Upload 23 files

.cardboardlint.yml

@@ -0,0 +1,5 @@
+linters:
+- pylint:
+    # pylintrc: pylintrc
+    filefilter: ['- test_*.py', '+ *.py', '- *.npy']
+    # exclude:

.dockerignore

@@ -0,0 +1,9 @@
+.git/
+Dockerfile
+build/
+dist/
+TTS.egg-info/
+tests/outputs/*
+tests/train_outputs/*
+__pycache__/
+*.pyc

.gitignore

@@ -0,0 +1,171 @@
+WadaSNR/
+.idea/
+*.pyc
+.DS_Store
+./__init__.py
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+.static_storage/
+.media/
+local_settings.py
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+
+# vim
+*.swp
+*.swm
+*.swn
+*.swo
+
+# pytorch models
+*.pth
+*.pth.tar
+!dummy_speakers.pth
+result/
+
+# setup.py
+version.py
+
+# jupyter dummy files
+core
+
+# ignore local datasets
+recipes/WIP/*
+recipes/ljspeech/LJSpeech-1.1/*
+recipes/vctk/VCTK/*
+recipes/**/*.npy
+recipes/**/*.json
+VCTK-Corpus-removed-silence/*
+
+# ignore training logs
+trainer_*_log.txt
+
+# files used internally for dev, test etc.
+tests/outputs/*
+tests/train_outputs/*
+TODO.txt
+.vscode/*
+data/*
+notebooks/data/*
+TTS/tts/utils/monotonic_align/core.c
+.vscode-upload.json
+temp_build/*
+events.out*
+old_configs/*
+model_importers/*
+model_profiling/*
+docs/source/TODO/*
+.noseids
+.dccache
+log.txt
+umap.png
+*.out
+SocialMedia.txt
+output.wav
+tts_output.wav
+deps.json
+speakers.json
+internal/*
+*_pitch.npy
+*_phoneme.npy
+wandb
+depot/*
+coqui_recipes/*
+local_scripts/*

.pre-commit-config.yaml

@@ -0,0 +1,27 @@
+repos:
+  - repo: 'https://github.com/pre-commit/pre-commit-hooks'
+    rev: v2.3.0
+    hooks:
+      - id: check-yaml
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+  - repo: 'https://github.com/psf/black'
+    rev: 22.3.0
+    hooks:
+      - id: black
+        language_version: python3
+  - repo: https://github.com/pycqa/isort
+    rev: 5.8.0
+    hooks:
+      - id: isort
+        name: isort (python)
+      - id: isort
+        name: isort (cython)
+        types: [cython]
+      - id: isort
+        name: isort (pyi)
+        types: [pyi]
+  - repo: https://github.com/pycqa/pylint
+    rev: v2.8.2
+    hooks:
+    -   id: pylint

