_timestamped/__init__.py b/whisper_timestamped/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..24fd61eeea212883b618d1fb974d40ab24f07ec0
--- /dev/null
+++ b/whisper_timestamped/__init__.py
@@ -0,0 +1,10 @@
+from whisper import available_models, _download, _MODELS # defined in __init__.py
+from whisper import audio, decoding, model, normalizers, tokenizer, utils
+from whisper.audio import load_audio, log_mel_spectrogram, pad_or_trim
+from whisper.decoding import DecodingOptions, DecodingResult, decode, detect_language
+from whisper.model import Whisper, ModelDimensions
+
+from .transcribe import transcribe_timestamped
+from .transcribe import transcribe_timestamped as transcribe
+from .transcribe import load_model
+from .transcribe import __version__
\ No newline at end of file
diff --git a/whisper_timestamped/make_subtitles.py b/whisper_timestamped/make_subtitles.py
new file mode 100644
index 0000000000000000000000000000000000000000..bfc49ceda111efd3ac8065b082276aed26e79977
--- /dev/null
+++ b/whisper_timestamped/make_subtitles.py
@@ -0,0 +1,157 @@
+#!/usr/bin/env python3
+
+import json
+import string
+
+_punctuation = "".join(c for c in string.punctuation if c not in ["-", "'"]) + "。，！？：”、…"
+
+def split_long_segments(segments, max_length, use_space = True):
+    new_segments = []
+    for segment in segments:
+        text = segment["text"]
+        if len(text) <= max_length:
+            new_segments.append(segment)
+        else:
+            meta_words = segment["words"]
+            # Note: we do this in case punctuation were removed from words
+            if use_space:
+                # Split text around spaces and punctuations (keeping punctuations)
+                words = text.split()
+            else:
+                words = [w["text"] for w in meta_words]
+            if len(words) != len(meta_words):
+                new_words = [w["text"] for w in meta_words]
+                print(f"WARNING: {' '.join(words)} != {' '.join(new_words)}")
+                words = new_words
+            current_text = ""
+            current_start = segment["start"]
+            current_best_idx = None
+            current_best_end = None
+            current_best_next_start = None
+            for i, (word, meta) in enumerate(zip(words, meta_words)):
+                current_text_before = current_text
+                if current_text and use_space:
+                    current_text += " "
+                current_text += word
+
+                if len(current_text) > max_length and len(current_text_before):
+                    start = current_start
+                    if current_best_idx is not None:
+                        text = current_text[:current_best_idx]
+                        end = current_best_end
+                        current_text = current_text[current_best_idx+1:]
+                        current_start = current_best_next_start
+                    else:
+                        text = current_text_before
+                        end = meta_words[i-1]["end"]
+                        current_text = word
+                        current_start = meta["start"]
+
+                    current_best_idx = None
+                    current_best_end = None
+                    current_best_next_start = None                        
+
+                    new_segments.append({"text": text, "start": start, "end": end})
+
+                # Try to cut after punctuation
+                if current_text and current_text[-1] in _punctuation:
+                    current_best_idx = len(current_text)
+                    current_best_end = meta["end"]
+                    current_best_next_start = meta_words[i+1]["start"] if i+1 < len(meta_words) else None
+            
+            if len(current_text):
+                new_segments.append({"text": current_text, "start": current_start, "end": segment["end"]})
+            
+    return new_segments
+
+def format_timestamp(seconds: float, always_include_hours: bool = False, decimal_marker: str = '.'):
+    assert seconds >= 0, "non-negative timestamp expected"
+    milliseconds = round(seconds * 1000.0)
+
+    hours = milliseconds // 3_600_000
+    milliseconds -= hours * 3_600_000
+
+    minutes = milliseconds // 60_000
+    milliseconds -= minutes * 60_000
+
+    seconds = milliseconds // 1_000
+    milliseconds -= seconds * 1_000
+
+    hours_marker = f"{hours:02d}:" if always_include_hours or hours > 0 else ""
+    return f"{hours_marker}{minutes:02d}:{seconds:02d}{decimal_marker}{milliseconds:03d}"
+
+def write_vtt(result, file):
+    print("WEBVTT\n", file=file)
+    for segment in result:
+        print(
+            f"{format_timestamp(segment['start'])} --> {format_timestamp(segment['end'])}\n"
+            f"{segment['text'].strip().replace('-->', '->')}\n",
+            file=file,
+            flush=True,
+        )
+
+def write_srt(result, file):
+    for i, segment in enumerate(result, start=1):
+        # write srt lines
+        print(
+            f"{i}\n"
+            f"{format_timestamp(segment['start'], always_include_hours=True, decimal_marker=',')} --> "
+            f"{format_timestamp(segment['end'], always_include_hours=True, decimal_marker=',')}\n"
+            f"{segment['text'].strip().replace('-->', '->')}\n",
+            file=file,
+            flush=True,
+        )
+
+def cli():
+
+    import os
+    import argparse
+
+    supported_formats = ["srt", "vtt"]
+
+    parser = argparse.ArgumentParser(
+        description='Convert .word.json transcription files (output of whisper_timestamped) to srt or vtt, being able to cut long segments',
+        formatter_class=argparse.ArgumentDefaultsHelpFormatter
+    )
+    parser.add_argument('input', type=str, help='Input json file, or input folder')
+    parser.add_argument('output', type=str, help='Output srt or vtt file, or output folder')
+    parser.add_argument('--max_length', default=200, help='Maximum length of a segment in characters', type=int)
+    parser.add_argument('--format', type=str, default="all", help='Output format (if the output is a folder, i.e. not a file with an explicit extension)', choices= supported_formats + ["all"])
+    args = parser.parse_args()
+
+    if os.path.isdir(args.input) or not max([args.output.endswith(e) for e in supported_formats]):
+        input_files = [f for f in os.listdir(args.input) if f.endswith(".words.json")] if os.path.isdir(args.input) else [os.path.basename(args.input)]
+        extensions = [args.format] if args.format != "all" else ["srt", "vtt"]
+        output_files = [[os.path.join(args.output, f[:-11] + "." + e) for e in extensions] for f in input_files]
+        if os.path.isdir(args.input):
+            input_files = [os.path.join(args.input, f) for f in input_files]
+        else:
+            input_files = [args.input]
+        if not os.path.isdir(args.output):
+            os.makedirs(args.output)
+    else:
+        input_files = [args.input]
+        output_files = [[args.output]]
+        if not os.path.isdir(os.path.dirname(args.output)):
+            os.makedirs(os.path.dirname(args.output))
+
+    for fn, outputs in zip(input_files, output_files):
+        with open(fn, "r", encoding="utf-8") as f:
+            transcript = json.load(f)
+        segments = transcript["segments"]
+        if args.max_length:
+            language = transcript["language"]
+            use_space = language not in ["zh", "ja", "th", "lo", "my"]
+            segments = split_long_segments(segments, args.max_length, use_space=use_space)
+        for output in outputs:
+            if output.endswith(".srt"):
+                with open(output, "w", encoding="utf-8") as f:
+                    write_srt(segments, file=f)
+            elif output.endswith(".vtt"):
+                with open(output, "w", encoding="utf-8") as f:
+                    write_vtt(segments, file=f)
+            else:
+                raise RuntimeError(f"Unknown output format for {output}")
+
+if __name__ == "__main__":
+    cli()
\ No newline at end of file
diff --git a/whisper_timestamped/transcribe.py b/whisper_timestamped/transcribe.py
new file mode 100644
index 0000000000000000000000000000000000000000..3f91d8d3e968e6432ac01600d682600c8bac3740
--- /dev/null
+++ b/whisper_timestamped/transcribe.py
@@ -0,0 +1,2646 @@
+#!/usr/bin/env python3
+
+__author__ = "Jérôme Louradour"
+__credits__ = ["Jérôme Louradour"]
+__license__ = "GPLv3"
+__version__ = "1.14.2"
+
+# Set some environment variables
+import os
+os.environ['TF_CPP_MIN_LOG_LEVEL'] = '1' # Remove warning "This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)..."
+os.environ['CUDA_DEVICE_ORDER'] = 'PCI_BUS_ID' # GPU in the right order
+
+# Whisper and Torch
+import whisper
+import torch
+import torch.nn.functional as F
+
+from importlib.util import find_spec
+if find_spec("intel_extension_for_pytorch") is not None:
+    try:
+        import intel_extension_for_pytorch
+    except ImportError:
+        pass
+
+# For alignment
+import numpy as np
+import dtw
+# from scipy.signal import medfilt as median_filter
+from scipy.ndimage import median_filter # faster owing to https://github.com/openai/whisper/commit/f0083e7eb20d032390e42f6f6039947fa8669c93
+from scipy.signal import find_peaks
+
+# Additional
+import string
+import csv
+import sys
+import gzip, base64
+import copy
+import re
+import shutil
+
+# Constant variables
+from whisper.utils import format_timestamp
+from whisper.audio import N_FRAMES, HOP_LENGTH, SAMPLE_RATE  # 3000, 160, 16000
+AUDIO_SAMPLES_PER_TOKEN = HOP_LENGTH * 2                     # 320
+AUDIO_TIME_PER_TOKEN = AUDIO_SAMPLES_PER_TOKEN / SAMPLE_RATE # 0.02 (sec)
+SEGMENT_DURATION = N_FRAMES * HOP_LENGTH / SAMPLE_RATE       # 30.0 (sec)
+
+# Logs
+import logging
+logger = logging.getLogger("whisper_timestamped")
+
+USE_EFFICIENT_BY_DEFAULT = True
+TRUST_WHISPER_TIMESTAMP_BY_DEFAULT = True
+DISFLUENCY_MARK = "[*]"
+
+try:
+    whisper_version = whisper.__version__
+except NameError:
+    whisper_version = ""
+WHIPSER_GE_20230306 = whisper_version >= "20230306"
+WHIPSER_GE_20230308 = whisper_version >= "20230308"
+
+def transcribe_timestamped(
+    # Main Whisper options
+    model,
+    audio,
+    language=None,
+    task="transcribe",
+
+    # Additional options for word alignment
+    remove_punctuation_from_words=False,
+    compute_word_confidence=True,
+    include_punctuation_in_confidence=False,
+    refine_whisper_precision=0.5,
+    min_word_duration=0.02, # Was 0.04 before 1.11
+    plot_word_alignment=False,
+    word_alignement_most_top_layers=None, # Was 6 before 1.9
+    remove_empty_words=False,
+
+    # Reproducibility
+    seed=1234,
+
+    vad=False,
+    detect_disfluencies=False,
+    trust_whisper_timestamps=TRUST_WHISPER_TIMESTAMP_BY_DEFAULT,
+    naive_approach=False,
+
+    # Other Whisper options
+    temperature=0.0 if USE_EFFICIENT_BY_DEFAULT else (0.0, 0.2, 0.4, 0.6, 0.8, 1.0),
+    best_of=None,
+    beam_size=None,
+    patience=None,
+    length_penalty=None,
+    compression_ratio_threshold=2.4,
+    logprob_threshold=-1.0,
+    no_speech_threshold=0.6,
+    fp16=None,
+    condition_on_previous_text=True,
+    initial_prompt=None,
+    suppress_tokens="-1",
+    sample_len=None,
+    verbose=False,
+):
+    """
+    Transcribe an audio file using Whisper
+
+    Parameters
+    ----------
+    model: Whisper
+        The Whisper model instance.
+
+    audio: Union[str, np.ndarray, torch.Tensor]
+        The path to the audio file to open, or the audio waveform in 16kHz.
+
+    language: str
+        The language to use for the transcription. If None, the language is detected automatically.
+
+    task: str
+        The task to perform: either "transcribe" or "translate".
+
+    remove_punctuation_from_words: bool
+        If False, words will be glued with the next punctuation mark (if any).
+        If True, there will be no punctuation mark in the `words[:]["text"]` list.
+        It only affects these strings; This has no influence on the computation of the word confidence, whatever the value of `include_punctuation_in_confidence` is.
+    
+    include_punctuation_in_confidence: bool
+        Whether to include proba of punctuation in the computation of the (previous) word confidence.
+
+    compute_word_confidence: bool
+        Whether to compute word confidence.
+        If True, a finer confidence for each segment will be computed as well.
+
+    vad: bool or str in ["silero", "silero:3.1", "auditok"]
+        Whether to perform voice activity detection (VAD) on the audio file, to remove silent parts before transcribing with Whisper model.
+        This should decrease hallucinations from the Whisper model.
+        When set to True, the default VAD algorithm is used (silero).
+        When set to a string, the corresponding VAD algorithm is used (silero, silero:3.1 or auditok).
+        Note that the library for the corresponding VAD algorithm must be installed.
+
+    detect_disfluencies: bool
+        Whether to detect disfluencies (i.e. hesitations, filler words, repetitions, corrections, etc.) that Whisper model might have omitted in the transcription.
+        This should make the word timestamp prediction more accurate.
+        And probable disfluencies will be marked as special words "[*]".
+
+    trust_whisper_timestamps: bool
+        Whether to rely on Whisper's timestamps to get approximative first estimate of segment positions (up to refine_whisper_precision).
+
+    refine_whisper_precision: float
+        How much can we refine Whisper segment positions, in seconds. Must be a multiple of 0.02.
+
+    min_word_duration: float
+        Minimum duration of a word, in seconds. If a word is shorter than this, timestamps will be adjusted.
+
+    plot_word_alignment: bool
+        Whether to plot the word alignment for each segment. matplotlib must be installed to use this option.
+
+    remove_empty_words: bool
+        Whether to remove words with no duration occuring at the end of segments (probable Whisper hallucinations).
+
+    seed: int
+        Random seed to use for temperature sampling, for the sake of reproducibility.
+        Choose None for unpredictable randomness.
+
+    naive_approach: bool
+        Force the naive approach that consists in decoding twice the audio file, once to get the transcritpion and once with the decoded tokens to get the alignment.
+        Note that this approach is used anyway when beam_size is not None and/or when the temperature is a list with more than one element.
+
+    temperature: float
+        Temperature for sampling.
+
+    compression_ratio_threshold: float
+        If the gzip compression ratio is above this value, treat as failed.
+
+    logprob_threshold: float
+        If the average log probability over sampled tokens is below this value, treat as failed.
+
+    no_speech_threshold: float
+        If the no_speech probability is higher than this value AND the average log probability
+        over sampled tokens is below `logprob_threshold`, consider the segment as silent.
+
+    condition_on_previous_text: bool
+        if True, the previous output of the model is provided as a prompt for the next window;
+        disabling may make the text inconsistent across windows, but the model becomes less prone to
+        getting stuck in a failure loop, such as repetition looping or timestamps going out of sync.
+
+    initial_prompt: str
+        Optional text to provide as a prompt for the first window.
+
+    suppress_tokens: str
+        Comma-separated list of token ids to suppress during sampling;
+        '-1' will suppress most special characters except common punctuations.
+
+    verbose: bool
+        Whether to display the text being decoded to the console. If True, displays all the details,
+        If False, displays minimal details. If None, does not display anything
+
+    Returns
+    -------
+    A dictionary containing the resulting text ("text") and segment-level details ("segments"), and
+    the spoken language ("language"), which is detected when `decode_options["language"]` is None.
