Update model

README.md

@@ -1,3 +1,1296 @@
----
-license: apache-2.0
----
+---
+tags:
+- espnet
+- audio
+- automatic-speech-summarization
+language: en
+datasets:
+- how2
+license: cc-by-4.0
+---
+
+## ESPnet2 ASR model 
+
+### `espnet/roshansh_how2_asr_raw_ft_sum_valid.acc`
+
+This model was trained by roshansh-cmu using how2 recipe in [espnet](https://github.com/espnet/espnet/).
+
+### Demo: How to use in ESPnet2
+
+```bash
+cd espnet
+git checkout e6f42a9783a5d9eba0687c19417f933e890722d7
+pip install -e .
+cd egs2/how2/sum1
+./run.sh --skip_data_prep false --skip_train true --download_model espnet/roshansh_how2_asr_raw_ft_sum_valid.acc
+```
+
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Mon Feb  7 15:24:21 EST 2022`
+- python version: `3.8.12 (default, Oct 12 2021, 13:49:34)  [GCC 7.5.0]`
+- espnet version: `espnet 0.10.6a1`
+- pytorch version: `pytorch 1.10.1`
+- Git hash: `04561cdf3b6c3bc1d51edb04c93b953759ef551d`
+  - Commit date: `Mon Feb 7 09:06:12 2022 -0500`
+
+## asr_raw_ft_sum
+|dataset|ROUGE-1|ROUGE-2|ROUGE-L|METEOR|BERTScore|
+|---|---|---|---|---|---|
+
+## ASR config
+
+<details><summary>expand</summary>
+
+```
+config: conf/train_asr_conformer_vid_lf.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/asr_raw_ft_sum
+ngpu: 1
+seed: 0
+num_workers: 1
+num_att_plot: 3
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: 8
+dist_rank: 0
+local_rank: 0
+dist_master_addr: localhost
+dist_master_port: 45875
+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: 100
+patience: 10
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - acc
+    - max
+keep_nbest_models: 10
+grad_clip: 5.0
+grad_clip_type: 2.0
+grad_noise: false
+accum_grad: 10
+no_forward_run: false
+resume: true
+train_dtype: float32
+use_amp: false
+log_interval: 5000
+use_tensorboard: true
+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:
+- exp/asr_raw_utt_conformer/valid.acc.ave_10best.pth:::ctc
+ignore_init_mismatch: false
+freeze_param: []
+num_iters_per_epoch: null
+batch_size: 20
+valid_batch_size: null
+batch_bins: 60000000
+valid_batch_bins: null
+train_shape_file:
+- exp/asr_stats_raw_vid_sum/train/speech_shape
+- exp/asr_stats_raw_vid_sum/train/text_shape.bpe
+valid_shape_file:
+- exp/asr_stats_raw_vid_sum/valid/speech_shape
+- exp/asr_stats_raw_vid_sum/valid/text_shape.bpe
+batch_type: length
+valid_batch_type: null
+fold_length:
+- 80000
+- 150
+sort_in_batch: descending
+sort_batch: descending
+multiple_iterator: false
+chunk_length: 500
+chunk_shift_ratio: 0.5
+num_cache_chunks: 1024
+train_data_path_and_name_and_type:
+-   - dump/raw/tr_2000h_sum_trim/wav.scp
+    - speech
+    - sound
+-   - dump/raw/tr_2000h_sum_trim/text
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - dump/raw/cv05_sum_trim/wav.scp
+    - speech
+    - sound
+-   - dump/raw/cv05_sum_trim/text
+    - text
+    - text
+allow_variable_data_keys: false
+max_cache_size: 0.0
+max_cache_fd: 32
+valid_max_cache_size: null
+optim: adam
+optim_conf:
+    lr: 0.001
+scheduler: reducelronplateau
+scheduler_conf:
+    mode: min
+    factor: 0.5
+    patience: 1
+token_list:
+- <blank>
+- <unk>
+- '[hes]'
+- S
+- ▁THE
+- ▁TO
+- ''''
+- ▁AND
+- ▁YOU
+- ▁A
+- ▁IT
+- T
+- ▁THAT
+- ▁OF
+- ▁I
+- ▁IS
+- RE
+- ▁IN
+- ING
+- ▁WE
+- M
+- ▁GOING
+- ▁SO
+- ▁THIS
+- ▁YOUR
+- ▁ON
+- E
+- D
+- ▁BE
+- ▁CAN
+- N
+- Y
+- O
+- ER
+- ▁HAVE
+- ▁JUST
+- ▁FOR
+- ▁WITH
+- ▁DO
+- ED
+- ▁ARE
+- ▁WANT
+- ▁UP
+- R
+- LL
+- P
+- ▁
+- L
+- B
+- ▁IF
+- C
+- ▁ONE
+- ▁S
+- ▁OR
+- A
+- ▁GO
+- ▁LIKE
+- ▁NOW
+- ▁HERE
+- VE
+- LE
+- U
+- ▁GET
+- ▁WHAT
+- ▁OUT
+- IN
+- W
+- ▁C
+- ▁LITTLE
+- ▁THERE
+- LY
+- ▁AS
+- ▁MAKE
+- I
+- ▁THEY
+- ▁MY
+- K
+- ▁THEN
+- ▁BUT
+- AL
+- G
+- ▁ALL
+- OR
+- ▁BACK
+- ▁NOT
+- ▁ABOUT
+- ▁RIGHT
+- ▁OUR
+- EN
+- ▁SOME
+- ▁DOWN
+- F
+- ▁WHEN
+- CH
+- ▁F
+- ▁HOW
+- AR
+- ▁WILL
+- ▁RE
+- CK
+- ▁G
+- ES
+- CE
+- ▁TAKE
+- ▁AT
+- ▁FROM
+- ▁WAY
+- TER
+- ▁SEE
+- RA
+- ▁USE
+- ▁REALLY
+- RI
+- TH
+- ▁TWO
+- ▁ME
+- ▁VERY
+- ▁E
+- ▁B
+- AT
+- ▁THEM
+- ▁DON
+- ▁AN
+- ▁BECAUSE
+- ▁MORE
+- RO
+- H
+- 'ON'
+- LI
+- ▁PUT
+- ▁ST
+- IL
+- ▁BIT
+- ▁START
+- ▁NEED
+- ▁INTO
+- UR
+- ▁TIME
+- ▁OVER
+- ▁W
+- ▁DE
+- ▁LOOK
+- ▁THESE
+- ▁LET
+- ▁GOOD
+- ▁ALSO
+- AN
+- ▁OFF
+- ▁HE
+- ▁KIND
+- ▁SIDE
+- ▁CO
+- ▁SURE
+- ▁AGAIN
+- ▁MA
+- ▁KNOW
+- IT
+- ▁WOULD
+- IC
+- ▁OTHER
+- LA
+- ▁P
+- ▁WHICH
+- '-'
+- IR
+- ▁LA
+- ▁HAND
+- EL
+- ▁LOT
+- ▁WHERE
+- ▁THREE
+- ▁PA
+- ION
+- LO
+- ▁KEEP
+- ▁SHOW
+- ▁THING
+- ▁FIRST
+- TE
+- ENT
+- ATE
+- ▁COME
+- AD
+- ▁GOT
+- NG
+- ▁NICE
+- ▁T
+- ET
+- ▁MO
+- ▁ANY
+- ▁ACTUALLY
+- ▁DIFFERENT
+- ▁SE
+- GE
+- ▁WORK
+- ▁THROUGH
+- ▁O
+- KE
+- V
+- ▁AROUND
+- ▁BA
+- PE
+- ▁HI
+- ▁BY
+- SH
+- ATION
+- ▁SU
+- ▁CA
+- ▁D
+- ▁LO
+- ▁HAS
+- ▁LI
+- ▁PLAY
+- Z
+- ▁ADD
+- ▁RO
+- ▁TA
+- AS
+- ▁FOUR
+- ▁CON
+- ▁THOSE
+- MP
+- NE
+- ▁SP
+- UT
+- ▁GIVE
+- ▁WELL
+- ▁BALL
+- TING
+- RY
+- X
+- ▁HO
+- INE
+- IVE
+- ▁NEXT
+- ▁PO
+- ▁STEP
+- ▁EVEN
+- TION
+- ▁MI
+- MENT
+- ▁CUT
+- ▁BO
+- ▁LINE
+- ▁MUCH
+- ▁THINGS
+- ▁TALK
+- UN
+- ▁PART
+- ▁WAS
+- ▁FA
+- ▁SOMETHING
+- PP
+- ANCE
+- ND
+- DI
+- ▁RA
+- AGE
+- ▁SAME
+- ▁EXPERT
+- ▁DOING
+- ▁LEFT
+- IST
+- ▁DI
+- ▁NO
+- RU
+- ME
+- TA