.pylintrc

@@ -0,0 +1,599 @@
+[MASTER]
+
+# A comma-separated list of package or module names from where C extensions may
+# be loaded. Extensions are loading into the active Python interpreter and may
+# run arbitrary code.
+extension-pkg-whitelist=
+
+# Add files or directories to the blacklist. They should be base names, not
+# paths.
+ignore=CVS
+
+# Add files or directories matching the regex patterns to the blacklist. The
+# regex matches against base names, not paths.
+ignore-patterns=
+
+# Python code to execute, usually for sys.path manipulation such as
+# pygtk.require().
+#init-hook=
+
+# Use multiple processes to speed up Pylint. Specifying 0 will auto-detect the
+# number of processors available to use.
+jobs=1
+
+# Control the amount of potential inferred values when inferring a single
+# object. This can help the performance when dealing with large functions or
+# complex, nested conditions.
+limit-inference-results=100
+
+# List of plugins (as comma separated values of python modules names) to load,
+# usually to register additional checkers.
+load-plugins=
+
+# Pickle collected data for later comparisons.
+persistent=yes
+
+# Specify a configuration file.
+#rcfile=
+
+# When enabled, pylint would attempt to guess common misconfiguration and emit
+# user-friendly hints instead of false-positive error messages.
+suggestion-mode=yes
+
+# Allow loading of arbitrary C extensions. Extensions are imported into the
+# active Python interpreter and may run arbitrary code.
+unsafe-load-any-extension=no
+
+
+[MESSAGES CONTROL]
+
+# Only show warnings with the listed confidence levels. Leave empty to show
+# all. Valid levels: HIGH, INFERENCE, INFERENCE_FAILURE, UNDEFINED.
+confidence=
+
+# Disable the message, report, category or checker with the given id(s). You
+# can either give multiple identifiers separated by comma (,) or put this
+# option multiple times (only on the command line, not in the configuration
+# file where it should appear only once). You can also use "--disable=all" to
+# disable everything first and then reenable specific checks. For example, if
+# you want to run only the similarities checker, you can use "--disable=all
+# --enable=similarities". If you want to run only the classes checker, but have
+# no Warning level messages displayed, use "--disable=all --enable=classes
+# --disable=W".
+disable=missing-docstring,
+        too-many-public-methods,
+        too-many-lines,
+        bare-except,
+        ## for avoiding weird p3.6 CI linter error
+        ## TODO: see later if we can remove this
+        assigning-non-slot,
+        unsupported-assignment-operation,
+        ## end
+        line-too-long,
+        fixme,
+        wrong-import-order,
+        ungrouped-imports,
+        wrong-import-position,
+        import-error,
+        invalid-name,
+        too-many-instance-attributes,
+        arguments-differ,
+        arguments-renamed,
+        no-name-in-module,
+        no-member,
+        unsubscriptable-object,
+        print-statement,
+        parameter-unpacking,
+        unpacking-in-except,
+        old-raise-syntax,
+        backtick,
+        long-suffix,
+        old-ne-operator,
+        old-octal-literal,
+        import-star-module-level,
+        non-ascii-bytes-literal,
+        raw-checker-failed,
+        bad-inline-option,
+        locally-disabled,
+        file-ignored,
+        suppressed-message,
+        useless-suppression,
+        deprecated-pragma,
+        use-symbolic-message-instead,
+        useless-object-inheritance,
+        too-few-public-methods,
+        too-many-branches,
+        too-many-arguments,
+        too-many-locals,
+        too-many-statements,
+        apply-builtin,
+        basestring-builtin,
+        buffer-builtin,
+        cmp-builtin,
+        coerce-builtin,
+        execfile-builtin,
+        file-builtin,
+        long-builtin,
+        raw_input-builtin,
+        reduce-builtin,
+        standarderror-builtin,
+        unicode-builtin,
+        xrange-builtin,
+        coerce-method,
+        delslice-method,
+        getslice-method,
+        setslice-method,
+        no-absolute-import,
+        old-division,
+        dict-iter-method,
+        dict-view-method,
+        next-method-called,
+        metaclass-assignment,
+        indexing-exception,
+        raising-string,
+        reload-builtin,
+        oct-method,
+        hex-method,
+        nonzero-method,
+        cmp-method,
+        input-builtin,
+        round-builtin,
+        intern-builtin,
+        unichr-builtin,
+        map-builtin-not-iterating,
+        zip-builtin-not-iterating,
+        range-builtin-not-iterating,
+        filter-builtin-not-iterating,
+        using-cmp-argument,
+        eq-without-hash,
+        div-method,
+        idiv-method,
+        rdiv-method,
+        exception-message-attribute,
+        invalid-str-codec,
+        sys-max-int,
+        bad-python3-import,
+        deprecated-string-function,
+        deprecated-str-translate-call,
+        deprecated-itertools-function,
+        deprecated-types-field,
+        next-method-defined,
+        dict-items-not-iterating,
+        dict-keys-not-iterating,
+        dict-values-not-iterating,
+        deprecated-operator-function,
+        deprecated-urllib-function,
+        xreadlines-attribute,
+        deprecated-sys-function,
+        exception-escape,
+        comprehension-escape,
+        duplicate-code,
+        not-callable,
+        import-outside-toplevel,
+        logging-fstring-interpolation,
+        logging-not-lazy
+
+# Enable the message, report, category or checker with the given id(s). You can
+# either give multiple identifier separated by comma (,) or put this option
+# multiple time (only on the command line, not in the configuration file where
+# it should appear only once). See also the "--disable" option for examples.
+enable=c-extension-no-member
+
+
+[REPORTS]
+
+# Python expression which should return a note less than 10 (10 is the highest
+# note). You have access to the variables errors warning, statement which
+# respectively contain the number of errors / warnings messages and the total
+# number of statements analyzed. This is used by the global evaluation report
+# (RP0004).
+evaluation=10.0 - ((float(5 * error + warning + refactor + convention) / statement) * 10)
+
+# Template used to display messages. This is a python new-style format string
+# used to format the message information. See doc for all details.
+#msg-template=
+
+# Set the output format. Available formats are text, parseable, colorized, json
+# and msvs (visual studio). You can also give a reporter class, e.g.
+# mypackage.mymodule.MyReporterClass.
+output-format=text
+
+# Tells whether to display a full report or only the messages.
+reports=no
+
+# Activate the evaluation score.
+score=yes
+
+
+[REFACTORING]
+
+# Maximum number of nested blocks for function / method body
+max-nested-blocks=5
+
+# Complete name of functions that never returns. When checking for
+# inconsistent-return-statements if a never returning function is called then
+# it will be considered as an explicit return statement and no message will be
+# printed.
+never-returning-functions=sys.exit
+
+
+[LOGGING]
+
+# Format style used to check logging format string. `old` means using %
+# formatting, while `new` is for `{}` formatting.
+logging-format-style=old
+
+# Logging modules to check that the string format arguments are in logging
+# function parameter format.
+logging-modules=logging
+
+
+[SPELLING]
+
+# Limits count of emitted suggestions for spelling mistakes.
+max-spelling-suggestions=4
+
+# Spelling dictionary name. Available dictionaries: none. To make it working
+# install python-enchant package..
+spelling-dict=
+
+# List of comma separated words that should not be checked.
+spelling-ignore-words=
+
+# A path to a file that contains private dictionary; one word per line.
+spelling-private-dict-file=
+
+# Tells whether to store unknown words to indicated private dictionary in
+# --spelling-private-dict-file option instead of raising a message.
+spelling-store-unknown-words=no
+
+
+[MISCELLANEOUS]
+
+# List of note tags to take in consideration, separated by a comma.
+notes=FIXME,
+      XXX,
+      TODO
+
+
+[TYPECHECK]
+
+# List of decorators that produce context managers, such as
+# contextlib.contextmanager. Add to this list to register other decorators that
+# produce valid context managers.
+contextmanager-decorators=contextlib.contextmanager
+
+# List of members which are set dynamically and missed by pylint inference
+# system, and so shouldn't trigger E1101 when accessed. Python regular
+# expressions are accepted.
+generated-members=numpy.*,torch.*
+
+# Tells whether missing members accessed in mixin class should be ignored. A
+# mixin class is detected if its name ends with "mixin" (case insensitive).
+ignore-mixin-members=yes
+
+# Tells whether to warn about missing members when the owner of the attribute
+# is inferred to be None.
+ignore-none=yes
+
+# This flag controls whether pylint should warn about no-member and similar
+# checks whenever an opaque object is returned when inferring. The inference
+# can return multiple potential results while evaluating a Python object, but
+# some branches might not be evaluated, which results in partial inference. In
+# that case, it might be useful to still emit no-member and other checks for
+# the rest of the inferred objects.
+ignore-on-opaque-inference=yes
+
+# List of class names for which member attributes should not be checked (useful
+# for classes with dynamically set attributes). This supports the use of
+# qualified names.
+ignored-classes=optparse.Values,thread._local,_thread._local
+
+# List of module names for which member attributes should not be checked
+# (useful for modules/projects where namespaces are manipulated during runtime
+# and thus existing member attributes cannot be deduced by static analysis. It
+# supports qualified module names, as well as Unix pattern matching.
+ignored-modules=
+
+# Show a hint with possible names when a member name was not found. The aspect
+# of finding the hint is based on edit distance.
+missing-member-hint=yes
+
+# The minimum edit distance a name should have in order to be considered a
+# similar match for a missing member name.
+missing-member-hint-distance=1
+
+# The total number of similar names that should be taken in consideration when
+# showing a hint for a missing member.
+missing-member-max-choices=1
+
+
+[VARIABLES]
+
+# List of additional names supposed to be defined in builtins. Remember that
+# you should avoid defining new builtins when possible.
+additional-builtins=
+
+# Tells whether unused global variables should be treated as a violation.
+allow-global-unused-variables=yes
+
+# List of strings which can identify a callback function by name. A callback
+# name must start or end with one of those strings.
+callbacks=cb_,
+          _cb
+
+# A regular expression matching the name of dummy variables (i.e. expected to
+# not be used).
+dummy-variables-rgx=_+$|(_[a-zA-Z0-9_]*[a-zA-Z0-9]+?$)|dummy|^ignored_|^unused_
+
+# Argument names that match this expression will be ignored. Default to name
+# with leading underscore.
+ignored-argument-names=_.*|^ignored_|^unused_
+
+# Tells whether we should check for unused import in __init__ files.
+init-import=no
+
+# List of qualified module names which can have objects that can redefine
+# builtins.
+redefining-builtins-modules=six.moves,past.builtins,future.builtins,builtins,io
+
+
+[FORMAT]
+
+# Expected format of line ending, e.g. empty (any line ending), LF or CRLF.
+expected-line-ending-format=
+
+# Regexp for a line that is allowed to be longer than the limit.
+ignore-long-lines=^\s*(# )?<?https?://\S+>?$
+
+# Number of spaces of indent required inside a hanging or continued line.
+indent-after-paren=4
+
+# String used as indentation unit. This is usually "    " (4 spaces) or "\t" (1
+# tab).
+indent-string='    '
+
+# Maximum number of characters on a single line.
+max-line-length=120
+
+# Maximum number of lines in a module.
+max-module-lines=1000
+
+# List of optional constructs for which whitespace checking is disabled. `dict-
+# separator` is used to allow tabulation in dicts, etc.: {1  : 1,\n222: 2}.
+# `trailing-comma` allows a space between comma and closing bracket: (a, ).
+# `empty-line` allows space-only lines.
+no-space-check=trailing-comma,
+               dict-separator
+
+# Allow the body of a class to be on the same line as the declaration if body
+# contains single statement.
+single-line-class-stmt=no
+
+# Allow the body of an if to be on the same line as the test if there is no
+# else.
+single-line-if-stmt=no
+
+
+[SIMILARITIES]
+
+# Ignore comments when computing similarities.
+ignore-comments=yes
+
+# Ignore docstrings when computing similarities.
+ignore-docstrings=yes
+
+# Ignore imports when computing similarities.
+ignore-imports=no
+
+# Minimum lines number of a similarity.
+min-similarity-lines=4
+
+
+[BASIC]
+
+# Naming style matching correct argument names.
+argument-naming-style=snake_case
+
+# Regular expression matching correct argument names. Overrides argument-
+# naming-style.
+argument-rgx=[a-z_][a-z0-9_]{0,30}$
+
+# Naming style matching correct attribute names.
+attr-naming-style=snake_case
+
+# Regular expression matching correct attribute names. Overrides attr-naming-
+# style.
+#attr-rgx=
+
+# Bad variable names which should always be refused, separated by a comma.
+bad-names=
+
+# Naming style matching correct class attribute names.
+class-attribute-naming-style=any
+
+# Regular expression matching correct class attribute names. Overrides class-
+# attribute-naming-style.
+#class-attribute-rgx=
+
+# Naming style matching correct class names.
+class-naming-style=PascalCase
+
+# Regular expression matching correct class names. Overrides class-naming-
+# style.
+#class-rgx=
+
+# Naming style matching correct constant names.
+const-naming-style=UPPER_CASE
+
+# Regular expression matching correct constant names. Overrides const-naming-
+# style.
+#const-rgx=
+
+# Minimum line length for functions/classes that require docstrings, shorter
+# ones are exempt.
+docstring-min-length=-1
+
+# Naming style matching correct function names.
+function-naming-style=snake_case
+
+# Regular expression matching correct function names. Overrides function-
+# naming-style.
+#function-rgx=
+
+# Good variable names which should always be accepted, separated by a comma.
+good-names=i,
+           j,
+           k,
+           x,
+           ex,
+           Run,
+           _
+
+# Include a hint for the correct naming format with invalid-name.
+include-naming-hint=no
+
+# Naming style matching correct inline iteration names.
+inlinevar-naming-style=any
+
+# Regular expression matching correct inline iteration names. Overrides
+# inlinevar-naming-style.
+#inlinevar-rgx=
+
+# Naming style matching correct method names.
+method-naming-style=snake_case
+
+# Regular expression matching correct method names. Overrides method-naming-
+# style.
+#method-rgx=
+
+# Naming style matching correct module names.
+module-naming-style=snake_case
+
+# Regular expression matching correct module names. Overrides module-naming-
+# style.
+#module-rgx=
+
+# Colon-delimited sets of names that determine each other's naming style when
+# the name regexes allow several styles.
+name-group=
+
+# Regular expression which should only match function or class names that do
+# not require a docstring.
+no-docstring-rgx=^_
+
+# List of decorators that produce properties, such as abc.abstractproperty. Add
+# to this list to register other decorators that produce valid properties.
+# These decorators are taken in consideration only for invalid-name.
+property-classes=abc.abstractproperty
+
+# Naming style matching correct variable names.
+variable-naming-style=snake_case
+
+# Regular expression matching correct variable names. Overrides variable-
+# naming-style.
+variable-rgx=[a-z_][a-z0-9_]{0,30}$
+
+
+[STRING]
+
+# This flag controls whether the implicit-str-concat-in-sequence should
+# generate a warning on implicit string concatenation in sequences defined over
+# several lines.
+check-str-concat-over-line-jumps=no
+
+
+[IMPORTS]
+
+# Allow wildcard imports from modules that define __all__.
+allow-wildcard-with-all=no
+
+# Analyse import fallback blocks. This can be used to support both Python 2 and
+# 3 compatible code, which means that the block might have code that exists
+# only in one or another interpreter, leading to false positives when analysed.
+analyse-fallback-blocks=no
+
+# Deprecated modules which should not be used, separated by a comma.
+deprecated-modules=optparse,tkinter.tix
+
+# Create a graph of external dependencies in the given file (report RP0402 must
+# not be disabled).
+ext-import-graph=
+
+# Create a graph of every (i.e. internal and external) dependencies in the
+# given file (report RP0402 must not be disabled).
+import-graph=
+
+# Create a graph of internal dependencies in the given file (report RP0402 must
+# not be disabled).
+int-import-graph=
+
+# Force import order to recognize a module as part of the standard
+# compatibility libraries.
+known-standard-library=
+
+# Force import order to recognize a module as part of a third party library.
+known-third-party=enchant
+
+
+[CLASSES]
+
+# List of method names used to declare (i.e. assign) instance attributes.
+defining-attr-methods=__init__,
+                      __new__,
+                      setUp
+
+# List of member names, which should be excluded from the protected access
+# warning.
+exclude-protected=_asdict,
+                  _fields,
+                  _replace,
+                  _source,
+                  _make
+
+# List of valid names for the first argument in a class method.
+valid-classmethod-first-arg=cls
+
+# List of valid names for the first argument in a metaclass class method.
+valid-metaclass-classmethod-first-arg=cls
+
+
+[DESIGN]
+
+# Maximum number of arguments for function / method.
+max-args=5
+
+# Maximum number of attributes for a class (see R0902).
+max-attributes=7
+
+# Maximum number of boolean expressions in an if statement.
+max-bool-expr=5
+
+# Maximum number of branch for function / method body.
+max-branches=12
+
+# Maximum number of locals for function / method body.
+max-locals=15
+
+# Maximum number of parents for a class (see R0901).
+max-parents=15
+
+# Maximum number of public methods for a class (see R0904).
+max-public-methods=20
+
+# Maximum number of return / yield for function / method body.
+max-returns=6
+
+# Maximum number of statements in function / method body.
+max-statements=50
+
+# Minimum number of public methods for a class (see R0903).
+min-public-methods=2
+
+
+[EXCEPTIONS]
+
+# Exceptions that will emit a warning when being caught. Defaults to
+# "BaseException, Exception".
+overgeneral-exceptions=BaseException,
+                       Exception

