Add model files

e2337d9 9 months ago

No virus

16.7 kB

	---
	tags:
	- espnet
	- audio
	- automatic-speech-recognition
	language: en
	datasets:
	- lrs3
	license: cc-by-4.0
	---

	## ESPnet2 AVSR model

	### `espnet/msk_lrs3_train_avsr_avhubert_large_extracted_en_bpe1000`

	This model was trained by ms-dot-k using lrs3 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
	pip install -e .
	cd egs2/lrs3/avsr1
	./run.sh --skip_data_prep false --skip_train true --download_model espnet/msk_lrs3_train_avsr_avhubert_large_extracted_en_bpe1000
	```

	<!-- Generated by scripts/utils/show_asr_result.sh -->
	# RESULTS
	## Environments
	- date: `Thu Sep 28 23:59:06 KST 2023`
	- python version: `3.8.18 (default, Sep 11 2023, 13:40:15) [GCC 11.2.0]`
	- espnet version: `espnet 202308`
	- pytorch version: `pytorch 1.12.0`
	- Git hash: `5d0758e2a7063b82d1f10a8ac2de98eb6cf8a352`
	- Commit date: `Wed Aug 30 18:03:42 2023 -0400`

	## exp/asr_train_avsr_avhubert_large_extracted_en_bpe1000
	### WER

	\|dataset\|Snt\|Wrd\|Corr\|Sub\|Del\|Ins\|Err\|S.Err\|
	\|---\|---\|---\|---\|---\|---\|---\|---\|---\|
	\|inference_asr_model_valid.acc.ave/test\|1321\|9890\|98.5\|1.1\|0.4\|0.2\|1.7\|8.8\|

	### CER

	\|dataset\|Snt\|Wrd\|Corr\|Sub\|Del\|Ins\|Err\|S.Err\|
	\|---\|---\|---\|---\|---\|---\|---\|---\|---\|
	\|inference_asr_model_valid.acc.ave/test\|1321\|49750\|99.4\|0.2\|0.4\|0.2\|0.8\|8.8\|

	### TER

	\|dataset\|Snt\|Wrd\|Corr\|Sub\|Del\|Ins\|Err\|S.Err\|
	\|---\|---\|---\|---\|---\|---\|---\|---\|---\|
	\|inference_asr_model_valid.acc.ave/test\|1321\|14940\|98.8\|0.8\|0.4\|0.3\|1.5\|8.8\|



	## ASR config

	<details><summary>expand</summary>

	```
	config: conf/train_avsr_avhubert_large.yaml
	print_config: false
	log_level: INFO
	drop_last_iter: false
	dry_run: false
	iterator_type: sequence
	valid_iterator_type: null
	output_dir: exp/asr_train_avsr_avhubert_large_extracted_en_bpe1000
	ngpu: 1
	seed: 0
	num_workers: 1
	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: 54927
	dist_launcher: null
	multiprocessing_distributed: true