+- UL
+- TI
+- ▁VILLAGE
+- DE
+- ERS
+- ▁PEOPLE
+- ▁TURN
+- VER
+- ▁FL
+- ▁LEG
+- ▁ONCE
+- ▁COLOR
+- ▁PULL
+- ▁USING
+- VI
+- ▁WATER
+- ▁SHE
+- ▁TOP
+- ▁OKAY
+- ▁ANOTHER
+- ▁THEIR
+- ▁SAY
+- URE
+- ▁HA
+- ▁IMPORTANT
+- ▁PIECE
+- ▁FOOT
+- ▁TRA
+- ▁SC
+- ▁BODY
+- ▁SET
+- ▁POINT
+- ▁HELP
+- ▁TODAY
+- ▁BRING
+- ▁V
+- ▁END
+- MA
+- ▁CH
+- ▁MOST
+- ▁K
+- ▁AHEAD
+- ▁HER
+- OL
+- ▁SA
+- AM
+- IES
+- ▁THINK
+- ▁NAME
+- ▁TRY
+- ▁MOVE
+- ONE
+- ▁LE
+- ▁TOO
+- TO
+- UM
+- ▁PLACE
+- ▁COULD
+- ▁FIND
+- ▁FIVE
+- ▁ALWAYS
+- ID
+- TY
+- NT
+- ▁FEEL
+- ▁HEAD
+- ▁THAN
+- NA
+- ▁EX
+- ▁EYE
+- ITY
+- CI
+- OP
+- ▁SHOULD
+- ▁MIGHT
+- ▁HOLD
+- ▁CAR
+- AND
+- ▁GREAT
+- ▁RI
+- ▁BU
+- ▁HIGH
+- ▁OPEN
+- ▁BEFORE
+- US
+- ▁FRONT
+- ▁LONG
+- ▁TOGETHER
+- NI
+- ▁HAIR
+- ▁LIGHT
+- ▁TEN
+- ▁HIT
+- EST
+- OUS
+- ▁PRETTY
+- ▁TYPE
+- IP
+- CO
+- ▁FINGER
+- ▁JO
+- ▁UN
+- ▁PRO
+- ▁STRAIGHT
+- ▁BEHALF
+- ▁TI
+- ▁SIX
+- ▁CLEAN
+- ▁DIS
+- ▁DA
+- ▁POSITION
+- IGHT
+- ACT
+- ▁CHA
+- ▁PE
+- GG
+- AP
+- ▁MEAN
+- ▁COMP
+- FI
+- ▁KNEE
+- ▁CALLED
+- ▁HANDS
+- ▁PRE
+- ▁FORWARD
+- ▁AREA
+- ANT
+- ▁TE
+- ▁WA
+- ▁AFTER
+- ▁SMALL
+- ▁THROW
+- ▁EVERY
+- ▁SHOULDER
+- NC
+- PER
+- ▁MAYBE
+- ▁ABLE
+- ▁BASICALLY
+- ▁AM
+- ▁READY
+- ▁BOTTOM
+- IE
+- ▁HALF
+- FF
+- ▁BIG
+- ▁EACH
+- ▁PUSH
+- ▁EIGHT
+- ▁NEW
+- ▁DONE
+- ▁MAY
+- ▁GETTING
+- HO
+- ▁HIS
+- ▁HARD
+- ▁CLOSE
+- ALLY
+- ▁SECOND
+- ▁FEET
+- ICAL
+- ▁JA
+- ▁PAINT
+- ▁LEARN
+- ▁SOUND
+- HE
+- ▁ROLL
+- ▁ONLY
+- ▁DOESN
+- WA
+- ▁DRAW
+- ▁VI
+- ▁DID
+- ▁SHA
+- ▁CENTER
+- CU
+- ▁CLIP
+- ▁PI
+- ▁CARD
+- ▁INSIDE
+- ▁PERSON
+- ▁STILL
+- ▁MAKING
+- 'NO'
+- ▁EVERYTHING
+- .
+- ▁FUN
+- ARD
+- ▁REMEMBER
+- ▁AWAY
+- ATED
+- COM
+- ▁SEVEN
+- ▁BEEN
+- ▁MANY
+- ABLE
+- ▁DAY
+- ▁SIT
+- IZE
+- ▁REAL
+- ▁HIP
+- ▁BASIC
+- ▁KICK
+- ▁TU
+- ATING
+- ▁STICK
+- ▁FLAT
+- ▁WHO
+- END
+- HA
+- ▁EXP
+- ▁PICK
+- ▁MIX
+- ▁TRI
+- ▁BI
+- ▁WHOLE
+- ▁STRETCH
+- ▁BOTH
+- ▁PROBABLY
+- CA
+- ▁HIM
+- ▁STRING
+- ▁EDGE
+- ▁BASE
+- ▁COMING
+- UGH
+- ▁LIFT
+- ▁STA
+- ▁WORKING
+- ▁MU
+- ▁QUICK
+- ▁SOMETIMES
+- ▁HAPPEN
+- ▁YOURSELF
+- ▁TALKING
+- ▁DR
+- ▁TELL
+- ▁ANYTHING
+- ▁BRA
+- ▁LOOKING
+- ▁SLOW
+- ▁NE
+- ▁STAND
+- NER
+- ▁COMES
+- ▁GOES
+- ISE
+- BE
+- ▁USED
+- ▁UNDER
+- ▁BETWEEN
+- ▁HU
+- ▁CREATE
+- ▁NA
+- ▁USUALLY
+- ▁ARM
+- ▁DRY
+- ▁RUN
+- LING
+- ▁BRUSH
+- ▁COVER
+- ▁HEAR
+- ▁DOES
+- ▁STAY
+- ▁EN
+- ▁FOLD
+- ▁CHANGE
+- ▁LAST
+- ▁EASY
+- ▁US
+- ▁PER
+- ▁FACE
+- ▁EAR
+- ▁TIGHT
+- ▁FE
+- ▁PIN
+- ▁MAN
+- ▁BETTER
+- ▁CALL
+- ▁PRI
+- ▁BEST
+- ▁KI
+- ▁COUPLE
+- ▁WHILE
+- ▁SHAPE
+- ▁GAME
+- IV
+- ▁SHOT
+- ▁PAPER
+- ▁OWN
+- ▁ALRIGHT
+- ▁HAD
+- TIC
+- ▁BREATH
+- ▁TOOL