.readthedocs.yml

@@ -0,0 +1,23 @@
+# .readthedocs.yml
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Set the version of Python and other tools you might need
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.11"
+
+# Optionally set the version of Python and requirements required to build your docs
+python:
+  install:
+    - requirements: docs/requirements.txt
+    - requirements: requirements.txt
+
+# Build documentation in the docs/ directory with Sphinx
+sphinx:
+  builder: html
+  configuration: docs/source/conf.py

CITATION.cff

@@ -0,0 +1,20 @@
+cff-version: 1.2.0
+message: "If you want to cite 🐸💬, feel free to use this (but only if you loved it 😊)"
+title: "Coqui TTS"
+abstract: "A deep learning toolkit for Text-to-Speech, battle-tested in research and production"
+date-released: 2021-01-01
+authors:
+  - family-names: "Eren"
+    given-names: "Gölge"
+  - name: "The Coqui TTS Team"
+version: 1.4
+doi: 10.5281/zenodo.6334862
+license: "MPL-2.0"
+url: "https://www.coqui.ai"
+repository-code: "https://github.com/coqui-ai/TTS"
+keywords:
+  - machine learning
+  - deep learning
+  - artificial intelligence
+  - text to speech
+  - TTS

CODE_OF_CONDUCT.md

@@ -0,0 +1,133 @@
+
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, caste, color, religion, or sexual identity
+and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the
+  overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+coc-report@coqui.ai.
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series
+of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or
+permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior,  harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within
+the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.0, available at
+[https://www.contributor-covenant.org/version/2/0/code_of_conduct.html][v2.0].
+
+Community Impact Guidelines were inspired by 
+[Mozilla's code of conduct enforcement ladder][Mozilla CoC].
+
+For answers to common questions about this code of conduct, see the FAQ at
+[https://www.contributor-covenant.org/faq][FAQ]. Translations are available 
+at [https://www.contributor-covenant.org/translations][translations].
+
+[homepage]: https://www.contributor-covenant.org
+[v2.0]: https://www.contributor-covenant.org/version/2/0/code_of_conduct.html
+[Mozilla CoC]: https://github.com/mozilla/diversity
+[FAQ]: https://www.contributor-covenant.org/faq
+[translations]: https://www.contributor-covenant.org/translations

CODE_OWNERS.rst

@@ -0,0 +1,75 @@
+TTS code owners / governance system
+==========================================
+
+TTS is run under a governance system inspired (and partially copied from) by the `Mozilla module ownership system <https://www.mozilla.org/about/governance/policies/module-ownership/>`_. The project is roughly divided into modules, and each module has its owners, which are responsible for reviewing pull requests and deciding on technical direction for their modules. Module ownership authority is given to people who have worked extensively on areas of the project.
+
+Module owners also have the authority of naming other module owners or appointing module peers, which are people with authority to review pull requests in that module. They can also sub-divide their module into sub-modules with their owners.
+
+Module owners are not tyrants. They are chartered to make decisions with input from the community and in the best interest of the community. Module owners are not required to make code changes or additions solely because the community wants them to do so. (Like anyone else, the module owners may write code because they want to, because their employers want them to, because the community wants them to, or for some other reason.) Module owners do need to pay attention to patches submitted to that module. However “pay attention” does not mean agreeing to every patch. Some patches may not make sense for the WebThings project; some may be poorly implemented. Module owners have the authority to decline a patch; this is a necessary part of the role. We ask the module owners to describe in the relevant issue their reasons for wanting changes to a patch, for declining it altogether, or for postponing review for some period. We don’t ask or expect them to rewrite patches to make them acceptable. Similarly, module owners may need to delay review of a promising patch due to an upcoming deadline. For example, a patch may be of interest, but not for the next milestone. In such a case it may make sense for the module owner to postpone review of a patch until after matters needed for a milestone have been finalized. Again, we expect this to be described in the relevant issue. And of course, it shouldn’t go on very often or for very long or escalation and review is likely.
+
+The work of the various module owners and peers is overseen by the global owners, which are responsible for making final decisions in case there's conflict between owners as well as set the direction for the project as a whole.
+
+This file describes module owners who are active on the project and which parts of the code they have expertise on (and interest in). If you're making changes to the code and are wondering who's an appropriate person to talk to, this list will tell you who to ping.
+
+There's overlap in the areas of expertise of each owner, and in particular when looking at which files are covered by each area, there is a lot of overlap. Don't worry about getting it exactly right when requesting review, any code owner will be happy to redirect the request to a more appropriate person.
+
+Global owners
+----------------
+
+These are people who have worked on the project extensively and are familiar with all or most parts of it. Their expertise and review guidance is trusted by other code owners to cover their own areas of expertise. In case of conflicting opinions from other owners, global owners will make a final decision.
+
+- Eren Gölge (@erogol)
+- Reuben Morais (@reuben)
+
+Training, feeding
+-----------------
+
+- Eren Gölge (@erogol)
+
+Model exporting
+---------------
+
+- Eren Gölge (@erogol)
+
+Multi-Speaker TTS
+-----------------
+
+- Eren Gölge (@erogol)
+- Edresson Casanova (@edresson)
+
+TTS
+---
+
+- Eren Gölge (@erogol)
+
+Vocoders
+--------
+
+- Eren Gölge (@erogol)
+
+Speaker Encoder
+---------------
+
+- Eren Gölge (@erogol)
+
+Testing & CI
+------------
+
+- Eren Gölge (@erogol)
+- Reuben Morais (@reuben)
+
+Python bindings
+---------------
+
+- Eren Gölge (@erogol)
+- Reuben Morais (@reuben)
+
+Documentation
+-------------
+
+- Eren Gölge (@erogol)
+
+Third party bindings
+--------------------
+
+Owned by the author.

CONTRIBUTING.md

@@ -0,0 +1,136 @@
+# Contribution guidelines
+
+Welcome to the 🐸TTS!
+
+This repository is governed by [the Contributor Covenant Code of Conduct](https://github.com/coqui-ai/TTS/blob/main/CODE_OF_CONDUCT.md).
+
+## Where to start.
+We welcome everyone who likes to contribute to 🐸TTS.
+
+You can contribute not only with code but with bug reports, comments, questions, answers, or just a simple tweet to spread the word.
+
+If you like to contribute code, squash a bug but if you don't know where to start, here are some pointers.
+
+- [Development Road Map](https://github.com/coqui-ai/TTS/issues/378)
+
+    You can pick something out of our road map. We keep the progess of the project in this simple issue thread. It has new model proposals or developmental updates etc.
+
+- [Github Issues Tracker](https://github.com/coqui-ai/TTS/issues)
+
+    This is a place to find feature requests, bugs.
+
+    Issues with the ```good first issue``` tag are good place for beginners to take on.
+
+- ✨**PR**✨ [pages](https://github.com/coqui-ai/TTS/pulls) with the ```🚀new version``` tag.
+
+    We list all the target improvements for the next version. You can pick one of them and start contributing.
+
+- Also feel free to suggest new features, ideas and models. We're always open for new things.
+
+## Call for sharing language models
+If possible, please consider sharing your pre-trained models in any language (if the licences allow for you to do so). We will include them in our model catalogue for public use and give the proper attribution, whether it be your name, company, website or any other source specified.
+
+This model can be shared in two ways:
+1. Share the model files with us and we serve them with the next 🐸 TTS release.
+2. Upload your models on GDrive and share the link.
+
+Models are served under `.models.json` file and any model is available under TTS CLI or Server end points.
+
+Either way you choose, please make sure you send the models [here](https://github.com/coqui-ai/TTS/issues/380). 
+
+## Sending a ✨**PR**✨
+
+If you have a new feature, a model to implement, or a bug to squash, go ahead and send a ✨**PR**✨.
+Please use the following steps to send a ✨**PR**✨.
+Let us know if you encounter a problem along the way.
+
+The following steps are tested on an Ubuntu system.
+
+1. Fork 🐸TTS[https://github.com/coqui-ai/TTS] by clicking the fork button at the top right corner of the project page.
+
+2. Clone 🐸TTS and add the main repo as a new remote named ```upsteam```.
+
+    ```bash
+    $ git clone git@github.com:<your Github name>/TTS.git
+    $ cd TTS
+    $ git remote add upstream https://github.com/coqui-ai/TTS.git
+    ```
+
+3. Install 🐸TTS for development.
+
+    ```bash
+    $ make system-deps  # intended to be used on Ubuntu (Debian). Let us know if you have a different OS.
+    $ make install
+    ```
+
+4. Create a new branch with an informative name for your goal.
+
+    ```bash
+    $ git checkout -b an_informative_name_for_my_branch
+    ```
+
+5. Implement your changes on your new branch.
+
+6. Explain your code using [Google Style](https://google.github.io/styleguide/pyguide.html#381-docstrings) docstrings.
+
+7. Add your tests to our test suite under ```tests```  folder. It is important to show that your code works, edge cases are considered, and inform others about the intended use.
+
+8. Run the tests to see how your updates work with the rest of the project. You can repeat this step multiple times as you implement your changes to make sure you are on the right direction.
+
+    ```bash
+    $ make test  # stop at the first error
+    $ make test_all  # run all the tests, report all the errors
+    ```
+
+9. Format your code. We use ```black``` for code and ```isort``` for ```import``` formatting.
+
+    ```bash
+    $ make style
+    ```
+
+10. Run the linter and correct the issues raised. We use ```pylint``` for linting.  It helps to enforce a coding standard, offers simple refactoring suggestions.
+
+    ```bash
+    $ make lint
+    ```
+
+11. When things are good, add new files and commit your changes.
+
+    ```bash
+    $ git add my_file1.py my_file2.py ...
+    $ git commit
+    ```
+
+    It's a good practice to regularly sync your local copy of the project with the upstream code to keep up with the recent updates.
+
+    ```bash
+    $ git fetch upstream
+    $ git rebase upstream/master
+    # or for the development version
+    $ git rebase upstream/dev
+    ```
+
+12. Send a PR to ```dev``` branch.
+
+    Push your branch to your fork.
+
+    ```bash
+    $ git push -u origin an_informative_name_for_my_branch
+    ```
+
+    Then go to your fork's Github page and click on 'Pull request' to send your ✨**PR**✨.
+
+    Please set ✨**PR**✨'s target branch to ```dev``` as we use ```dev``` to work on the next version.
+
+13. Let's discuss until it is perfect. 💪
+
+    We might ask you for certain changes that would appear in the ✨**PR**✨'s page under 🐸TTS[https://github.com/coqui-ai/TTS/pulls].
+
+14. Once things look perfect, We merge it to the ```dev``` branch and make it ready for the next version.
+
+Feel free to ping us at any step you need help using our communication channels.
+
+If you are new to Github or open-source contribution, These are good resources.
+
+- [Github Docs](https://docs.github.com/en/github/collaborating-with-issues-and-pull-requests/proposing-changes-to-your-work-with-pull-requests)
+- [First-Contribution](https://github.com/firstcontributions/first-contributions)