	unused_parameters: true
	sharded_ddp: false
	cudnn_enabled: true
	cudnn_benchmark: false
	cudnn_deterministic: true
	collect_stats: false
	write_collected_feats: false
	max_epoch: 20
	patience: null
	val_scheduler_criterion:
	- valid
	- loss
	early_stopping_criterion:
	- valid
	- loss
	- min
	best_model_criterion:
	- - valid
	- acc
	- max
	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
	pretrain_path: null
	init_param: []
	ignore_init_mismatch: false
	freeze_param: []
	num_iters_per_epoch: null
	batch_size: 16
	valid_batch_size: null
	batch_bins: 1000000
	valid_batch_bins: null
	train_shape_file:
	- exp/asr_stats_extracted_en_bpe1000/train/speech_shape
	- exp/asr_stats_extracted_en_bpe1000/train/text_shape.bpe
	valid_shape_file:
	- exp/asr_stats_extracted_en_bpe1000/valid/speech_shape
	- exp/asr_stats_extracted_en_bpe1000/valid/text_shape.bpe
	batch_type: folded
	valid_batch_type: null
	fold_length:
	- 800
	- 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: []
	train_data_path_and_name_and_type:
	- - dump/extracted/train/feats.scp
	- speech
	- kaldi_ark
	- - dump/extracted/train/text
	- text
	- text
	valid_data_path_and_name_and_type:
	- - dump/extracted/val/feats.scp
	- speech
	- kaldi_ark
	- - dump/extracted/val/text
	- text
	- text
	allow_variable_data_keys: false
	max_cache_size: 0.0
	max_cache_fd: 32
	valid_max_cache_size: null
	exclude_weight_decay: false
	exclude_weight_decay_conf: {}
	optim: adam
	optim_conf:
	lr: 0.0003
	scheduler: warmuplr
	scheduler_conf:
	warmup_steps: 8000
	token_list:
	- <blank>
	- <unk>
	- S
	- ▁THE
	- ▁TO
	- ▁A
	- ▁AND
	- T
	- ▁I
	- ''''
	- ▁OF
	- ▁THAT
	- ▁IN
	- ING
	- D
	- ▁YOU
	- ▁WE
	- E
	- ▁IT
	- N
	- ED
	- ▁IS
	- R
	- M
	- P
	- Y
	- ▁FOR
	- ER
	- ▁THIS
	- ▁WAS
	- RE
	- C
	- G
	- ▁SO
	- A
	- ▁BE
	- ▁THEY
	- ▁HAVE
	- ▁ARE
	- O
	- ▁
	- ▁ON
	- ▁WITH
	- LY
	- ▁WHAT
	- U
	- IN
	- AL
	- ▁MY
	- I
	- ▁S
	- ▁DO
	- B
	- ▁RE
	- L
	- ▁ME
	- ▁CAN
	- ▁BUT
	- LE
	- ▁ABOUT
	- OR
	- ▁NOT
	- VE
	- F
	- AR
	- RA
	- ▁ALL
	- ▁OUR
	- ▁PEOPLE
	- ▁AT
	- ▁C
	- ▁AS
	- IC
	- ▁OR
	- ▁LIKE
