balaji1312
/

jibo_kids_wavlm_aed_transformer

Automatic Speech Recognition

ESPnet

English

audio

Model card Files Files and versions Community

balaji1312 commited on Jan 30

Commit

7f5d7b4

1 Parent(s): a6dd6b8

Update model

Browse files

Files changed (1) hide show

README.md +1390 -2

README.md CHANGED Viewed

@@ -1,2 +1,1390 @@
-# balaji1312/asr_train_asr_wavlm_transformer_raw_en_bpe1024_valid.acc.best
-This model was uploaded to Hugging Face by balaji1312.

+---
+tags:
+- espnet
+- audio
+- automatic-speech-recognition
+language:
+datasets:
+-
+license: cc-by-4.0
+---
+## ESPnet2 ASR model
+### `balaji1312/jibo_kids_wavlm_aed_transformer`
+This model was trained by  using  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/jibo_kids/asr1
+./run.sh --skip_data_prep false --skip_train true --download_model balaji1312/jibo_kids_wavlm_aed_transformer
+```
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Thu Jan 30 06:18:01 EST 2025`
+- python version: `3.9.19 (main, May  6 2024, 19:43:03)  [GCC 11.2.0]`
+- espnet version: `espnet 202402`
+- pytorch version: `pytorch 2.4.0`
+- Git hash: `c46aa9a594ff83d52cbf61d84c5650325d1ce527`
+  - Commit date: `Sun Oct 13 14:39:31 2024 -0400`
+## exp/asr_train_asr_wavlm_transformer_raw_en_bpe1024
+### WER
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_asr_model_valid.acc.ave/test|1044|3686|34.9|41.4|23.7|20.9|86.0|60.2|
+|decode_asr_asr_model_valid.acc.best/test|1044|3686|56.1|31.4|12.5|8.1|52.0|62.3|
+### CER
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_asr_model_valid.acc.ave/test|1044|16215|54.8|17.3|28.0|25.5|70.7|60.2|
+|decode_asr_asr_model_valid.acc.best/test|1044|16215|75.4|8.1|16.6|9.4|34.1|62.3|
+### TER
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_asr_model_valid.acc.ave/test|1044|5220|45.9|29.6|24.5|21.3|75.4|60.2|
+|decode_asr_asr_model_valid.acc.best/test|1044|5220|64.5|18.0|17.5|10.4|45.9|62.3|
+## exp/asr_train_asr_wavlm_transformer_raw_en_bpe1024/decode_asr_asr_model_valid.acc.best
+### WER
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|org/dev|853|2372|59.8|31.2|8.9|7.2|47.3|64.0|
+### CER