Dockerfile

@@ -0,0 +1,13 @@
+ARG BASE=nvidia/cuda:11.8.0-base-ubuntu22.04
+FROM ${BASE}
+RUN apt-get update && apt-get upgrade -y
+RUN apt-get install -y --no-install-recommends gcc g++ make python3 python3-dev python3-pip python3-venv python3-wheel espeak-ng libsndfile1-dev && rm -rf /var/lib/apt/lists/*
+RUN pip3 install llvmlite --ignore-installed
+
+WORKDIR /root
+COPY . /root
+RUN pip3 install torch torchaudio --extra-index-url https://download.pytorch.org/whl/cu118
+RUN rm -rf /root/.cache/pip
+RUN make install
+ENTRYPOINT ["tts"]
+CMD ["--help"]

LICENSE.txt

@@ -0,0 +1,373 @@
+Mozilla Public License Version 2.0
+==================================
+
+1. Definitions
+--------------
+
+1.1. "Contributor"
+    means each individual or legal entity that creates, contributes to
+    the creation of, or owns Covered Software.
+
+1.2. "Contributor Version"
+    means the combination of the Contributions of others (if any) used
+    by a Contributor and that particular Contributor's Contribution.
+
+1.3. "Contribution"
+    means Covered Software of a particular Contributor.
+
+1.4. "Covered Software"
+    means Source Code Form to which the initial Contributor has attached
+    the notice in Exhibit A, the Executable Form of such Source Code
+    Form, and Modifications of such Source Code Form, in each case
+    including portions thereof.
+
+1.5. "Incompatible With Secondary Licenses"
+    means
+
+    (a) that the initial Contributor has attached the notice described
+        in Exhibit B to the Covered Software; or
+
+    (b) that the Covered Software was made available under the terms of
+        version 1.1 or earlier of the License, but not also under the
+        terms of a Secondary License.
+
+1.6. "Executable Form"
+    means any form of the work other than Source Code Form.
+
+1.7. "Larger Work"
+    means a work that combines Covered Software with other material, in 
+    a separate file or files, that is not Covered Software.
+
+1.8. "License"
+    means this document.
+
+1.9. "Licensable"
+    means having the right to grant, to the maximum extent possible,
+    whether at the time of the initial grant or subsequently, any and
+    all of the rights conveyed by this License.
+
+1.10. "Modifications"
+    means any of the following:
+
+    (a) any file in Source Code Form that results from an addition to,
+        deletion from, or modification of the contents of Covered
+        Software; or
+
+    (b) any new file in Source Code Form that contains any Covered
+        Software.
+
+1.11. "Patent Claims" of a Contributor
+    means any patent claim(s), including without limitation, method,
+    process, and apparatus claims, in any patent Licensable by such
+    Contributor that would be infringed, but for the grant of the
+    License, by the making, using, selling, offering for sale, having
+    made, import, or transfer of either its Contributions or its
+    Contributor Version.
+
+1.12. "Secondary License"
+    means either the GNU General Public License, Version 2.0, the GNU
+    Lesser General Public License, Version 2.1, the GNU Affero General
+    Public License, Version 3.0, or any later versions of those
+    licenses.
+
+1.13. "Source Code Form"
+    means the form of the work preferred for making modifications.
+
+1.14. "You" (or "Your")
+    means an individual or a legal entity exercising rights under this
+    License. For legal entities, "You" includes any entity that
+    controls, is controlled by, or is under common control with You. For
+    purposes of this definition, "control" means (a) the power, direct
+    or indirect, to cause the direction or management of such entity,
+    whether by contract or otherwise, or (b) ownership of more than
+    fifty percent (50%) of the outstanding shares or beneficial
+    ownership of such entity.
+
+2. License Grants and Conditions
+--------------------------------
+
+2.1. Grants
+
+Each Contributor hereby grants You a world-wide, royalty-free,
+non-exclusive license:
+
+(a) under intellectual property rights (other than patent or trademark)
+    Licensable by such Contributor to use, reproduce, make available,
+    modify, display, perform, distribute, and otherwise exploit its
+    Contributions, either on an unmodified basis, with Modifications, or
+    as part of a Larger Work; and
+
+(b) under Patent Claims of such Contributor to make, use, sell, offer
+    for sale, have made, import, and otherwise transfer either its
+    Contributions or its Contributor Version.
+
+2.2. Effective Date
+
+The licenses granted in Section 2.1 with respect to any Contribution
+become effective for each Contribution on the date the Contributor first
+distributes such Contribution.
+
+2.3. Limitations on Grant Scope
+
+The licenses granted in this Section 2 are the only rights granted under
+this License. No additional rights or licenses will be implied from the
+distribution or licensing of Covered Software under this License.
+Notwithstanding Section 2.1(b) above, no patent license is granted by a
+Contributor:
+
+(a) for any code that a Contributor has removed from Covered Software;
+    or
+
+(b) for infringements caused by: (i) Your and any other third party's
+    modifications of Covered Software, or (ii) the combination of its
+    Contributions with other software (except as part of its Contributor
+    Version); or
+
+(c) under Patent Claims infringed by Covered Software in the absence of
+    its Contributions.
+
+This License does not grant any rights in the trademarks, service marks,
+or logos of any Contributor (except as may be necessary to comply with
+the notice requirements in Section 3.4).
+
+2.4. Subsequent Licenses
+
+No Contributor makes additional grants as a result of Your choice to
+distribute the Covered Software under a subsequent version of this
+License (see Section 10.2) or under the terms of a Secondary License (if
+permitted under the terms of Section 3.3).
+
+2.5. Representation
+
+Each Contributor represents that the Contributor believes its
+Contributions are its original creation(s) or it has sufficient rights
+to grant the rights to its Contributions conveyed by this License.
+
+2.6. Fair Use
+
+This License is not intended to limit any rights You have under
+applicable copyright doctrines of fair use, fair dealing, or other
+equivalents.
+
+2.7. Conditions
+
+Sections 3.1, 3.2, 3.3, and 3.4 are conditions of the licenses granted
+in Section 2.1.
+
+3. Responsibilities
+-------------------
+
+3.1. Distribution of Source Form
+
+All distribution of Covered Software in Source Code Form, including any
+Modifications that You create or to which You contribute, must be under
+the terms of this License. You must inform recipients that the Source
+Code Form of the Covered Software is governed by the terms of this
+License, and how they can obtain a copy of this License. You may not
+attempt to alter or restrict the recipients' rights in the Source Code
+Form.
+
+3.2. Distribution of Executable Form
+
+If You distribute Covered Software in Executable Form then:
+
+(a) such Covered Software must also be made available in Source Code
+    Form, as described in Section 3.1, and You must inform recipients of
+    the Executable Form how they can obtain a copy of such Source Code
+    Form by reasonable means in a timely manner, at a charge no more
+    than the cost of distribution to the recipient; and
+
+(b) You may distribute such Executable Form under the terms of this
+    License, or sublicense it under different terms, provided that the
+    license for the Executable Form does not attempt to limit or alter
+    the recipients' rights in the Source Code Form under this License.
+
+3.3. Distribution of a Larger Work
+
+You may create and distribute a Larger Work under terms of Your choice,
+provided that You also comply with the requirements of this License for
+the Covered Software. If the Larger Work is a combination of Covered
+Software with a work governed by one or more Secondary Licenses, and the
+Covered Software is not Incompatible With Secondary Licenses, this
+License permits You to additionally distribute such Covered Software
+under the terms of such Secondary License(s), so that the recipient of
+the Larger Work may, at their option, further distribute the Covered
+Software under the terms of either this License or such Secondary
+License(s).
+
+3.4. Notices
+
+You may not remove or alter the substance of any license notices
+(including copyright notices, patent notices, disclaimers of warranty,
+or limitations of liability) contained within the Source Code Form of
+the Covered Software, except that You may alter any license notices to
+the extent required to remedy known factual inaccuracies.
+
+3.5. Application of Additional Terms
+
+You may choose to offer, and to charge a fee for, warranty, support,
+indemnity or liability obligations to one or more recipients of Covered
+Software. However, You may do so only on Your own behalf, and not on
+behalf of any Contributor. You must make it absolutely clear that any
+such warranty, support, indemnity, or liability obligation is offered by
+You alone, and You hereby agree to indemnify every Contributor for any
+liability incurred by such Contributor as a result of warranty, support,
+indemnity or liability terms You offer. You may include additional
+disclaimers of warranty and limitations of liability specific to any
+jurisdiction.
+
+4. Inability to Comply Due to Statute or Regulation
+---------------------------------------------------
+
+If it is impossible for You to comply with any of the terms of this
+License with respect to some or all of the Covered Software due to
+statute, judicial order, or regulation then You must: (a) comply with
+the terms of this License to the maximum extent possible; and (b)
+describe the limitations and the code they affect. Such description must
+be placed in a text file included with all distributions of the Covered
+Software under this License. Except to the extent prohibited by statute
+or regulation, such description must be sufficiently detailed for a
+recipient of ordinary skill to be able to understand it.
+
+5. Termination
+--------------
+
+5.1. The rights granted under this License will terminate automatically
+if You fail to comply with any of its terms. However, if You become
+compliant, then the rights granted under this License from a particular
+Contributor are reinstated (a) provisionally, unless and until such
+Contributor explicitly and finally terminates Your grants, and (b) on an
+ongoing basis, if such Contributor fails to notify You of the
+non-compliance by some reasonable means prior to 60 days after You have
+come back into compliance. Moreover, Your grants from a particular
+Contributor are reinstated on an ongoing basis if such Contributor
+notifies You of the non-compliance by some reasonable means, this is the
+first time You have received notice of non-compliance with this License
+from such Contributor, and You become compliant prior to 30 days after
+Your receipt of the notice.
+
+5.2. If You initiate litigation against any entity by asserting a patent
+infringement claim (excluding declaratory judgment actions,
+counter-claims, and cross-claims) alleging that a Contributor Version
+directly or indirectly infringes any patent, then the rights granted to
+You by any and all Contributors for the Covered Software under Section
+2.1 of this License shall terminate.
+
+5.3. In the event of termination under Sections 5.1 or 5.2 above, all
+end user license agreements (excluding distributors and resellers) which
+have been validly granted by You or Your distributors under this License
+prior to termination shall survive termination.
+
+************************************************************************
+*                                                                      *
+*  6. Disclaimer of Warranty                                           *
+*  -------------------------                                           *
+*                                                                      *
+*  Covered Software is provided under this License on an "as is"       *
+*  basis, without warranty of any kind, either expressed, implied, or  *
+*  statutory, including, without limitation, warranties that the       *
+*  Covered Software is free of defects, merchantable, fit for a        *
+*  particular purpose or non-infringing. The entire risk as to the     *
+*  quality and performance of the Covered Software is with You.        *
+*  Should any Covered Software prove defective in any respect, You     *
+*  (not any Contributor) assume the cost of any necessary servicing,   *
+*  repair, or correction. This disclaimer of warranty constitutes an   *
+*  essential part of this License. No use of any Covered Software is   *
+*  authorized under this License except under this disclaimer.         *
+*                                                                      *
+************************************************************************
+
+************************************************************************
+*                                                                      *
+*  7. Limitation of Liability                                          *
+*  --------------------------                                          *
+*                                                                      *
+*  Under no circumstances and under no legal theory, whether tort      *
+*  (including negligence), contract, or otherwise, shall any           *
+*  Contributor, or anyone who distributes Covered Software as          *
+*  permitted above, be liable to You for any direct, indirect,         *
+*  special, incidental, or consequential damages of any character      *
+*  including, without limitation, damages for lost profits, loss of    *
+*  goodwill, work stoppage, computer failure or malfunction, or any    *
+*  and all other commercial damages or losses, even if such party      *
+*  shall have been informed of the possibility of such damages. This   *
+*  limitation of liability shall not apply to liability for death or   *
+*  personal injury resulting from such party's negligence to the       *
+*  extent applicable law prohibits such limitation. Some               *
+*  jurisdictions do not allow the exclusion or limitation of           *
+*  incidental or consequential damages, so this exclusion and          *
+*  limitation may not apply to You.                                    *
+*                                                                      *
+************************************************************************
+
+8. Litigation
+-------------
+
+Any litigation relating to this License may be brought only in the
+courts of a jurisdiction where the defendant maintains its principal
+place of business and such litigation shall be governed by laws of that
+jurisdiction, without reference to its conflict-of-law provisions.
+Nothing in this Section shall prevent a party's ability to bring
+cross-claims or counter-claims.
+
+9. Miscellaneous
+----------------
+
+This License represents the complete agreement concerning the subject
+matter hereof. If any provision of this License is held to be
+unenforceable, such provision shall be reformed only to the extent
+necessary to make it enforceable. Any law or regulation which provides
+that the language of a contract shall be construed against the drafter
+shall not be used to construe this License against a Contributor.
+
+10. Versions of the License
+---------------------------
+
+10.1. New Versions
+
+Mozilla Foundation is the license steward. Except as provided in Section
+10.3, no one other than the license steward has the right to modify or
+publish new versions of this License. Each version will be given a
+distinguishing version number.
+
+10.2. Effect of New Versions
+
+You may distribute the Covered Software under the terms of the version
+of the License under which You originally received the Covered Software,
+or under the terms of any subsequent version published by the license
+steward.
+
+10.3. Modified Versions
+
+If you create software not governed by this License, and you want to
+create a new license for such software, you may create and use a
+modified version of this License if you rename the license and remove
+any references to the name of the license steward (except to note that
+such modified license differs from this License).
+
+10.4. Distributing Source Code Form that is Incompatible With Secondary
+Licenses
+
+If You choose to distribute Source Code Form that is Incompatible With
+Secondary Licenses under the terms of this version of the License, the
+notice described in Exhibit B of this License must be attached.
+
+Exhibit A - Source Code Form License Notice
+-------------------------------------------
+
+  This Source Code Form is subject to the terms of the Mozilla Public
+  License, v. 2.0. If a copy of the MPL was not distributed with this
+  file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+If it is not possible or desirable to put the notice in a particular
+file, then You may include the notice in a location (such as a LICENSE
+file in a relevant directory) where a recipient would be likely to look
+for such a notice.
+
+You may add additional accurate notices of copyright ownership.
+
+Exhibit B - "Incompatible With Secondary Licenses" Notice
+---------------------------------------------------------
+
+  This Source Code Form is "Incompatible With Secondary Licenses", as
+  defined by the Mozilla Public License, v. 2.0.