	- W
	- LL
	- K
	- ▁AN
	- ▁THERE
	- ENT
	- ▁ONE
	- ES
	- ▁HE
	- RI
	- 'ON'
	- ▁P
	- ▁IF
	- ▁FROM
	- ▁JUST
	- ▁WHEN
	- TH
	- ▁YOUR
	- ▁US
	- CE
	- ▁DE
	- ION
	- IT
	- ▁KNOW
	- ▁HOW
	- ▁T
	- ▁BECAUSE
	- CH
	- V
	- ▁OUT
	- ▁B
	- ▁UP
	- ▁E
	- ▁F
	- TE
	- ▁HAD
	- ▁CO
	- LI
	- ▁TIME
	- ▁THEIR
	- ▁MORE
	- UR
	- ▁WHO
	- ▁GO
	- EN
	- ▁G
	- ATION
	- AN
	- CK
	- TER
	- ▁SEE
	- ▁WOULD
	- ▁THESE
	- ▁NO
	- ▁THEM
	- ▁BY
	- ▁THINK
	- ▁WERE
	- IL
	- ATE
	- ▁GET
	- ▁SE
	- ▁VERY
	- ▁GOING
	- ▁EX
	- ▁REALLY
	- ITY
	- ▁WAY
	- ▁CON
	- H
	- RO
	- ▁DON
	- ▁NOW
	- ▁W
	- X
	- NE
	- GE
	- ▁WILL
	- ▁MAKE
	- ▁WANT
	- ▁OTHER
	- ▁SOME
	- LA
	- ▁WORLD
	- ▁ST
	- ▁COULD
	- TION
	- ▁WORK
	- MENT
	- ▁SHE
	- ▁NEED
	- ▁PA
	- LO
	- OL
	- ▁SAY
	- ▁MO
	- ▁BA
	- IST
	- ▁FA
	- IR
	- ▁MA
	- ERS
	- ▁HAS
	- VER
	- ▁PO
	- IVE
	- ▁PRO
	- ▁LIFE
	- ▁INTO
	- ▁WHICH
	- ▁THINGS
	- ▁WHERE
	- ND
	- ▁LA
	- MP
	- ▁BEEN
	- ▁SOMETHING
	- MA
	- ▁THOSE
	- US
	- ▁NEW
	- ▁CH
	- ▁RA
	- ▁ACTUALLY
	- ▁YEARS
	- ▁EVEN
	- ▁TAKE
	- ▁LOOK
	- UL
	- ▁RIGHT
	- ▁SAID
	- TIC
	- ▁UN
	- Z
	- AS
	- ▁DAY
	- ▁HER
	- IDE
	- ▁BO
	- ▁THAN
	- ▁HERE
	- ▁OVER
	- ▁BACK
	- ▁LO
	- ▁FIRST
	- ▁DI
	- ▁MOST
	- ▁COME
	- ▁ALSO
	- VI
	- KE
	- ▁WELL
	- IES
	- ABLE
	- UT
	- ▁THEN
	- ▁CHANGE
	- AGE
	- ▁MUCH
	- '0'
	- ▁MEAN
	- OM
	- ▁CA
	- CO
	- AT
	- ▁ANY
	- ▁HAPPEN
	- ▁ONLY
	- ▁PART
	- ▁SU
	- ▁HIS
	- ▁SP
	- ▁DIS
	- ANCE
	- ID
	- ▁MANY
	- ▁RO
	- '}'
	- ▁{
	- OW
	- ▁O
	- IGHT
	- ▁GOOD
	- UM
	- ▁LIVE
	- ▁LOT
	- ▁D
	- ▁TWO
	- ▁LI
	- ▁THING
	- ▁GOT
	- ▁TELL
	- AC
	- ▁EVERY
	- EL
	- CI
	- ▁WHY
	- TA
	- FUL
	- ▁BEING
	- ANT
	- EST
	- ▁LEARN
	- ▁COMP
	- ▁DID
	- URE
	- PE
	- ▁FEEL
	- ▁DIFFERENT
	- ▁PRE
	- MO
	- TI
	- ▁HO
	- ▁K
	- ▁LITTLE
	- IV
	- ▁THROUGH
	- ▁1
	- INE
	- ▁KIND
	- ME
	- RY
	- ▁LET
	- ▁HELP
	- UN
	- ICAL
	- ▁VI
	- ▁SAME
	- ECT
	- ▁HUMAN
	- ▁GIVE
	- HE
	- ▁TALK
	- ▁FE
	- ▁HA
	- ▁OWN
	- ▁AROUND
	- ▁USE
	- IS
	- ALLY
	- ▁IDEA
	- RESS
	- ▁PROBLEM
	- ▁PERSON
	- ▁TE
	- ▁FI
	- ▁FIND
	- ▁SA
	- ▁START
	- OS
	- TED
	- ▁BU
	- LG
	- NCE
	- ATED
	- ▁YEAR
	- ▁DIDN
	- ▁LOVE
	- HO
	- '5'
	- ▁DOWN
	- ▁SCHOOL
	- ▁TODAY
	- ▁QUESTION