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|org/dev|853|9855|78.3|7.3|14.3|8.4|30.1|64.0|
+### TER
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|org/dev|853|3590|68.2|16.2|15.6|6.4|38.3|64.0|
+## exp/asr_train_asr_wavlm_transformer_raw_en_bpe1024/decode_asr_asr_model_valid.acc.ave
+### WER
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|org/dev|853|2372|39.9|39.2|21.0|15.8|75.9|60.3|
+### CER
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|org/dev|853|9855|56.7|15.4|27.9|19.1|62.4|60.3|
+### TER
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|org/dev|853|3590|51.5|25.8|22.7|13.6|62.1|60.3|
+## ASR config
+<details><summary>expand</summary>
+```
+config: conf/tuning/train_asr_wavlm_transformer.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_asr_wavlm_transformer_raw_en_bpe1024
+ngpu: 1
+seed: 2022
+num_workers: 4
+num_att_plot: 0
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: null
+dist_rank: null
+local_rank: 0
+dist_master_addr: null
+dist_master_port: null
+dist_launcher: null
+multiprocessing_distributed: false
+unused_parameters: false
+sharded_ddp: false
+use_deepspeed: false
+deepspeed_config: null
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: false
+use_tf32: false
+collect_stats: false
+write_collected_feats: false
+max_epoch: 100
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - acc
+    - max
+keep_nbest_models: 4
+nbest_averaging_interval: 0
+grad_clip: 5.0
+grad_clip_type: 2.0
+grad_noise: false
+accum_grad: 4
+no_forward_run: false
+resume: true
+train_dtype: float32
+use_amp: true
+log_interval: 400
+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_adapter: false
+adapter: lora
+save_strategy: all
+adapter_conf: {}
+pretrain_path: null
+init_param: []
+ignore_init_mismatch: false
+freeze_param:
+- frontend.upstream
+num_iters_per_epoch: null
+batch_size: 20
+valid_batch_size: null
+batch_bins: 1200000
+valid_batch_bins: null
+category_sample_size: 10
+train_shape_file:
+- exp/asr_stats_raw_en_bpe1024/train/speech_shape
+- exp/asr_stats_raw_en_bpe1024/train/text_shape.bpe
+valid_shape_file:
+- exp/asr_stats_raw_en_bpe1024/valid/speech_shape