MANIFEST.in

@@ -0,0 +1,15 @@
+include README.md
+include LICENSE.txt
+include requirements.*.txt
+include *.cff
+include requirements.txt
+include TTS/VERSION
+recursive-include TTS *.json
+recursive-include TTS *.html
+recursive-include TTS *.png
+recursive-include TTS *.md
+recursive-include TTS *.py
+recursive-include TTS *.pyx
+recursive-include images *.png
+recursive-exclude tests *
+prune tests*

Makefile

@@ -0,0 +1,72 @@
+.DEFAULT_GOAL := help
+.PHONY: test system-deps dev-deps deps style lint install help docs
+
+help:
+	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | sort | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[36m%-30s\033[0m %s\n", $$1, $$2}'
+
+target_dirs := tests TTS notebooks recipes
+
+test_all:	## run tests and don't stop on an error.
+	nose2 --with-coverage --coverage TTS tests
+	./run_bash_tests.sh
+
+test:	## run tests.
+	nose2 -F -v -B --with-coverage --coverage TTS tests
+
+test_vocoder:	## run vocoder tests.
+	nose2 -F -v -B --with-coverage --coverage TTS tests.vocoder_tests
+
+test_tts:	## run tts tests.
+	nose2 -F -v -B --with-coverage --coverage TTS tests.tts_tests
+
+test_aux:	## run aux tests.
+	nose2 -F -v -B --with-coverage --coverage TTS tests.aux_tests
+	./run_bash_tests.sh
+
+test_zoo:	## run zoo tests.
+	nose2 -F -v -B --with-coverage --coverage TTS tests.zoo_tests
+
+inference_tests: ## run inference tests.
+	nose2 -F -v -B --with-coverage --coverage TTS tests.inference_tests
+
+data_tests: ## run data tests.
+	nose2 -F -v -B --with-coverage --coverage TTS tests.data_tests
+
+test_text: ## run text tests.
+	nose2 -F -v -B --with-coverage --coverage TTS tests.text_tests
+
+test_failed:  ## only run tests failed the last time.
+	nose2 -F -v -B --with-coverage --coverage TTS tests
+
+style:	## update code style.
+	black ${target_dirs}
+	isort ${target_dirs}
+
+lint:	## run pylint linter.
+	pylint ${target_dirs}
+	black ${target_dirs} --check
+	isort ${target_dirs} --check-only
+
+system-deps:	## install linux system deps
+	sudo apt-get install -y libsndfile1-dev
+
+dev-deps:  ## install development deps
+	pip install -r requirements.dev.txt
+
+doc-deps:  ## install docs dependencies
+	pip install -r docs/requirements.txt
+
+build-docs: ## build the docs
+	cd docs && make clean && make build
+
+hub-deps:  ## install deps for torch hub use
+	pip install -r requirements.hub.txt
+
+deps:	## install 🐸 requirements.
+	pip install -r requirements.txt
+
+install:	## install 🐸 TTS for development.
+	pip install -e .[all]
+
+docs:	## build the docs
+	$(MAKE) -C docs clean && $(MAKE) -C docs html