	- ▁HEAR
	- DI
	- ▁MAN
	- ▁CAR
	- MI
	- ▁GREAT
	- ▁CR
	- ▁DOING
	- IG
	- ▁FACT
	- ▁LE
	- ▁LONG
	- OUS
	- ▁RU
	- ▁PUT
	- ▁AFTER
	- ▁EN
	- ▁M
	- ▁GA
	- ▁SHOW
	- OP
	- ▁SI
	- ▁SHOULD
	- ▁NE
	- ▁STA
	- ▁NEVER
	- ▁BIG
	- NS
	- ▁THOUGHT
	- ISH
	- ▁MIGHT
	- ▁ACT
	- ▁PLACE
	- LU
	- END
	- IZE
	- ▁REAL
	- ▁BETTER
	- ATIVE
	- IA
	- ▁UNDERSTAND
	- ▁POWER
	- ▁IMPORTANT
	- IAN
	- ▁BRAIN
	- ▁SYSTEM
	- UAL
	- NESS
	- ▁END
	- ▁ABLE
	- ▁BEFORE
	- ▁STORY
	- ▁OFF
	- TOR
	- FF
	- ▁STARTED
	- ▁DR
	- ▁MADE
	- ▁ASK
	- NA
	- ▁HU
	- ▁CREATE
	- ATING
	- ▁BI
	- ARY
	- ▁HIGH
	- ▁HIM
	- BO
	- ITION
	- ▁THREE
	- ▁PER
	- ▁AM
	- ▁CALLED
	- ▁APP
	- ▁CAME
	- ▁WOMEN
	- ▁OLD
	- TY
	- ▁PLAY
	- '4'
	- PP
	- ▁PH
	- AG
	- ▁BELIEVE
	- ▁HOME
	- ARD
	- ▁FRIEND
	- ▁RI
	- ▁FOUND
	- HA
	- ▁HAND
	- ▁DA
	- ▁STILL
	- ▁NA
	- ▁WORD
	- ▁TRANS
	- ▁HEALTH
	- OUND
	- ▁BUILD
	- ▁CARE
	- ▁WI
	- ▁NEXT
	- ▁THANK
	- ▁TURN
	- ▁TOGETHER
	- ▁TA
	- ▁BECOME
	- ▁EXPERIENCE
	- VING
	- ▁EM
	- ▁MEN
	- ISE
	- ▁MAR
	- ▁EACH
	- ▁WENT
	- ▁TRI
	- ▁POINT
	- ▁LAST
	- ▁MAYBE
	- ▁EVER
	- ▁CALL
	- WARD
	- ▁CHILDREN
	- ▁DOES
	- CA
	- ▁BIT
	- UC
	- LIC
	- UGH
	- ▁EXAMPLE
	- ▁FEW
	- ITIES
	- ▁ANOTHER
	- SH
	- ▁TH
	- ▁ALWAYS
	- ▁H
	- ▁READ
	- ▁INTEREST
	- FORM
	- ▁STATE
	- ▁MOVE
	- IOUS
	- ▁MIND
	- 'NO'
	- AM
	- ▁TEACH
	- ▁2
	- ▁HARD
	- ▁WANTED
	- ▁20
	- ▁GROW
	- ▁JOB
	- DA
	- ▁TOO
	- ▁VA
	- OME
	- ▁MAY
	- '8'
	- ▁SOCIAL
	- ▁HI
	- ▁FOOD
	- BI
	- ▁JO
	- ▁COURSE
	- ▁FR
	- BA
	- ▁MOMENT
	- ▁AGAIN
	- ▁DOESN
	- ▁SHARE
	- ▁AWAY
	- ▁BETWEEN
	- ▁LESS
	- ▁SHA
	- ▁MONEY
	- ▁UNDER
	- BER
	- ▁DEVELOP
	- ▁SECOND
	- ▁NUMBER
	- ▁ART
	- QUE
	- ▁FAMILY
	- '1'
	- '7'
	- ▁SH
	- '6'
	- ▁EVERYTHING
	- ▁FAR
	- ▁WORKING
	- ▁KIDS
	- ▁PLAN
	- ▁CHA
	- ▁AGO
	- ▁PI
	- ▁ENOUGH
	- ISM
	- ▁AMERICA
	- ▁THINKING
	- ▁USED
	- ▁REASON
	- ▁TRY
	- ▁SOMEONE
	- ▁GENE
	- ▁CU
	- ▁STUDENT
	- ▁TOLD
	- ▁GU
	- ▁TRYING
	- ▁LEAD
	- ▁MYSELF
	- ▁BEST
	- ▁FUTURE
	- ▁MILLION
	- ▁SMALL
	- ▁TECHNOLOGY
	- LESS
	- ▁PASS
	- ▁DONE
	- ▁YOUNG
	- '9'
	- ▁SPACE
	- ▁WATER
	- ▁MATTER
	- ▁OPEN
	- ▁COUNTRY
	- ▁REMEMBER
	- ▁TALKING
	- ▁REALIZE
	- LAND