+    """
+
+    if seed is not None:
+        torch.manual_seed(seed)
+        torch.cuda.manual_seed_all(seed)
+
+    # Check input options
+    assert refine_whisper_precision >= 0 and refine_whisper_precision / AUDIO_TIME_PER_TOKEN == round(refine_whisper_precision / AUDIO_TIME_PER_TOKEN), f"refine_whisper_precision must be a positive multiple of {AUDIO_TIME_PER_TOKEN}"
+    refine_whisper_precision_nframes = round(refine_whisper_precision / AUDIO_TIME_PER_TOKEN)
+    assert min_word_duration >= 0, f"min_word_duration must be a positive number"
+    assert word_alignement_most_top_layers is None or word_alignement_most_top_layers > 0, f"word_alignement_most_top_layers must be a strictly positive number"
+
+    if isinstance(temperature, (list, tuple)) and len(temperature) == 1:
+        temperature = temperature[0]
+    if isinstance(temperature, (list, tuple)):
+        # temperature fallback
+        naive_approach = True
+    elif temperature > 0 and best_of is not None and best_of > 1:
+        naive_approach = True
+    if beam_size is not None:
+        # beam-search
+        naive_approach = True
+
+    # Input options
+    vad = check_vad_method(vad)
+    if isinstance(model, str):
+        model = load_model(model)
+    if fp16 is None:
+        fp16 = model.device != torch.device("cpu")
+
+    # Safety check
+    input_stride = N_FRAMES // model.dims.n_audio_ctx
+    time_precision = input_stride * HOP_LENGTH / SAMPLE_RATE
+    assert time_precision == AUDIO_TIME_PER_TOKEN
+
+    alignment_heads = get_alignment_heads(model) if word_alignement_most_top_layers is None else None
+    if alignment_heads is None and word_alignement_most_top_layers is None:
+        word_alignement_most_top_layers = 6
+
+    alignment_options = dict(
+            remove_punctuation_from_words=remove_punctuation_from_words,
+            compute_word_confidence=compute_word_confidence,
+            include_punctuation_in_confidence=include_punctuation_in_confidence,
+            detect_disfluencies=detect_disfluencies,
+            refine_whisper_precision_nframes=refine_whisper_precision_nframes,
+            plot_word_alignment=plot_word_alignment,
+            word_alignement_most_top_layers=word_alignement_most_top_layers,
+            alignment_heads=alignment_heads,
+    )
+    whisper_options = dict(
+            language=language,
+            task=task,
+            fp16=fp16,
+            temperature=temperature,
+            best_of=best_of,
+            beam_size=beam_size,
+            patience=patience,
+            length_penalty=length_penalty,
+            condition_on_previous_text=condition_on_previous_text,
+            initial_prompt=initial_prompt,
+            suppress_tokens=suppress_tokens,
+            sample_len=sample_len,
+            verbose=verbose if (not vad or verbose is not True) else False,
+    )
+    other_options = dict(
+        no_speech_threshold=no_speech_threshold,
+        logprob_threshold=logprob_threshold,
+        compression_ratio_threshold=compression_ratio_threshold,
+    )
+
+    if vad:
+        audio = get_audio_tensor(audio)
+        audio, convert_timestamps = remove_non_speech(audio, method=vad, plot=plot_word_alignment)
+
+    global num_alignment_for_plot
+    num_alignment_for_plot = 0
+
+    if naive_approach:
+        (transcription, words) = _transcribe_timestamped_naive(model, audio,
+                                                               min_word_duration=0.0, # Was 0.04 before 1.11
+                                                               trust_whisper_timestamps=trust_whisper_timestamps,
+                                                               **alignment_options, **whisper_options, **other_options)
+    else:
+        (transcription, words) = _transcribe_timestamped_efficient(model, audio,
+                                                                   trust_whisper_timestamps=trust_whisper_timestamps,
+                                                                   **alignment_options, **whisper_options, **other_options)
+    if remove_empty_words:
+        # Remove words with empty duration happening at the end of segments, to remove some hallucinations
+        transcription, words = remove_last_null_duration_words(transcription, words, recompute_text=True)
+
+    # Refine word positions
+    ensure_increasing_positions(words, min_duration=min_word_duration if trust_whisper_timestamps else 0)
+    
+    # Combine words and segments
+    whisper_segments = transcription["segments"]
+    for word in words:
+        if verbose and not naive_approach and not vad:
+            print_timestamped(word)
+        word.pop("tokens")
+        word.pop("tokens_indices")
+        if "avg_logprob_reliable" in word:
+            word.pop("avg_logprob_reliable")
+        idx_segment = word.pop("idx_segment")
+        assert idx_segment < len(whisper_segments), f"Fatal error: Got unexpected segment index {idx_segment} >= {len(whisper_segments)}"
+        segment = whisper_segments[idx_segment]
+        if "words" in segment:
+            segment["words"].append(word)
+        else:
+            segment["words"] = [word]
+            if refine_whisper_precision:
+                segment["start"] = word["start"]
+        if refine_whisper_precision:
+            segment["end"] = word["end"]
+
+    if vad:
+        # Recompute timestamps to match the original audio
+        for segment in whisper_segments:
+            for word in segment.get("words", []):
+                word["start"], word["end"] = convert_timestamps(word["start"], word["end"])
+                if verbose:
+                    print_timestamped(word)
+            if refine_whisper_precision and len(segment.get("words", [])):
+                segment["start"] = segment["words"][0]["start"]
+                segment["end"] = segment["words"][-1]["end"]
+            else:
+                segment["start"], segment["end"] = convert_timestamps(segment["start"], segment["end"])
+
+    return transcription
+
+def _transcribe_timestamped_efficient(
+    model,
+    audio,
+    remove_punctuation_from_words,
+    compute_word_confidence,
+    include_punctuation_in_confidence,
+    refine_whisper_precision_nframes,
+    alignment_heads,
+    plot_word_alignment,
+    word_alignement_most_top_layers,
+    detect_disfluencies,
+    trust_whisper_timestamps,
+    use_timestamps_for_alignment = True,
+    # Whisper specific options
+    **whisper_options,
+):
+
+    # Get options
+    sample_len = whisper_options["sample_len"]
+    temperature = whisper_options["temperature"]
+    no_speech_threshold = whisper_options["no_speech_threshold"]
+    logprob_threshold = whisper_options["logprob_threshold"]
+    verbose = whisper_options["verbose"]
+    # Note: "on-the-fly" verbose is not implementable in the current state (we don't know the absolute position of the current chunk). See issue #18
+    verbose_bugged = False
+    whisper_options["verbose"] = None if whisper_options["verbose"] is True else whisper_options["verbose"]  # We will print intermediate results ourselves
+
+    logit_filters = get_logit_filters(model, whisper_options)
+    language = whisper_options["language"]
+    tokenizer = get_tokenizer(model, task=whisper_options["task"], language=language)
+
+    max_sample_len = sample_len or model.dims.n_text_ctx // 2 
+    n_ctx = model.dims.n_text_ctx
+
+    debug = logger.getEffectiveLevel() >= logging.DEBUG
+
+    word_alignement_most_top_layers = float("inf") if word_alignement_most_top_layers is None else word_alignement_most_top_layers
+
+    # The main outcome
+    timestamped_word_segments = []  # list of timestamped word segments that have been collected so far
+    # Main variables to be accumulated
+    segment_tokens = [[]]              # list of lists of token indices that have been collected so far (one list per segment)
+    segment_attweights = [[] for _ in range(min(word_alignement_most_top_layers, len(model.decoder.blocks)))]
+                                    # attention weights on the last segments
+    segment_avglogprobs = []        # average log probability for each segment (actually of the corresponding chunk, as computed by whisper)
+    segment_logprobs = []           # token log probabilities for each segment
+    # Variables related to options that can skip some segments
+    sot_index = None                # index of the SOT token in the current set of processed tokens
+    no_speech_prob = None           # no speech probability for the current 30 sec chunk
+    chunk_logprobs = []             # log probabilities for the current 30 sec chunk
+    chunk_tokens = []               # tokens for the current 30 sec chunk (list of Torch tensors)
+    chunk_tokens_nosot = []         # tokens for the current 30 sec chunk, without the SOT tokens (list of indices)
+    last_chunk_token = None         # last token of the current chunk, that may be needed for corner cases
+    last_token_fallback = None      # last token to use as a fallback if the model gets stuck
+    has_started = False             # whether we have started decoding
+    mfcc = None                     # MFCC features for the current 30 sec chunk
+    new_mfcc = None                 #
+    num_inference_steps = 0         # number of inference steps performed so far (for debugging only)
+    language_probs = None           # language detection probabilities
+
+    def is_sot(curr_tokens):
+        return curr_tokens is None or len(curr_tokens) > 1 or curr_tokens[0] == tokenizer.sot
+    
+    def has_reached_decoding_limit():
+        n = len(chunk_tokens_nosot) + 1
+        m = n + (len(chunk_tokens[0]) if len(chunk_tokens) > 0 else 0)
+        return n + 1 >= max_sample_len or m > n_ctx
+
+    def reset(add_segment, keep_last_token=True):
+        """ Reset the list of tokens for the current speech segment, and corresponding cross-attention weights """
+        nonlocal segment_tokens, segment_attweights
+        if add_segment:
+            if keep_last_token:
+                segment_tokens.append([segment_tokens[-1][-1]])
+                segment_attweights = [w[-1:] for w in segment_attweights]
+            else:
+                segment_tokens.append([])
+                segment_attweights = [[] for w in segment_attweights]
+            segment_tokens[-2].pop(0)
+        elif len(segment_tokens[-1]) > 0:
+            if debug:
+                logger.debug(f"Reset last segment: {tokenizer.decode_with_timestamps(segment_tokens[-1])}")
+            segment_tokens[-1] = []
+            segment_attweights = [[] for w in segment_attweights]
+
+    saw_consecutive_timestamps = False
+    def must_flush_segment(curr_tokens):
+        """ Return whether or not the previously collected tokens must be used to add a new speech segment """
+        nonlocal segment_tokens, saw_consecutive_timestamps, chunk_tokens_nosot
+
+        if not is_sot(curr_tokens):
+            is_timestamp = curr_tokens[0] >= tokenizer.timestamp_begin
+            is_previous_timestamp = segment_tokens[-1][-1] >= tokenizer.timestamp_begin if len(segment_tokens[-1]) > 0 else False
+            consecutive_timestamps = is_timestamp and is_previous_timestamp
+            if consecutive_timestamps:
+                saw_consecutive_timestamps = True
+            return consecutive_timestamps
+        else: # Several tokens as a prompt or must flush last segments
+
+            must_flush = len(segment_tokens[-1]) > 1 and not saw_consecutive_timestamps
+            if not must_flush and WHIPSER_GE_20230306: # If the last token is a timestamp, the last segment is used
+                if last_chunk_token is None:
+                    must_flush = (len(segment_tokens[-1]) > 2 and segment_tokens[-1][-1] >= tokenizer.timestamp_begin)
+                else:
+                    must_flush = (last_chunk_token >= tokenizer.timestamp_begin)
+            if not must_flush and trust_whisper_timestamps:
+                # Discard the end of the last transcription
+                reset(False)
+            saw_consecutive_timestamps = False
+            return must_flush
+
+    index_begin_30sec_chunck = 0
+    def get_index_begin_30sec_chunck(curr_tokens):
+        nonlocal index_begin_30sec_chunck, has_started
+
+        if is_sot(curr_tokens) and has_started:
+            if trust_whisper_timestamps:
+                res = index_begin_30sec_chunck
+                index_begin_30sec_chunck = len(segment_tokens)-1
+            else:
+                res = len(segment_tokens)-1
+            return res
+
+    def align_last_segment(curr_tokens=None):
+        nonlocal segment_tokens, segment_attweights, timestamped_word_segments, has_started, no_speech_prob, chunk_tokens, chunk_tokens_nosot, chunk_logprobs, mfcc, new_mfcc, logit_filters, index_begin_30sec_chunck, last_token_fallback, num_inference_steps
+
+        if debug and trust_whisper_timestamps:
+            logger.debug(f"Add segment {len(timestamped_word_segments)+1} at step {num_inference_steps}:\n\t{tokenizer.decode_with_timestamps(segment_tokens[-1])}")
+
+        tokens = segment_tokens[-1][1:]
+
+        # When the decoding hit the max limit (number of tokens) -- usually when the language model gets stuck --
+        # then we have to recover the last token from what is send to the decoder
+        unfinished_decoding = has_reached_decoding_limit()
+        last_is_not_timestamp = len(tokens) and tokens[-1] < tokenizer.timestamp_begin
+        last_token_reliable = True
+
+        if unfinished_decoding:
+            logger.debug(f"WARNING: decoding hit the max limit for segment {segment_tokens[-1]} (It usually happens when the language model gets stuck)")
+            # The last token chosen is in the prompt for the new chunk
+            if curr_tokens is not None and curr_tokens[0] == tokenizer.sot_prev:
+                index_sot =  (curr_tokens == tokenizer.sot).nonzero(as_tuple=True)
+                assert len(index_sot) == 1
+                index_sot = index_sot[0].item()
+                assert index_sot > 0 
+                last_token_fallback = curr_tokens[index_sot-1].item()
+                logger.debug(f"         Guessed last token from the prompt for the new chunk: {last_token_fallback}")
+            # Fallback for the last segment, or without prompt: Assume greedy decoding
+            else:
+                last_token_fallback = torch.argmax(chunk_logprobs[-1]).item() if last_chunk_token is None else last_chunk_token
+                last_token_reliable = (temperature == 0)
+                logger.debug(f"         Guess last token using probas (assuming greedy decoding): {last_token_fallback}")
+            if debug:
+                logger.debug(f"WARNING: also add last token: {tokenizer.decode_with_timestamps([last_token_fallback])}")
+
+            tokens.append(last_token_fallback)
+            segment_tokens[-1].append(last_token_fallback)
+            attention_weights = [torch.cat(w, dim=-2) for w in segment_attweights]
+            last_logprobs = chunk_logprobs[-1]
+        elif last_is_not_timestamp: # <eot> was emitted early, without a timestamp before
+            logger.debug(f"WARNING: end timestamp not produced. Adding <|endoftext|>")
+            tokens.append(tokenizer.eot)
+            segment_tokens[-1].append(tokenizer.eot)
+            attention_weights = [torch.cat(w, dim=-2) for w in segment_attweights]
+            last_logprobs = chunk_logprobs[-1]
+        else:
+            attention_weights = [torch.cat(w[:-1], dim=-2) for w in segment_attweights]
+            last_logprobs = chunk_logprobs[-2]
+
+        # Check prediction of last token
+        end_token = tokens[-1]
+        if end_token >= tokenizer.timestamp_begin:
+            start_token = tokens[0]
+            assert start_token >= tokenizer.timestamp_begin
+            # If Whisper prediction of the end is obviously wrong, we predict it again (constrained)
+            if end_token <= start_token:
+                new_end_token = last_logprobs[start_token+1:].argmax() + start_token + 1
+                tokens[-1] = new_end_token.item()
+                if debug:
+                    logger.debug(f"Re-estimated end token {tokenizer.decode_with_timestamps([new_end_token])} (was {tokenizer.decode_with_timestamps([end_token])}) to be after start token {tokenizer.decode_with_timestamps([start_token])}")
+
+        if len(tokens) <= 1:
+            # Corner case: nothing in between timestamps
+            ws = []
+        else:
+            ws = perform_word_alignment(
+                tokens,
+                attention_weights,
+                tokenizer,
+                use_space=should_use_space(language),
+                alignment_heads=alignment_heads,
+                remove_punctuation_from_words=remove_punctuation_from_words,
+                refine_whisper_precision_nframes=refine_whisper_precision_nframes,
+                detect_disfluencies=detect_disfluencies,
+                unfinished_decoding=unfinished_decoding,
+                mfcc=mfcc,
+                plot=plot_word_alignment,
+                debug=debug,
+            )
+
+        add_segment = len(ws) > 0
+        if add_segment:
+            timestamped_word_segments.append(ws)
+        else:
+            logger.debug(f"Not added!")
+        reset(add_segment, not is_sot(curr_tokens))
+
+        return add_segment, unfinished_decoding, last_token_reliable
+
+    def may_flush_segment(curr_tokens = None):
+        """ Add a speech segment with the new tokens if necessary.