README.md

@@ -1,3 +1,373 @@
----
-license: agpl-3.0
----
+
+
+## 🐸Coqui.ai News
+- 📣 [🐶Bark](https://github.com/suno-ai/bark) is now available for inference with uncontrained voice cloning. [Docs](https://tts.readthedocs.io/en/dev/models/bark.html)
+- 📣 You can use [~1100 Fairseq models](https://github.com/facebookresearch/fairseq/tree/main/examples/mms) with 🐸TTS.
+- 📣 🐸TTS now supports 🐢Tortoise with faster inference. [Docs](https://tts.readthedocs.io/en/dev/models/tortoise.html)
+- 📣 **Coqui Studio API** is landed on 🐸TTS. - [Example](https://github.com/coqui-ai/TTS/blob/dev/README.md#-python-api)
+- 📣 [**Coqui Studio API**](https://docs.coqui.ai/docs) is live.
+- 📣 Voice generation with prompts - **Prompt to Voice** - is live on [**Coqui Studio**](https://app.coqui.ai/auth/signin)!! - [Blog Post](https://coqui.ai/blog/tts/prompt-to-voice)
+- 📣 Voice generation with fusion - **Voice fusion** - is live on [**Coqui Studio**](https://app.coqui.ai/auth/signin).
+- 📣 Voice cloning is live on [**Coqui Studio**](https://app.coqui.ai/auth/signin).
+
+## <img src="https://raw.githubusercontent.com/coqui-ai/TTS/main/images/coqui-log-green-TTS.png" height="56"/>
+
+
+🐸TTS is a library for advanced Text-to-Speech generation. It's built on the latest research, was designed to achieve the best trade-off among ease-of-training, speed and quality.
+🐸TTS comes with pretrained models, tools for measuring dataset quality and already used in **20+ languages** for products and research projects.
+
+[![Dicord](https://img.shields.io/discord/1037326658807533628?color=%239B59B6&label=chat%20on%20discord)](https://discord.gg/5eXr5seRrv)
+[![License](<https://img.shields.io/badge/License-MPL%202.0-brightgreen.svg>)](https://opensource.org/licenses/MPL-2.0)
+[![PyPI version](https://badge.fury.io/py/TTS.svg)](https://badge.fury.io/py/TTS)
+[![Covenant](https://camo.githubusercontent.com/7d620efaa3eac1c5b060ece5d6aacfcc8b81a74a04d05cd0398689c01c4463bb/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f436f6e7472696275746f72253230436f76656e616e742d76322e3025323061646f707465642d6666363962342e737667)](https://github.com/coqui-ai/TTS/blob/master/CODE_OF_CONDUCT.md)
+[![Downloads](https://pepy.tech/badge/tts)](https://pepy.tech/project/tts)
+[![DOI](https://zenodo.org/badge/265612440.svg)](https://zenodo.org/badge/latestdoi/265612440)
+
+![GithubActions](https://github.com/coqui-ai/TTS/actions/workflows/aux_tests.yml/badge.svg)
+![GithubActions](https://github.com/coqui-ai/TTS/actions/workflows/data_tests.yml/badge.svg)
+![GithubActions](https://github.com/coqui-ai/TTS/actions/workflows/docker.yaml/badge.svg)
+![GithubActions](https://github.com/coqui-ai/TTS/actions/workflows/inference_tests.yml/badge.svg)
+![GithubActions](https://github.com/coqui-ai/TTS/actions/workflows/style_check.yml/badge.svg)
+![GithubActions](https://github.com/coqui-ai/TTS/actions/workflows/text_tests.yml/badge.svg)
+![GithubActions](https://github.com/coqui-ai/TTS/actions/workflows/tts_tests.yml/badge.svg)
+![GithubActions](https://github.com/coqui-ai/TTS/actions/workflows/vocoder_tests.yml/badge.svg)
+![GithubActions](https://github.com/coqui-ai/TTS/actions/workflows/zoo_tests0.yml/badge.svg)
+![GithubActions](https://github.com/coqui-ai/TTS/actions/workflows/zoo_tests1.yml/badge.svg)
+![GithubActions](https://github.com/coqui-ai/TTS/actions/workflows/zoo_tests2.yml/badge.svg)
+[![Docs](<https://readthedocs.org/projects/tts/badge/?version=latest&style=plastic>)](https://tts.readthedocs.io/en/latest/)
+
+📰 [**Subscribe to 🐸Coqui.ai Newsletter**](https://coqui.ai/?subscription=true)
+
+📢 [English Voice Samples](https://erogol.github.io/ddc-samples/) and [SoundCloud playlist](https://soundcloud.com/user-565970875/pocket-article-wavernn-and-tacotron2)
+
+📄 [Text-to-Speech paper collection](https://github.com/erogol/TTS-papers)
+
+<img src="https://static.scarf.sh/a.png?x-pxid=cf317fe7-2188-4721-bc01-124bb5d5dbb2" />
+
+## 💬 Where to ask questions
+Please use our dedicated channels for questions and discussion. Help is much more valuable if it's shared publicly so that more people can benefit from it.
+
+| Type                            | Platforms                               |
+| ------------------------------- | --------------------------------------- |
+| 🚨 **Bug Reports**              | [GitHub Issue Tracker]                  |
+| 🎁 **Feature Requests & Ideas** | [GitHub Issue Tracker]                  |
+| 👩‍💻 **Usage Questions**          | [GitHub Discussions]                    |
+| 🗯 **General Discussion**       | [GitHub Discussions] or [Discord]   |
+
+[github issue tracker]: https://github.com/coqui-ai/tts/issues
+[github discussions]: https://github.com/coqui-ai/TTS/discussions
+[discord]: https://discord.gg/5eXr5seRrv
+[Tutorials and Examples]: https://github.com/coqui-ai/TTS/wiki/TTS-Notebooks-and-Tutorials
+
+
+## 🔗 Links and Resources
+| Type                            | Links                               |
+| ------------------------------- | --------------------------------------- |
+| 💼 **Documentation**              | [ReadTheDocs](https://tts.readthedocs.io/en/latest/)
+| 💾 **Installation**               | [TTS/README.md](https://github.com/coqui-ai/TTS/tree/dev#install-tts)|
+| 👩‍💻 **Contributing**               | [CONTRIBUTING.md](https://github.com/coqui-ai/TTS/blob/main/CONTRIBUTING.md)|
+| 📌 **Road Map**                   | [Main Development Plans](https://github.com/coqui-ai/TTS/issues/378)
+| 🚀 **Released Models**            | [TTS Releases](https://github.com/coqui-ai/TTS/releases) and [Experimental Models](https://github.com/coqui-ai/TTS/wiki/Experimental-Released-Models)|
+
+## 🥇 TTS Performance
+<p align="center"><img src="https://raw.githubusercontent.com/coqui-ai/TTS/main/images/TTS-performance.png" width="800" /></p>
+
+Underlined "TTS*" and "Judy*" are **internal** 🐸TTS models that are not released open-source. They are here to show the potential.
+
+## Features
+- High-performance Deep Learning models for Text2Speech tasks.
+    - Text2Spec models (Tacotron, Tacotron2, Glow-TTS, SpeedySpeech).
+    - Speaker Encoder to compute speaker embeddings efficiently.
+    - Vocoder models (MelGAN, Multiband-MelGAN, GAN-TTS, ParallelWaveGAN, WaveGrad, WaveRNN)
+- Fast and efficient model training.
+- Detailed training logs on the terminal and Tensorboard.
+- Support for Multi-speaker TTS.
+- Efficient, flexible, lightweight but feature complete `Trainer API`.
+- Released and ready-to-use models.
+- Tools to curate Text2Speech datasets under```dataset_analysis```.
+- Utilities to use and test your models.
+- Modular (but not too much) code base enabling easy implementation of new ideas.
+
+## Implemented Models
+### Spectrogram models
+- Tacotron: [paper](https://arxiv.org/abs/1703.10135)
+- Tacotron2: [paper](https://arxiv.org/abs/1712.05884)
+- Glow-TTS: [paper](https://arxiv.org/abs/2005.11129)
+- Speedy-Speech: [paper](https://arxiv.org/abs/2008.03802)
+- Align-TTS: [paper](https://arxiv.org/abs/2003.01950)
+- FastPitch: [paper](https://arxiv.org/pdf/2006.06873.pdf)
+- FastSpeech: [paper](https://arxiv.org/abs/1905.09263)
+- FastSpeech2: [paper](https://arxiv.org/abs/2006.04558)
+- SC-GlowTTS: [paper](https://arxiv.org/abs/2104.05557)
+- Capacitron: [paper](https://arxiv.org/abs/1906.03402)
+- OverFlow: [paper](https://arxiv.org/abs/2211.06892)
+- Neural HMM TTS: [paper](https://arxiv.org/abs/2108.13320)
+
+### End-to-End Models
+- VITS: [paper](https://arxiv.org/pdf/2106.06103)
+- 🐸 YourTTS: [paper](https://arxiv.org/abs/2112.02418)
+- 🐢 Tortoise: [orig. repo](https://github.com/neonbjb/tortoise-tts)
+- 🐶 Bark: [orig. repo](https://github.com/suno-ai/bark)
+
+### Attention Methods
+- Guided Attention: [paper](https://arxiv.org/abs/1710.08969)
+- Forward Backward Decoding: [paper](https://arxiv.org/abs/1907.09006)
+- Graves Attention: [paper](https://arxiv.org/abs/1910.10288)
+- Double Decoder Consistency: [blog](https://erogol.com/solving-attention-problems-of-tts-models-with-double-decoder-consistency/)
+- Dynamic Convolutional Attention: [paper](https://arxiv.org/pdf/1910.10288.pdf)
+- Alignment Network: [paper](https://arxiv.org/abs/2108.10447)
+
+### Speaker Encoder
+- GE2E: [paper](https://arxiv.org/abs/1710.10467)
+- Angular Loss: [paper](https://arxiv.org/pdf/2003.11982.pdf)
+
+### Vocoders
+- MelGAN: [paper](https://arxiv.org/abs/1910.06711)
+- MultiBandMelGAN: [paper](https://arxiv.org/abs/2005.05106)
+- ParallelWaveGAN: [paper](https://arxiv.org/abs/1910.11480)
+- GAN-TTS discriminators: [paper](https://arxiv.org/abs/1909.11646)
+- WaveRNN: [origin](https://github.com/fatchord/WaveRNN/)
+- WaveGrad: [paper](https://arxiv.org/abs/2009.00713)
+- HiFiGAN: [paper](https://arxiv.org/abs/2010.05646)
+- UnivNet: [paper](https://arxiv.org/abs/2106.07889)
+
+### Voice Conversion
+- FreeVC: [paper](https://arxiv.org/abs/2210.15418)
+
+You can also help us implement more models.
+
+## Install TTS