+- exp/asr_stats_raw_en_bpe1024/valid/text_shape.bpe
+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
+chunk_max_abs_length: null
+chunk_discard_short_samples: true
+train_data_path_and_name_and_type:
+-   - dump/raw/train/wav.scp
+    - speech
+    - sound
+-   - dump/raw/train/text
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - dump/raw/dev/wav.scp
+    - speech
+    - sound
+-   - dump/raw/dev/text
+    - text
+    - text
+multi_task_dataset: false
+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: 0.002
+    weight_decay: 1.0e-06
+scheduler: warmuplr
+scheduler_conf:
+    warmup_steps: 15000
+token_list:
+- <blank>
+- <unk>
+- .
+- ▁I
+- ▁AND
+- ''''
+- ▁A
+- ▁YOU
+- S
+- ▁IT
+- T
+- ▁TO
+- ▁THE
+- ▁LIKE
+- ▁THAT
+- ▁NO
+- ▁BECAUSE
+- ▁ONE
+- ▁THEN
+- ▁DON
+- ▁TEETH
+- ▁TWO
+- ▁FIVE
+- ▁KNOW
+- ▁MY
+- ▁SO
+- ▁YOUR
+- ▁IS
+- ▁THEM
+- ▁DO
+- ▁SIX
+- ▁THREE
+- ▁G
+- ▁U
+- ▁TEN
+- ▁FOUR
+- ▁GET
+- ▁O
+- ▁K
+- ▁B
+- ▁L
+- ▁N
+- ▁S
+- ▁E
+- ▁M
+- ▁BRUSH
+- ▁THIS
+- ▁T
+- ▁CAN
+- ▁SEVEN
+- ▁EIGHT
+- ▁C
+- ▁HAVE
+- ▁PUT
+- ▁MAKE
+- ▁W
+- ▁J
+- ▁F
+- ▁IN
+- ▁P
+- ▁NINE
+- ▁Y
+- ▁D
+- ▁V
+- ▁OKAY
+- ▁Q
+- ▁Z
+- ▁ZERO
+- ▁IF
+- ▁H
+- ▁WHAT
+- ▁COUNT
+- ING
+- ▁R
+- ▁X
+- ▁OF
+- ▁HOW
+- ▁
+- ▁WANT
+- ▁COLOR
+- ▁JUST
+- ▁WITH
+- ▁ON
+- N
+- ▁AN
+- ▁MIX
+- ▁COLORS
+- ▁THEY
+- ▁YEAH
+- ▁YES
+- ▁UP
+- ▁BLUE
+- ▁BY
+- ▁GO
+- M
+- ▁THERE
+- ▁ALL
+- ▁OR
+- ▁CLEAN
+- ED
+- ▁SEE
+- ▁BUT
+- ▁USE
+- ▁FOR
+- ▁BE
+- ▁TOOTHPASTE
+- ▁WAS
+- ▁UM
+- ▁LETTER
+- ▁NEED
+- ▁HE
+- ▁WILL
+- ▁PLUS
+- ▁DOG
+- ▁RED
+- RE
+- ▁PURPLE
+- ▁NOT
+- ▁CAVITIES
+- ▁OH
+- ▁ARE
+- ▁THINK
+- ▁WHY
+- ▁SHE
+- ▁DID
+- ▁HAT
+- Y
+- ▁PAINT
+- ▁BRUSHING
+- ▁BOX
+- ▁TOOTHBRUSH
+- ▁SICK
+- ▁OUT
+- ▁ME
+- ▁JUG
+- ▁DOES
+- ▁FLU
+- ▁MAKES
+- ▁WIG
+- ▁SH
+- ▁MAN
+- ▁WE
+- ▁MORE
+- OULD
+- ▁PLAY
+- ▁SOME
+- ▁JIBO
+- ▁GREEN
+- ▁VAN
+- ▁NUMBER
+- ▁YELLOW
+- ▁REALLY
+- D
+- ▁WHITE
+- ▁PINK
+- ▁WATER
+- ▁QUIZ
+- ▁NOW
+- ▁UH
+- ▁DIFFERENT
+- ▁RIGHT
+- IND
+- ▁SAY
+- ▁TREE
+- LL
+- CH
+- ▁HELP
+- ▁HUNDRED
+- ▁LOOK
+- ▁COULD
+- ▁COUNTING
+- ▁WAY
+- ▁MAYBE
+- ▁EASY
+- ▁WOULD
+- ▁BLACK
+- ▁TAKE
+- ▁HER
+- ▁LI
+- E
+- TTLE
+- F
+- ▁AL
+- ▁THING
+- ▁ELSE
+- ▁WELL
+- LY
+- ▁TOGETHER
+- ▁WHEN
