Update model

README.md

@@ -0,0 +1,1337 @@
+---
+tags:
+- espnet
+- audio
+- automatic-speech-recognition
+language: en
+datasets:
+- slue-voxceleb
+license: cc-by-4.0
+---
+
+## ESPnet2 ASR model
+
+### `espnet/sluevoxceleb_whisper_lightweight_asr`
+
+This model was trained by “siddhu001” using slue-voxceleb recipe in [espnet](https://github.com/espnet/espnet/).
+
+### Demo: How to use in ESPnet2
+
+Follow the [ESPnet installation instructions](https://espnet.github.io/espnet/installation.html)
+if you haven't done that already.
+
+```bash
+cd espnet
+git checkout e23ef85f0b3116ad5c60d0833f186da0deec0734
+pip install -e .
+cd egs2/slue-voxceleb/slu1_asr
+./run.sh --skip_data_prep false --skip_train true --download_model espnet/sluevoxceleb_whisper_lightweight_asr
+```
+
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Mon Feb  5 19:05:58 CST 2024`
+- python version: `3.9.13 (main, Aug 25 2022, 23:26:10)  [GCC 11.2.0]`
+- espnet version: `espnet 202310`
+- pytorch version: `pytorch 2.1.0+cu121`
+- Git hash: `21d2105784e4da98397bf487b2550d4c6e16d40d`
+  - Commit date: `Wed Jan 31 13:40:37 2024 -0600`
+
+## exp/slu_train_asr_whisper_superb_raw_en_word_sp
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_ctc_slu_model_valid.cer_ctc.ave/test|3426|135368|88.9|6.9|4.2|3.5|14.6|91.9|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_ctc_slu_model_valid.cer_ctc.ave/test|3426|591261|95.0|1.6|3.5|3.3|8.3|91.9|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+## exp/slu_train_asr_whisper_superb_raw_en_word_sp/decode_asr_ctc_slu_model_valid.cer_ctc.ave
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|org/devel|1437|56031|90.5|6.0|3.6|3.0|12.5|89.8|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|org/devel|1437|241556|95.9|1.2|2.9|2.9|6.9|89.8|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+
+## ASR config
+
+<details><summary>expand</summary>
+
+```
+config: conf/tuning/train_asr_whisper_superb.yaml
+print_config: false
+log_level: INFO
+drop_last_iter: false
+dry_run: false
+iterator_type: sequence
+valid_iterator_type: null
+output_dir: exp/slu_train_asr_whisper_superb_raw_en_word_sp
+ngpu: 1
+seed: 2022
+num_workers: 2
+num_att_plot: 3
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: 4
+dist_rank: 0
+local_rank: 0
+dist_master_addr: localhost
+dist_master_port: 49737
+dist_launcher: null
+multiprocessing_distributed: true
+unused_parameters: false
+sharded_ddp: false
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: true
+collect_stats: false
+write_collected_feats: false
+max_epoch: 70
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - cer_ctc
+    - min
+-   - valid
+    - loss
+    - min
+keep_nbest_models: 10
+nbest_averaging_interval: 0
+grad_clip: 5.0
+grad_clip_type: 2.0
+grad_noise: false
+accum_grad: 1
+no_forward_run: false
+resume: true
+train_dtype: float32
+use_amp: false
+log_interval: null
+use_matplotlib: true
+use_tensorboard: true
+create_graph_in_tensorboard: false
+use_wandb: false
+wandb_project: null
+wandb_id: null
+wandb_entity: null
+wandb_name: null
+wandb_model_log_interval: -1
+detect_anomaly: false
+use_lora: false
+save_lora_only: true
+lora_conf: {}
+pretrain_path: null
+init_param: []
+ignore_init_mismatch: false
+freeze_param:
+- encoder
+num_iters_per_epoch: null
+batch_size: 20
+valid_batch_size: null
+batch_bins: 12000000
+valid_batch_bins: null
+train_shape_file:
+- exp/slu_stats_raw_en_word_sp/train/speech_shape
+- exp/slu_stats_raw_en_word_sp/train/text_shape.word
+valid_shape_file:
+- exp/slu_stats_raw_en_word_sp/valid/speech_shape
+- exp/slu_stats_raw_en_word_sp/valid/text_shape.word
+batch_type: numel
+valid_batch_type: null
+fold_length:
+- 80000
+- 150
+sort_in_batch: descending
+shuffle_within_batch: false
+sort_batch: descending
+multiple_iterator: false
+chunk_length: 500