	- ▁RESEARCH
	- Q
	- IAL
	- ▁WAR
	- ▁GROUP
	- ▁BOOK
	- ▁KEEP
	- ▁DEF
	- ▁STOP
	- ▁HOPE
	- ▁CONNECT
	- ▁SENSE
	- ▁ANSWER
	- ▁WALK
	- ▁DESIGN
	- ▁WEEK
	- ▁LANGUAGE
	- ▁DATA
	- ▁LOOKING
	- ▁PERCENT
	- ADE
	- ▁CLASS
	- ▁WHOLE
	- ▁BODY
	- ▁FOUR
	- ▁OFTEN
	- ▁ELSE
	- ▁WITHOUT
	- ▁PROCESS
	- ▁FREE
	- ▁MAKING
	- IBLE
	- ▁BRING
	- ▁CHILD
	- ▁GETTING
	- ▁PROBABLY
	- ▁ALLOW
	- ▁SPEAK
	- ▁COMMUNITY
	- ▁HAVING
	- ▁TOOK
	- ▁OP
	- ▁JU
	- ▁MU
	- ▁FACE
	- ▁INFORMATION
	- ABILITY
	- ▁NAME
	- ▁NI
	- '2'
	- ▁GIRL
	- ▁CELL
	- ▁ANYTHING
	- ▁SCIENCE
	- ▁STAND
	- ▁WHILE
	- ▁SUCH
	- '000'
	- ▁CASE
	- J
	- ANG
	- ▁FIVE
	- ▁GUY
	- ▁FUN
	- ▁BUSINESS
	- ▁ROOM
	- ▁SELF
	- ▁LIVING
	- ▁SURE
	- ▁IMAGINE
	- ▁ASKED
	- ▁MIS
	- ▁ENERGY
	- ▁PROJECT
	- ▁STUDY
	- ▁DREAM
	- ▁10
	- ▁STORIES
	- ▁ALREADY
	- ▁TERM
	- ▁EFFECT
	- ▁KNEW
	- ▁SOCIETY
	- ▁PRODUCT
	- ▁PRETTY
	- ▁EVERYONE
	- ▁HEAD
	- ▁19
	- ▁JA
	- ▁LIGHT
	- ▁LISTEN
	- ▁MUSIC
	- ▁LARGE
	- ▁QUITE
	- ▁J
	- ▁BOTH
	- ▁CHALLENGE
	- ▁SORT
	- ▁FELT
	- ▁TREAT
	- ▁EDUCATION
	- ▁WRONG
	- ▁YOURSELF
	- ▁MIL
	- ▁OURSELVES
	- ▁SOUND
	- ▁PROGRAM
	- ▁3
	- ▁CLOSE
	- ▁QUA
	- ▁SINGLE
	- ▁MINUTE
	- ▁NOTHING
	- ▁ENVIRONMENT
	- ▁PUBLIC
	- ▁ORDER
	- ▁OB
	- ▁TRUE
	- ▁STEP
	- ▁WONDER
	- ▁NIGHT
	- ▁YET
	- ▁EYE
	- ▁LEFT
	- SHIP
	- ▁VALUE
	- ▁WHETHER
	- ▁MOTHER
	- ▁SIMPLE
	- ▁NU
	- ▁WOMAN
	- ▁LU
	- ▁CONTROL
	- ▁COMING
	- ▁SAW
	- ▁LEVEL
	- ▁TEST
	- ▁POSSIBLE
	- ▁ACROSS
	- ▁HOUSE
	- ▁WATCH
	- ▁GOVERNMENT
	- ▁PARENTS
	- ▁HALF
	- ▁TEN
	- ▁DEEP
	- ▁CANCER
	- ▁ISSUE
	- ▁LATER
	- ▁SOMETIMES
	- ▁ANIMAL
	- ▁SUPPORT
	- ▁EAT
	- ▁CULTURE
	- ▁FULL
	- ▁INSTEAD
	- ▁EARTH
	- ▁DISEASE
	- ▁MIN
	- ▁GAME
	- ▁DECIDED
	- ▁ALMOST
	- ▁SUCCESS
	- ▁AMAZING
	- ▁DRIVE
	- ▁DU
	- ▁EMOTION
	- ▁GLOBAL
	- ▁EQU
	- ▁PLANET
	- ▁CERTAIN
	- ▁HISTORY
	- ▁MEET
	- ▁TRAIN
	- ▁COMPUTER
	- ▁BECAME
	- ▁TEAM
	- ▁DISCOVER
	- ▁DIFFERENCE
	- WAY
	- ▁FOCUS
	- ▁PAST
	- ▁RESULT
	- ▁MONTHS
	- ▁MODEL
	- ▁YES
	- ▁VO
	- ▁COUNTRIES
	- ▁STUFF
	- ▁FIGURE
	- ▁30
	- ▁PATIENT
	- ▁SPEND
	- ▁ENTIRE
	- ▁INDIVIDUAL
	- ▁UNTIL
	- ▁THOUGH
	- ▁DECISION
	- ▁CHOICE
	- ▁AFRICA
	- ▁RELATIONSHIP
	- ▁BREAK