+- ▁SIDE
+- ▁CAVITY
+- ▁FIRST
+- ▁DOWN
+- ▁DAY
+- ▁OTHER
+- ▁HERE
+- ▁CUBES
+- ▁COUNTED
+- ▁EVERY
+- ▁SA
+- ▁TELL
+- ▁DAD
+- ▁ORANGE
+- ▁SAME
+- ▁SOMETIMES
+- ▁MANY
+- OTHER
+- ID
+- ▁WON
+- ▁BIT
+- ▁HI
+- ▁TOO
+- ▁TIME
+- UH
+- ▁WAIT
+- ▁NOTHING
+- ▁FALL
+- ▁NAME
+- ▁LOT
+- ▁THAN
+- ▁EH
+- ▁MEAN
+- ▁NEW
+- W
+- H
+- ▁TOOTH
+- ER
+- ▁FLOSS
+- ▁START
+- ▁BROWN
+- ▁STACK
+- ▁NOPE
+- ▁GOOD
+- A
+- L
+- ▁LET
+- ▁WHI
+- O
+- ▁ALREADY
+- ▁INAUDIBLE
+- ▁MOUTH
+- ▁EAT
+- ▁HAS
+- ▁DONE
+- ▁THOSE
+- ▁BETTER
+- ▁FUN
+- ▁GERMS
+- TO
+- ▁UMM
+- CK
+- SO
+- EVEN
+- ▁WASH
+- ▁ACTUALLY
+- ▁DRINK
+- ▁FRIEND
+- ▁REMEMBER
+- ▁SUGAR
+- ▁SOMETHING
+- ▁HARD
+- ▁COME
+- ▁PAINTING
+- ▁SPI
+- ▁AT
+- I
+- TER
+- ▁MUCH
+- ▁GUESS
+- ▁HIM
+- ▁HA
+- IGHT
+- Z
+- ▁FRO
+- ▁IMPORTANT
+- ▁AGAIN
+- ▁STUFF
+- ▁BACK
+- ▁BUGS
+- ▁NIGHT
+- ▁ADD
+- G
+- ▁EA
+- HIS
+- K
+- EVER
+- ▁TH
+- ▁DARK
+- ▁FORGOT
+- ▁MOM
+- BODY
+- ▁UHHUH
+- ▁BAD
+- ▁TURN
+- ▁ANY
+- AH
+- EL
+- U
+- AKING
+- VERY
+- ▁GONNA
+- ▁FOUAH
+- ▁SURE
+- ▁PULL
+- ▁LONG
+- ▁KEEP
+- ES
+- P
+- ▁WAYS
+- TING
+- ALLY
+- VE
+- ONE
+- ▁QUESTION
+- ▁PAPER
+- ▁STU
+- YTHING
+- ▁SHOW
+- ▁CALLED
+- ▁LOVE
+- ▁MM
+- ▁TRY
+- ▁BYE
+- ▁TOP
+- LD
+- ▁MMM
+- ▁PE
+- ▁NUMBERS
+- BLE
+- PLE
+- ▁CUBE
+- OUT
+- R
+- ▁BOTTOM
+- ▁FAVORITE
+- ▁SPANISH
+- ▁TONGUE
+- ▁SCHOOL
+- ▁TWENTY
+- ▁MHM
+- ▁FRONT
+- ▁STAY
+- ▁SPELL
+- ▁TEEF
+- ▁LAST
+- ▁GUM
+- ▁HOLD
+- TY
+- ▁GROUPS
+- ▁OFF
+- ▁EQUALS
+- ▁FINGERS
+- ▁QUI
+- RAB
+- ▁MEANS
+- AW
+- ▁UHH
+- IT
+- WEE
+- ▁CH
+- ▁AM
+- ▁SI
+- RY
+- SIX
+- ▁WI
+- ▁BEAUTIFUL
+- ▁DENTIST
+- ▁HEALTHY
+- ▁HURT
+- ▁ZEWO
+- ▁KNEW
+- ▁MATH
+- ▁BOY
+- ▁HOLE
+- ▁DIRTY
+- ▁YET
+- ▁EX
+- ▁STARTED
+- ▁LIGHT
+- ▁THESE
+- ▁CU
+- B
+- ▁THINGS
+- ▁GRA
+- ▁WHO
+- ▁TWOS
+- ▁CIRCLE
+- ▁YO
+- ▁FINGER
+- ▁BA
+- CE
+- OTH
+- X
+- IR
+- MOST
+- ▁LEARN
+- FIVE
+- CI
+- ▁ANSWER
+- ▁EASIER
+- ▁LAUGHS
+- ▁MORNING
+- ▁MOUTHWASH
+- ▁PICTURE
+- ▁RINSE
+- ▁FORGET
+- ▁SISTER
+- ▁THOUGH
+- ▁TALKING
+- ▁GROW
+- ▁WHERE
+- ▁MINUTES
+- ▁SUP
+- ▁WISH
+- ▁OUR
+- ▁STI
+- ▁FLOSSING
+- SIC
+- EPT
+- ▁BIG
+- PER
+- ▁AH
+- TH
+- TEN
+- EN
+- ▁FAI
+- ▁ONES
+- ▁EQUAL
+- ▁SP
+- KAY
+- SIDE
+- WAYS
+- ▁AROUND
+- ▁PRETTY