+chunk_shift_ratio: 0.5
+num_cache_chunks: 1024
+chunk_excluded_key_prefixes: []
+chunk_default_fs: null
+train_data_path_and_name_and_type:
+-   - dump/raw/train_sp/wav.scp
+    - speech
+    - sound
+-   - dump/raw/train_sp/text
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - dump/raw/devel/wav.scp
+    - speech
+    - sound
+-   - dump/raw/devel/text
+    - text
+    - text
+allow_variable_data_keys: false
+max_cache_size: 0.0
+max_cache_fd: 32
+allow_multi_rates: false
+valid_max_cache_size: null
+exclude_weight_decay: false
+exclude_weight_decay_conf: {}
+optim: adam
+optim_conf:
+    lr: 0.005
+    weight_decay: 1.0e-06
+scheduler: warmuplr
+scheduler_conf:
+    warmup_steps: 5000
+token_list:
+- <blank>
+- <unk>
+- ▁i
+- ▁and
+- ''''
+- s
+- ▁the
+- ▁a
+- ▁it
+- ▁to
+- ▁you
+- ▁that
+- ▁of
+- ▁in
+- ��was
+- ▁uh
+- ▁know
+- t
+- ▁so
+- ▁we
+- ▁he
+- ing
+- m
+- ▁um
+- ▁like
+- ed
+- ▁is
+- ▁but
+- ▁just
+- ▁they
+- re
+- y
+- ▁this
+- ▁for
+- ▁be
+- ▁my
+- er
+- ▁with
+- ▁on
+- ▁think
+- ▁have
+- ▁p
+- ▁she
+- ▁me
+- e
+- ▁really
+- ▁there
+- ▁what
+- al
+- ▁m
+- ▁do
+- ▁all
+- a
+- ve
+- ▁as
+- c
+- n
+- ▁about
+- ▁not
+- i
+- ▁at
+- l
+- ▁t
+- ▁had
+- ▁when
+- ▁c
+- g
+- in
+- ▁b
+- d
+- le
+- en
+- ▁out
+- u
+- ly
+- ▁an
+- or
+- ▁people
+- ar
+- ll
+- o
+- ▁are
+- ▁very
+- ▁because
+- es
+- ▁can
+- ▁don
+- ▁s
+- ▁or
+- ▁up
+- it
+- b
+- ▁e
+- ▁one
+- an
+- st
+- ▁if
+- ▁f
+- ▁were
+- p
+- ▁mean
+- ▁d
+- ▁who
+- ▁then
+- ic
+- 'on'
+- ▁no
+- ▁go
+- ▁her
+- ▁g
+- ▁st
+- ▁kind
+- ri
+- ▁would
+- ▁get
+- at
+- r
+- ▁time
+- v
+- ent
+- ▁re
+- h
+- ▁from
+- ▁l
+- ▁said
+- ▁w
+- ▁him
+- ▁how
+- ▁well
+- ▁h
+- ▁gonna
+- ▁lot
+- ▁see
+- w
+- ▁his
+- ce
+- ion
+- ▁been
+- f
+- ▁great
+- ▁yeah
+- ▁love
+- ▁which
+- ▁got
+- k
+- ▁them
+- ▁way
+- ▁n
+- id
+- ▁show
+- ▁some
+- ▁your
+- ▁did
+- ▁sort
+- et
+- ▁has
+- ▁things
+- ▁back
+- ▁where
+- ▁something
+- ir
+- ▁thing
+- ad
+- ▁su
+- il
+- as
+- ▁j
+- ▁more
+- ▁co
+- se
+- ▁say
+- nd
+- ▁much
+- ▁come
+- ▁always
+- ine
+- ▁r
+- ation
+- ▁other
+- th
+- ur
+- ▁se
+- ▁now
+- ate
+- ▁doing
+- ▁work
+- ow
+- ▁could
+- ally
+- ▁these
+- ▁good
+- ▁any
+- ▁cause
+- ▁ex
+- ▁ch
+- ers
+- ▁little
+- ▁actually
+- ▁into
+- ▁make
+- ▁first
+- ▁being
+- ra
+- ▁our
+- ▁al
+- ▁by
+- ▁didn
+- ▁v
+- ct
+- ity
+- ch
+- un
+- ▁part
+- ▁de
+- is
+- ▁film
+- ie
+- ▁right
+- ▁pro
+- ▁off
+- ol
+- ▁two
+- ▁never
+- ▁o
+- ▁
+- ▁le
+- ot
+- ut
+- ▁movie
+- ▁play
+- ge
+- ies
+- el
+- ▁going
+- ke
+- ▁want
+- ▁con
+- ck
+- ▁feel
+- ive
+- ro
+- ▁mo
+- im
+- ▁different
+- ▁life
+- ci
+- am
+- ▁oh
+- all
+- ▁lo
+- ard
+- ▁went
+- and
+- ist
+- ▁sh
+- ▁even
+- ry
+- ▁years
+- ▁look
+- ▁k
+- ▁us
+- ant
+- ▁te
+- ▁li
+- ▁happen
+- ure
+- ▁their
+- ▁those
+- ▁take
+- ment
+- ▁day
+- ast
+- ▁every
+- ill
+- ▁thought
+- ou
+- us
+- ▁th
+- ay
+- ▁put
+- ▁story
+- ▁new
+- ▁down
+- ish
+- ▁big
+- ▁wanna
+- red
+- ▁ro
+- ▁also
+- ▁read
+- ▁around
+- ous
+- ▁through
+- ▁came
+- ▁character
+- ess
+- te
+- ver
+- ▁will
+- ag
+- ss
+- ▁fun
+- ▁over
+- ▁many
+- ▁bl
+- ▁cl
+- ▁man
+- ▁than
+- ▁pre
+- ▁world
+- ▁person
+- z
+- ▁sp
+- ven
+- ▁wanted
+- ▁bit
+- ▁before
+- ▁mar
+- one
+- ab
+- ain
+- ▁en
+- ▁set
+- ▁ha
+- ▁find
+- ul
+- ▁end
+- ▁un
+- ▁sc
+- ▁after
+- een
+- ▁working
+- ▁why
+- ter
+- me
+- ▁such
+- ne
+- ▁whole
+- om
+- ▁kinda
+- pe
+- ▁bo
+- ▁fi
+- x
+- ▁most
+- ▁ad
+- ▁guy
+- ▁spe
+- ars
+- op
+- ▁am
+- ful
+- pt
+- ▁together
+- ▁let
+- ▁quite
+- ▁everything
+- ▁made
+- ig
+- ▁old
+- able
+- ▁comp
+- ▁tr
+- ak
+- ▁fo
+- ▁po
+- ore
+- ice
+- ▁real
+- ▁bas
+- ▁knew
+- ▁hard
+- pp
+- age
+- ated
+- ▁same
+- ▁start
+- ▁ever
+- ning
+- ▁watch
+- art
+- ▁again
+- ▁here
+- are
+- ght
+- ong
+- ▁done
+- ▁only
+- ▁live
+- ▁wasn
+- ▁ho
+- ▁u
+- ▁maybe
+- ▁need
+- ▁everybody
+- ust
+- ▁three
+- ▁having
+- ▁music
+- ack