+- '2'
+- ▁ENOUGH
+- ▁COURSE
+- ▁SKIN
+- ▁SPIN
+- ▁VA
+- ▁ARMS
+- ▁TEA
+- ▁BREAK
+- ▁DOG
+- ▁1
+- QUE
+- ▁DROP
+- ▁NUMBER
+- IG
+- ▁RED
+- ▁NOTE
+- ▁WEIGHT
+- WARD
+- ▁PLAYING
+- ▁FINISH
+- ▁MINUTE
+- ▁R
+- ▁PRESS
+- ▁EITHER
+- ▁CHE
+- ▁PU
+- BER
+- ▁FEW
+- ▁SIZE
+- ▁MADE
+- ▁LEAVE
+- ▁GA
+- ▁ALREADY
+- ▁GUY
+- ▁FAR
+- ▁HOME
+- ▁BAR
+- UP
+- ▁GRAB
+- ▁MARK
+- ▁WHITE
+- ▁PROPER
+- ▁CAUSE
+- ▁OK
+- ▁ART
+- HI
+- ▁SORT
+- ▁EXERCISE
+- ▁LOWER
+- PORT
+- ▁PLANT
+- ▁BOARD
+- ▁CASE
+- ▁YEAR
+- CENT
+- ▁DU
+- ▁CHECK
+- ▁WHATEVER
+- ▁OIL
+- ▁IDEA
+- ▁SIMPLE
+- ▁PRACTICE
+- ▁FAST
+- '0'
+- ▁CONTROL
+- ▁J
+- ▁KEY
+- ▁MIDDLE
+- ▁FULL
+- ▁GLASS
+- ▁OUTSIDE
+- ▁LOW
+- ▁REST
+- ▁STUFF
+- ▁ACT
+- ▁UNTIL
+- ▁BLACK
+- ▁POP
+- ▁CLICK
+- ▁HOLE
+- ▁Z
+- ▁COUNT
+- ▁POT
+- ▁ALLOW
+- ▁HAVING
+- ▁TRYING
+- ▁MUSCLE
+- ▁GU
+- ▁BOX
+- ▁NOTICE
+- ▁EXAMPLE
+- UND
+- ▁ALONG
+- FUL
+- ISH
+- ▁STORE
+- ▁LU
+- ▁FLOOR
+- ▁MOVING
+- ▁LARGE
+- ▁STOP
+- ▁PH
+- ▁WALK
+- '5'
+- ▁QU
+- ▁TECHNIQUE
+- ▁SOFT
+- ▁GROUND
+- ▁JUMP
+- ▁JU
+- ▁FILL
+- ▁WHY
+- ▁BUY
+- ▁GREEN
+- ▁WALL
+- ▁HEEL
+- NESS
+- ▁LEVEL
+- ▁UNDERNEATH
+- ▁PATTERN
+- ▁BEHIND
+- ▁OLD
+- ▁TIP
+- ▁COMPLETE
+- ▁WON
+- ▁TEACH
+- ▁FIT
+- ▁NECK
+- ▁REMOVE
+- ▁TRICK
+- ▁MOVEMENT
+- ▁TOWARDS
+- ▁PARTICULAR
+- ▁CHI
+- ▁EFFECT
+- J
+- ▁FREE
+- ▁ACROSS
+- ▁BEND
+- ▁SAFE
+- ▁SLIDE
+- ▁PROBLEM
+- ▁BLOCK
+- ▁PAN
+- ▁NATURAL
+- ▁TOUCH
+- ▁CHILD
+- LINE
+- ▁CROSS
+- ▁REASON
+- '4'
+- ▁POWER
+- ▁APPLY
+- ▁FOLLOW
+- ▁DESIGN
+- ▁SPACE
+- ▁ORDER
+- ▁WOOD
+- ▁RID
+- '3'
+- ▁COOK
+- ▁BEGIN
+- ▁WATCH
+- ▁STYLE
+- QUA
+- ▁PRODUCT
+- ▁TAKING
+- ▁PUTTING
+- ▁EXHALE
+- ▁THOUGH
+- ▁DEEP
+- IAN
+- ▁REACH
+- ▁FOOD
+- ▁ALMOST
+- ▁COOL
+- ▁SECTION
+- ▁SAID
+- ▁ANGLE
+- ▁MUSIC
+- ▁RELAX
+- ▁CORNER
+- ▁DARK
+- ▁CHORD
+- ▁ESPECIALLY
+- ▁SCALE
+- ▁WARM
+- ▁WITHOUT
+- ▁WHEEL
+- ▁SEGMENT
+- ▁TABLE
+- ▁BOOK
+- ▁PASS
+- ▁ELBOW
+- ▁ROUND
+- ▁INHALE
+- ▁SMOOTH
+- ▁ROOM
+- /
+- ▁NINE
+- ▁SHORT
+- ▁MEASURE
+- ▁LESS
+- ▁TWIST
+- ▁BALANCE
+- ▁PROCESS
+- ▁SWITCH
+- ▁GENERAL
+- ▁CLAY
+- ▁CERTAIN
+- ▁NEVER
+- ▁BLUE
+- ▁CUP
+- ▁HOUSE
+- ▁EXTRA
+- ▁MOTION
+- ▁PRESSURE
+- ▁FIRE
+- ▁SIMPLY
+- ▁DOUBLE
+- ▁TWENTY
+- ▁CATCH
+- ▁BECOME
+- ▁BUILD
+- ▁SPEED
+- ▁TRANS
+- ▁DRUM
+- ▁CHEST
+- ▁PICTURE
+- ▁LENGTH
+- ▁CONTINUE
+- ▁COMFORTABLE
+- ▁FISH
+- ▁PHOTO
+- ▁LOOSE
+- ▁SKI
+- ▁LIFE
+- ▁DEGREE
+- ▁OPTION
+- ▁WORD
+- ▁SHARP
+- ▁SHOOT
+- ▁FOUND
+- ▁STRONG
+- ▁QUITE
+- ▁THIRD
+- ▁GLUE
+- ▁MIND
+- ▁DEFINITELY
+- ▁EASIER
+- GRAPH
+- ▁HOOK
+- ▁CLEAR
+- ▁POSE
+- ▁BUTTON
+- ▁CHOOSE
+- ▁THICK
+- ▁SYSTEM
+- ▁PERFECT
+- ▁BEAUTIFUL
+- ▁SPOT
+- ▁GROW
+- ▁SIGN