+            May also remove the last collected segments if filtered out by Whisper (no_speech_prob <= no_speech_threshold)
+        """
+        nonlocal segment_tokens, segment_attweights, timestamped_word_segments, segment_logprobs, has_started, no_speech_prob, chunk_tokens, chunk_tokens_nosot, chunk_logprobs, mfcc, new_mfcc, logit_filters, index_begin_30sec_chunck, last_token_fallback, num_inference_steps, last_chunk_token
+
+        # Check if a new segment should be added
+        unfinished_decoding = False
+        last_token_reliable = True
+        
+        if must_flush_segment(curr_tokens) and trust_whisper_timestamps:
+            _, unfinished_decoding, last_token_reliable = align_last_segment(curr_tokens)
+
+        i_start = get_index_begin_30sec_chunck(curr_tokens)
+
+        # All segments from previous 30sec chunck have been collected
+        if i_start is not None:
+
+            if not trust_whisper_timestamps:
+
+                tokens = torch.Tensor(segment_tokens[-1]).int()
+                idx_task = torch.where(tokens==tokenizer.sot_sequence[-1])[0][0].item() # index of <|transcribe|>
+
+                is_special = tokens.ge(tokenizer.eot)
+                # Remove prompt
+                is_special[:idx_task] = True
+                # Keep begin timestamp
+                is_special[idx_task:idx_task+2] = False
+
+                is_timestamp = tokens.ge(tokenizer.timestamp_begin)
+                consecutive = torch.where(is_timestamp[1:] & is_timestamp[:-1])[0]
+                if (WHIPSER_GE_20230306 or has_reached_decoding_limit()) and (
+                    (is_timestamp[-1] and not is_timestamp[-2]) if last_chunk_token is None else
+                    last_chunk_token >= tokenizer.timestamp_begin and not is_timestamp[-2]
+                ):
+                    consecutive = torch.cat([consecutive, torch.Tensor([len(tokens)-1]).int()])
+                last_is_timestamp = True
+                if len(consecutive):
+                    # Remove last tokens
+                    is_special[consecutive[-1]+1:] = True 
+                    # Keep end timestamp
+                    is_special[consecutive[-1]] = False
+                elif is_timestamp[-1]:
+                    # Keep end timestamp
+                    is_special[-1] = False
+                else:
+                    last_is_timestamp = False
+
+                if use_timestamps_for_alignment and len(consecutive):
+                    # Keep all timestamps
+                    is_special[idx_task+2:consecutive[-1]] = False
+
+                # Do remove what has to be removed
+                is_next_achar = ~torch.cat([is_special[1:], torch.Tensor([False]).bool()])
+                for i, weights in enumerate(segment_attweights):
+                    assert len(weights) == len(tokens), f"{len(weights)} attention weights != {len(tokens)}"
+                    # We must remove attention weights used to predict timestamp tokens
+                    segment_attweights[i] = [w for s, w in zip(is_next_achar, weights) if s]
+                tokens_filtered = tokens[~is_special]                        
+                assert len(segment_attweights[0]) == len(tokens_filtered), f"{len(segment_attweights[0])} attention weights != {len(tokens_filtered)} "
+
+                # Replace first and last timestamp
+                orig_start, orig_end = tokens_filtered[1].item(), tokens_filtered[-1].item()
+                tokens_filtered[1] = tokenizer.timestamp_begin # <|0.00|>
+                if last_is_timestamp:
+                    tokens_filtered[-1] = tokenizer.timestamp_begin + N_FRAMES // 2 # <|30.00|>
+                segment_tokens[-1] = tokens_filtered.tolist()
+
+                # Do alignement
+                added, unfinished_decoding, last_token_reliable = align_last_segment()
+
+                # Re-split into segments (if necessary)
+                if added:
+                    if len(consecutive) > 1:
+                        segments_timestamped_concat = timestamped_word_segments[-1]
+                        new_segments_timestamped = []
+                        new_segment_tokens = []
+                        start = idx_task+1
+                        i_word = 0
+                        for i, end in enumerate(consecutive):
+                            end = end.item()
+                            new_segment_tokens.append(tokens[start:end+1].tolist())
+                            if debug:
+                                logger.debug(f"Add segment {len(timestamped_word_segments)+i}:\n\t{tokenizer.decode_with_timestamps(new_segment_tokens[-1])}")
+                            total_length = end - start - 1
+                            start = end+1
+                            length = 0
+                            new_segments_timestamped.append([])
+                            while length < total_length:
+                                if not use_timestamps_for_alignment and i_word == len(segments_timestamped_concat):
+                                    # This can happen in the case of "..."
+                                    assert total_length == 1 and i == len(consecutive)-1, "Unexpected situation!"
+                                    break
+                                assert i_word < len(segments_timestamped_concat), f"i_word={i_word} < len(segments_timestamped_concat)={len(segments_timestamped_concat)}"
+                                word = segments_timestamped_concat[i_word]
+                                new_segments_timestamped[-1].append(word)
+                                length += len(word["tokens_indices"])
+                                i_word += 1
+                            # This can be non zero, when a punctuation (alone in a segment) is glued to the previous segment
+                            if use_timestamps_for_alignment:
+                                assert length == total_length, f"length={length} != total_length={total_length}"
+                            elif length > total_length:
+                                delta = length - total_length
+                                word = new_segments_timestamped[-1][-1]
+                                word_tokindices = word["tokens_indices"]
+                                word_tokens = word["tokens"]
+                                word["tokens_indices"] = word_tokindices[:-delta]
+                                word["tokens"] = word_tokens[:-delta]
+                                word["word"] = "".join(word_tokens[:-delta])
+                                i_word -= 1
+                                t = segments_timestamped_concat[i_word]["end"]
+                                segments_timestamped_concat[i_word] = dict(
+                                    text="".join(word_tokens[-delta:]),
+                                    start=t, end=t, # Word without timestamp
+                                    tokens=word_tokens[-delta:],
+                                    tokens_indices=word_tokindices[-delta:],
+                                )
+
+                        assert i_word == len(segments_timestamped_concat)
+
+                        segment_tokens = segment_tokens[:-2] + new_segment_tokens + [segment_tokens[-1]]
+                        timestamped_word_segments = timestamped_word_segments[:-1] + new_segments_timestamped
+
+                    else:
+
+                        # Recover start and end token
+                        segment = segment_tokens[-2]
+                        tokenizer.decode_with_timestamps([orig_start,orig_end])
+                        segment[0] = orig_start
+                        if last_is_timestamp:
+                            segment[-1] = orig_end
+
+                        if debug:
+                            logger.debug(f"Add segment {len(timestamped_word_segments)}:\n\t{tokenizer.decode_with_timestamps(segment)}")
+                        
+                    if unfinished_decoding:
+                        timestamped_word_segments[-1][-1]["avg_logprob_reliable"] = last_token_reliable
+
+                reset(False)
+
+            mfcc = new_mfcc
+
+            n_segments = len(segment_tokens)-1
+
+            # Get word confidence and/or check if previous segments shoud have been skipped
+            should_skip = False
+            if compute_word_confidence or no_speech_threshold is not None:
+
+                # no voice activity check
+                should_skip = (no_speech_prob > no_speech_threshold) if (no_speech_threshold is not None) else False
+                if compute_word_confidence or (should_skip and logprob_threshold is not None):
+                    n = len(chunk_logprobs)
+                    if n == len(chunk_tokens_nosot):
+                        chunk_tokens_nosot = chunk_tokens_nosot[1:]
+                    if unfinished_decoding:
+                        assert last_token_fallback is not None
+                        last_tokens = [last_token_fallback]
+                        timestamped_word_segments[-1][-1]["avg_logprob_reliable"] = last_token_reliable
+                        n += 1
+                    elif has_reached_decoding_limit():
+                        # there were segments in the 30sec chunck, and then the LM got stuck
+                        last_tokens = [torch.argmax(chunk_logprobs[-1]).item()]
+                        timestamped_word_segments[-1][-1]["avg_logprob_reliable"] = (temperature == 0)
+                    else:
+                        last_tokens = [tokenizer.eot]
+                    chunck_indices = chunk_tokens_nosot + last_tokens
+                    assert len(chunk_logprobs) == len(chunck_indices), f"{len(chunk_logprobs)} != {len(chunck_indices)}"
+                    logprobs = torch.cat([logprob[i].unsqueeze(0) for (logprob, i) in zip(chunk_logprobs, chunck_indices)])
+                    assert min([p.isfinite().item() for p in logprobs]), \
+                        f"Got infinite logprob among ({len(logprobs)}) {[(i, tokenizer.decode_with_timestamps([i]), v.item()) for (i,v) in zip(chunck_indices, logprobs)]}"
+                    sum_logprob = sum(logprobs)
+                    avg_logprob = sum_logprob/n
+                    # don't skip if the logprob is high enough, whatever the no_speech_prob is
+                    if logprob_threshold is not None and avg_logprob > logprob_threshold:
+                        should_skip = False
+
+                if should_skip:
+                    logger.debug(f"Skipping last {n_segments-i_start} segments (no_speech_prob {no_speech_prob} > {no_speech_threshold} and avg_logprob {avg_logprob} < {logprob_threshold})")
+                    index_begin_30sec_chunck -= n_segments-i_start
+                    segment_tokens = segment_tokens[:i_start] + [segment_tokens[-1]]
+                    timestamped_word_segments = timestamped_word_segments[:i_start]
+                elif compute_word_confidence:
+                    avg_logprob = avg_logprob.item()
+                    i_token_end = -1
+                    for i in range(i_start, n_segments):
+                        tokens = segment_tokens[i]
+                        i_token_start = i_token_end + 1
+                        i_token_end = i_token_start + len(tokens)
+                        assert chunck_indices[i_token_start:i_token_end] == tokens, f"Inconsistent token list {tokenizer.decode_with_timestamps(chunck_indices[i_token_start:i_token_end])} != {tokenizer.decode_with_timestamps(tokens)}"
+                        i_token_start += 1 # skip sos (start time)
+                        if not unfinished_decoding or i != n_segments-1:
+                            i_token_end -= 1 # skip eos (end time)
+                        segment_logprobs.append(logprobs[i_token_start:i_token_end])
+                        segment_avglogprobs.append(avg_logprob)
+                else:
+                    for i in range(i_start, n_segments):
+                        segment_logprobs.append(None)
+                        segment_avglogprobs.append(None)
+               
+            else:
+                for i in range(i_start, n_segments):
+                    segment_logprobs.append(None)
+                    segment_avglogprobs.append(None)
+
+            if verbose_bugged and not should_skip:
+                for segment in timestamped_word_segments[i_start:]:
+                    for word in segment:
+                        print_timestamped(word)
+
+            # Reset counters
+            chunk_tokens = []
+            chunk_tokens_nosot = []
+            chunk_logprobs = []
+            no_speech_prob = None
+
+    def hook_attention_weights(layer, ins, outs, index):
+        nonlocal segment_attweights
+        # In old version of whisper, output is a single tensor
+        assert isinstance(outs, tuple) and len(outs) == 2, "whisper seems to be outdated, please update it (pip install --upgrade --no-deps --force-reinstall git+https://github.com/openai/whisper.git)"
+        if not has_started:
+            return
+        w = outs[-1]
+        # Only the last attention weights is useful
+        if w.shape[-2] > 1:
+            w = w[:, :, -1:, :]
+        segment_attweights[index].append(w.cpu())
+
+    def hook_mfcc(layer, ins, outs):
+        nonlocal new_mfcc, mfcc
+        new_mfcc = ins[0]
+        if mfcc is None:
+            mfcc = new_mfcc
+
+    def hook_input_tokens(layer, ins, outs):
+        nonlocal segment_tokens, sot_index, chunk_tokens, chunk_tokens_nosot, logit_filters, has_started, language, num_inference_steps
+        num_inference_steps += 1
+
+        curr_tokens = ins[0]
+        assert curr_tokens.shape[0] == 1, "Batch decoding is not supported"
+        curr_tokens = curr_tokens.squeeze(0)
+
+        if is_sot(curr_tokens):
+            chunk_prompt = curr_tokens.tolist()
+            if language is None:
+                if len(curr_tokens) > 1:
+                    language = tokenizer.decode(curr_tokens[-2:-1])
+                    language = language[2:-2] # remove trailing "<|" and "|>"
+                    whisper_options["language"] = language
+
+                    if verbose and not whisper_options["verbose"] and len(curr_tokens) > 1:
+                        # Reproduce whisper verbose (2/2)
+                        print(f"Detected language: {whisper.tokenizer.LANGUAGES[language].title()}")
+                        sys.stdout.flush()
+
+            logit_filters = get_logit_filters(model, whisper_options, prompt = chunk_prompt[1:-len(tokenizer.sot_sequence)])
+        
+        may_flush_segment(curr_tokens)
+
+        # Get the index of the <|startoftranscript|> tokens (to get proba of silence later)
+        if is_sot(curr_tokens):
+            has_started = len(curr_tokens) > 1 or not model.is_multilingual
+            if no_speech_threshold is not None:
+                sot_index = curr_tokens.tolist().index(tokenizer.sot)
+        else:
+            sot_index = None
+
+        # Keep the last token only
+        if has_started:
+            segment_tokens[-1].append(curr_tokens[-1].item())
+
+        # Accumulate tokens
+        if has_started:
+            chunk_tokens.append(curr_tokens)
+            if not is_sot(curr_tokens):
+                chunk_tokens_nosot.append(curr_tokens[-1].item())
+        else:
+            if verbose and not whisper_options["verbose"]:
+                # Reproduce whisper verbose (1/2)
+                print("Detecting language using up to the first 30 seconds. Use `--language` to specify the language")
+
+    embedding_weights = None 
+    def hook_output_logits(layer, ins, outs):
+        nonlocal no_speech_prob, chunk_logprobs, segment_tokens, chunk_tokens, chunk_tokens_nosot, last_chunk_token, embedding_weights, has_started, language, language_probs
+        
+        if embedding_weights is None:
+            embedding_weights = torch.transpose(model.decoder.token_embedding.weight, 0, 1).to(outs[0].dtype)
+
+        # Get the probability of silence
+        if sot_index is not None and no_speech_prob is None:
+            logits = (outs[0][sot_index,:] @ embedding_weights).float()
+            logits = logits.softmax(dim=-1)
+            no_speech_prob = logits[tokenizer.no_speech].item()
+
+        # Get language probabilities
+        if language is None and sot_index is not None and model.is_multilingual:
+            index_start = tokenizer.sot + 1
+            index_end = index_start + len(tokenizer.all_language_tokens)
+            logits = (outs[0][sot_index,:] @ embedding_weights).float()
+            language_probs = logits[index_start:index_end].softmax(dim=-1)
+            language_probs = dict(zip(whisper.tokenizer.LANGUAGES, language_probs.tolist()))
+
+        # Get the log-probabilities of tokens (we don't know yet which one will be chosen)
+        if has_started:
+            logits = (outs[0][-1:,:] @ embedding_weights).float()
+            tokens = torch.cat(chunk_tokens).unsqueeze(0)
+            for logit_filter in logit_filters:
+                logit_filter.apply(logits, tokens)
+            logits = F.log_softmax(logits.squeeze(0), dim=-1)
+            chunk_logprobs.append(logits)
+
+            if WHIPSER_GE_20230306 and has_reached_decoding_limit():
+                last_chunk_token = torch.argmax(logits).item()
+            else:
+                last_chunk_token = None
+
+    try:
+
+        # Add hooks to the model, to get tokens and attention weights on the fly
+        all_hooks = []
+        all_hooks.append(model.encoder.conv1.register_forward_hook(hook_mfcc))
+        all_hooks.append(model.decoder.token_embedding.register_forward_hook(hook_input_tokens))
+        nblocks = len(model.decoder.blocks)
+        j = 0
+        for i, block in enumerate(model.decoder.blocks):
+            if i < nblocks - word_alignement_most_top_layers:
+                continue
+            all_hooks.append(
+                block.cross_attn.register_forward_hook(
+                    lambda layer, ins, outs, index=j: hook_attention_weights(layer, ins, outs, index))
+            )
+            j += 1
+        if compute_word_confidence or no_speech_threshold is not None:
+            all_hooks.append(model.decoder.ln.register_forward_hook(hook_output_logits))
+
+        transcription = model.transcribe(audio, **whisper_options)
+
+    finally:
+
+        # Remove hooks
+        for hook in all_hooks:
+            hook.remove()
+
+    # Finalize (collect last segment)
+    may_flush_segment()
+    segment_tokens.pop(-1)
+
+    token_special_idx = min(tokenizer.sot, tokenizer.eot)
+    def filter_tokens(tokens):
+        while len(tokens) and tokens[0] >= token_special_idx:
+            tokens = tokens[1:]
+        while len(tokens) and tokens[-1] >= token_special_idx:
+            tokens = tokens[:-1]
+        return tokens
+
+    assert len(segment_tokens) == len(timestamped_word_segments), f"Inconsistent number of segments: tokens ({len(segment_tokens)}) != timestamped_word_segments ({len(timestamped_word_segments)})"
+    assert len(segment_avglogprobs) == len(segment_tokens), f"Inconsistent number of segments: avg logprobs ({len(segment_avglogprobs)}) != tokens ({len(segment_tokens)})"
+    assert len(segment_logprobs) == len(segment_tokens), f"Inconsistent number of segments: logprobs ({len(segment_logprobs)}) != tokens ({len(segment_tokens)})"
+
+    whisper_segments = transcription["segments"]
+    l1 = len(whisper_segments)
+    l2 = len(timestamped_word_segments)
+    if l1 != l2 and l1 != 0:
+        logger.warning(f"Inconsistent number of segments: whisper_segments ({l1}) != timestamped_word_segments ({l2})")
+    assert l1 == l2 or l1 == 0, f"Inconsistent number of segments: whisper_segments ({l1}) != timestamped_word_segments ({l2})"
+
+    logger.debug("Compile results")
+    words = []
+    for i, (segment, timestamped_words, token, avglogprob, logprobs) in enumerate(zip(whisper_segments, timestamped_word_segments, segment_tokens, segment_avglogprobs, segment_logprobs)):
+        timestamped_tokens = filter_tokens(token)
+        whisper_tokens = filter_tokens(segment["tokens"])
+        if timestamped_tokens != whisper_tokens:
+            if len(timestamped_tokens) == len(whisper_tokens) + 1:
+                logger.warning(f"An additional token was added on segment {i}")
+            elif WHIPSER_GE_20230306 and len(whisper_tokens) == 0:
+                logger.warning(f"Whisper has empty segment {i}")
+                assert segment["end"] == segment["start"], f"Fatal Error: Got empty segment {i} with non-zero duration"
+                segment["tokens"] = timestamped_tokens
+                segment["text"] = tokenizer.decode(timestamped_tokens)
+            else:
+                assert len(timestamped_tokens) < len(whisper_tokens) and timestamped_tokens == whisper_tokens[:len(timestamped_tokens)], \
+                    f"Fatal Error: Got inconsistent text for segment {i}:\n({len(timestamped_tokens)})\n{tokenizer.decode_with_timestamps(timestamped_tokens)}\n{timestamped_tokens}\n!=\n({len(whisper_tokens)})\n{tokenizer.decode_with_timestamps(whisper_tokens)}\n{whisper_tokens[:len(timestamped_tokens)]}"
+                segment["tokens"] = token if WHIPSER_GE_20230306 else timestamped_tokens # tokens include special timestamp tokens since 20230306
+                segment["text"] = tokenizer.decode(segment["tokens"])
+                logger.warning(f"Text had to be shortned on segment {i}:\n{tokenizer.decode(timestamped_tokens)}\n!=\n{tokenizer.decode(whisper_tokens)}")
+            timestamped_words[-1]["avg_logprob_reliable"] = False
+
+        offset = segment["seek"] * HOP_LENGTH / SAMPLE_RATE
+        for timestamped_word in timestamped_words:
+            timestamped_word["start"] += offset
+            timestamped_word["end"] += offset
+            timestamped_word["idx_segment"] = i
+
+        if compute_word_confidence:
+            if "avg_logprob_reliable" not in timestamped_words[-1] or timestamped_words[-1]["avg_logprob_reliable"]:
+                # assert abs(segment["avg_logprob"] - avglogprob) < 1e-2, f"Fatal Error: Got inconsistent logprob for segment {i}: {segment['avg_logprob']} != {avglogprob}"
+                if abs(segment["avg_logprob"] - avglogprob) >= 1e-2:
+                    logger.warning(f"Recomputed different logprob for segment {i}: {avglogprob} != {segment['avg_logprob']}")
+            if include_punctuation_in_confidence:
+                segment["confidence"] = round_confidence(logprobs.mean().exp().item())
+            else:
+                logprobs_nopunc = []
+            i_end = 0
+            for timestamped_word in timestamped_words:
+                i_start = i_end
+                tokens = timestamped_word["tokens"]
+                i_end += len(tokens)
+
+                assert i_end <= len(logprobs), f"Fatal Error: Got out-of-bound index for segment {i}: {i_end} > {len(logprobs)}"
+                if include_punctuation_in_confidence:
+                    word_logprobs = logprobs[i_start:i_end]
+                else:
+                    while len(tokens) > 1 and len(tokens[-1]) and tokens[-1][-1] in _punctuation: # Note: look at the last character of token, to take into account "...", "!!", etc.