+🐸TTS is tested on Ubuntu 18.04 with **python >= 3.7, < 3.11.**.
+
+If you are only interested in [synthesizing speech](https://tts.readthedocs.io/en/latest/inference.html) with the released 🐸TTS models, installing from PyPI is the easiest option.
+
+```bash
+pip install TTS
+```
+
+If you plan to code or train models, clone 🐸TTS and install it locally.
+
+```bash
+git clone https://github.com/coqui-ai/TTS
+pip install -e .[all,dev,notebooks]  # Select the relevant extras
+```
+
+If you are on Ubuntu (Debian), you can also run following commands for installation.
+
+```bash
+$ make system-deps  # intended to be used on Ubuntu (Debian). Let us know if you have a different OS.
+$ make install
+```
+
+If you are on Windows, 👑@GuyPaddock wrote installation instructions [here](https://stackoverflow.com/questions/66726331/how-can-i-run-mozilla-tts-coqui-tts-training-with-cuda-on-a-windows-system).
+
+
+## Docker Image
+You can also try TTS without install with the docker image.
+Simply run the following command and you will be able to run TTS without installing it.
+
+```bash
+docker run --rm -it -p 5002:5002 --entrypoint /bin/bash ghcr.io/coqui-ai/tts-cpu
+python3 TTS/server/server.py --list_models #To get the list of available models
+python3 TTS/server/server.py --model_name tts_models/en/vctk/vits # To start a server
+```
+
+You can then enjoy the TTS server [here](http://[::1]:5002/)
+More details about the docker images (like GPU support) can be found [here](https://tts.readthedocs.io/en/latest/docker_images.html)
+
+
+## Synthesizing speech by 🐸TTS
+
+### 🐍 Python API
+
+```python
+from TTS.api import TTS
+
+# Running a multi-speaker and multi-lingual model
+
+# List available 🐸TTS models and choose the first one
+model_name = TTS.list_models()[0]
+# Init TTS
+tts = TTS(model_name)
+
+# Run TTS
+
+# ❗ Since this model is multi-speaker and multi-lingual, we must set the target speaker and the language
+# Text to speech with a numpy output
+wav = tts.tts("This is a test! This is also a test!!", speaker=tts.speakers[0], language=tts.languages[0])
+# Text to speech to a file
+tts.tts_to_file(text="Hello world!", speaker=tts.speakers[0], language=tts.languages[0], file_path="output.wav")
+
+# Running a single speaker model
+
+# Init TTS with the target model name
+tts = TTS(model_name="tts_models/de/thorsten/tacotron2-DDC", progress_bar=False, gpu=False)
+# Run TTS
+tts.tts_to_file(text="Ich bin eine Testnachricht.", file_path=OUTPUT_PATH)
+
+# Example voice cloning with YourTTS in English, French and Portuguese
+
+tts = TTS(model_name="tts_models/multilingual/multi-dataset/your_tts", progress_bar=False, gpu=True)
+tts.tts_to_file("This is voice cloning.", speaker_wav="my/cloning/audio.wav", language="en", file_path="output.wav")
+tts.tts_to_file("C'est le clonage de la voix.", speaker_wav="my/cloning/audio.wav", language="fr-fr", file_path="output.wav")
+tts.tts_to_file("Isso é clonagem de voz.", speaker_wav="my/cloning/audio.wav", language="pt-br", file_path="output.wav")
+
+
+# Example voice conversion converting speaker of the `source_wav` to the speaker of the `target_wav`
+
+tts = TTS(model_name="voice_conversion_models/multilingual/vctk/freevc24", progress_bar=False, gpu=True)
+tts.voice_conversion_to_file(source_wav="my/source.wav", target_wav="my/target.wav", file_path="output.wav")
+
+# Example voice cloning by a single speaker TTS model combining with the voice conversion model. This way, you can
+# clone voices by using any model in 🐸TTS.
+
+tts = TTS("tts_models/de/thorsten/tacotron2-DDC")
+tts.tts_with_vc_to_file(
+    "Wie sage ich auf Italienisch, dass ich dich liebe?",
+    speaker_wav="target/speaker.wav",
+    file_path="output.wav"
+)
+
+# Example text to speech using [🐸Coqui Studio](https://coqui.ai) models.
+
+# You can use all of your available speakers in the studio.
+# [🐸Coqui Studio](https://coqui.ai) API token is required. You can get it from the [account page](https://coqui.ai/account).
+# You should set the `COQUI_STUDIO_TOKEN` environment variable to use the API token.
+
+# If you have a valid API token set you will see the studio speakers as separate models in the list.
+# The name format is coqui_studio/en/<studio_speaker_name>/coqui_studio
+models = TTS().list_models()
+# Init TTS with the target studio speaker
+tts = TTS(model_name="coqui_studio/en/Torcull Diarmuid/coqui_studio", progress_bar=False, gpu=False)
+# Run TTS
+tts.tts_to_file(text="This is a test.", file_path=OUTPUT_PATH)
+# Run TTS with emotion and speed control
+tts.tts_to_file(text="This is a test.", file_path=OUTPUT_PATH, emotion="Happy", speed=1.5)
+
+
+#Example text to speech using **Fairseq models in ~1100 languages** 🤯.
+
+#For these models use the following name format: `tts_models/<lang-iso_code>/fairseq/vits`.
+#You can find the list of language ISO codes [here](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html) and learn about the Fairseq models [here](https://github.com/facebookresearch/fairseq/tree/main/examples/mms).
+
+# TTS with on the fly voice conversion
+api = TTS("tts_models/deu/fairseq/vits")
+api.tts_with_vc_to_file(
+    "Wie sage ich auf Italienisch, dass ich dich liebe?",
+    speaker_wav="target/speaker.wav",
+    file_path="output.wav"
+)
+```
+
+### Command line `tts`
+#### Single Speaker Models
+
+- List provided models:
+
+    ```
+    $ tts --list_models
+    ```
+- Get model info (for both tts_models and vocoder_models):
+    - Query by type/name:
+        The model_info_by_name uses the name as it from the --list_models.
+        ```
+        $ tts --model_info_by_name "<model_type>/<language>/<dataset>/<model_name>"
+        ```
+        For example:
+
+        ```
+        $ tts --model_info_by_name tts_models/tr/common-voice/glow-tts
+        ```
+        ```
+        $ tts --model_info_by_name vocoder_models/en/ljspeech/hifigan_v2
+        ```
+    - Query by type/idx:
+        The model_query_idx uses the corresponding idx from --list_models.
+        ```
+        $ tts --model_info_by_idx "<model_type>/<model_query_idx>"
+        ```
+        For example:
+
+        ```
+        $ tts --model_info_by_idx tts_models/3
+        ```
+
+- Run TTS with default models:
+
+    ```
+    $ tts --text "Text for TTS" --out_path output/path/speech.wav
+    ```
+
+- Run a TTS model with its default vocoder model:
+
+    ```
+    $ tts --text "Text for TTS" --model_name "<model_type>/<language>/<dataset>/<model_name>" --out_path output/path/speech.wav
+    ```
+  For example:
+
+    ```
+    $ tts --text "Text for TTS" --model_name "tts_models/en/ljspeech/glow-tts" --out_path output/path/speech.wav
+    ```
+
+- Run with specific TTS and vocoder models from the list:
+
+    ```
+    $ tts --text "Text for TTS" --model_name "<model_type>/<language>/<dataset>/<model_name>" --vocoder_name "<model_type>/<language>/<dataset>/<model_name>" --out_path output/path/speech.wav
+    ```
+
+  For example:
+
+    ```
+    $ tts --text "Text for TTS" --model_name "tts_models/en/ljspeech/glow-tts" --vocoder_name "vocoder_models/en/ljspeech/univnet" --out_path output/path/speech.wav
+    ```
+
+
+- Run your own TTS model (Using Griffin-Lim Vocoder):
+
+    ```
+    $ tts --text "Text for TTS" --model_path path/to/model.pth --config_path path/to/config.json --out_path output/path/speech.wav
+    ```
+
+- Run your own TTS and Vocoder models:
+    ```
+    $ tts --text "Text for TTS" --model_path path/to/model.pth --config_path path/to/config.json --out_path output/path/speech.wav
+        --vocoder_path path/to/vocoder.pth --vocoder_config_path path/to/vocoder_config.json
+    ```
+
+#### Multi-speaker Models
+
+- List the available speakers and choose a <speaker_id> among them:
+
+    ```
+    $ tts --model_name "<language>/<dataset>/<model_name>"  --list_speaker_idxs
+    ```
+
+- Run the multi-speaker TTS model with the target speaker ID:
+
+    ```
+    $ tts --text "Text for TTS." --out_path output/path/speech.wav --model_name "<language>/<dataset>/<model_name>"  --speaker_idx <speaker_id>
+    ```
+
+- Run your own multi-speaker TTS model:
+
+    ```
+    $ tts --text "Text for TTS" --out_path output/path/speech.wav --model_path path/to/model.pth --config_path path/to/config.json --speakers_file_path path/to/speaker.json --speaker_idx <speaker_id>
+    ```
+
+## Directory Structure
+```
+|- notebooks/       (Jupyter Notebooks for model evaluation, parameter selection and data analysis.)
+|- utils/           (common utilities.)
+|- TTS
+    |- bin/             (folder for all the executables.)
+      |- train*.py                  (train your target model.)
+      |- ...
+    |- tts/             (text to speech models)
+        |- layers/          (model layer definitions)
+        |- models/          (model definitions)
+        |- utils/           (model specific utilities.)
+    |- speaker_encoder/ (Speaker Encoder models.)
+        |- (same)
+    |- vocoder/         (Vocoder models.)
+        |- (same)
+```