+- ▁ELSE
+- ▁CONNECT
+- ▁SELECT
+- ▁PUNCH
+- ▁DIRECTION
+- ▁WRAP
+- ▁RELEASE
+- QUI
+- SIDE
+- ▁CAREFUL
+- ▁VIDEO
+- ▁INSTEAD
+- ▁CIRCLE
+- ▁WIRE
+- ▁NOSE
+- ▁AMOUNT
+- ▁FOCUS
+- ▁NORMAL
+- ▁MAJOR
+- ▁WHETHER
+- ▁SURFACE
+- ▁THUMB
+- ▁DRIVE
+- ▁SCREW
+- ▁POSSIBLE
+- ▁OBVIOUSLY
+- ▁COMMON
+- ▁REGULAR
+- ▁ADJUST
+- ▁WIDE
+- ▁BLADE
+- ▁FRET
+- ▁RECOMMEND
+- ▁BOWL
+- BOARD
+- ▁IMAGE
+- ▁DEPENDING
+- ▁PROTECT
+- ▁CLOTH
+- ▁HEALTH
+- ▁WRIST
+- ▁CLUB
+- ▁DRINK
+- ▁SINCE
+- ▁FRIEND
+- '00'
+- ▁RUNNING
+- ▁ITSELF
+- ▁RECORD
+- ▁SWING
+- ▁DIRECT
+- ▁MATERIAL
+- ▁YO
+- ▁LEAST
+- ▁EXACTLY
+- ▁BEGINNING
+- ▁SLIGHTLY
+- ▁TREAT
+- ▁CAMERA
+- ▁QUARTER
+- ▁WINDOW
+- '8'
+- ▁SOMEBODY
+- ▁BURN
+- ▁DEMONSTRATE
+- ▁DIFFERENCE
+- ▁COMPUTER
+- IBLE
+- ▁SHOE
+- ▁PERFORM
+- ▁SQUARE
+- ▁CONSIDER
+- ▁DRILL
+- ▁TEXT
+- ▁FILE
+- ▁RUB
+- ▁FABRIC
+- ▁HUNDRED
+- ▁GRIP
+- ▁CHARACTER
+- ▁SPECIFIC
+- ▁KNOT
+- ▁CURL
+- ▁STITCH
+- ▁BLEND
+- ▁FRAME
+- ▁THIRTY
+- '1'
+- ▁HORSE
+- ▁ATTACH
+- ▁GROUP
+- ▁STROKE
+- ▁GUITAR
+- ▁APART
+- ▁MACHINE
+- ▁CLASS
+- ▁COMB
+- ▁ROOT
+- ▁HELLO
+- ▁ENERGY
+- ▁ATTACK
+- ▁CORRECT
+- ▁EXTEND
+- ▁MINOR
+- ▁PROFESSIONAL
+- ▁MONEY
+- ▁STRIP
+- ▁FLAVOR
+- ▁EVERYBODY
+- ▁RULE
+- ▁DIFFICULT
+- ▁PROJECT
+- ▁DISCUSS
+- ▁FIGURE
+- ▁HOWEVER
+- ▁FINAL
+- ▁STRENGTH
+- ▁ENTIRE
+- ▁FIELD
+- ▁CONTACT
+- ▁SUPPORT
+- ▁PALM
+- ▁SERIES
+- ▁ENJOY
+- '6'
+- ▁WORLD
+- ▁DECIDE
+- ▁SPEAK
+- ▁SEVERAL
+- ▁WRITE
+- ▁PROGRAM
+- ABILITY
+- ▁KNIFE
+- ▁PLASTIC
+- ▁ORGAN
+- '7'
+- ▁UNDERSTAND
+- ▁FIFTEEN
+- ▁FLEX
+- ▁INFORMATION
+- ▁TWELVE
+- ▁DETAIL
+- ▁STRIKE
+- ▁ACTUAL
+- ▁SPRAY
+- ▁LOCAL
+- ▁MOUTH
+- ▁NIGHT
+- ▁VEHICLE
+- ▁OPPOSITE
+- ▁SCHOOL
+- '9'
+- ▁QUESTION
+- ▁SPECIAL
+- ▁BIGGER
+- ▁DEVELOP
+- ▁PEPPER
+- ▁PREFER
+- Q
+- '%'
+- ']'
+- '['
+- '&'
+- ','
+- _
+- '#'
+- '='
+- '@'
+- +
+- '*'
+- $
+- '~'
+- <sos/eos>
+init: null
+input_size: null
+ctc_conf:
+    ignore_nan_grad: true
+model_conf:
+    ctc_weight: 0.0
+    lsm_weight: 0.15
+    length_normalized_loss: false
+use_preprocessor: true
+token_type: bpe
+bpemodel: data/en_token_list/bpe_unigram1000/bpe.model
+non_linguistic_symbols: data/nlsyms
+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'
+frontend: default
+frontend_conf:
+    n_fft: 512
+    hop_length: 256
+    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
+    - 30
+    num_freq_mask: 2
+    apply_time_mask: true
+    time_mask_width_range:
+    - 0
+    - 40
+    num_time_mask: 2
+normalize: global_mvn
+normalize_conf:
+    stats_file: exp/asr_stats_raw_vid_sum/train/feats_stats.npz
+preencoder: null
+preencoder_conf: {}