+                        tokens = tokens[:-1]
+                    word_logprobs = logprobs[i_start:i_start + len(tokens)]
+                    logprobs_nopunc.append(word_logprobs)
+
+                timestamped_word["confidence"] = round_confidence(word_logprobs.mean().exp().item() if len(word_logprobs) else 0.0)
+
+            if i_end not in [len(logprobs), len(logprobs)-1]:
+                logger.warning(f"Got inconsistent length for segment {i} ({len(logprobs)} != {i_end}). Some words have been ignored.")
+            if not include_punctuation_in_confidence:   
+                logprobs_nopunc = torch.cat(logprobs_nopunc)
+                segment["confidence"] = round_confidence(logprobs_nopunc.mean().exp().item())
+
+        words.extend(timestamped_words)
+
+    if language_probs:
+        transcription["language_probs"] = language_probs
+
+    return transcription, words
+
+def _transcribe_timestamped_naive(
+    model,
+    audio,
+    remove_punctuation_from_words,
+    compute_word_confidence,
+    include_punctuation_in_confidence,
+    refine_whisper_precision_nframes,
+    alignment_heads,
+    plot_word_alignment,
+    word_alignement_most_top_layers,
+    detect_disfluencies,
+    trust_whisper_timestamps,
+    min_word_duration,
+    **whisper_options,
+):
+    verbose = whisper_options["verbose"]
+    whisper_options["verbose"] = None if whisper_options["verbose"] is True else whisper_options["verbose"]  # We will print intermediate results ourselves
+    language = whisper_options["language"]
+    refine_whisper_precision_sec = refine_whisper_precision_nframes * AUDIO_TIME_PER_TOKEN
+
+    word_alignement_most_top_layers = float("inf") if word_alignement_most_top_layers is None else word_alignement_most_top_layers
+
+    audio = get_audio_tensor(audio)
+    audio_duration = audio.shape[-1] / SAMPLE_RATE
+
+    if verbose and language is None and not whisper_options["verbose"]:
+        # Reproduce whisper verbose (1/2)
+        print("Detecting language using up to the first 30 seconds. Use `--language` to specify the language")
+
+    tokenizer = get_tokenizer(model, task=whisper_options["task"], language=language)
+
+    language_probs = None
+    def hook_output_logits(layer, ins, outs):
+        nonlocal language_probs, tokenizer
+        
+        # Get language probabilities
+        if language_probs is None:
+            if outs.shape[1] == 1:
+                embedding_weights = torch.transpose(model.decoder.token_embedding.weight, 0, 1).to(outs[0].dtype)
+                index_start = tokenizer.sot + 1
+                index_end = index_start + len(tokenizer.all_language_tokens)
+                logits = (outs[0][0,:] @ embedding_weights).float()
+                language_probs = logits[index_start:index_end].softmax(dim=-1)
+                language_probs = dict(zip(whisper.tokenizer.LANGUAGES, language_probs.tolist()))
+            else:
+                language_probs = False
+
+    all_hooks = []
+    if model.is_multilingual:
+        all_hooks.append(model.decoder.ln.register_forward_hook(hook_output_logits))
+
+    try:
+        transcription = model.transcribe(audio, **whisper_options)
+    finally:
+        for hook in all_hooks:
+            hook.remove()
+
+    if verbose and language is None and not whisper_options["verbose"]:
+        # Reproduce whisper verbose (2/2)
+        print(f"Detected language: {whisper.tokenizer.LANGUAGES[transcription['language']].title()}")
+        sys.stdout.flush()
+
+    language = norm_language(transcription["language"])
+    use_space = should_use_space(language)
+
+    n_mels = model.dims.n_mels if hasattr(model.dims, "n_mels") else 80
+
+    attention_weights = [[] for _ in range(min(word_alignement_most_top_layers,len(model.decoder.blocks)))]
+
+    try:
+
+        all_hooks = []
+
+        # Hook the model
+        nblocks = len(model.decoder.blocks)
+        j = 0
+        for i, block in enumerate(model.decoder.blocks):
+            if i < nblocks - word_alignement_most_top_layers:
+                continue
+            all_hooks.append(
+                block.cross_attn.register_forward_hook(
+                    lambda layer, ins, outs, index=j: attention_weights.__setitem__(index, outs[-1])
+                )
+            )
+            j += 1
+
+
+        # When not relying on Whisper timestamps
+        current_tokens = []
+        token_to_idx_segment = []
+
+        words = []
+        previous_end = 0
+        whisper_segments = transcription["segments"]
+        for i_segment, segment in enumerate(whisper_segments):
+
+            # Note: this could also be a fix to issue #61 where a "<|te|>" token was predicted
+            # segment["tokens"] = [t for t in segment["tokens"] if t < tokenizer.eot or t >= tokenizer.timestamp_begin]
+
+            start = end = tokens = None
+            if trust_whisper_timestamps:
+
+                start = segment["start"]
+                end = segment["end"]
+                if end < start:
+                    # Whisper is wrong on the prediction of segment end
+                    end = min(audio_duration, start + SEGMENT_DURATION)
+
+                start_margin_min = start - refine_whisper_precision_sec
+                start_margin_max = start + refine_whisper_precision_sec
+                if start >= audio_duration - min_word_duration or (previous_end >= start_margin_min and previous_end <= start_margin_max):
+                    # Make start as accurate as possible (as the decoding will start with timestamp <|0|>)
+                    start = previous_end
+                else:
+                    # Fallback
+                    start = start_margin_min
+
+                if start > audio_duration - min_word_duration:
+                    # Skip last segment if too short
+                    logger.warning(f"Skipping segment outside of audio duration {audio_duration} (original: {segment['start']}-{segment['end']}, new: {start}-XXX)")
+                    continue
+
+                end_margin_min = end - refine_whisper_precision_sec
+                end_margin_max = end + refine_whisper_precision_sec
+                if i_segment < len(whisper_segments) - 1:
+                    # Try to enforce:
+                    #   end + min_word_duration <= next start + refine_whisper_precision_sec
+                    end_margin_max2 = whisper_segments[i_segment + 1]["start"] + refine_whisper_precision_sec - min_word_duration
+                    if end_margin_max2 >= end_margin_min:
+                        end_margin_max = min(end_margin_max2, end_margin_max)
+                end = min(audio_duration, end_margin_max)
+
+                if end < start + min_word_duration:
+                    logger.warning(f"Got super short segment (original from whisper: {segment['start']}-{segment['end']}, new: {start, end})")
+                    end = min(audio_duration, start + min_word_duration)
+                    if end <= start:
+                        logger.warning(f"Skipping this short segment occuring too close to the end of the audio")
+                        continue
+
+                tokens = segment["tokens"]
+
+            else:
+
+                seek = segment["seek"]
+                new_tokens = segment["tokens"]
+                if not len(new_tokens):
+                    continue
+                # Add timestamps that will be needed after
+                if new_tokens[0] < tokenizer.timestamp_begin:
+                    relative_start = segment["start"] - (seek * HOP_LENGTH / SAMPLE_RATE)
+                    start_token = round(relative_start * SAMPLE_RATE / AUDIO_SAMPLES_PER_TOKEN) + tokenizer.timestamp_begin
+                    new_tokens = [start_token] + new_tokens
+                if new_tokens[-1] < tokenizer.timestamp_begin:
+                    relative_end = segment["end"] - (seek * HOP_LENGTH / SAMPLE_RATE)
+                    end_token = round(relative_end * SAMPLE_RATE / AUDIO_SAMPLES_PER_TOKEN) + tokenizer.timestamp_begin
+                    new_tokens = new_tokens + [end_token]
+
+                current_tokens.extend(new_tokens)
+                token_to_idx_segment.extend([i_segment] * len(new_tokens))
+
+                next_seek = whisper_segments[i_segment+1]["seek"] if i_segment < len(whisper_segments) - 1 else None
+                if seek != next_seek:
+                    start = float(seek * HOP_LENGTH / SAMPLE_RATE)
+                    assert start < audio_duration, f"Got start {start} which is outside of audio duration {audio_duration}"
+                    end = min(start + SEGMENT_DURATION, audio_duration)
+                    tokens = current_tokens
+
+            if tokens is None or not len(tokens):
+                continue
+
+            start_sample = min(round(start * SAMPLE_RATE), audio.shape[-1])
+            end_sample = min(round(end * SAMPLE_RATE), audio.shape[-1])
+
+            # Extract features on the audio segment
+            sub_audio = audio_minimum_padding(audio[start_sample:end_sample])
+
+            mfcc = whisper.log_mel_spectrogram(sub_audio, n_mels).to(model.device)
+            mfcc = whisper.pad_or_trim(mfcc, N_FRAMES)
+            mfcc = mfcc.unsqueeze(0)
+
+            segment_tokens_check = []
+            if tokens[0] >= tokenizer.timestamp_begin:
+                segment_tokens_check.append(tokens[0])
+            while tokens[0] >= tokenizer.timestamp_begin:
+                tokens = tokens[1:]
+                assert len(tokens), "Got transcription with only timestamps!"
+            last_token_check = None
+            while tokens[-1] >= tokenizer.timestamp_begin:
+                last_token_check = tokens[-1]
+                tokens = tokens[:-1]
+
+            tokens = [
+                    *tokenizer.sot_sequence,
+                    tokenizer.timestamp_begin,
+                ] + tokens
+
+            i_start = len(tokenizer.sot_sequence)
+
+            with torch.no_grad():
+                logprobs = model(mfcc, torch.Tensor(tokens).int().to(model.device).unsqueeze(0))
+                logprobs = F.log_softmax(logprobs, dim=-1)
+
+            end_token = tokenizer.timestamp_begin + round(min(N_FRAMES * HOP_LENGTH, end_sample - start_sample) // AUDIO_SAMPLES_PER_TOKEN)
+            tokens = tokens[i_start:] + [end_token]
+            attention_weights = [w[:, :, i_start-1:, :] for w in attention_weights]
+
+            ws = perform_word_alignment(
+                tokens,
+                attention_weights,
+                tokenizer,
+                use_space=use_space,
+                alignment_heads=alignment_heads,
+                remove_punctuation_from_words=remove_punctuation_from_words,
+                refine_whisper_precision_nframes=refine_whisper_precision_nframes,
+                detect_disfluencies=detect_disfluencies,
+                mfcc=mfcc,
+                plot=plot_word_alignment,
+            )
+
+            segment_logprobs = []
+            i_token = 1
+            
+            for word in ws:
+
+                word["start"] = round(word["start"] + start, 2)
+                word["end"] = round(word["end"] + start, 2)
+                
+                if trust_whisper_timestamps:
+                    word.update({"idx_segment": i_segment})
+                else:
+                    assert i_token < len(tokens)
+                    assert not len(word["tokens_indices"]) or word["tokens_indices"][0] == tokens[i_token]
+                    word.update({"idx_segment": token_to_idx_segment[i_token]})
+                    i_token += len(word["tokens"])
+                    while i_token < len(tokens) and tokens[i_token] >= tokenizer.timestamp_begin:
+                        i_token += 1
+                
+                tok_indices = word["tokens_indices"]
+                segment_tokens_check.extend(tok_indices)
+
+                if compute_word_confidence:
+                    tok = word["tokens"]
+                    i_end = i_start + len(tok)
+                    if include_punctuation_in_confidence:
+                        while len(tok) > 1 and len(tok[-1]) and tok[-1][-1] in _punctuation: # Note: look at the last character of token, to take into account "...", "!!", etc.