+- ld
+- ▁trying
+- ▁guys
+- rou
+- ach
+- ving
+- ▁tell
+- ▁should
+- ff
+- ide
+- ▁four
+- ▁started
+- ass
+- ▁long
+- ▁fe
+- ans
+- ▁course
+- ▁called
+- ▁own
+- ress
+- ▁moment
+- ▁pl
+- ▁still
+- ▁anything
+- ▁family
+- ▁fin
+- ▁dan
+- ▁bro
+- 'no'
+- ▁com
+- ther
+- ▁amazing
+- ▁stuff
+- os
+- ▁per
+- ▁jo
+- ▁certain
+- ▁talk
+- ater
+- per
+- ▁help
+- ▁too
+- ▁year
+- ight
+- ▁fa
+- self
+- ces
+- ▁br
+- ▁bet
+- ▁someone
+- ▁di
+- ▁sing
+- nt
+- ick
+- ▁ph
+- row
+- ▁script
+- ▁remember
+- ▁try
+- qu
+- ite
+- ▁young
+- ▁wh
+- ▁ser
+- ▁ask
+- um
+- ▁book
+- ▁each
+- ▁wr
+- ▁best
+- ▁ag
+- ▁women
+- ose
+- ions
+- ved
+- j
+- ue
+- ▁does
+- ty
+- ▁five
+- ▁both
+- ▁friends
+- ▁act
+- iz
+- ind
+- cess
+- ▁somebody
+- ft
+- ▁nice
+- ▁tur
+- ▁myself
+- mb
+- fe
+- ict
+- ▁child
+- ud
+- ▁hope
+- ▁fact
+- ▁saying
+- les
+- ave
+- icul
+- au
+- ris
+- ▁twenty
+- ▁school
+- ▁doesn
+- ▁able
+- pect
+- ▁last
+- ▁song
+- od
+- ▁str
+- ▁interesting
+- lf
+- ▁wor
+- sp
+- ap
+- og
+- ▁ra
+- ▁dis
+- ▁coming
+- ▁ab
+- ▁house
+- ▁next
+- ▁tra
+- ▁okay
+- ere
+- ib
+- ary
+- ▁incredib
+- ▁car
+- ▁job
+- ▁used
+- ▁give
+- ▁god
+- ▁americ
+- ▁characters
+- ▁app
+- ▁walk
+- ▁yes
+- rew
+- ▁getting
+- ▁six
+- ▁chan
+- ▁ne
+- ale
+- ▁pretty
+- mp
+- ang
+- ▁creat
+- ▁another
+- ▁ter
+- ▁kids
+- ▁felt
+- ▁sometimes
+- ▁place
+- ▁int
+- ically
+- out
+- ▁funny
+- ase
+- ich
+- act
+- ▁days
+- ▁bring
+- ▁making
+- ▁become
+- ute
+- ▁wonderful
+- ron
+- ▁saw
+- ▁point
+- ia
+- ▁realiz
+- ▁away
+- ays
+- ▁home
+- ace
+- ▁relationship
+- day
+- ▁woman
+- ▁everyone
+- ▁comes
+- ▁high
+- ▁wee
+- dd
+- ▁night
+- ath
+- ts
+- ▁else
+- vent
+- ▁shoot
+- vers
+- ▁sure
+- ried
+- ned
+- ▁obviously
+- ▁dra
+- co
+- iew
+- man
+- ▁playing
+- ▁important
+- ort
+- uck
+- ision
+- pport
+- ▁nor
+- ▁seen
+- ▁fl
+- est
+- ▁inter
+- ks
+- ▁actor
+- ▁lear
+- ▁worked
+- ▁believe
+- ▁gen
+- ▁keep
+- ull
+- ▁friend
+- ▁sw
+- ▁des
+- ▁times
+- ▁sur
+- ms
+- ▁sit
+- ▁probably
+- ok
+- ▁took
+- ep
+- ough
+- ip
+- ood
+- ▁sa
+- ▁season
+- vel
+- wn
+- ▁dec
+- ▁excited
+- ame
+- ian
+- ire
+- ▁name
+- ▁im
+- ▁month
+- ner
+- ▁min
+- ▁rel
+- ating
+- body
+- ition
+- ▁loved
+- ▁aw
+- ▁hear
+- ph
+- ▁cool
+- ▁list
+- ord
+- pl
+- ble
+- our
+- ▁game
+- ub
+- ▁might
+- ▁kid
+- ▁movies
+- ical
+- ▁bad
+- ▁scene
+- iv
+- ▁enough
+- ▁sm
+- ▁fift
+- ▁eight
+- ▁experience
+- ▁actors
+- ▁understand
+- ▁few
+- gin
+- ting
+- ▁director
+- ▁almost
+- ▁open
+- ren
+- ▁star
+- ▁room
+- ▁call
+- oy
+- ▁goes
+- ▁told
+- ▁once
+- ▁found
+- arly
+- ations
+- ward
+- ▁audience
+- ird
+- ▁qu
+- ▁ar
+- ▁definitely
+- ious
+- iting
+- ▁pol
+- ▁huge
+- ▁makes
+- aking
+- ▁la
+- ▁ac
+- iter
+- ▁run
+- ▁gotta
+- ▁gr
+- ▁cam
+- sh
+- ▁gets
+- ▁wa
+- ully
+- ▁says
+- ▁cont
+- side
+- ▁bus
+- ▁shows
+- ▁dr
+- ▁inv
+- ▁idea
+- ▁talking
+- way
+- ▁art
+- ▁whatever
+- ▁write
+- ash
+- itt
+- ▁met
+- ▁wants
+- ▁role
+- if
+- ▁mu
+- ▁boy
+- ▁wrote
+- ger
+- ately
+- ▁exc
+- ▁gu
+- ▁mother
+- ▁produ
+- ▁cra
+- ates
+- ▁though
+- av
+- ▁episode
+- ▁sl
+- ▁change
+- be
+- ▁voice
+- ▁played
+- ily
+- ▁guess
+- ves
+- ▁hand
+- ady
+- ▁happy
+- ith
+- ny
+- ▁gi
+- med
+- ▁looking
+- lev
+- ream
+- ▁acting
+- aught
+- iss
+- ount
+- rom
+- ▁tw
+- ▁john
+- ▁far
+- ▁res
+- ▁sense
+- ake
+- ▁meet
+- ▁bre
+- ens
+- ety
+- ▁girl
+- ▁york
+- ▁count
+- ▁shot
+- ise
+- ject
+- ▁tot
+- ▁stud
+- ▁feels
+- ▁thinking
+- ma
+- ▁head
+- ▁cast
+- ▁writing
+- ▁imp
+- ▁rehe
+- ▁written
+- ▁perfor
+- ▁fan
+- der
+- ect
+- ▁sk
+- ▁hour
+- ▁father
+- ered
+- ▁hundred
+- ▁ind
+- ▁che
+- ▁acc
+- up
+- ▁while
+- fort
+- ▁true
+- itch
+- ▁inst
+- ▁second
+- ▁pick
+- ▁record
+- ross
+- ▁quest
+- ged
+- ▁career
+- ▁reason
+- ▁since
+- ▁bu
+- ▁bra
+- ▁char
+- ree
+- ▁girls
+- ▁dad
+- ▁fant
+- ▁extra
+- ▁laugh
+- ▁stand
+- ▁honest
+- na
+- als
+- ▁yet