+encoder: conformer
+encoder_conf:
+    output_size: 512
+    attention_heads: 8
+    linear_units: 2048
+    num_blocks: 12
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.1
+    input_layer: conv2d
+    normalize_before: true
+    macaron_style: true
+    pos_enc_layer_type: abs_pos
+    selfattention_layer_type: lf_selfattn
+    activation_type: swish
+    use_cnn_module: true
+    cnn_module_kernel: 31
+    attention_windows:
+    - 40
+    - 40
+    - 40
+    - 40
+    - 40
+    - 40
+    - 40
+    - 40
+    - 40
+    - 40
+    - 40
+    - 40
+    attention_dilation:
+    - 1
+    - 1
+    - 1
+    - 1
+    - 1
+    - 1
+    - 1
+    - 1
+    - 1
+    - 1
+    - 1
+    - 1
+    attention_mode: tvm
+decoder: transformer
+decoder_conf:
+    attention_heads: 4
+    linear_units: 512
+    num_blocks: 6
+    dropout_rate: 0.15
+    positional_dropout_rate: 0.15
+    self_attention_dropout_rate: 0.15
+    src_attention_dropout_rate: 0.15
+required:
+- output_dir
+- token_list
+version: 0.10.0
+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}
+}
+```

data/en_token_list/bpe_unigram1000/bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80f7c79144bddbe6d5fd80aa8da9797a88cd0c546c40bf4350da35f8993085d3
+size 253157

exp/roshansh_how2_asr_raw_ft_sum/RESULTS.md

@@ -0,0 +1,13 @@
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Mon Feb  7 15:24:21 EST 2022`
+- python version: `3.8.12 (default, Oct 12 2021, 13:49:34)  [GCC 7.5.0]`
+- espnet version: `espnet 0.10.6a1`
+- pytorch version: `pytorch 1.10.1`
+- Git hash: `04561cdf3b6c3bc1d51edb04c93b953759ef551d`
+  - Commit date: `Mon Feb 7 09:06:12 2022 -0500`
+
+## asr_raw_ft_sum
+|dataset|ROUGE-1|ROUGE-2|ROUGE-L|METEOR|BERTScore|
+|---|---|---|---|---|---|

exp/roshansh_how2_asr_raw_ft_sum/config.yaml

@@ -0,0 +1,1214 @@
+config: conf/train_asr_conformer_vid_lf.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/asr_raw_ft_sum
+ngpu: 1
+seed: 0
+num_workers: 1
+num_att_plot: 3
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: 8
+dist_rank: 0
+local_rank: 0
+dist_master_addr: localhost
+dist_master_port: 45875
+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: 100
+patience: 10
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - acc
+    - max
+keep_nbest_models: 10
+grad_clip: 5.0
+grad_clip_type: 2.0
+grad_noise: false
+accum_grad: 10
+no_forward_run: false
+resume: true
+train_dtype: float32
+use_amp: false
+log_interval: 5000
+use_tensorboard: true
+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:
+- exp/asr_raw_utt_conformer/valid.acc.ave_10best.pth:::ctc