+                            tok = tok[:-1]
+                            tok_indices = tok_indices[:-1]
+                    word_logprobs = [logprobs[:, step, tok] for (step, tok) in zip(range(i_start, i_start + len(tok_indices)), tok_indices)]
+                    i_start = i_end
+                    if len(word_logprobs):
+                        word_logprobs = torch.cat(word_logprobs)
+                        segment_logprobs.append(word_logprobs)
+                        word_confidence = word_logprobs.mean().exp().item()
+                    else:
+                        word_confidence = 0
+                    word.update({"confidence": round_confidence(word_confidence)})
+
+                words.append(word)
+
+                if verbose:
+                    print_timestamped(word)
+
+            if last_token_check is not None:
+                segment_tokens_check.append(last_token_check)
+            if trust_whisper_timestamps:
+                if segment_tokens_check != segment["tokens"]:
+                    assert len(segment_tokens_check) < len(segment["tokens"]) and segment_tokens_check[:-1] == segment["tokens"][:len(segment_tokens_check)-1], \
+                        f"Got inconsistent tokens: {tokenizer.decode(segment_tokens_check)} != {tokenizer.decode(segment['tokens'])}"
+                    segment["tokens"] = segment_tokens_check
+                    segment["text"] = tokenizer.decode(segment["tokens"])
+            # else: TODO
+
+            if len(segment_logprobs):
+                segment.update({"confidence": round_confidence(torch.cat(segment_logprobs).mean().exp().item())})
+
+            if len(ws):
+                previous_end = ws[-1]["end"]
+
+            if not trust_whisper_timestamps:
+                current_tokens = []
+                token_to_idx_segment = []
+
+    finally:
+
+        # Remove hooks
+        for hook in all_hooks:
+            hook.remove()
+
+    if language_probs:
+        transcription["language_probs"] = language_probs
+
+    return (transcription, words)
+
+def get_audio_tensor(audio, device="cpu"):
+    if isinstance(audio, str):
+        audio = whisper.load_audio(audio)
+    if isinstance(audio, np.ndarray):
+        audio = torch.Tensor(audio)
+    else:
+        assert isinstance(audio, torch.Tensor), f"Got unexpected audio of type {type(audio)}"
+    return audio.to(device)
+
+def audio_minimum_padding(audio):
+    if audio.shape[-1] <= 200:
+        return whisper.pad_or_trim(audio, 201)
+    return audio
+
+
+def should_use_space(language):
+    return norm_language(language) not in ["zh", "ja", "th", "lo", "my", "yue"]
+
+def norm_language(language):
+    if language is None:
+        return "en"
+    return whisper.tokenizer.TO_LANGUAGE_CODE.get(language.lower(), language)
+
+def print_timestamped(w):
+    line = f"[{format_timestamp(w['start'])} --> {format_timestamp(w['end'])}] {w['text']}\n"
+    # compared to just `print(line)`, this replaces any character not representable using
+    # the system default encoding with an '?', avoiding UnicodeEncodeError.
+    sys.stdout.write(line.encode(sys.getdefaultencoding(), errors="replace").decode())
+    sys.stdout.flush()
+
+
+def get_logit_filters(model, whisper_options, prompt = None):
+    decoding_options = get_decoding_options(whisper_options)
+    if "initial_prompt" in decoding_options:
+        prompt0 = decoding_options.pop("initial_prompt")
+        if prompt is None:
+            prompt = prompt0
+    if prompt is not None:
+        decoding_options["prompt"] = prompt
+    decoding_options = whisper.DecodingOptions(
+        without_timestamps=False,
+        max_initial_timestamp=1.0,
+        prefix=None,
+        suppress_blank=True,
+        **decoding_options
+    )
+
+    # This performs some checks on the options
+    decoding_task = whisper.decoding.DecodingTask(model, decoding_options)
+    return decoding_task.logit_filters
+
+def get_decoding_options(whisper_options):
+    return dict([(k,v) for (k,v) in whisper_options.items()
+        if k not in [
+            "no_speech_threshold",
+            "logprob_threshold",
+            "compression_ratio_threshold",
+            "condition_on_previous_text",
+            "verbose",
+        ]
+    ])
+
+def get_tokenizer(model, task="transcribe", language="en"):
+    try:
+        return whisper.tokenizer.get_tokenizer(
+            model.is_multilingual,
+            num_languages=model.num_languages if hasattr(model, "num_languages") else 99,
+            task=task, language=language
+        )
+    except TypeError: # Old openai-whisper version
+        return whisper.tokenizer.get_tokenizer(
+            model.is_multilingual,
+            task=task, language=language
+        )
+
+def perform_word_alignment(
+    tokens,
+    attention_weights,
+    tokenizer,
+    use_space=True,
+    mfcc=None,
+    refine_whisper_precision_nframes=0,
+    remove_punctuation_from_words=False,
+    include_punctuation_in_timing=False, # Was True before 1.9
+    unfinished_decoding=False,
+    alignment_heads=None,
+    medfilt_width=9,
+    qk_scale=1.0,
+    detect_disfluencies=True,
+    subwords_can_be_empty=True, # Was False before 1.11
+    plot=False,
+    debug=False,
+):
+    """
+    Perform word alignment on the given tokens and attention weights.
+    Returns a list of (word, start_time, end_time) tuples.
+
+    tokens: list of tokens (integers)
+    attention_weights: list of attention weights (torch tensors)
+    tokenizer: tokenizer used to tokenize the text
+    use_space: whether to use spaces to split the tokens into words (should be true for all languages except Japanese, Chinese, ...)
+    mfcc: MFCC features (used to identify padded region, and for plotting)
+    refine_whisper_precision_nframes: precision time
+    remove_punctuation_from_words: whether to remove punctuation from words
+    include_punctuation_in_timing: whether to include punctuation in the timing of (previous) words
+    unfinished_decoding: whether the decoding is unfinished (e.g. because the model is stuck)
+    alignment_heads: list of attention heads to use for alignment
+    medfilt_width: width of the median filter used to smooth the attention weights
+    qk_scale: scale factor applied to the attention weights
+    plot: whether to plot the word alignment
+    debug: whether to print debug information
+    """
+
+    assert len(tokens) > 1, f"Got unexpected sequence of tokens of length {len(tokens)} {tokenizer.decode_with_timestamps(tokens)}"
+    start_token = tokens[0] - tokenizer.timestamp_begin
+    end_token = tokens[-1] - tokenizer.timestamp_begin
+
+    # Check start / end tokens
+    if start_token < 0:
+        raise RuntimeError(f"Missing start token in: {tokenizer.decode_with_timestamps(tokens)}")
+    if len(tokens) == 1 or end_token < 0:
+        # This can happens when Whisper is stucked as a Language Model
+        if debug:
+            logger.debug(f"Missing end token in {tokenizer.decode_with_timestamps(tokens)}")
+        end_token = N_FRAMES // 2
+    if end_token == start_token and refine_whisper_precision_nframes == 0:
+        if debug:
+            logger.debug(f"Got empty segment in {tokenizer.decode_with_timestamps(tokens)}")
+        return []
+
+    # Let a minimal duration given the number of tokens (see https://github.com/linto-ai/whisper-timestamped/issues/67)
+    end_token = min(N_FRAMES // 2, max(end_token, start_token + len(tokens)))
+
+    # Put some margin around the segment
+    if refine_whisper_precision_nframes > 0:
+        start_token = max(start_token - refine_whisper_precision_nframes, 0)
+        end_token = min(end_token + refine_whisper_precision_nframes, N_FRAMES // 2)
+
+    if end_token <= start_token:
+        raise RuntimeError(f"Got segment with null or negative duration {tokenizer.decode_with_timestamps(tokens)}: {start_token} {end_token}")
+
+    start_time = start_token * AUDIO_TIME_PER_TOKEN
+    # end_time = end_token * AUDIO_TIME_PER_TOKEN
+
+    split_tokens = split_tokens_on_spaces if use_space else split_tokens_on_unicode
+    words, word_tokens, word_tokens_indices = split_tokens(tokens, tokenizer, remove_punctuation_from_words=remove_punctuation_from_words)
+
+    # If the last token is a punctuation that comes after a word
+    # group this final punctuation with the final timestamp
+    # This is to avoid assigning the final punctuation to a big silence or a noise/music background coming after
+    num_punctuations_per_tokens = [
+        0 if len(w) == 1 or w[-1] not in _punctuation else 1
+        for w in word_tokens
+    ]
+    if include_punctuation_in_timing:
+        num_punctuations_per_tokens[:-2]=[0]*(len(num_punctuations_per_tokens)-2)
+
+    for i, w in enumerate(attention_weights):
+        assert w.shape[-2] == len(tokens), f"Attention weights have wrong shape: {w.shape[-2]} (expected {len(tokens)})."
+    weights = torch.cat(attention_weights) # layers * heads * tokens * frames
+
+    num_tokens = weights.shape[-2]
+    num_frames = end_token - start_token
+    if num_tokens > num_frames:
+        logger.warning(f"Too much text ({num_tokens} tokens) for the given number of frames ({num_frames}) in: {tokenizer.decode_with_timestamps(tokens)}\nThe end of the text will be removed.")
+        return perform_word_alignment(
+            tokens[:num_frames-1] + [tokens[-1]],
+            [torch.cat([w[:, :, :num_frames-1, :], w[:, :, -1:, :]], dim=-2)
+                for w in attention_weights],
+            tokenizer,
+            use_space=use_space,
+            refine_whisper_precision_nframes=refine_whisper_precision_nframes,
+            medfilt_width=medfilt_width,
+            qk_scale=qk_scale,
+            alignment_heads=alignment_heads,
+            mfcc=mfcc,
+            plot=plot,
+            remove_punctuation_from_words=remove_punctuation_from_words,
+            detect_disfluencies=detect_disfluencies,
+            subwords_can_be_empty=subwords_can_be_empty,
+            unfinished_decoding=True,
+            debug=debug,
+        )
+
+    assert end_token <= weights.shape[-1]
+    assert len(tokens) == num_tokens
+
+    weights = weights[..., start_token: end_token].cpu()                        # layers * heads * tokens * frames
+
+    if alignment_heads is None:
+        weights = weights.reshape(-1, *weights.shape[-2:])                      # N * tokens * frames
+    else:
+        weights = torch.stack([weights[l][h] for l, h in alignment_heads.indices().T])
+    weights = median_filter(weights, (1, 1, medfilt_width))
+    weights = torch.tensor(weights * qk_scale).softmax(dim=-1)
+    weights = weights.mean(axis=(0))  # average over layers and heads           # tokens * frames
+    weights = weights / weights.norm(dim=-2, keepdim=True)  # This was before the mean before 1.9
+    weights = -weights.double().numpy()
+    worse_weight = 0
+
+    # Get the limit of audio duration
+    max_duration = None
+    if mfcc is not None:
+        max_duration = find_start_padding(mfcc)
+        if max_duration is not None:
+            max_duration = max_duration // 2
+
+    # Enforce the max duration
+    if max_duration:
+        if start_token >= max_duration:
+            logger.warning(f"Got start time outside of audio boundary")
+        else:
+            weights[:-1, max_duration:] = worse_weight
+
+    # Encourage to start early
+    weights[0, 0] = weights.min()
+    # weights[0, refine_whisper_precision_nframes*2:] = worse_weight
+
+    if subwords_can_be_empty:
+        step_pattern = dtw.stepPattern.symmetric1
+    else:
+        # Similar as "symmetric1" but without the possibility to have the same timestamp for two tokens
+        step_pattern = dtw.stepPattern.StepPattern(dtw.stepPattern._c(
+            1, 1, 1, -1,
+            1, 0, 0, 1,
+            2, 0, 1, -1,
+            2, 0, 0, 1,
+        ))
+    alignment = dtw.dtw(weights, step_pattern=step_pattern)
+
+    global num_alignment_for_plot
+    num_alignment_for_plot += 1
+
+    if plot:
+        import matplotlib.pyplot as plt
+        import matplotlib.ticker as ticker
+
+        plot_mfcc = 1 if mfcc is not None else 0
+        plot_disfluencies = 1 if detect_disfluencies else 0
+        nplots = (1 + plot_mfcc + plot_disfluencies)
+
+        plt.subplots(nplots, 1, figsize=(16, 9), gridspec_kw={'height_ratios': [3] + [1] * (nplots - 1)})
+        plt.subplot(nplots, 1, 1, frameon=False)
+
+        plt.imshow(-weights, aspect="auto")
+        plt.plot(alignment.index2s, alignment.index1s, color="red")
+
+        xticks = np.arange(0, weights.shape[1], 1 / AUDIO_TIME_PER_TOKEN)
+        xticklabels = [round_timestamp(x) for x in xticks * AUDIO_TIME_PER_TOKEN + start_time]
+
+        ylims = plt.gca().get_ylim()
+
+        ax = plt.gca()
+        ax.tick_params('both', length=0, width=0, which='minor', pad=6)
+
+        ax.yaxis.set_ticks_position("left")
+        ax.yaxis.set_label_position("left")
+        ax.invert_yaxis()
+        ax.set_ylim(ylims)
+
+        major_ticks = [-0.5]
+        minor_ticks = []
+        current_y = 0
+
+        for word, word_token in zip(words, word_tokens):
+            minor_ticks.append(current_y + len(word_token) / 2 - 0.5)
+            current_y += len(word_token)
+            major_ticks.append(current_y - 0.5)
+
+        words_with_subwords = ["|".join(s).strip() for (w, s) in zip(words, word_tokens)]
+
+        ax.yaxis.set_minor_locator(ticker.FixedLocator(minor_ticks))
+        ax.yaxis.set_minor_formatter(
+            ticker.FixedFormatter(words_with_subwords))
+        ax.set_yticks(major_ticks)
+        ax.yaxis.set_major_formatter(ticker.NullFormatter())
+        for y in major_ticks:
+            plt.axhline(y, color="black", linestyle="dashed")
+
+        plt.ylabel("Words")
+
+        if plot_mfcc:
+            plt.xticks(xticks)
+            plt.setp(plt.gca().get_xticklabels(), visible=False)
+
+            xticks *= 2
+
+            plt.subplot(nplots, 1, 2, frameon=False)
+            plt.imshow(mfcc[0, :, start_token * 2: end_token * 2].cpu(), aspect="auto", origin="lower")
+            plt.yticks([])
+            plt.ylabel("MFCC")
+
+        plt.xticks(xticks, xticklabels)
+        plt.xlabel("Time (s)")
+
+    jumps = np.diff(alignment.index1s)
+    jumps = np.pad(jumps, (1, 0), constant_values=1)
+    jumps = jumps.astype(bool)
+    jumps = alignment.index2s[jumps]
+    jumps = np.pad(jumps, (0, 1), constant_values=alignment.index2s[-1])
+
+    jumps_start = jumps
+    disfluences = {}
+    if detect_disfluencies:
+        jumps_start = copy.copy(jumps)
+
+        for (i_token, (tok, begin, end)) in enumerate(zip(tokens, jumps[:-1], jumps[1:])):
+
+            # Find local maxima in the portion of attention weights
+            attention_weights = -weights[i_token, begin:end]
+            peaks, properties = find_peaks(attention_weights,
+                width=3,
+                prominence=0.02,
+            )
+            # If more than 
+            if len(peaks) > 1:
+                if "left_ips" in properties:
+                    left = [round(x) for x in properties["left_ips"]]
+                else:
+                    left = properties["left_bases"]
+
+                new_begin = left[-1] + begin
+
+                jumps_start[i_token] = new_begin
+
+                if new_begin != begin:
+                    is_punctuation = tokenizer.decode_with_timestamps([tok]) in _punctuation
+                    if not is_punctuation:
+                        disfluences[i_token] = (begin, jumps_start[i_token])
+                    else:
+                        disfluences[i_token+1] = (begin, end)
+
+            if plot:
+                plt.subplot(nplots, 1, 2 + plot_mfcc, frameon=False)
+                plt.plot(range(begin,end), attention_weights)
+                plt.xlim(0, end)
+                
+                for i, p in enumerate(peaks):
+                    color = 'red' if (len(peaks)>1 and i<len(peaks)-1) else 'green'
+                    plt.vlines(begin+p, 0, 1, color=color, linestyle="--")
+
+                if "left_bases" in properties:
+                    def barxxy(start, end, y, **kwargs):
+                        middle = (start + end) / 2
+                        plt.bar(middle, y, width=end-start, **kwargs)
+                    color = 'red' if len(peaks)>1 else 'green'
+                    barxxy(begin+properties["left_bases"], begin+properties["right_bases"], properties.get("prominences",[1]*len(properties["left_bases"])), alpha=0.5,