hubconf.py

@@ -0,0 +1,46 @@
+dependencies = [
+    'torch', 'gdown', 'pysbd', 'gruut', 'anyascii', 'pypinyin', 'coqpit', 'mecab-python3', 'unidic-lite'
+]
+import torch
+
+from TTS.utils.manage import ModelManager
+from TTS.utils.synthesizer import Synthesizer
+
+
+def tts(model_name='tts_models/en/ljspeech/tacotron2-DCA',
+        vocoder_name=None,
+        use_cuda=False):
+    """TTS entry point for PyTorch Hub that provides a Synthesizer object to synthesize speech from a give text.
+
+    Example:
+        >>> synthesizer = torch.hub.load('coqui-ai/TTS', 'tts', source='github')
+        >>> wavs = synthesizer.tts("This is a test! This is also a test!!")
+            wavs - is a list of values of the synthesized speech.
+
+    Args:
+        model_name (str, optional): One of the model names from .model.json. Defaults to 'tts_models/en/ljspeech/tacotron2-DCA'.
+        vocoder_name (str, optional): One of the model names from .model.json. Defaults to 'vocoder_models/en/ljspeech/multiband-melgan'.
+        pretrained (bool, optional): [description]. Defaults to True.
+
+    Returns:
+        TTS.utils.synthesizer.Synthesizer: Synthesizer object wrapping both vocoder and tts models.
+    """
+    manager = ModelManager()
+
+    model_path, config_path, model_item = manager.download_model(model_name)
+    vocoder_name = model_item[
+        'default_vocoder'] if vocoder_name is None else vocoder_name
+    vocoder_path, vocoder_config_path, _ = manager.download_model(vocoder_name)
+
+    # create synthesizer
+    synt = Synthesizer(tts_checkpoint=model_path,
+                       tts_config_path=config_path,
+                       vocoder_checkpoint=vocoder_path,
+                       vocoder_config=vocoder_config_path,
+                       use_cuda=use_cuda)
+    return synt
+
+
+if __name__ == '__main__':
+    synthesizer = torch.hub.load('coqui-ai/TTS:dev', 'tts', source='github')
+    synthesizer.tts("This is a test!")

pyproject.toml

@@ -0,0 +1,33 @@
+[build-system]
+requires = ["setuptools", "wheel", "cython==0.29.30", "numpy==1.22.0", "packaging"]
+
+[flake8]
+max-line-length=120
+
+[tool.black]
+line-length = 120
+target-version = ['py39']
+exclude = '''
+
+(
+  /(
+      \.eggs         # exclude a few common directories in the
+    | \.git          # root of the project
+    | \.hg
+    | \.mypy_cache
+    | \.tox
+    | \.venv
+    | _build
+    | buck-out
+    | build
+    | dist
+  )/
+  | foo.py           # also separately exclude a file named foo.py in
+                     # the root of the project
+)
+'''
+
+[tool.isort]
+line_length = 120
+profile = "black"
+multi_line_output = 3

requirements.dev.txt

@@ -0,0 +1,5 @@
+black
+coverage
+isort
+nose2
+pylint==2.10.2

requirements.notebooks.txt

@@ -0,0 +1 @@
+bokeh==1.4.0

requirements.txt

@@ -0,0 +1,53 @@
+# core deps
+numpy==1.22.0;python_version<="3.10"
+numpy==1.24.3;python_version>"3.10"
+cython==0.29.30
+scipy>=1.4.0
+torch>=1.7
+torchaudio
+soundfile
+librosa==0.10.0.*
+numba==0.55.1;python_version<"3.9"
+numba==0.57.0;python_version>="3.9"
+inflect==5.6.0
+tqdm
+anyascii
+pyyaml
+fsspec>=2021.04.0
+aiohttp
+packaging
+# deps for examples
+flask
+# deps for inference
+pysbd
+# deps for notebooks
+umap-learn==0.5.1
+pandas
+# deps for training
+matplotlib
+# coqui stack
+trainer
+# config management
+coqpit>=0.0.16
+# chinese g2p deps
+jieba
+pypinyin
+# japanese g2p deps
+mecab-python3==1.0.6
+unidic-lite==1.0.8
+# gruut+supported langs
+gruut[de,es,fr]==2.2.3
+# deps for korean
+jamo
+nltk
+g2pkk>=0.1.1
+# deps for bangla
+bangla==0.0.2
+bnnumerizer
+bnunicodenormalizer==0.1.1
+#deps for tortoise
+k_diffusion
+einops
+transformers
+#deps for bark
+encodec

run_bash_tests.sh

@@ -0,0 +1,7 @@
+set -e
+TF_CPP_MIN_LOG_LEVEL=3
+
+# runtime bash based tests
+# TODO: move these to python
+./tests/bash_tests/test_demo_server.sh && \
+./tests/bash_tests/test_compute_statistics.sh

setup.cfg

@@ -0,0 +1,8 @@
+[build_py]
+build_lib=temp_build
+
+[bdist_wheel]
+bdist_dir=temp_build
+
+[install_lib]
+build_dir=temp_build

setup.py

@@ -0,0 +1,138 @@
+#!/usr/bin/env python
+#                   ,*++++++*,                ,*++++++*,
+#                *++.        .+++          *++.        .++*
+#              *+*     ,++++*   *+*      *+*   ,++++,     *+*
+#             ,+,   .++++++++++* ,++,,,,*+, ,++++++++++.   *+,
+#             *+.  .++++++++++++..++    *+.,++++++++++++.  .+*
+#             .+*   ++++++++++++.*+,    .+*.++++++++++++   *+,
+#              .++   *++++++++* ++,      .++.*++++++++*   ++,
+#               ,+++*.    . .*++,          ,++*.      .*+++*
+#              *+,   .,*++**.                  .**++**.   ,+*
+#             .+*                                          *+,
+#             *+.                   Coqui                  .+*
+#             *+*              +++   TTS  +++              *+*
+#             .+++*.            .          .             *+++.
+#              ,+* *+++*...                       ...*+++* *+,
+#               .++.    .""""+++++++****+++++++"""".     ++.
+#                 ,++.                                .++,
+#                   .++*                            *++.
+#                       *+++,                  ,+++*
+#                           .,*++++::::::++++*,.
+#                                  ``````
+
+import os
+import subprocess
+import sys
+from packaging.version import Version
+
+import numpy
+import setuptools.command.build_py
+import setuptools.command.develop
+from Cython.Build import cythonize
+from setuptools import Extension, find_packages, setup
+
+python_version = sys.version.split()[0]
+if Version(python_version) < Version("3.9") or Version(python_version) >= Version("3.12"):
+    raise RuntimeError("TTS requires python >= 3.9 and < 3.12 " "but your Python version is {}".format(sys.version))
+
+
+cwd = os.path.dirname(os.path.abspath(__file__))
+with open(os.path.join(cwd, "TTS", "VERSION")) as fin:
+    version = fin.read().strip()
+
+
+class build_py(setuptools.command.build_py.build_py):  # pylint: disable=too-many-ancestors
+    def run(self):
+        setuptools.command.build_py.build_py.run(self)
+
+
+class develop(setuptools.command.develop.develop):
+    def run(self):
+        setuptools.command.develop.develop.run(self)
+
+
+# The documentation for this feature is in server/README.md
+package_data = ["TTS/server/templates/*"]
+
+
+def pip_install(package_name):
+    subprocess.call([sys.executable, "-m", "pip", "install", package_name])
+
+
+requirements = open(os.path.join(cwd, "requirements.txt"), "r").readlines()
+with open(os.path.join(cwd, "requirements.notebooks.txt"), "r") as f:
+    requirements_notebooks = f.readlines()
+with open(os.path.join(cwd, "requirements.dev.txt"), "r") as f:
+    requirements_dev = f.readlines()
+requirements_all = requirements_dev + requirements_notebooks
+
+with open("README.md", "r", encoding="utf-8") as readme_file:
+    README = readme_file.read()
+
+exts = [
+    Extension(
+        name="TTS.tts.utils.monotonic_align.core",
+        sources=["TTS/tts/utils/monotonic_align/core.pyx"],
+    )
+]
+setup(
+    name="TTS",
+    version=version,
+    url="https://github.com/coqui-ai/TTS",
+    author="Eren Gölge",
+    author_email="egolge@coqui.ai",
+    description="Deep learning for Text to Speech by Coqui.",
+    long_description=README,
+    long_description_content_type="text/markdown",
+    license="MPL-2.0",
+    # cython
+    include_dirs=numpy.get_include(),
+    ext_modules=cythonize(exts, language_level=3),
+    # ext_modules=find_cython_extensions(),
+    # package
+    include_package_data=True,
+    packages=find_packages(include=["TTS"], exclude=["*.tests", "*tests.*", "tests.*", "*tests", "tests"]),
+    package_data={
+        "TTS": [
+            "VERSION",
+        ]
+    },
+    project_urls={
+        "Documentation": "https://github.com/coqui-ai/TTS/wiki",
+        "Tracker": "https://github.com/coqui-ai/TTS/issues",
+        "Repository": "https://github.com/coqui-ai/TTS",
+        "Discussions": "https://github.com/coqui-ai/TTS/discussions",
+    },
+    cmdclass={
+        "build_py": build_py,
+        "develop": develop,
+        # 'build_ext': build_ext
+    },
+    install_requires=requirements,
+    extras_require={
+        "all": requirements_all,
+        "dev": requirements_dev,
+        "notebooks": requirements_notebooks,
+    },
+    python_requires=">=3.9.0, <3.12",
+    entry_points={"console_scripts": ["tts=TTS.bin.synthesize:main", "tts-server = TTS.server.server:main"]},
+    classifiers=[
+        "Programming Language :: Python",
+        "Programming Language :: Python :: 3",
+        "Programming Language :: Python :: 3.9",
+        "Programming Language :: Python :: 3.10",
+        "Programming Language :: Python :: 3.11",
+        "Development Status :: 3 - Alpha",
+        "Intended Audience :: Science/Research",
+        "Intended Audience :: Developers",
+        "Operating System :: POSIX :: Linux",
+        "License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)",
+        "Topic :: Software Development",
+        "Topic :: Software Development :: Libraries :: Python Modules",
+        "Topic :: Multimedia :: Sound/Audio :: Speech",
+        "Topic :: Multimedia :: Sound/Audio",
+        "Topic :: Multimedia",
+        "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    ],
+    zip_safe=False,
+)