+- ▁human
+- ▁couple
+- dy
+- ▁mind
+- ▁sound
+- ▁ke
+- ▁pop
+- ▁ent
+- ory
+- ▁war
+- ▁ten
+- ink
+- ▁bec
+- ▁direct
+- reat
+- round
+- ien
+- ▁under
+- ile
+- ▁diff
+- ually
+- thing
+- sic
+- ▁gon
+- ather
+- ▁aud
+- ert
+- for
+- ▁scen
+- mber
+- atch
+- ▁sho
+- ever
+- tra
+- ▁pe
+- ▁hu
+- ild
+- int
+- ▁ob
+- ▁care
+- ▁fam
+- ▁ide
+- ade
+- right
+- ▁may
+- he
+- mo
+- ody
+- ense
+- ▁interest
+- ah
+- ork
+- ▁episod
+- ▁prob
+- ▁rec
+- ▁hop
+- ited
+- ▁exper
+- gh
+- ▁bel
+- ▁el
+- ▁stu
+- enty
+- ound
+- ▁gott
+- ▁id
+- ime
+- rie
+- ▁inc
+- ertain
+- ▁wo
+- ▁mon
+- az
+- xt
+- riend
+- now
+- ▁y
+- ple
+- ome
+- so
+- ause
+- ▁cou
+- iously
+- ▁sch
+- ▁vo
+- ▁fil
+- ▁op
+- ason
+- ▁mov
+- ▁hi
+- ▁pers
+- ▁ye
+- ▁def
+- ▁belie
+- fore
+- ix
+- very
+- ▁differe
+- ▁wonder
+- nder
+- ▁obv
+- ▁ep
+- ship
+- ▁lau
+- ience
+- ool
+- ▁sin
+- rect
+- ▁happ
+- ▁gir
+- ▁hel
+- du
+- ng
+- ▁underst
+- most
+- eric
+- ouse
+- time
+- ▁cour
+- ▁relation
+- rough
+- q
+- ▁defin
+- ▁reme
+- redib
+- ▁fir
+- anna
+- ways
+- itten
+- elt
+- ▁sometime
+- ':'
+- alk
+- ▁ok
+- ably
+- rote
+- gether
+- ▁definite
+- ▁import
+- '&'
+- new
+- fter
+- onest
+- erest
+- ▁amaz
+- ▁ano
+- <sos/eos>
+transcript_token_list: null
+two_pass: false
+pre_postencoder_norm: false
+init: null
+input_size: 1
+ctc_conf:
+    dropout_rate: 0.0
+    ctc_type: builtin
+    reduce: true
+    ignore_nan_grad: null
+    zero_infinity: true
+    brctc_risk_strategy: exp
+    brctc_group_strategy: end
+    brctc_risk_factor: 0.0
+joint_net_conf: null
+use_preprocessor: true
+token_type: word
+bpemodel: null
+non_linguistic_symbols: null
+cleaner: null
+g2p: null
+speech_volume_normalize: null
+rir_scp: null
+rir_apply_prob: 1.0
+noise_scp: null
+noise_apply_prob: 1.0
+noise_db_range: '13_15'
+short_noise_thres: 0.5
+frontend: null
+frontend_conf: {}
+specaug: null
+specaug_conf: {}
+normalize: null
+normalize_conf: {}
+model: espnet
+model_conf:
+    ctc_weight: 1.0
+    lsm_weight: 0.1
+    length_normalized_loss: false
+    weighted_sum: true
+    extract_feats_in_collect_stats: false
+preencoder: null
+preencoder_conf: {}
+encoder: whisper
+encoder_conf:
+    whisper_model: medium
+    dropout_rate: 0.0
+    use_specaug: true
+    specaug_conf:
+        apply_time_warp: true
+        time_warp_window: 5
+        time_warp_mode: bicubic
+        apply_freq_mask: true
+        freq_mask_width_range:
+        - 0
+        - 40
+        num_freq_mask: 2
+        apply_time_mask: true
+        time_mask_width_ratio_range:
+        - 0.0
+        - 0.12
+        num_time_mask: 5
+prepostencoder: linear
+prepostencoder_conf:
+    input_size: 1024
+    output_size: 80
+postencoder: conformer_full
+postencoder_conf:
+    output_size: 256
+    attention_heads: 4
+    linear_units: 1024
+    num_blocks: 2
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.1
+    input_layer: conv2d1
+    normalize_before: true
+    macaron_style: true
+    rel_pos_type: latest
+    pos_enc_layer_type: rel_pos
+    selfattention_layer_type: rel_selfattn
+    activation_type: swish
+    use_cnn_module: true
+    cnn_module_kernel: 31
+deliberationencoder: null
+deliberationencoder_conf: {}
+decoder: transformer
+decoder_conf:
+    attention_heads: 4
+    linear_units: 2048
+    num_blocks: 6
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    self_attention_dropout_rate: 0.1
+    src_attention_dropout_rate: 0.1
+postdecoder: null
+postdecoder_conf: {}
+required:
+- output_dir
+- token_list
+version: '202310'
+distributed: true
+```
+
+</details>
+
+
+
+### Citing ESPnet
+
+```BibTex
+@inproceedings{watanabe2018espnet,
+  author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
+  title={{ESPnet}: End-to-End Speech Processing Toolkit},
+  year={2018},
+  booktitle={Proceedings of Interspeech},