+- ▁RAINBOW
+- ▁VIOLET
+- ▁LEFT
+- ▁GIRL
+- ▁SENSE
+- ▁SOUND
+- ▁EYES
+- ▁EVERYTHING
+- ▁GUY
+- ▁SHINY
+- ▁ELEVEN
+- ▁READY
+- ▁STICK
+- ▁FROG
+- ▁FOOD
+- ▁KEY
+- DE
+- ▁PL
+- ▁PART
+- OVE
+- ▁PR
+- ▁ROT
+- ▁TEE
+- ▁WERE
+- VER
+- ▁DIS
+- ▁HEY
+- USH
+- OH
+- IN
+- ISH
+- OVER
+- EEN
+- ▁MIND
+- ▁AB
+- SE
+- SH
+- DENTAL
+- OOL
+- ET
+- AR
+- ICK
+- NA
+- ENT
+- ▁BU
+- AT
+- UNTI
+- OW
+- OK
+- ▁EL
+- ▁MA
+- ▁QU
+- ▁WOR
+- ▁SIN
+- AKE
+- AND
+- ▁PRETEND
+- ▁BUS
+- ▁PLA
+- ▁CALL
+- ▁ONETWOTHREEFOUR
+- ▁CLASS
+- ▁CONNECT
+- ▁DISCOVER
+- ▁HOUSE
+- ▁RABBIT
+- ▁SQUEEZE
+- ▁THOUSAND
+- ▁ROBOT
+- ▁SCRUB
+- ▁SMELL
+- EXT
+- ▁BROTHER
+- ▁PILE
+- ▁BOTTLE
+- ▁PAINTBRUSH
+- IMA
+- ▁CROCODILE
+- ▁JUMP
+- ▁CANNOT
+- ▁TWICE
+- ▁STOP
+- UNCH
+- ▁SKIN
+- ▁TUR
+- ▁MOVING
+- IES
+- ▁FAST
+- ▁PRETENDING
+- EEP
+- ▁SHAKING
+- ▁MAY
+- ▁FAKE
+- ▁AWAY
+- ▁DI
+- ▁HAPP
+- ▁DUH
+- OO
+- ▁JUH
+- LE
+- ▁HUH
+- ▁BUH
+- BOOK
+- WENT
+- ▁CA
+- OSE
+- EM
+- IC
+- AG
+- ▁LETTERS
+- IS
+- EW
+- ONG
+- V
+- AL
+- PAY
+- REE
+- EE
+- ▁TIMES
+- ▁SPIN
+- UR
+- CU
+- GER
+- ▁TR
+- ▁AW
+- UGH
+- UT
+- ▁BL
+- ▁SL
+- ▁FORT
+- ▁GE
+- EA
+- ▁TA
+- GU
+- ▁FINISH
+- ▁UN
+- READ
+- THER
+- DAY
+- ▁BLA
+- ▁ARTIST
+- ▁BACKWARDS
+- ▁DOCTOR
+- ▁DREAMS
+- ▁EXPLA
+- ▁MIDDLE
+- ▁MOUSE
+- ▁PROB
+- ▁RINSING
+- ▁STRAIGHT
+- ▁SUNFLOWER
+- ▁TOOTHPICK
+- ▁TWELVE
+- ▁VULTURE
+- ▁CONFUS
+- TION
+- ▁HOME
+- ▁OPEN
+- ▁SORRY
+- ▁BORING
+- ▁MINE
+- ▁ENOUGH
+- ▁HELLO
+- ▁BORED
+- RITE
+- ▁TOWER
+- ▁BUIL
+- ▁ODD
+- ▁UNP
+- ▁APPLY
+- ▁ANYMORE
+- ▁FOUW
+- APE
+- OUNT
+- ▁FIFT
+- ▁ZEBRA
+- ▁LION
+- ▁BLAH
+- ▁BLOCK
+- ▁COP
+- ▁HMM
+- ▁ASK
+- ▁BAB
+- ▁DARKER
+- ▁HEAR
+- ▁CHO
+- ▁CLOSE
+- ▁JACK
+- ▁FULL
+- ▁CUP
+- ▁WHE
+- ▁IDEA
+- ▁PIRATES
+- ▁SPE
+- ▁HEAD
+- ▁GIVE
+- ▁END
+- DER
+- ▁HAND
+- ▁BOXES
+- ▁BEST
+- ▁LEARNING
+- ▁MESS
+- ▁MOST
+- ▁FLA
+- LIT
+- ▁AC
+- ▁AHW
+- ▁FUH
+- ▁LU
+- ▁SSS
+- OWN
+- ▁PUH
+- ▁PW
+- POS
+- ▁CIRCLES
+- ENS
+- LK
+- ▁PLAYING
+- AIL
+- AP
+- PIT
+- NG
+- ▁LETTU
+- IK
+- DDING
+- HH
+- PPER
+- ▁GW
+- ABL
+- OL
+- ▁KID
+- DING
+- ▁KA
+- ERS
+- ▁FI
+- LIP
+- ▁SE
+- ▁TREES
+- UN
+- ▁RO
+- ATE
+- ND
+- ▁FO
+- ICE
+- IF
+- HW
+- AY
+- ▁BIGGE
+- UST
+- ▁DE
+- ▁KI
+- ▁LOS