	- ▁SOMEBODY
	- ▁FOLLOW
	- ▁CONVERSATION
	- ▁LEAVE
	- ▁THOUSAND
	- ▁SIGN
	- ▁SINCE
	- ▁DIFFICULT
	- ▁IMPACT
	- ▁HOURS
	- ▁COUPLE
	- ▁CAUSE
	- ▁PARTICULAR
	- ▁DOCTOR
	- ▁TAKING
	- ▁COMPANY
	- ▁EVERYBODY
	- ▁50
	- ▁DIRECT
	- ▁EXPECT
	- ▁200
	- ▁ORGAN
	- ▁EXACTLY
	- ▁THEMSELVES
	- ▁HAPPY
	- ▁MUST
	- ▁SAFE
	- ▁BASED
	- ▁BEAUTIFUL
	- ▁PHONE
	- ▁AGAINST
	- ▁WRITE
	- ▁DRUG
	- ▁PICTURE
	- ▁MEDIA
	- ▁WAIT
	- ▁FRONT
	- ▁RISK
	- ▁BEHAVIOR
	- ▁BLACK
	- ▁100
	- ▁NATURE
	- ▁ORGANIZATION
	- ▁HUNDRED
	- ▁EASY
	- ▁ACCESS
	- ▁HOLD
	- ▁COMMON
	- ▁MARKET
	- ▁GRAND
	- ▁VOICE
	- ▁DEATH
	- ▁PIECE
	- ▁BILLION
	- ▁LEAST
	- ▁DURING
	- '3'
	- ▁NATURAL
	- ▁TYPE
	- ▁INVEST
	- ▁GENERATION
	- ENCY
	- ▁STRONG
	- OLOGICAL
	- ▁CLEAR
	- ▁PRESENT
	- ▁INTERNET
	- ▁KILL
	- OLOGY
	- ▁SUPER
	- ▁UNITED
	- ▁IMAGE
	- ▁RATHER
	- ▁SOLUTION
	- ▁ECONOMIC
	- ▁PROTECT
	- ▁BEHIND
	- ▁COLLECT
	- ▁SCIENTIST
	- UDE
	- ▁PRODUCE
	- ▁PERFECT
	- ▁DOLLARS
	- ▁VIEW
	- ▁CONSIDER
	- ▁THIRD
	- ▁MACHINE
	- ▁OUTSIDE
	- ▁SKILL
	- ▁EXPERIMENT
	- ▁COLLEGE
	- ▁QUI
	- ▁OPPORTUNITY
	- ▁LOCAL
	- ▁SIMPLY
	- ▁EARLY
	- ▁MAJOR
	- ▁CANNOT
	- ▁PHYSICAL
	- ▁WHATEVER
	- ▁MIDDLE
	- ▁VIDEO
	- ▁ALONG
	- OGRAPH
	- ▁SOLVE
	- ▁KEY
	- ▁TRUST
	- ▁FIELD
	- HOOD
	- ▁ATTENTION
	- ▁MICRO
	- ▁SHORT
	- ▁SITUATION
	- ▁STREET
	- ▁COMPANIES
	- ▁POLITICAL
	- ▁NORMAL
	- ▁AMOUNT
	- ▁SERVICE
	- ▁OBJECT
	- ▁POTENTIAL
	- ▁COLOR
	- ▁KNOWLEDGE
	- ▁MORNING
	- ▁TRUTH
	- ▁UNIVERSITY
	- ▁PROVIDE
	- ▁RESOURCE
	- ▁POSITIVE
	- ▁EUROPE
	- ▁SPECIAL
	- ▁CONTINUE
	- ▁BASICALLY
	- ▁SMART
	- ▁PRACTICE
	- ▁POPULATION
	- ▁TRAVEL
	- ▁AFFECT
	- ▁FINALLY
	- ▁APPROACH
	- ▁COUNT
	- ▁PERHAPS
	- ▁INTERACT
	- ▁EXPLAIN
	- ▁ENGINEER
	- ▁ENGAGE
	- ▁SITTING
	- ▁OFFICE
	- ▁COMPLEX
	- ▁WHITE
	- ▁GENDER
	- ▁MESSAGE
	- ▁WORTH
	- ▁ITSELF
	- IZATION
	- ▁BUILT
	- ▁IMPROVE
	- ▁OKAY
	- ▁PRISON
	- ▁MATERIAL
	- ▁NETWORK
	- ▁EITHER
	- ▁GIVING
	- ▁LIMIT
	- ▁MEASURE
	- ▁DARK
	- ▁AUDIENCE
	- ▁ACCEPT
	- ▁RECORD
	- ▁OCEAN
	- ▁CHOOSE
	- ▁SPECIES
	- ▁YORK
	- ▁SUSTAIN
	- ▁SLEEP
	- ▁OBVIOUS
	- ▁HOSPITAL
	- ▁PERSPECTIVE
	- ▁INCREASE
	- ▁OPERA
	- ▁TAUGHT
	- ▁MULTI