+  pages={2207--2211},
+  doi={10.21437/Interspeech.2018-1456},
+  url={http://dx.doi.org/10.21437/Interspeech.2018-1456}
+}
+
+
+
+
+
+
+```
+
+or arXiv:
+
+```bibtex
+@misc{watanabe2018espnet,
+  title={ESPnet: End-to-End Speech Processing Toolkit},
+  author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
+  year={2018},
+  eprint={1804.00015},
+  archivePrefix={arXiv},
+  primaryClass={cs.CL}
+}
+```

exp/slu_train_asr_whisper_superb_raw_en_word_sp/RESULTS.md

@@ -0,0 +1,44 @@
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Mon Feb  5 19:05:58 CST 2024`
+- python version: `3.9.13 (main, Aug 25 2022, 23:26:10)  [GCC 11.2.0]`
+- espnet version: `espnet 202310`
+- pytorch version: `pytorch 2.1.0+cu121`
+- Git hash: `21d2105784e4da98397bf487b2550d4c6e16d40d`
+  - Commit date: `Wed Jan 31 13:40:37 2024 -0600`
+
+## exp/slu_train_asr_whisper_superb_raw_en_word_sp
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_ctc_slu_model_valid.cer_ctc.ave/test|3426|135368|88.9|6.9|4.2|3.5|14.6|91.9|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_ctc_slu_model_valid.cer_ctc.ave/test|3426|591261|95.0|1.6|3.5|3.3|8.3|91.9|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+## exp/slu_train_asr_whisper_superb_raw_en_word_sp/decode_asr_ctc_slu_model_valid.cer_ctc.ave
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|org/devel|1437|56031|90.5|6.0|3.6|3.0|12.5|89.8|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|org/devel|1437|241556|95.9|1.2|2.9|2.9|6.9|89.8|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|

exp/slu_train_asr_whisper_superb_raw_en_word_sp/config.yaml

@@ -0,0 +1,1219 @@
+config: conf/tuning/train_asr_whisper_superb.yaml
+print_config: false
+log_level: INFO
+drop_last_iter: false
+dry_run: false
+iterator_type: sequence
+valid_iterator_type: null
+output_dir: exp/slu_train_asr_whisper_superb_raw_en_word_sp
+ngpu: 1
+seed: 2022
+num_workers: 2
+num_att_plot: 3
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: 4
+dist_rank: 0
+local_rank: 0
+dist_master_addr: localhost
+dist_master_port: 49737
+dist_launcher: null
+multiprocessing_distributed: true
+unused_parameters: false
+sharded_ddp: false
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: true
+collect_stats: false
+write_collected_feats: false
+max_epoch: 70
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - cer_ctc
+    - min
+-   - valid
+    - loss
+    - min
+keep_nbest_models: 10
+nbest_averaging_interval: 0
+grad_clip: 5.0
+grad_clip_type: 2.0
+grad_noise: false
+accum_grad: 1
+no_forward_run: false
+resume: true
+train_dtype: float32
+use_amp: false
+log_interval: null
+use_matplotlib: true
+use_tensorboard: true
+create_graph_in_tensorboard: false
+use_wandb: false
+wandb_project: null
+wandb_id: null
+wandb_entity: null
+wandb_name: null
+wandb_model_log_interval: -1
+detect_anomaly: false
+use_lora: false
+save_lora_only: true
+lora_conf: {}
+pretrain_path: null
+init_param: []
+ignore_init_mismatch: false
+freeze_param:
+- encoder
+num_iters_per_epoch: null
+batch_size: 20
+valid_batch_size: null
+batch_bins: 12000000
+valid_batch_bins: null
+train_shape_file:
+- exp/slu_stats_raw_en_word_sp/train/speech_shape
+- exp/slu_stats_raw_en_word_sp/train/text_shape.word
+valid_shape_file:
+- exp/slu_stats_raw_en_word_sp/valid/speech_shape
+- exp/slu_stats_raw_en_word_sp/valid/text_shape.word
+batch_type: numel
+valid_batch_type: null
+fold_length:
+- 80000
+- 150
+sort_in_batch: descending
+shuffle_within_batch: false
+sort_batch: descending
+multiple_iterator: false
+chunk_length: 500
+chunk_shift_ratio: 0.5
+num_cache_chunks: 1024
+chunk_excluded_key_prefixes: []
+chunk_default_fs: null
+train_data_path_and_name_and_type:
+-   - dump/raw/train_sp/wav.scp
+    - speech
+    - sound
+-   - dump/raw/train_sp/text