+                        # put a line with a custom color
+                        linewidth=1, edgecolor=color
+                    )
+                if "left_ips" in properties:
+                    for left in properties["left_ips"]:
+                        plt.vlines(begin+left, 0, 0.5, color='green', linestyle=':')
+                    for right in properties["right_ips"]:  
+                        plt.vlines(begin+right, 0, 0.5, color='red', linestyle=':')
+
+
+    # display the word-level timestamps in a table
+    word_boundaries = np.cumsum([len(t) for t in word_tokens])
+    word_boundaries = np.pad(word_boundaries, (1, 0))
+    begin_times = jumps_start[word_boundaries[:-1]]
+    end_times = jumps[word_boundaries[1:] - num_punctuations_per_tokens]
+
+    begin_times = begin_times * AUDIO_TIME_PER_TOKEN
+    end_times = end_times * AUDIO_TIME_PER_TOKEN
+
+    if detect_disfluencies:
+        to_be_added = []
+        i_start = 0
+        for i_word, toks in enumerate(word_tokens[:-1]):
+            i_end = i_start + len(toks)
+            if i_start in disfluences and i_word > 0:
+                begin, end = disfluences[i_start]
+                begin *= AUDIO_TIME_PER_TOKEN
+                end *= AUDIO_TIME_PER_TOKEN
+                to_be_added.append((i_word, begin, end))
+            i_start = i_end
+        # Add from the end to avoid messing up the indices
+        for (i_word, begin, end) in to_be_added[-1::-1]:
+            words.insert(i_word, DISFLUENCY_MARK)
+            word_tokens.insert(i_word, [])
+            word_tokens_indices.insert(i_word, [])
+            begin_times = np.insert(begin_times, i_word, begin)
+            end_times = np.insert(end_times, i_word, end)
+
+    # Ignore start / end tokens
+    if not refine_whisper_precision_nframes:
+        begin_times[1] = begin_times[0]
+    if not refine_whisper_precision_nframes:
+        end_times[-2] = end_times[-1]
+    if unfinished_decoding:
+        words = words[1:]
+        word_tokens = word_tokens[1:]
+        word_tokens_indices = word_tokens_indices[1:]
+        begin_times = begin_times[1:]
+        end_times = end_times[1:]
+    else:
+        words = words[1:-1]
+        word_tokens = word_tokens[1:-1]
+        word_tokens_indices = word_tokens_indices[1:-1]
+        begin_times = begin_times[1:-1]
+        end_times = end_times[1:-1]
+
+    if plot:
+        ymin = 1
+
+        plt.subplot(nplots, 1, 1)
+        for i, (w, ws, begin, end) in enumerate(zip(words, word_tokens, begin_times, end_times)):
+            ymax = ymin + len(ws)
+            if mfcc is None:
+                plt.text(begin / AUDIO_TIME_PER_TOKEN, num_tokens-0.5, w, ha="left", va="top", color="red")
+            for x in [begin, end,]:
+                plt.axvline(x / AUDIO_TIME_PER_TOKEN, color="red", linestyle="dotted",
+                            ymin=1-ymin/num_tokens,
+                            ymax=0,  # 1-ymax/num_tokens,
+                            )
+            ymin = ymax
+
+        if plot_mfcc:
+            plt.subplot(nplots, 1, 2)
+            for i, (w, begin, end) in enumerate(zip(words, begin_times, end_times)):
+                plt.text(begin * 2 / AUDIO_TIME_PER_TOKEN, mfcc.shape[-2]*1.05, w, ha="left", va="bottom", color="red")
+                for x in [begin, end,]:
+                    plt.axvline(x * 2 / AUDIO_TIME_PER_TOKEN, color="red", linestyle="dotted")
+
+        if isinstance(plot, str):
+            plt.savefig(f"{plot}.alignment{num_alignment_for_plot:03d}.jpg", bbox_inches='tight', pad_inches=0)
+        else:
+            plt.show()
+
+    return [
+        dict(
+            text=word,
+            start=round_timestamp(begin + start_time),
+            end=round_timestamp(end + start_time),
+            tokens=tokens,
+            tokens_indices=tokens_indices,
+        )
+        for word, begin, end, tokens, tokens_indices in zip(words, begin_times, end_times, word_tokens, word_tokens_indices)
+        if not word.startswith("<|")
+    ]
+
+def find_start_padding(mfcc):
+    """ Return start of padding given the mfcc, or None if there is no padding """
+    last_mfcc = mfcc[0, :, -1]
+    if torch.min(last_mfcc) == torch.max(last_mfcc) == 0:
+        candidate_index = mfcc.shape[-1] - 2
+        while candidate_index > 0:
+            candidate = mfcc[0, :, candidate_index]
+            if not torch.equal(candidate, last_mfcc):
+                return candidate_index + 1
+            candidate_index -= 1
+        return 0 # WTF!?
+
+def round_confidence(x):
+    return round(x, 3)
+
+def round_timestamp(x):
+    return round(x, 2)
+
+_punctuation = "".join(c for c in string.punctuation if c not in ["-", "'"]) + "。，！？：”、…"
+
+def split_tokens_on_unicode(tokens: list, tokenizer, remove_punctuation_from_words=False, isolate_punctuations=False):
+    words = []
+    word_tokens = []
+    word_tokens_indices = []
+    current_tokens = []
+
+    for token in tokens:
+        current_tokens.append(token)
+        decoded = tokenizer.decode_with_timestamps([t for t in current_tokens if t < tokenizer.eot or t >= tokenizer.timestamp_begin])
+        if "\ufffd" not in decoded:
+            empty_tokens = [""] * (len(current_tokens)-1)
+            punctuation = not isolate_punctuations and (decoded.strip() and decoded.strip() in _punctuation)
+            previous_special = len(word_tokens_indices) > 0 and (word_tokens_indices[-1][-1] >= tokenizer.timestamp_begin)
+            if punctuation and not previous_special:
+                if len(words) == 0:
+                    words = [""]
+                    word_tokens = [[]]
+                if not remove_punctuation_from_words:
+                    words[-1] += decoded
+                word_tokens[-1].extend(empty_tokens + [decoded])
+                word_tokens_indices[-1].extend(current_tokens)
+            else:
+                words.append(decoded)
+                word_tokens.append(empty_tokens + [decoded])
+                word_tokens_indices.append(current_tokens)
+            current_tokens = []
+
+    return words, word_tokens, word_tokens_indices
+
+
+def split_tokens_on_spaces(tokens: torch.Tensor, tokenizer, remove_punctuation_from_words=False):
+    subwords, subword_tokens_list, subword_tokens_indices_list = split_tokens_on_unicode(tokens, tokenizer, remove_punctuation_from_words=remove_punctuation_from_words)
+    words = []
+    word_tokens = []
+    word_tokens_indices = []
+
+    for i, (subword, subword_tokens, subword_tokens_indices) in enumerate(zip(subwords, subword_tokens_list, subword_tokens_indices_list)):
+        special = (subword_tokens_indices[0] >= tokenizer.timestamp_begin)
+        previous_special = (i > 0) and (subword_tokens_indices_list[i-1][0] >= tokenizer.timestamp_begin)
+        next_special = (i < len(subword_tokens_indices_list)-1) and (subword_tokens_indices_list[i+1][0] >= tokenizer.timestamp_begin)
+        previous_space = (i > 0) and (not subwords[i-1].strip())
+        is_space = not subword.strip()
+        with_space = subword.startswith(" ") and not is_space
+        punctuation = not is_space and subword.strip() in _punctuation
+        if special or (not previous_space and (previous_special or (with_space and not punctuation) or (is_space and not next_special))):
+            words.append(subword.strip())
+            word_tokens.append(subword_tokens)
+            word_tokens_indices.append(subword_tokens_indices)
+        else:
+            words[-1] = words[-1] + subword.strip()
+            word_tokens[-1].extend(subword_tokens)
+            word_tokens_indices[-1].extend(subword_tokens_indices)
+
+    return words, word_tokens, word_tokens_indices
+
+def check_vad_method(method, with_version=False):
+    if method in [True, "True", "true"]:
+        return check_vad_method("silero") # default method
+    elif method in [False, "False", "false"]:
+        return False
+    elif method.startswith("silero"):
+        version = None
+        if method != "silero":
+            assert method.startswith("silero:"), f"Got unexpected VAD method {method}"
+            version = method.split(":")[1]
+            if not version.startswith("v"):
+                version = "v" + version
+            try:
+                assert float(version[1:]) >= 1
+            except:
+                raise ValueError(f"Got unexpected silero version {version} (please check https://github.com/snakers4/silero-vad/wiki/Version-history-and-Available-Models)")
+        if with_version:
+            return ("silero", version)
+        else:
+            return method
+    elif method == "auditok":
+        try:
+            import auditok
+        except ImportError:
+            raise ImportError("Please install auditok to use the auditok VAD (or use another VAD method)")
+    else:
+        raise ValueError(f"Got unexpected VAD method {method}")
+    return method
+
+_silero_vad_model = None
+_has_onnx = None
+def get_vad_segments(audio,
+    output_sample=False,
+    min_speech_duration=0.1,
+    min_silence_duration=0.1,
+    dilatation=0.5,
+    method="silero",
+    ):
+    """
+    Get speech segments from audio using Silero VAD
+    parameters:
+        audio: torch.Tensor
+            audio data *in 16kHz*
+        output_sample: bool
+            if True, return start and end in samples instead of seconds
+        min_speech_duration: float
+            minimum duration (in sec) of a speech segment
+        min_silence_duration: float
+            minimum duration (in sec) of a silence segment
+        dilatation: float
+            how much (in sec) to enlarge each speech segment detected by the VAD
+        method: str
+            VAD method to use (auditok, silero, silero:v3.1)
+    """
+    global _silero_vad_model, _silero_get_speech_ts, _has_onnx
+
+    if method.startswith("silero"):
+
+        version = None
+        _, version = check_vad_method(method, True)
+        # See discussion https://github.com/linto-ai/whisper-timestamped/pull/142/files#r1398326287
+        need_folder_hack = version and (version < "v4")
+
+        if _silero_vad_model is None:
+            # ONNX support since 3.1 in silero
+            if (version is None or version >= "v3.1") and (_has_onnx is not False):
+                onnx=True
+                try:
+                    import onnxruntime
+                    onnxruntime.set_default_logger_severity(3) # Remove warning "Removing initializer 'XXX'. It is not used by any node and should be removed from the model."
+                    _has_onnx = True
+                except ImportError as err:
+                    logger.warning(f"Please install onnxruntime to use more efficiently silero VAD")
+                    _has_onnx = False
+                    onnx=False
+            else:
+                onnx=False
+
+            # Choose silero version because of problems with version 4, see  https://github.com/linto-ai/whisper-timestamped/issues/74
+            repo_or_dir_master = os.path.expanduser("~/.cache/torch/hub/snakers4_silero-vad_master")
+            repo_or_dir_specific = os.path.expanduser(f"~/.cache/torch/hub/snakers4_silero-vad_{version}") if version else repo_or_dir_master
+            repo_or_dir = repo_or_dir_specific
+            tmp_folder = None
+            def apply_folder_hack():
+                nonlocal tmp_folder
+                if os.path.exists(repo_or_dir_master):
+                    tmp_folder = repo_or_dir_master + ".tmp"
+                    shutil.move(repo_or_dir_master, tmp_folder)
+                # Make a symlink to the v3.1 model, otherwise it fails
+                input_exists = os.path.exists(repo_or_dir_specific)
+                if not input_exists:
+                    # Make dummy file for the symlink to work
+                    os.makedirs(repo_or_dir_specific, exist_ok=True)
+                os.symlink(repo_or_dir_specific, repo_or_dir_master)
+                if not input_exists:
+                    shutil.rmtree(repo_or_dir_specific)
+
+            source = "local"
+            if not os.path.exists(repo_or_dir):
+                # Load specific version of silero
+                repo_or_dir = f"snakers4/silero-vad:{version}" if version else "snakers4/silero-vad"
+                source = "github"
+            if need_folder_hack:
+                apply_folder_hack()
+            try:
+                _silero_vad_model, utils = torch.hub.load(repo_or_dir=repo_or_dir, model="silero_vad", onnx=onnx, source=source)
+            except ImportError as err:
+                raise RuntimeError(f"Please install what is needed to use the silero VAD (or use another VAD method)") from err
+            except Exception as err:
+                raise RuntimeError(f"Problem when installing silero with version {version}. Check versions here: https://github.com/snakers4/silero-vad/wiki/Version-history-and-Available-Models") from err
+            finally:
+                if need_folder_hack:
+                    if os.path.exists(repo_or_dir_master):
+                        os.remove(repo_or_dir_master)
+                    if tmp_folder:
+                        shutil.move(tmp_folder, repo_or_dir_master)
+            assert os.path.isdir(repo_or_dir_specific), f"Unexpected situation: missing {repo_or_dir_specific}"
+
+            _silero_get_speech_ts = utils[0]
+
+        # Cheap normalization of the volume
+        audio = audio / max(0.1, audio.abs().max())
+
+        segments = _silero_get_speech_ts(audio, _silero_vad_model,
+            min_speech_duration_ms = round(min_speech_duration * 1000),
+            min_silence_duration_ms = round(min_silence_duration * 1000),
+            return_seconds = False,
+        )
+
+    elif method == "auditok":
+        import auditok
+
+        # Cheap normalization of the volume
+        audio = audio / max(0.1, audio.abs().max())
+
+        data = (audio.numpy() * 32767).astype(np.int16).tobytes()
+
+        segments = auditok.split(
+            data,
+            sampling_rate=SAMPLE_RATE,        # sampling frequency in Hz
+            channels=1,                       # number of channels
+            sample_width=2,                   # number of bytes per sample
+            min_dur=min_speech_duration,      # minimum duration of a valid audio event in seconds
+            max_dur=len(audio)/SAMPLE_RATE,   # maximum duration of an event
+            max_silence=min_silence_duration, # maximum duration of tolerated continuous silence within an event
+            energy_threshold=50,
+            drop_trailing_silence=True,
+        )
+
+        segments = [{"start": s._meta.start * SAMPLE_RATE, "end": s._meta.end * SAMPLE_RATE} for s in segments]
+
+    else:
+        raise ValueError(f"Got unexpected VAD method {method}")
+
+    if dilatation > 0:
+        dilatation = round(dilatation * SAMPLE_RATE)
+        new_segments = []
+        for seg in segments:
+            new_seg = {
+                "start": max(0, seg["start"] - dilatation),
+                "end": min(len(audio), seg["end"] + dilatation)
+            }
+            if len(new_segments) > 0 and new_segments[-1]["end"] >= new_seg["start"]:
+                new_segments[-1]["end"] = new_seg["end"]
+            else:
+                new_segments.append(new_seg)
+        segments = new_segments
+
+    ratio = 1 if output_sample else 1 / SAMPLE_RATE
+
+    if ratio != 1:
+        for seg in segments:
+            seg["start"] *= ratio
+            seg["end"] *= ratio
+    if output_sample:
+        for seg in segments:
+            seg["start"] = round(seg["start"])
+            seg["end"] = round(seg["end"])
+    return segments
+
+def remove_non_speech(audio,
+    use_sample=False,
+    min_speech_duration=0.1,
+    min_silence_duration=1,
+    method="silero",
+    plot=False,
+    ):
+    """
+    Remove non-speech segments from audio (using Silero VAD),
+    glue the speech segments together and return the result along with
+    a function to convert timestamps from the new audio to the original audio
+
+    parameters:
+        audio: torch.Tensor
+            audio data *in 16kHz*
+        use_sample: bool
+            if True, return start and end in samples instead of seconds
+        min_speech_duration: float
+            minimum duration (in sec) of a speech segment
+        min_silence_duration: float
+            minimum duration (in sec) of a silence segment
+        method: str
+            method to use to remove non-speech segments
+        plot: bool or str
+            if True, plot the result.