+- ▁THA
+- ▁PAN
+- IL
+- MB
+- ▁BOO
+- SPE
+- 'NO'
+- ACK
+- ▁FIN
+- C
+- ▁GROUP
+- ▁GERM
+- EAD
+- ▁SOMETIME
+- LZ
+- IVE
+- UP
+- TWO
+- HIRT
+- HRO
+- JELLYFISH
+- ▁PAR
+- PART
+- IBO
+- WHAT
+- KEY
+- FOUR
+- AME
+- ANGE
+- EC
+- TIME
+- ▁REAL
+- ELEPHANT
+- ▁BATHROOM
+- ▁BIVY
+- ▁BRACES
+- ▁FLOWER
+- ▁GARFIELD
+- ▁GARGLE
+- ▁KOALA
+- ▁PROBLEMS
+- ▁SEVENEIGHTNINE
+- ▁STINKY
+- ▁SWORD
+- ▁UPPERCASE
+- EMBER
+- FUL
+- ▁SEPARAT
+- ▁BEFORE
+- ▁BROKE
+- ▁LOUD
+- ▁MONSTER
+- ▁MOUF
+- ▁POOP
+- ▁SHINNY
+- ▁DRAW
+- ▁MAILBOX
+- ▁HUNGRY
+- ▁BREAK
+- ▁SARA
+- ▁JOB
+- ▁WATCH
+- ▁SPARKL
+- ▁SHORT
+- ▁WEEK
+- ▁BIRD
+- ▁MOMMY
+- ▁LOOSE
+- ▁GREAT
+- ▁PRETTIER
+- ▁SMIL
+- ▁FACE
+- ▁HAV
+- ▁PIECE
+- ▁FUNNY
+- ▁UNDER
+- ▁SLOWER
+- ACT
+- ▁PLEA
+- ▁VEHA
+- ▁PEAR
+- ▁FEEL
+- ▁SPIDER
+- ▁WORSE
+- ▁SWI
+- ▁AYE
+- UNU
+- ▁EVER
+- ▁HOPE
+- ▁SIGN
+- AK
+- UIZ
+- ▁SOFT
+- ▁POP
+- ▁TEEH
+- ▁DEH
+- IBLE
+- ▁SIDEWAYS
+- ROT
+- ▁ORDER
+- ▁FINISHED
+- ▁JELLYFISH
+- ▁FELL
+- KEU
+- ▁IMPO
+- HEAD
+- UM
+- ▁PRESS
+- ▁SECONDS
+- ▁LEA
+- ▁MOLD
+- LLUH
+- ▁READ
+- ▁ONETWO
+- ▁LINE
+- FE
+- ▁FOH
+- ▁HOT
+- ▁FOU
+- ▁MOH
+- ▁DEN
+- ▁WIN
+- ▁NINETY
+- IRTY
+- ▁TWEE
+- OUR
+- IRED
+- TLE
+- ▁HEH
+- ▁JU
+- PASTE
+- ▁FEVER
+- ▁WR
+- ▁PAI
+- MINT
+- TEEN
+- ▁WASHING
+- ▁BI
+- ▁NAH
+- DY
+- ▁RA
+- ▁DA
+- AHW
+- ▁YUH
+- ULL
+- ▁WL
+- UHTY
+- ▁SHO
+- ▁CUH
+- ASTE
+- OOD
+- ▁LAM
+- ▁CI
+- OLD
+- UNN
+- NUH
+- OCK
+- US
+- ▁SM
+- MPLE
+- ▁HIT
+- ▁THRO
+- ▁DEU
+- HOLE
+- ▁THINKING
+- UBB
+- ▁FU
+- ▁PI
+- ▁SMO
+- ▁VO
+- AN
+- UG
+- ▁HM
+- UE
+- GLE
+- ▁MOV
+- LI
+- ▁BLU
+- PORT
+- ▁WED
+- ▁TRI
+- ▁CHE
+- CA
+- ▁SC
+- ▁STO
+- ▁BED
+- ▁TELLS
+- ▁MI
+- OR
+- TTER
+- NES
+- OUGH
+- ▁AR
+- ROW
+- UA
+- AB
+- IG
+- OF
+- MAN
+- RK
+- OUN
+- ROUGH
+- LUH
+- DENT
+- ▁PIE
+- LAP
+- KUH
+- OT
+- RSE
+- ▁LA
+- ▁PAST
+- ▁ANOTH
+- OP
+- EP
+- ▁LATE
+- AM
+- LU
+- ▁WOO
+- HUH
+- ▁CER
+- OU
+- IPP
+- ▁CO
+- EH
+- TE
+- WHERE
+- ASH
+- PPY
+- WAY
+- RO
+- SHE
+- OST
+- AIN
+- ▁SECOND
+- ▁PIRATE
+- ▁MINUTE
+- ABET
+- ▁DIFFEREN
+- BE
+- IGH
+- ▁COO
+- ▁WHA
+- BRUSH
+- TRA
+- ▁PRES
+- ▁TRYIN
+- ▁GIV
+- OPE
+- SHIN
+- STRO
+- SIGN
+- ▁PLU
+- ZEBRA
+- LION
+- CROCODILE
+- LATE
+- UF