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - dump/raw/devel/wav.scp
+    - speech
+    - sound
+-   - dump/raw/devel/text
+    - text
+    - text
+allow_variable_data_keys: false
+max_cache_size: 0.0
+max_cache_fd: 32
+allow_multi_rates: false
+valid_max_cache_size: null
+exclude_weight_decay: false
+exclude_weight_decay_conf: {}
+optim: adam
+optim_conf:
+    lr: 0.005
+    weight_decay: 1.0e-06
+scheduler: warmuplr
+scheduler_conf:
+    warmup_steps: 5000
+token_list:
+- <blank>
+- <unk>
+- ▁i
+- ▁and
+- ''''
+- s
+- ▁the
+- ▁a
+- ▁it
+- ▁to
+- ▁you
+- ▁that
+- ▁of
+- ▁in
+- ▁was
+- ▁uh
+- ▁know
+- t
+- ▁so
+- ▁we
+- ▁he
+- ing
+- m
+- ▁um
+- ▁like
+- ed
+- ▁is
+- ▁but
+- ▁just
+- ▁they
+- re
+- y
+- ▁this
+- ▁for
+- ▁be
+- ▁my
+- er
+- ▁with
+- ▁on
+- ▁think
+- ▁have
+- ▁p
+- ▁she
+- ▁me
+- e
+- ▁really
+- ▁there
+- ▁what
+- al
+- ▁m
+- ▁do
+- ▁all
+- a
+- ve
+- ▁as
+- c
+- n
+- ▁about
+- ▁not
+- i
+- ▁at
+- l
+- ▁t
+- ▁had
+- ▁when
+- ▁c
+- g
+- in
+- ▁b
+- d
+- le
+- en
+- ▁out
+- u
+- ly
+- ▁an
+- or
+- ▁people
+- ar
+- ll
+- o
+- ▁are
+- ▁very
+- ▁because
+- es
+- ▁can
+- ▁don
+- ▁s
+- ▁or
+- ▁up
+- it
+- b
+- ▁e
+- ▁one
+- an
+- st
+- ▁if
+- ▁f
+- ▁were
+- p
+- ▁mean
+- ▁d
+- ▁who
+- ▁then
+- ic
+- 'on'
+- ▁no
+- ▁go
+- ▁her
+- ▁g
+- ▁st
+- ▁kind
+- ri
+- ▁would
+- ▁get
+- at
+- r
+- ▁time
+- v
+- ent
+- ▁re
+- h
+- ▁from
+- ▁l
+- ▁said
+- ▁w
+- ▁him
+- ▁how
+- ▁well
+- ▁h
+- ▁gonna
+- ▁lot
+- ▁see
+- w
+- ▁his
+- ce
+- ion
+- ▁been
+- f
+- ▁great
+- ▁yeah
+- ▁love
+- ▁which
+- ▁got
+- k
+- ▁them
+- ▁way
+- ▁n
+- id
+- ▁show
+- ▁some
+- ▁your
+- ▁did
+- ▁sort
+- et
+- ▁has
+- ▁things
+- ▁back
+- ▁where
+- ▁something
+- ir
+- ▁thing
+- ad
+- ▁su
+- il
+- as
+- ▁j
+- ▁more
+- ▁co
+- se
+- ▁say
+- nd
+- ▁much
+- ▁come
+- ▁always
+- ine
+- ▁r
+- ation
+- ▁other
+- th
+- ur
+- ▁se
+- ▁now
+- ate
+- ▁doing
+- ▁work
+- ow
+- ▁could
+- ally
+- ▁these
+- ▁good
+- ▁any
+- ▁cause
+- ▁ex
+- ▁ch
+- ers
+- ▁little
+- ▁actually
+- ▁into
+- ▁make
+- ▁first
+- ▁being
+- ra
+- ▁our
+- ▁al
+- ▁by
+- ▁didn
+- ▁v
+- ct
+- ity
+- ch
+- un
+- ▁part
+- ▁de
+- is
+- ▁film
+- ie
+- ▁right
+- ▁pro
+- ▁off
+- ol
+- ▁two
+- ▁never
+- ▁o
+- ▁
+- ▁le
+- ot
+- ut
+- ▁movie
+- ▁play
+- ge
+- ies
+- el
+- ▁going
+- ke
+- ▁want
+- ▁con
+- ck
+- ▁feel
+- ive
+- ro
+- ▁mo
+- im
+- ▁different
+- ▁life
+- ci
+- am
+- ▁oh
+- all
+- ▁lo
+- ard
+- ▁went
+- and
+- ist
+- ▁sh
+- ▁even
+- ry
+- ▁years
+- ▁look
+- ▁k
+- ▁us
+- ant
+- ▁te
+- ▁li
+- ▁happen
+- ure
+- ▁their
+- ▁those
+- ▁take
+- ment
+- ▁day
+- ast
+- ▁every
+- ill
+- ▁thought
+- ou
+- us
+- ▁th
+- ay
+- ▁put
+- ▁story
+- ▁new
+- ▁down
+- ish
+- ▁big
+- ▁wanna
+- red
+- ▁ro
+- ▁also
+- ▁read
+- ▁around
+- ous
+- ▁through
+- ▁came
+- ▁character
+- ess
+- te
+- ver
+- ▁will
+- ag
+- ss
+- ▁fun
+- ▁over
+- ▁many
+- ▁bl
+- ▁cl
+- ▁man
+- ▁than
+- ▁pre
+- ▁world
+- ▁person
+- z
+- ▁sp
+- ven
+- ▁wanted
+- ▁bit
+- ▁before
+- ▁mar
+- one
+- ab
+- ain
+- ▁en
+- ▁set
+- ▁ha
+- ▁find
+- ul
+- ▁end
+- ▁un
+- ▁sc
+- ▁after
+- een
+- ▁working
+- ▁why
+- ter
+- me
+- ▁such
+- ne
+- ▁whole
+- om
+- ▁kinda
+- pe
+- ▁bo
+- ▁fi
+- x
+- ▁most
+- ▁ad
+- ▁guy
+- ▁spe
+- ars
+- op
+- ▁am
+- ful
+- pt
+- ▁together
+- ▁let
+- ▁quite
+- ▁everything
+- ▁made
+- ig
+- ▁old
+- able
+- ▁comp
+- ▁tr
+- ak
+- ▁fo
+- ▁po
+- ore
+- ice
+- ▁real
+- ▁bas
+- ▁knew
+- ▁hard
+- pp
+- age
+- ated
+- ▁same
+- ▁start
+- ▁ever
+- ning
+- ▁watch
+- art
+- ▁again
+- ▁here
+- are
+- ght
+- ong
+- ▁done
+- ▁only
+- ▁live
+- ▁wasn
+- ▁ho
+- ▁u
+- ▁maybe
+- ▁need
+- ▁everybody
+- ust
+- ▁three
+- ▁having
+- ▁music
+- ack
+- ld
+- ▁trying
+- ▁guys
+- rou
+- ach
+- ving
+- ▁tell
+- ▁should
+- ff
+- ide
+- ▁four
+- ▁started
+- ass
+- ▁long
+- ▁fe
+- ans
+- ▁course
+- ▁called
+- ▁own
+- ress
+- ▁moment
+- ▁pl
+- ▁still
+- ▁anything
+- ▁family
+- ▁fin
+- ▁dan
+- ▁bro
+- 'no'
+- ▁com
+- ther
+- ▁amazing