+ignore_init_mismatch: false
+freeze_param: []
+num_iters_per_epoch: null
+batch_size: 20
+valid_batch_size: null
+batch_bins: 60000000
+valid_batch_bins: null
+train_shape_file:
+- exp/asr_stats_raw_vid_sum/train/speech_shape
+- exp/asr_stats_raw_vid_sum/train/text_shape.bpe
+valid_shape_file:
+- exp/asr_stats_raw_vid_sum/valid/speech_shape
+- exp/asr_stats_raw_vid_sum/valid/text_shape.bpe
+batch_type: length
+valid_batch_type: null
+fold_length:
+- 80000
+- 150
+sort_in_batch: descending
+sort_batch: descending
+multiple_iterator: false
+chunk_length: 500
+chunk_shift_ratio: 0.5
+num_cache_chunks: 1024
+train_data_path_and_name_and_type:
+-   - dump/raw/tr_2000h_sum_trim/wav.scp
+    - speech
+    - sound
+-   - dump/raw/tr_2000h_sum_trim/text
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - dump/raw/cv05_sum_trim/wav.scp
+    - speech
+    - sound
+-   - dump/raw/cv05_sum_trim/text
+    - text
+    - text
+allow_variable_data_keys: false
+max_cache_size: 0.0
+max_cache_fd: 32
+valid_max_cache_size: null
+optim: adam
+optim_conf:
+    lr: 0.001
+scheduler: reducelronplateau
+scheduler_conf:
+    mode: min
+    factor: 0.5
+    patience: 1
+token_list:
+- <blank>
+- <unk>
+- '[hes]'
+- S
+- ▁THE
+- ▁TO
+- ''''
+- ▁AND
+- ▁YOU
+- ▁A
+- ▁IT
+- T
+- ▁THAT
+- ▁OF
+- ▁I
+- ▁IS
+- RE
+- ▁IN
+- ING
+- ▁WE
+- M
+- ▁GOING
+- ▁SO
+- ▁THIS
+- ▁YOUR
+- ▁ON
+- E
+- D
+- ▁BE
+- ▁CAN
+- N
+- Y
+- O
+- ER
+- ▁HAVE
+- ▁JUST
+- ▁FOR
+- ▁WITH
+- ▁DO
+- ED
+- ▁ARE
+- ▁WANT
+- ▁UP
+- R
+- LL
+- P
+- ▁
+- L
+- B
+- ▁IF
+- C
+- ▁ONE
+- ▁S
+- ▁OR
+- A
+- ▁GO
+- ▁LIKE
+- ▁NOW
+- ▁HERE
+- VE
+- LE
+- U
+- ▁GET
+- ▁WHAT
+- ▁OUT
+- IN
+- W
+- ▁C
+- ▁LITTLE
+- ▁THERE
+- LY
+- ▁AS
+- ▁MAKE
+- I
+- ▁THEY
+- ▁MY
+- K
+- ▁THEN
+- ▁BUT
+- AL
+- G
+- ▁ALL
+- OR
+- ▁BACK
+- ▁NOT
+- ▁ABOUT
+- ▁RIGHT
+- ▁OUR
+- EN
+- ▁SOME
+- ▁DOWN
+- F
+- ▁WHEN
+- CH
+- ▁F
+- ▁HOW
+- AR
+- ▁WILL
+- ▁RE
+- CK
+- ▁G
+- ES
+- CE
+- ▁TAKE
+- ▁AT
+- ▁FROM
+- ▁WAY
+- TER
+- ▁SEE
+- RA
+- ▁USE
+- ▁REALLY
+- RI
+- TH
+- ▁TWO
+- ▁ME
+- ▁VERY
+- ▁E
+- ▁B
+- AT
+- ▁THEM
+- ▁DON
+- ▁AN
+- ▁BECAUSE
+- ▁MORE
+- RO
+- H
+- 'ON'
+- LI
+- ▁PUT
+- ▁ST
+- IL
+- ▁BIT
+- ▁START
+- ▁NEED
+- ▁INTO
+- UR
+- ▁TIME
+- ▁OVER
+- ▁W
+- ▁DE
+- ▁LOOK
+- ▁THESE
+- ▁LET
+- ▁GOOD
+- ▁ALSO
+- AN
+- ▁OFF
+- ▁HE
+- ▁KIND
+- ▁SIDE
+- ▁CO
+- ▁SURE
+- ▁AGAIN
+- ▁MA
+- ▁KNOW
+- IT
+- ▁WOULD
+- IC
+- ▁OTHER
+- LA
+- ▁P
+- ▁WHICH
+- '-'
+- IR
+- ▁LA
+- ▁HAND
+- EL
+- ▁LOT
+- ▁WHERE
+- ▁THREE
+- ▁PA
+- ION
+- LO
+- ▁KEEP
+- ▁SHOW
+- ▁THING
+- ▁FIRST
+- TE
+- ENT
+- ATE
+- ▁COME
+- AD