	- ▁CHANGING
	- ▁JOURNEY
	- ▁INDUSTRY
	- ▁NEURO
	- ▁REQUIRE
	- ▁DECADE
	- ▁CURRENT
	- ▁PUSH
	- ▁BENEFIT
	- ▁YEAH
	- ▁BLOOD
	- ▁SCALE
	- ▁ESPECIALLY
	- ▁COMMUNITIES
	- ▁ADULT
	- ▁CHARACTER
	- ▁REPRESENT
	- IFIED
	- ▁SUFFER
	- ▁RECOGNIZE
	- ▁CENTURY
	- ▁SUDDEN
	- ▁FUNCTION
	- ▁ACHIEVE
	- ▁SIMILAR
	- ▁BROUGHT
	- ▁TRADITION
	- ▁UNIVERSE
	- ▁CLIMATE
	- ▁BREATH
	- ▁EXTREME
	- ▁REPORT
	- ▁DAUGHTER
	- ▁COMFORT
	- ▁CONCEPT
	- ▁ECONOMY
	- ▁INNOVATION
	- ▁QUICKLY
	- ▁SUGGEST
	- ▁SPECIFIC
	- ▁CRAZY
	- ▁CONSCIOUS
	- ▁SPREAD
	- ▁TRULY
	- '{'
	- <sos/eos>
	init: xavier_uniform
	input_size: 2048
	ctc_conf:
	dropout_rate: 0.0
	ctc_type: builtin
	reduce: true
	ignore_nan_grad: null
	zero_infinity: true
	joint_net_conf: null
	use_preprocessor: true
	token_type: bpe
	bpemodel: data/en_token_list/bpe_unigram1000/bpe.model
	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
	aux_ctc_tasks: []
	frontend: null
	frontend_conf: {}
	specaug: null
	specaug_conf: {}
	normalize: global_mvn
	normalize_conf:
	stats_file: exp/asr_stats_extracted_en_bpe1000/train/feats_stats.npz
	model: espnet
	model_conf:
	ctc_weight: 0.3
	lsm_weight: 0.1
	length_normalized_loss: false
	preencoder: null
	preencoder_conf: {}
	encoder: avhubert
	encoder_conf:
	avhubert_url: https://dl.fbaipublicfiles.com/avhubert/model/lrs3_vox/noise-pretrain/large_vox_iter5.pt
	avhubert_dir_path: ./local/pre-trained
	encoder_embed_dim: 1024
	encoder_attention_heads: 16
	encoder_ffn_embed_dim: 4096
	encoder_layers: 24
	dropout: 0.1
	dropout_features: 0.1
	encoder_layerdrop: 0.05
	attention_dropout: 0.1
	extracted: true
	freeze_finetune_updates: 10000
	feature_grad_mult: 1.0
	postencoder: null
	postencoder_conf: {}
	decoder: transformer
	decoder_conf:
	attention_heads: 4
	linear_units: 4096
	num_blocks: 6
	dropout_rate: 0.1
	positional_dropout_rate: 0.1
	self_attention_dropout_rate: 0.1
	src_attention_dropout_rate: 0.1
	preprocessor: default
	preprocessor_conf: {}
	required:
	- output_dir
	- token_list
	version: '202308'
	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}
	}
	```