+- ▁stuff
+- os
+- ▁per
+- ▁jo
+- ▁certain
+- ▁talk
+- ater
+- per
+- ▁help
+- ▁too
+- ▁year
+- ight
+- ▁fa
+- self
+- ces
+- ▁br
+- ▁bet
+- ▁someone
+- ▁di
+- ▁sing
+- nt
+- ick
+- ▁ph
+- row
+- ▁script
+- ▁remember
+- ▁try
+- qu
+- ite
+- ▁young
+- ▁wh
+- ▁ser
+- ▁ask
+- um
+- ▁book
+- ▁each
+- ▁wr
+- ▁best
+- ▁ag
+- ▁women
+- ose
+- ions
+- ved
+- j
+- ue
+- ▁does
+- ty
+- ▁five
+- ▁both
+- ▁friends
+- ▁act
+- iz
+- ind
+- cess
+- ▁somebody
+- ft
+- ▁nice
+- ▁tur
+- ▁myself
+- mb
+- fe
+- ict
+- ▁child
+- ud
+- ▁hope
+- ▁fact
+- ▁saying
+- les
+- ave
+- icul
+- au
+- ris
+- ▁twenty
+- ▁school
+- ▁doesn
+- ▁able
+- pect
+- ▁last
+- ▁song
+- od
+- ▁str
+- ▁interesting
+- lf
+- ▁wor
+- sp
+- ap
+- og
+- ▁ra
+- ▁dis
+- ▁coming
+- ▁ab
+- ▁house
+- ▁next
+- ▁tra
+- ▁okay
+- ere
+- ib
+- ary
+- ▁incredib
+- ▁car
+- ▁job
+- ▁used
+- ▁give
+- ▁god
+- ▁americ
+- ▁characters
+- ▁app
+- ▁walk
+- ▁yes
+- rew
+- ▁getting
+- ▁six
+- ▁chan
+- ▁ne
+- ale
+- ▁pretty
+- mp
+- ang
+- ▁creat
+- ▁another
+- ▁ter
+- ▁kids
+- ▁felt
+- ▁sometimes
+- ▁place
+- ▁int
+- ically
+- out
+- ▁funny
+- ase
+- ich
+- act
+- ▁days
+- ▁bring
+- ▁making
+- ▁become
+- ute
+- ▁wonderful
+- ron
+- ▁saw
+- ▁point
+- ia
+- ▁realiz
+- ▁away
+- ays
+- ▁home
+- ace
+- ▁relationship
+- day
+- ▁woman
+- ▁everyone
+- ▁comes
+- ▁high
+- ▁wee
+- dd
+- ▁night
+- ath
+- ts
+- ▁else
+- vent
+- ▁shoot
+- vers
+- ▁sure
+- ried
+- ned
+- ▁obviously
+- ▁dra
+- co
+- iew
+- man
+- ▁playing
+- ▁important
+- ort
+- uck
+- ision
+- pport
+- ▁nor
+- ▁seen
+- ▁fl
+- est
+- ▁inter
+- ks
+- ▁actor
+- ▁lear
+- ▁worked
+- ▁believe
+- ▁gen
+- ▁keep
+- ull
+- ▁friend
+- ▁sw
+- ▁des
+- ▁times
+- ▁sur
+- ms
+- ▁sit
+- ▁probably
+- ok
+- ▁took
+- ep
+- ough
+- ip
+- ood
+- ▁sa
+- ▁season
+- vel
+- wn
+- ▁dec
+- ▁excited
+- ame
+- ian
+- ire
+- ▁name
+- ▁im
+- ▁month
+- ner
+- ▁min
+- ▁rel
+- ating
+- body
+- ition
+- ▁loved
+- ▁aw
+- ▁hear
+- ph
+- ▁cool
+- ▁list
+- ord
+- pl
+- ble
+- our
+- ▁game
+- ub
+- ▁might
+- ▁kid
+- ▁movies
+- ical
+- ▁bad
+- ▁scene
+- iv
+- ▁enough
+- ▁sm
+- ▁fift
+- ▁eight
+- ▁experience
+- ▁actors
+- ▁understand
+- ▁few
+- gin
+- ting
+- ▁director
+- ▁almost
+- ▁open
+- ren
+- ▁star
+- ▁room
+- ▁call
+- oy
+- ▁goes
+- ▁told
+- ▁once
+- ▁found
+- arly
+- ations
+- ward
+- ▁audience
+- ird
+- ▁qu
+- ▁ar
+- ▁definitely
+- ious
+- iting
+- ▁pol
+- ▁huge
+- ▁makes
+- aking
+- ▁la
+- ▁ac
+- iter
+- ▁run
+- ▁gotta
+- ▁gr
+- ▁cam
+- sh
+- ▁gets
+- ▁wa
+- ully
+- ▁says
+- ▁cont
+- side
+- ▁bus
+- ▁shows
+- ▁dr
+- ▁inv
+- ▁idea
+- ▁talking
+- way
+- ▁art
+- ▁whatever
+- ▁write
+- ash
+- itt
+- ▁met
+- ▁wants
+- ▁role
+- if
+- ▁mu
+- ▁boy
+- ▁wrote
+- ger
+- ately
+- ▁exc
+- ▁gu
+- ▁mother
+- ▁produ
+- ▁cra
+- ates
+- ▁though
+- av
+- ▁episode
+- ▁sl
+- ▁change
+- be
+- ▁voice
+- ▁played
+- ily
+- ▁guess
+- ves
+- ▁hand
+- ady
+- ▁happy
+- ith
+- ny
+- ▁gi
+- med
+- ▁looking
+- lev
+- ream
+- ▁acting
+- aught
+- iss
+- ount
+- rom
+- ▁tw
+- ▁john
+- ▁far
+- ▁res
+- ▁sense
+- ake
+- ▁meet
+- ▁bre
+- ens
+- ety
+- ▁girl
+- ▁york
+- ▁count
+- ▁shot
+- ise
+- ject
+- ▁tot
+- ▁stud
+- ▁feels
+- ▁thinking
+- ma
+- ▁head
+- ▁cast
+- ▁writing
+- ▁imp
+- ▁rehe
+- ▁written
+- ▁perfor
+- ▁fan
+- der
+- ect
+- ▁sk
+- ▁hour
+- ▁father
+- ered
+- ▁hundred
+- ▁ind
+- ▁che
+- ▁acc
+- up
+- ▁while
+- fort
+- ▁true
+- itch
+- ▁inst
+- ▁second
+- ▁pick
+- ▁record
+- ross
+- ▁quest
+- ged
+- ▁career
+- ▁reason
+- ▁since
+- ▁bu
+- ▁bra
+- ▁char
+- ree
+- ▁girls
+- ▁dad
+- ▁fant
+- ▁extra
+- ▁laugh
+- ▁stand
+- ▁honest
+- na
+- als
+- ▁yet
+- ▁human
+- ▁couple
+- dy
+- ▁mind
+- ▁sound
+- ▁ke
+- ▁pop
+- ▁ent
+- ory
+- ▁war
+- ▁ten
+- ink
+- ▁bec
+- ▁direct
+- reat
+- round
+- ien
+- ▁under
+- ile
+- ▁diff
+- ually
+- thing
+- sic
+- ▁gon
+- ather
+- ▁aud
+- ert
+- for
+- ▁scen
+- mber
+- atch
+- ▁sho
+- ever
+- tra