+- EQUALS
+- COME
+- UBE
+- J
+- TOGETHER
+- MAYBE
+- BOX
+- CLEAN
+- THEY
+- JIBO
+- EASY
+- MOUTH
+- ▁TALK
+- ▁SKI
+- WHY
+- WICE
+- CAUSE
+- UMP
+- TRIC
+- ▁CLOS
+- ▁SEVE
+- ▁DIRT
+- ▁NUMB
+- YOU
+- PRI
+- ▁JIB
+- ETTIER
+- FFERENT
+- ERCASE
+- ROOM
+- ▁DIFF
+- ▁JELLY
+- ▁SEVENEIGHT
+- ORGE
+- ▁YELL
+- DRA
+- ▁SLOW
+- ▁MON
+- ▁BUG
+- YPE
+- ▁BRU
+- COL
+- PUS
+- WO
+- INET
+- NGRY
+- BRUSHING
+- ▁CUB
+- OCTO
+- HIC
+- UDE
+- RUB
+- MOR
+- LOCK
+- ▁BR
+- YOUR
+- ▁STR
+- ▁KNE
+- ▁CRO
+- ▁BO
+- UALLY
+- ▁TOOTHB
+- ▁ANYMO
+- UKU
+- ▁GUE
+- MA
+- ENTY
+- PHA
+- ▁QUE
+- PF
+- KE
+- NOW
+- ▁LAS
+- ▁SHIN
+- ARN
+- GE
+- ▁MAIL
+- RUSHING
+- Q
+- <sos/eos>
+init: null
+input_size: null
+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
+use_lang_prompt: false
+use_nlp_prompt: false
+token_type: bpe
+bpemodel: data/en_token_list/bpe_unigram1024/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: s3prl
+frontend_conf:
+    frontend_conf:
+        upstream: wavlm_large
+    download_dir: ./hub
+    multilayer_feature: true
+    fs: 16k
+specaug: specaug
+specaug_conf:
+    apply_time_warp: true
+    time_warp_window: 5
+    time_warp_mode: bicubic
+    apply_freq_mask: true
+    freq_mask_width_range:
+    - 0
+    - 27
+    num_freq_mask: 2
+    apply_time_mask: true
+    time_mask_width_ratio_range:
+    - 0.0
+    - 0.05
+    num_time_mask: 5
+normalize: utterance_mvn
+normalize_conf: {}
+model: espnet
+model_conf:
+    ctc_weight: 0.3
+    lsm_weight: 0.1
+    length_normalized_loss: false
+    extract_feats_in_collect_stats: false
+preencoder: linear
+preencoder_conf:
+    input_size: 1024
+    output_size: 80
+encoder: transformer
+encoder_conf:
+    output_size: 256
+    attention_heads: 4
+    linear_units: 1024
+    num_blocks: 18
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.1
+    input_layer: conv2d2
+    normalize_before: true
+postencoder: null
+postencoder_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
+preprocessor: default
+preprocessor_conf: {}
+required:
+- output_dir
+- token_list
+version: '202402'
+distributed: false
+```
+</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}
+}
+```