+            If a string, save the plot to the given file
+    """
+
+    segments = get_vad_segments(
+        audio,
+        output_sample=True,
+        min_speech_duration=min_speech_duration,
+        min_silence_duration=min_silence_duration,
+        method=method,
+    )
+
+    segments = [(seg["start"], seg["end"]) for seg in segments]
+    if len(segments) == 0:
+        segments = [(0, audio.shape[-1])]
+
+    audio_speech = torch.cat([audio[..., s:e] for s,e in segments], dim=-1)
+
+    if plot:
+        import matplotlib.pyplot as plt
+        plt.figure()
+        max_num_samples = 10000
+        step = (audio.shape[-1] // max_num_samples) + 1
+        times = [i*step/SAMPLE_RATE for i in range((audio.shape[-1]-1) // step + 1)]
+        plt.plot(times, audio[::step])
+        for s, e in segments:
+            plt.axvspan(s/SAMPLE_RATE, e/SAMPLE_RATE, color='red', alpha=0.1)
+        if isinstance(plot, str):
+            plt.savefig(f"{plot}.VAD.jpg", bbox_inches='tight', pad_inches=0)
+        else:
+            plt.show()
+
+    if not use_sample:
+        segments = [(float(s)/SAMPLE_RATE, float(e)/SAMPLE_RATE) for s,e in segments]
+ 
+    return audio_speech, lambda t, t2 = None: do_convert_timestamps(segments, t, t2)
+
+def do_convert_timestamps(segments, t, t2 = None):
+    """
+    Convert timestamp from audio without non-speech segments to original audio (with non-speech segments)
+
+    parameters:
+        segments: list of tuple (start, end) corresponding to non-speech segments in original audio
+        t: timestamp to convert
+        t2: second timestamp to convert (optional), when the two timestamps should be in the same segment
+    """
+    assert len(segments)
+    ioffset = 0 # Input offset
+    ooffset = 0 # Output offset
+    ipreviousend = 0
+    result = []
+    for istart, iend in segments:
+        ostart = ooffset
+        oend = ostart + (iend - istart)
+        ooffset = oend
+        ioffset += istart - ipreviousend
+        ipreviousend = iend
+        t_in = t <= oend
+        t2_in = t_in if t2 is None else t2 <= oend
+        if t_in or t2_in:
+            result.append([
+                max(istart, min(iend, ioffset + t)),
+                max(istart, min(iend, ioffset + t2)) if t2 is not None else None
+            ])
+            if t_in and t2_in:
+                break
+    if not len(result):
+        result.append(
+            [ioffset + t, ioffset + t2 if t2 is not None else None]
+        )
+        
+    if len(result) > 1:
+        # Minimize difference between durations
+        result = sorted(result, key=lambda x: abs(abs(t2-t) - abs(x[1]-x[0])))
+    result = result[0]
+    if t2 is None:
+        result = round(result[0], 2)
+    else:
+        result = [round(x, 2) for x in result]
+    return result
+
+def remove_last_null_duration_words(transcription, words, recompute_text=False):
+    """
+    Remove words with null duration happening at the end of a chunk (probable Whisper hallucinations)
+    """
+    # First group segments by audio chunk
+    segments_groups = {}
+    seek = None
+    current_chunk = -1
+    for i, segment in enumerate(transcription["segments"]):
+        if segment["seek"] != seek:
+            current_chunk += 1
+            seek = segment["seek"]
+        segments_groups[i] = current_chunk
+
+    # Remove words with null duration happening at the end of a chunk
+    current_chunk = -1
+    is_last_empty = False
+    to_remove = []
+    for i, word in enumerate(words[::-1]): # Reverse order
+        i = len(words) - i - 1
+        empty = (word["start"] == word["end"])
+        idx_segment = word["idx_segment"]
+        group = segments_groups[idx_segment]
+        if current_chunk != group:
+            is_last_empty = empty
+            current_chunk = group
+        elif not empty:
+            is_last_empty = False
+        if is_last_empty:
+            # Remove word
+            to_remove.append(i)
+            # Shorten text of segment
+            full_word = "".join(word["tokens"])
+            logger.debug(f"Removing word {i+1}/{len(words)} \"{full_word}\" with empty duration at the end of segment {idx_segment+1}/{len(transcription['segments'])}")
+            segment = transcription["segments"][idx_segment]
+            text = segment["text"]
+            if not text.endswith(full_word): # see issue #62
+                if text.endswith(full_word[:-1]):
+                    full_word = full_word[:-1]
+                elif text[:-1].endswith(full_word):
+                    text = text[:-1]
+                else:
+                    raise RuntimeError(f"\"{text}\" not ending with \"{full_word}\"")
+            text = text[:-len(full_word)]
+            if i > 0 and words[i-1]["idx_segment"] == idx_segment:
+                segment["text"] = text
+            else:
+                logger.debug(f"Removing empty segment {idx_segment}")
+                # Remove segment with no more words
+                transcription["segments"].pop(idx_segment)
+                for j in range(i+1, len(words)):
+                    words[j]["idx_segment"] -= 1
+            recompute_text = True
+
+    for i in to_remove:
+        words.pop(i) # Warning: inplace modification
+
+    if recompute_text:
+        transcription["text"] = "".join([s["text"] for s in transcription["segments"]])
+
+    return transcription, words
+
+
+def ensure_increasing_positions(segments, min_duration=0):
+    """
+    Ensure that "start" and "end" come in increasing order
+    """
+    has_modified_backward = False
+    previous_end = 0
+    for i, seg in enumerate(segments):
+        if seg["start"] < previous_end:
+            assert i > 0
+            new_start = round_timestamp((previous_end + seg["start"]) / 2)
+            if new_start < segments[i-1]["start"] + min_duration:
+                new_start = previous_end
+            else:
+                segments[i-1]["end"] = new_start
+                has_modified_backward = True
+            seg["start"] = new_start
+        if seg["end"] <= seg["start"] + min_duration:
+            seg["end"] = seg["start"] + min_duration
+        previous_end = seg["end"]
+    if has_modified_backward:
+        return ensure_increasing_positions(segments, min_duration)
+
+    previous_end = 0
+    for seg in segments:
+        seg["start"] = round_timestamp(seg["start"])
+        seg["end"] = round_timestamp(seg["end"])
+        assert seg["start"] >= previous_end, f"Got segment {seg} coming before the previous finishes ({previous_end} > {seg['start']})"
+        assert seg["end"] >= seg["start"], f"Got segment {seg} with end < start"
+        previous_end = seg["end"]
+
+    return segments
+
+## Some utilities for writing transcripts to files
+
+def flatten(list_of_lists, key = None):
+    for sublist in list_of_lists:
+        for item in sublist.get(key, []) if key else sublist:
+            yield item
+
+def remove_keys(list_of_dicts, key):
+    for d in list_of_dicts:
+        yield {k: d[k] for k in d.keys() - {key}}
+        
+
+def write_csv(transcript, file, sep = ",", text_first=True, format_timestamps=None, header=False):
+    writer = csv.writer(file, delimiter=sep)
+    if format_timestamps is None: format_timestamps = lambda x: x
+    if header is True:
+        header = ["text", "start", "end"] if text_first else ["start", "end", "text"]
+    if header:
+        writer.writerow(header)
+    if text_first:
+        writer.writerows(
+            [[segment["text"].strip(), format_timestamps(segment["start"]), format_timestamps(segment["end"])] for segment in transcript]
+        )
+    else:
+        writer.writerows(
+            [[format_timestamps(segment["start"]), format_timestamps(segment["end"]), segment["text"].strip()] for segment in transcript]
+        )
+
+# https://stackoverflow.com/questions/66588715/runtimeerror-cudnn-error-cudnn-status-not-initialized-using-pytorch
+# CUDA initialization may fail on old GPU card
+def force_cudnn_initialization(device=None, s=32):
+    if device is None:
+        device = get_default_device()
+    torch.nn.functional.conv2d(torch.zeros(s, s, s, s, device=device), torch.zeros(s, s, s, s, device=device))
+
+def get_default_device():
+    if torch.cuda.is_available():
+        device = "cuda"
+    elif find_spec('torch.xpu') is not None and torch.xpu.is_available():
+        device = "xpu"
+    else:
+        device = "cpu"
+    return device
+
+# base85-encoded (n_layers, n_heads) boolean arrays indicating the cross-attention heads that are
+# highly correlated to the word-level timing, i.e. the alignment between audio and text tokens.
+_ALIGNMENT_HEADS = {
+    "tiny.en": b"ABzY8J1N>@0{>%R00Bk>$p{7v037`oCl~+#00",
+    "tiny": b"ABzY8bu8Lr0{>%RKn9Fp%m@SkK7Kt=7ytkO",
+    "base.en": b"ABzY8;40c<0{>%RzzG;p*o+Vo09|#PsxSZm00",
+    "base": b"ABzY8KQ!870{>%RzyTQH3`Q^yNP!>##QT-<FaQ7m",
+    "small.en": b"ABzY8>?_)10{>%RpeA61k&I|OI3I$65C{;;pbCHh0B{qLQ;+}v00",
+    "small": b"ABzY8DmU6=0{>%Rpa?J`kvJ6qF(V^F86#Xh7JUGMK}P<N0000",
+    "medium.en": b"ABzY8usPae0{>%R7<zz_OvQ{)4kMa0BMw6u5rT}kRKX;$NfYBv00*Hl@qhsU00",
+    "medium": b"ABzY8B0Jh+0{>%R7}kK1fFL7w6%<-Pf*t^=N)Qr&0RR9",
+    "large-v1": b"ABzY8r9j$a0{>%R7#4sLmoOs{s)o3~84-RPdcFk!JR<kSfC2yj",
+    "large-v2": b'ABzY8zd+h!0{>%R7=D0pU<_bnWW*tkYAhobTNnu$jnkEkXqp)j;w1Tzk)UH3X%SZd&fFZ2fC2yj',
+    "large-v3": b"ABzY8gWO1E0{>%R7(9S+Kn!D~%ngiGaR?*L!iJG9p-nab0JQ=-{D1-g00",
+}
+
+_PARAMETERS_TO_MODEL_NAME = {
+    37184256 : "tiny.en",
+    37184640 : "tiny",
+    71825408 : "base.en",
+    71825920 : "base",
+    240582144 : "small.en",
+    240582912 : "small",
+    762320896 : "medium.en",
+    762321920 : "medium",
+    1541384960 : "large",
+    1541570560 : "large-v3",
+}
+
+def get_alignment_heads(model, max_top_layer=3):
+    if hasattr(model, "alignment_heads"): # Since version 20230306
+        return model.alignment_heads
+    num_parameters = _get_number_of_parameters(model)
+    num_layers = model.dims.n_text_layer
+    num_heads = model.dims.n_text_head
+    if num_parameters not in _PARAMETERS_TO_MODEL_NAME:
+        logger.warning("Could not retrieve alignment heads : taking all attention heads from the top layers")
+        return None
+    model_name = _PARAMETERS_TO_MODEL_NAME[num_parameters]
+    if model_name == "large":
+        if next(model.parameters())[0,0,0] > 0:
+            model_name = "large-v1"
+        else:
+            model_name = "large-v2"
+    return _get_alignment_heads(model_name, num_layers, num_heads)
+
+def _get_alignment_heads(model_name, num_layers, num_heads):
+    dump = _ALIGNMENT_HEADS[model_name]
+    array = np.frombuffer(gzip.decompress(base64.b85decode(dump)), dtype=bool).copy()
+    mask = torch.from_numpy(array).reshape(num_layers, num_heads)
+    alignment_heads = mask.to_sparse()
+    return alignment_heads
+
+def _get_number_of_parameters(model):
+    return sum(p.numel() for p in model.parameters())
+
+from typing import Optional, Union
+def load_model(
+    name: str,
+    device: Optional[Union[str, torch.device]] = None,
+    download_root: str = None,
+    in_memory: bool = False,
+):
+    extension = os.path.splitext(name)[-1] if os.path.isfile(name) else None
+
+    if name in whisper.available_models() or extension == ".pt":
+        return whisper.load_model(name, device=device, download_root=download_root, in_memory=in_memory)
+    
+    # Otherwise, assume transformers
+    if extension in [".ckpt", ".bin"]:
+        model_path = name
+    else:
+        # Search for the cached file (download if necessary)
+        try:
+            import transformers
+        except ImportError:
+            raise ImportError(f"If you are trying to download a HuggingFace model with {name}, please install first the transformers library")
+        from transformers.utils import cached_file
+
+        try:
+            model_path = cached_file(name, "pytorch_model.bin", cache_dir=download_root, use_auth_token=None, revision=None)
+        except Exception as e:
+            try:
+                if isinstance(e, OSError):
+                    model_path = cached_file(name, "whisper.ckpt", cache_dir=download_root, use_auth_token=None, revision=None)
+                else:
+                    raise e
+            except:
+                raise RuntimeError(f"Original error: {e}\nCould not find model {name} from HuggingFace nor local folders.")