+- ▁pe
+- ▁hu
+- ild
+- int
+- ▁ob
+- ▁care
+- ▁fam
+- ▁ide
+- ade
+- right
+- ▁may
+- he
+- mo
+- ody
+- ense
+- ▁interest
+- ah
+- ork
+- ▁episod
+- ▁prob
+- ▁rec
+- ▁hop
+- ited
+- ▁exper
+- gh
+- ▁bel
+- ▁el
+- ▁stu
+- enty
+- ound
+- ▁gott
+- ▁id
+- ime
+- rie
+- ▁inc
+- ertain
+- ▁wo
+- ▁mon
+- az
+- xt
+- riend
+- now
+- ▁y
+- ple
+- ome
+- so
+- ause
+- ▁cou
+- iously
+- ▁sch
+- ▁vo
+- ▁fil
+- ▁op
+- ason
+- ▁mov
+- ▁hi
+- ▁pers
+- ▁ye
+- ▁def
+- ▁belie
+- fore
+- ix
+- very
+- ▁differe
+- ▁wonder
+- nder
+- ▁obv
+- ▁ep
+- ship
+- ▁lau
+- ience
+- ool
+- ▁sin
+- rect
+- ▁happ
+- ▁gir
+- ▁hel
+- du
+- ng
+- ▁underst
+- most
+- eric
+- ouse
+- time
+- ▁cour
+- ▁relation
+- rough
+- q
+- ▁defin
+- ▁reme
+- redib
+- ▁fir
+- anna
+- ways
+- itten
+- elt
+- ▁sometime
+- ':'
+- alk
+- ▁ok
+- ably
+- rote
+- gether
+- ▁definite
+- ▁import
+- '&'
+- new
+- fter
+- onest
+- erest
+- ▁amaz
+- ▁ano
+- <sos/eos>
+transcript_token_list: null
+two_pass: false
+pre_postencoder_norm: false
+init: null
+input_size: 1
+ctc_conf:
+    dropout_rate: 0.0
+    ctc_type: builtin
+    reduce: true
+    ignore_nan_grad: null
+    zero_infinity: true
+    brctc_risk_strategy: exp
+    brctc_group_strategy: end
+    brctc_risk_factor: 0.0
+joint_net_conf: null
+use_preprocessor: true
+token_type: word
+bpemodel: null
+non_linguistic_symbols: null
+cleaner: null
+g2p: null
+speech_volume_normalize: null
+rir_scp: null
+rir_apply_prob: 1.0
+noise_scp: null
+noise_apply_prob: 1.0
+noise_db_range: '13_15'
+short_noise_thres: 0.5
+frontend: null
+frontend_conf: {}
+specaug: null
+specaug_conf: {}
+normalize: null
+normalize_conf: {}
+model: espnet
+model_conf:
+    ctc_weight: 1.0
+    lsm_weight: 0.1
+    length_normalized_loss: false
+    weighted_sum: true
+    extract_feats_in_collect_stats: false
+preencoder: null
+preencoder_conf: {}
+encoder: whisper
+encoder_conf:
+    whisper_model: medium
+    dropout_rate: 0.0
+    use_specaug: true
+    specaug_conf:
+        apply_time_warp: true
+        time_warp_window: 5
+        time_warp_mode: bicubic
+        apply_freq_mask: true
+        freq_mask_width_range:
+        - 0
+        - 40
+        num_freq_mask: 2
+        apply_time_mask: true
+        time_mask_width_ratio_range:
+        - 0.0
+        - 0.12
+        num_time_mask: 5
+prepostencoder: linear
+prepostencoder_conf:
+    input_size: 1024
+    output_size: 80
+postencoder: conformer_full
+postencoder_conf:
+    output_size: 256
+    attention_heads: 4
+    linear_units: 1024
+    num_blocks: 2
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.1
+    input_layer: conv2d1
+    normalize_before: true
+    macaron_style: true
+    rel_pos_type: latest
+    pos_enc_layer_type: rel_pos
+    selfattention_layer_type: rel_selfattn
+    activation_type: swish
+    use_cnn_module: true
+    cnn_module_kernel: 31
+deliberationencoder: null
+deliberationencoder_conf: {}
+decoder: transformer
+decoder_conf:
+    attention_heads: 4
+    linear_units: 2048
+    num_blocks: 6
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    self_attention_dropout_rate: 0.1
+    src_attention_dropout_rate: 0.1
+postdecoder: null
+postdecoder_conf: {}
+required:
+- output_dir
+- token_list
+version: '202310'
+distributed: true

exp/slu_train_asr_whisper_superb_raw_en_word_sp/valid.loss.ave_10best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e850933a200d1eac3a7f07193e078303fb4124f45fbfa622ba1cd6423e76208d
+size 1265398202

meta.yaml

@@ -0,0 +1,8 @@
+espnet: '202310'
+files:
+  slu_model_file: exp/slu_train_asr_whisper_superb_raw_en_word_sp/valid.loss.ave_10best.pth
+python: "3.9.13 (main, Aug 25 2022, 23:26:10) \n[GCC 11.2.0]"
+timestamp: 1715351510.883123
+torch: 2.1.0+cu121
+yaml_files:
+  slu_train_config: exp/slu_train_asr_whisper_superb_raw_en_word_sp/config.yaml