+    # Load HF Model
+    hf_state_dict = torch.load(model_path, map_location="cpu")
+
+    # Rename layers
+    for key in list(hf_state_dict.keys())[:]:
+        new_key = hf_to_whisper_states(key)
+        if new_key is None:
+            hf_state_dict.pop(key)
+        elif new_key != key:
+            hf_state_dict[new_key] = hf_state_dict.pop(key)
+    
+
+    # Init Whisper Model and replace model weights
+    dims = whisper.model.ModelDimensions(**states_to_dim(hf_state_dict))
+
+    if "proj_out.weight" in hf_state_dict:
+        hf_state_dict["decoder.proj_out.weight"] = hf_state_dict.pop("proj_out.weight")
+        logger.warning("Using untied projection layer")
+        whisper_model = WhisperUntied(dims)
+    else:
+        whisper_model = whisper.model.Whisper(dims)
+
+    whisper_model.load_state_dict(hf_state_dict)
+    del hf_state_dict
+    if hasattr(whisper_model, "alignment_heads"):
+        del whisper_model.alignment_heads # Will be recomputed later
+    whisper_model = whisper_model.to(device)
+    return whisper_model
+
+# Credit: https://github.com/openai/whisper/discussions/830
+def hf_to_whisper_states(text):
+    # From Speechbrain
+    if text == "_mel_filters":
+        return None
+    
+    # From PEFT
+    if "default" in text:
+        # print(f"WARNING: Ignoring {text}")
+        return None
+    if text.startswith("base_model.model."):
+        text = text[len("base_model.model."):]
+
+    text = re.sub('.layers.', '.blocks.', text)
+    text = re.sub('.self_attn.', '.attn.', text)
+    text = re.sub('.q_proj.', '.query.', text)
+    text = re.sub('.k_proj.', '.key.', text)
+    text = re.sub('.v_proj.', '.value.', text)
+    text = re.sub('.out_proj.', '.out.', text)
+    text = re.sub('.fc1.', '.mlp.0.', text)
+    text = re.sub('.fc2.', '.mlp.2.', text)
+    text = re.sub('.fc3.', '.mlp.3.', text)
+    text = re.sub('.fc3.', '.mlp.3.', text)
+    text = re.sub('.encoder_attn.', '.cross_attn.', text)
+    text = re.sub('.cross_attn.ln.', '.cross_attn_ln.', text)
+    text = re.sub('.embed_positions.weight', '.positional_embedding', text)
+    text = re.sub('.embed_tokens.', '.token_embedding.', text)
+    text = re.sub('model.', '', text)
+    text = re.sub('attn.layer_norm.', 'attn_ln.', text)
+    text = re.sub('.final_layer_norm.', '.mlp_ln.', text)
+    text = re.sub('encoder.layer_norm.', 'encoder.ln_post.', text)
+    text = re.sub('decoder.layer_norm.', 'decoder.ln.', text)
+    return text
+
+def states_to_dim(state_dict):
+    n_audio_state = len(state_dict['encoder.ln_post.bias'])
+    n_text_state = len(state_dict["decoder.ln.bias"])
+    return {
+        "n_mels":        state_dict["encoder.conv1.weight"].shape[1],           # 80
+        "n_vocab":       state_dict["decoder.token_embedding.weight"].shape[0], # 51864 / 51865
+        "n_audio_ctx":   state_dict["encoder.positional_embedding"].shape[0],   # 1500
+        "n_audio_state": n_audio_state,         # 384 / 512 / 768 / 1024 / 1280
+        "n_audio_head":  n_audio_state // 64,   # 6 / 8 / 12 / 16 / 20
+        "n_audio_layer": len(set([".".join(k.split(".")[:3]) for k in state_dict.keys() if "encoder.blocks." in k])), # 4 / 6 / 12 / 24 / 32
+        "n_text_ctx":    state_dict["decoder.positional_embedding"].shape[0],   # 448
+        "n_text_state":  n_text_state,          # 384 / 512 / 768 / 1024 / 1280
+        "n_text_head":   n_text_state // 64,    # 6 / 8 / 12 / 16 / 20
+        "n_text_layer":  len(set([".".join(k.split(".")[:3]) for k in state_dict.keys() if "decoder.blocks." in k])), # 4 / 6 / 12 / 24 / 32
+    }
+
+class TextDecoderUntied(whisper.model.TextDecoder):
+    """
+    Same as TextDecoder but with untied weights
+    """
+    def __init__(self, *args, **kwargs):
+        import torch
+        super().__init__(*args, **kwargs)
+
+        n_vocab, n_state = self.token_embedding.weight.shape
+
+        self.proj_out = torch.nn.Linear(n_state, n_vocab, bias=False)
+
+    def forward(self, x, xa, kv_cache = None):
+        offset = next(iter(kv_cache.values())).shape[1] if kv_cache else 0
+        x = self.token_embedding(x) + self.positional_embedding[offset : offset + x.shape[-1]]
+        x = x.to(xa.dtype)
+
+        for block in self.blocks:
+            x = block(x, xa, mask=self.mask, kv_cache=kv_cache)
+
+        x = self.ln(x)
+
+        # logits = self.proj_out(x).float()
+        # logits = (x @ torch.transpose(self.proj_out.weight.to(x.dtype), 0, 1)).float()
+        logits = self.proj_out.to(x.dtype)(x).float()
+
+        return logits
+
+class WhisperUntied(whisper.model.Whisper):
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.decoder = TextDecoderUntied(
+            self.dims.n_vocab,
+            self.dims.n_text_ctx,
+            self.dims.n_text_state,
+            self.dims.n_text_head,
+            self.dims.n_text_layer,
+        )
+
+def cli():
+
+    import os
+    import sys
+    import argparse
+    import json
+
+    from whisper.utils import str2bool, optional_float, optional_int
+    
+    try:
+        # Old whisper version # Before https://github.com/openai/whisper/commit/da600abd2b296a5450770b872c3765d0a5a5c769
+        from whisper.utils import write_txt, write_srt, write_vtt
+        write_tsv = lambda transcript, file: write_csv(transcript, file, sep="\t", header=True, text_first=False, format_timestamps=lambda x: round(1000 * x))
+    
+    except ImportError:
+        # New whisper version
+        from whisper.utils import get_writer
+
+        def do_write(transcript, file, output_format):
+            writer = get_writer(output_format, os.path.curdir)
+            try:
+                return writer.write_result({"segments": transcript}, file)
+            except TypeError:
+                # Version > 20230314
+                return writer.write_result({"segments": list(transcript)}, file, {
+                    "highlight_words": False,
+                    "max_line_width": None,
+                    "max_line_count": None,
+                })
+        def get_do_write(output_format):
+            return lambda transcript, file: do_write(transcript, file, output_format)
+
+        write_txt = get_do_write("txt")
+        write_srt = get_do_write("srt")
+        write_vtt = get_do_write("vtt")
+        write_tsv = get_do_write("tsv")
+
+    parser = argparse.ArgumentParser(
+        description='Transcribe a single audio with whisper and compute word timestamps',
+        formatter_class=argparse.ArgumentDefaultsHelpFormatter
+    )
+    parser.add_argument('-v', '--version', help="show version and exit", action='version', version=f'{__version__}')
+    parser.add_argument('--versions', help="show versions (of whisper-timestamped and whisper) and exit", action='version',
+                        version=f'{__version__} -- Whisper {whisper.__version__} in {os.path.realpath(os.path.dirname(whisper.__file__))}')
+
+    parser.add_argument('audio', help="audio file(s) to transcribe", nargs='+')
+    parser.add_argument('--model', help=f"name of the Whisper model to use. Examples: {', '.join(whisper.available_models())}", default="small")
+    parser.add_argument("--model_dir", default=None, help="the path to save model files; uses ~/.cache/whisper by default", type=str)
+    parser.add_argument("--device", default=get_default_device(), help="device to use for PyTorch inference")
+    parser.add_argument("--output_dir", "-o", default=None, help="directory to save the outputs", type=str)
+    valid_formats = ["txt", "vtt", "srt", "tsv", "csv", "json"]
+    def str2output_formats(string):
+        if string == "all":
+            return valid_formats
+        formats = string.split(",")
+        for format in formats:
+            if format not in valid_formats:
+                raise ValueError(f"Expected one of {valid_formats}, got {format}")
+        return formats
+    parser.add_argument("--output_format", "-f", default="all", help=f"Format(s) of the output file(s). Possible formats are: {', '.join(valid_formats)}. Several formats can be specified by using commas (ex: \"json,vtt,srt\"). By default (\"all\"), all available formats will be produced", type=str2output_formats)
+
+    parser.add_argument("--task", default="transcribe", help="whether to perform X->X speech recognition ('transcribe') or X->English translation ('translate')", choices=["transcribe", "translate"], type=str)
+    parser.add_argument('--language', help=f"language spoken in the audio, specify None to perform language detection.", choices=sorted(whisper.tokenizer.LANGUAGES.keys()) + sorted([k.title() for k in whisper.tokenizer.TO_LANGUAGE_CODE.keys()]), default=None)
+    # f"{', '.join(sorted(k+'('+v+')' for k,v in whisper.tokenizer.LANGUAGES.items()))}
+
+    parser.add_argument('--vad', default=False, help="whether to run Voice Activity Detection (VAD) to remove non-speech segment before applying Whisper model (removes hallucinations). Can be: True, False, silero, silero:3.1 (or another version), or autitok. Some additional libraries might be needed")
+    parser.add_argument('--detect_disfluencies', default=False, help="whether to try to detect disfluencies, marking them as special words [*]", type=str2bool)
+    parser.add_argument('--recompute_all_timestamps', default=not TRUST_WHISPER_TIMESTAMP_BY_DEFAULT, help="Do not rely at all on Whisper timestamps (Experimental option: did not bring any improvement, but could be useful in cases where Whipser segment timestamp are wrong by more than 0.5 seconds)", type=str2bool)
+    parser.add_argument("--punctuations_with_words", default=True, help="whether to include punctuations in the words", type=str2bool)
+        
+    parser.add_argument("--temperature", default=0.0, help="temperature to use for sampling", type=float)
+    parser.add_argument("--best_of", type=optional_int, default=None if USE_EFFICIENT_BY_DEFAULT else 5, help="number of candidates when sampling with non-zero temperature")
+    parser.add_argument("--beam_size", type=optional_int, default=None if USE_EFFICIENT_BY_DEFAULT else 5, help="number of beams in beam search, only applicable when temperature is zero")
+    parser.add_argument("--patience", type=float, default=None, help="optional patience value to use in beam decoding, as in https://arxiv.org/abs/2204.05424, the default (1.0) is equivalent to conventional beam search")
+    parser.add_argument("--length_penalty", type=float, default=None, help="optional token length penalty coefficient (alpha) as in https://arxiv.org/abs/1609.08144, uses simple length normalization by default")
+
+    parser.add_argument("--suppress_tokens", default="-1", help="comma-separated list of token ids to suppress during sampling; '-1' will suppress most special characters except common punctuations", type=str)
+    parser.add_argument("--initial_prompt", default=None, help="optional text to provide as a prompt for the first window.", type=str)
+    parser.add_argument("--condition_on_previous_text", default=True, help="if True, provide the previous output of the model as a prompt for the next window; disabling may make the text inconsistent across windows, but the model becomes less prone to getting stuck in a failure loop", type=str2bool)
+    parser.add_argument("--fp16", default=None, help="whether to perform inference in fp16; Automatic by default (True if GPU available, False otherwise)", type=str2bool)
+
+    parser.add_argument("--temperature_increment_on_fallback", default=0.0 if USE_EFFICIENT_BY_DEFAULT else 0.2, help="temperature to increase when falling back when the decoding fails to meet either of the thresholds below", type=optional_float)
+    parser.add_argument("--compression_ratio_threshold", default=2.4, help="if the gzip compression ratio is higher than this value, treat the decoding as failed", type=optional_float)
+    parser.add_argument("--logprob_threshold", default=-1.0, help="if the average log probability is lower than this value, treat the decoding as failed", type=optional_float)
+    parser.add_argument("--no_speech_threshold", default=0.6, help="if the probability of the <|nospeech|> token is higher than this value AND the decoding has failed due to `logprob_threshold`, consider the segment as silence", type=optional_float)
+    parser.add_argument("--threads", default=0, help="number of threads used by torch for CPU inference; supercedes MKL_NUM_THREADS/OMP_NUM_THREADS", type=optional_int)
+
+    parser.add_argument("--compute_confidence", default=True, help="whether to compute confidence scores for words", type=str2bool)
+    parser.add_argument("--verbose", type=str2bool, default=False, help="whether to print out the progress and debug messages of Whisper")
+    parser.add_argument('--plot', help="plot word alignments (save the figures if an --output_dir is specified, otherwhise just show figures that have to be closed to continue)", default=False, action="store_true")
+    parser.add_argument('--debug', help="print some debug information about word alignement", default=False, action="store_true")
+
+    class ActionSetAccurate(argparse.Action):
+        def __init__(self, option_strings, dest, nargs=None, **kwargs):
+            assert nargs is None
+            super().__init__(option_strings, dest, nargs=0, **kwargs)
+        def __call__(self, parser, namespace, values, option_string=None):
+            setattr(namespace, "best_of", 5)
+            setattr(namespace, "beam_size", 5)
+            setattr(namespace, "temperature_increment_on_fallback", 0.2)
+    parser.add_argument('--accurate', help="Shortcut to use the same default option as in Whisper (best_of=5, beam_search=5, temperature_increment_on_fallback=0.2)", action=ActionSetAccurate)
+
+    class ActionSetEfficient(argparse.Action):
+        def __init__(self, option_strings, dest, nargs=None, **kwargs):
+            assert nargs is None
+            super().__init__(option_strings, dest, nargs=0, **kwargs)
+        def __call__(self, parser, namespace, values, option_string=None):
+            setattr(namespace, "best_of", None)
+            setattr(namespace, "beam_size", None)
+            setattr(namespace, "temperature_increment_on_fallback", None)
+    parser.add_argument('--efficient', help="Shortcut to disable beam size and options that requires to sample several times, for an efficient decoding", action=ActionSetEfficient)
+
+    parser.add_argument('--naive', help="use naive approach, doing inference twice (once to get the transcription, once to get word timestamps and confidence scores).", default=False, action="store_true")
+
+    args = parser.parse_args().__dict__
+    args.pop("accurate")
+    args.pop("efficient")
+
+    temperature = args.pop("temperature")
+    temperature_increment_on_fallback = args.pop("temperature_increment_on_fallback")
+    if temperature_increment_on_fallback:
+        temperature = tuple(np.arange(temperature, 1.0 + 1e-6, temperature_increment_on_fallback))
+    else:
+        temperature = [temperature]
+
+    threads = args.pop("threads")
+    if threads:
+        torch.set_num_threads(threads)
+
+    audio_files = args.pop("audio")
+    
+    model = args.pop("model")
+    device = args.pop("device")
+    model_dir = args.pop("model_dir")
+
+    if device.lower().startswith("cuda"):
+        force_cudnn_initialization(device)
+
+    output_format = args.pop("output_format")
+
+    model = load_model(model, device=device, download_root=model_dir)
+
+    plot_word_alignment = args.pop("plot")
+
+    debug = args.pop("debug")
+    logging.basicConfig()
+    if debug:
+        logger.setLevel(logging.DEBUG)
+        # This supposes to plug a logger with name "WHISPER" into Whisper source code (no harm if it's not set)
+        logging.getLogger("WHISPER").setLevel(logging.DEBUG)
+
+    output_dir = args.pop("output_dir")
+    if output_dir and not os.path.isdir(output_dir):
+        os.makedirs(output_dir)
+
+    args["naive_approach"] = args.pop("naive")
+    args["remove_punctuation_from_words"] = not args.pop("punctuations_with_words")
+    args["compute_word_confidence"] = args.pop("compute_confidence")
+    args["trust_whisper_timestamps"] = not args.pop("recompute_all_timestamps")
+
+    for audio_path in audio_files:
+
+        outname = os.path.join(output_dir, os.path.basename(audio_path)) if output_dir else None
+
+        result = transcribe_timestamped(
+            model, audio_path,
+            temperature=temperature,
+            plot_word_alignment=outname if (outname and plot_word_alignment) else plot_word_alignment,
+            **args
+        )
+
+        if output_dir:
+
+            if "json" in output_format:
+                # save JSON
+                with open(outname + ".words.json", "w", encoding="utf-8") as js:
+                    json.dump(result, js, indent=2, ensure_ascii=False)
+
+            # save TXT
+            if "txt" in output_format:
+                with open(outname + ".txt", "w", encoding="utf-8") as txt:
+                    write_txt(result["segments"], file=txt)
+
+            # save VTT
+            if "vtt" in output_format:
+                with open(outname + ".vtt", "w", encoding="utf-8") as vtt:
+                    write_vtt(remove_keys(result["segments"], "words"), file=vtt)
+                with open(outname + ".words.vtt", "w", encoding="utf-8") as vtt:
+                    write_vtt(flatten(result["segments"], "words"), file=vtt)
+
+            # save SRT
+            if "srt" in output_format:
+                with open(outname + ".srt", "w", encoding="utf-8") as srt:
+                    write_srt(remove_keys(result["segments"], "words"), file=srt)
+                with open(outname + ".words.srt", "w", encoding="utf-8") as srt:
+                    write_srt(flatten(result["segments"], "words"), file=srt)
+
+            # save CSV
+            if "csv" in output_format:
+                with open(outname + ".csv", "w", encoding="utf-8") as csv:
+                    write_csv(result["segments"], file=csv)
+                with open(outname + ".words.csv", "w", encoding="utf-8") as csv:
+                    write_csv(flatten(result["segments"], "words"), file=csv)
+
+            # save TSV
+            if "tsv" in output_format:
+                with open(outname + ".tsv", "w", encoding="utf-8") as csv:
+                    write_tsv(result["segments"], file=csv)
+                with open(outname + ".words.tsv", "w", encoding="utf-8") as csv:
+                    write_tsv(flatten(result["segments"], "words"), file=csv)
+
+        elif not args["verbose"]:
+
+            json.dump(filtered_keys(result), sys.stdout, indent=2, ensure_ascii=False)
+
+
+def filtered_keys(result, keys = [
+    "text",
+    "segments", "words",
+    "language",
+    "start",
+    "end",
+    "confidence",
+    "language_probs",
+]):
+    if isinstance(result, dict):
+        return {k: (filtered_keys(v, keys) if k not in ["language_probs"] else v) for k, v in result.items() if k in keys}
+    if isinstance(result, list):
+        return [filtered_keys(v, keys) for v in result]
+    if isinstance(result, float):
+        return round(result, 2)
+    return result
+
+
+if __name__ == "__main__":
+    cli()
\ No newline at end of file