+- ▁GOT
+- NG
+- ▁NICE
+- ▁T
+- ET
+- ▁MO
+- ▁ANY
+- ▁ACTUALLY
+- ▁DIFFERENT
+- ▁SE
+- GE
+- ▁WORK
+- ▁THROUGH
+- ▁O
+- KE
+- V
+- ▁AROUND
+- ▁BA
+- PE
+- ▁HI
+- ▁BY
+- SH
+- ATION
+- ▁SU
+- ▁CA
+- ▁D
+- ▁LO
+- ▁HAS
+- ▁LI
+- ▁PLAY
+- Z
+- ▁ADD
+- ▁RO
+- ▁TA
+- AS
+- ▁FOUR
+- ▁CON
+- ▁THOSE
+- MP
+- NE
+- ▁SP
+- UT
+- ▁GIVE
+- ▁WELL
+- ▁BALL
+- TING
+- RY
+- X
+- ▁HO
+- INE
+- IVE
+- ▁NEXT
+- ▁PO
+- ▁STEP
+- ▁EVEN
+- TION
+- ▁MI
+- MENT
+- ▁CUT
+- ▁BO
+- ▁LINE
+- ▁MUCH
+- ▁THINGS
+- ▁TALK
+- UN
+- ▁PART
+- ▁WAS
+- ▁FA
+- ▁SOMETHING
+- PP
+- ANCE
+- ND
+- DI
+- ▁RA
+- AGE
+- ▁SAME
+- ▁EXPERT
+- ▁DOING
+- ▁LEFT
+- IST
+- ▁DI
+- ▁NO
+- RU
+- ME
+- TA
+- UL
+- TI
+- ▁VILLAGE
+- DE
+- ERS
+- ▁PEOPLE
+- ▁TURN
+- VER
+- ▁FL
+- ▁LEG
+- ▁ONCE
+- ▁COLOR
+- ▁PULL
+- ▁USING
+- VI
+- ▁WATER
+- ▁SHE
+- ▁TOP
+- ▁OKAY
+- ▁ANOTHER
+- ▁THEIR
+- ▁SAY
+- URE
+- ▁HA
+- ▁IMPORTANT
+- ▁PIECE
+- ▁FOOT
+- ▁TRA
+- ▁SC
+- ▁BODY
+- ▁SET
+- ▁POINT
+- ▁HELP
+- ▁TODAY
+- ▁BRING
+- ▁V
+- ▁END
+- MA
+- ▁CH
+- ▁MOST
+- ▁K
+- ▁AHEAD
+- ▁HER
+- OL
+- ▁SA
+- AM
+- IES
+- ▁THINK
+- ▁NAME
+- ▁TRY
+- ▁MOVE
+- ONE
+- ▁LE
+- ▁TOO
+- TO
+- UM
+- ▁PLACE
+- ▁COULD
+- ▁FIND
+- ▁FIVE
+- ▁ALWAYS
+- ID
+- TY
+- NT
+- ▁FEEL
+- ▁HEAD
+- ▁THAN
+- NA
+- ▁EX
+- ▁EYE
+- ITY
+- CI
+- OP
+- ▁SHOULD
+- ▁MIGHT
+- ▁HOLD
+- ▁CAR
+- AND
+- ▁GREAT
+- ▁RI
+- ▁BU
+- ▁HIGH
+- ▁OPEN
+- ▁BEFORE
+- US
+- ▁FRONT
+- ▁LONG
+- ▁TOGETHER
+- NI
+- ▁HAIR
+- ▁LIGHT
+- ▁TEN
+- ▁HIT
+- EST
+- OUS
+- ▁PRETTY
+- ▁TYPE
+- IP
+- CO
+- ▁FINGER
+- ▁JO
+- ▁UN
+- ▁PRO
+- ▁STRAIGHT
+- ▁BEHALF
+- ▁TI
+- ▁SIX
+- ▁CLEAN
+- ▁DIS
+- ▁DA
+- ▁POSITION
+- IGHT
+- ACT
+- ▁CHA
+- ▁PE
+- GG
+- AP
+- ▁MEAN
+- ▁COMP
+- FI
+- ▁KNEE
+- ▁CALLED
+- ▁HANDS
+- ▁PRE
+- ▁FORWARD
+- ▁AREA
+- ANT
+- ▁TE
+- ▁WA
+- ▁AFTER
+- ▁SMALL
+- ▁THROW
+- ▁EVERY
+- ▁SHOULDER
+- NC
+- PER
+- ▁MAYBE
+- ▁ABLE
+- ▁BASICALLY
+- ▁AM
+- ▁READY
+- ▁BOTTOM
+- IE
+- ▁HALF
+- FF
+- ▁BIG
+- ▁EACH
+- ▁PUSH
+- ▁EIGHT
+- ▁NEW
+- ▁DONE
+- ▁MAY
+- ▁GETTING
+- HO
+- ▁HIS
+- ▁HARD
+- ▁CLOSE
+- ALLY
+- ▁SECOND
+- ▁FEET
+- ICAL
+- ▁JA
+- ▁PAINT
+- ▁LEARN
+- ▁SOUND
+- HE
+- ▁ROLL
+- ▁ONLY
+- ▁DOESN
+- WA
+- ▁DRAW
+- ▁VI
+- ▁DID
+- ▁SHA
+- ▁CENTER
+- CU
+- ▁CLIP
+- ▁PI
+- ▁CARD
+- ▁INSIDE
+- ▁PERSON
+- ▁STILL
+- ▁MAKING
+- 'NO'
+- ▁EVERYTHING
+- .
+- ▁FUN
+- ARD
+- ▁REMEMBER
+- ▁AWAY
+- ATED
+- COM
+- ▁SEVEN
+- ▁BEEN
+- ▁MANY
+- ABLE
+- ▁DAY
+- ▁SIT
+- IZE
+- ▁REAL
+- ▁HIP
+- ▁BASIC
+- ▁KICK
+- ▁TU
+- ATING
+- ▁STICK
+- ▁FLAT
+- ▁WHO
+- END
+- HA
+- ▁EXP
+- ▁PICK
+- ▁MIX
+- ▁TRI
+- ▁BI
+- ▁WHOLE
+- ▁STRETCH
+- ▁BOTH
+- ▁PROBABLY
+- CA
+- ▁HIM
+- ▁STRING
+- ▁EDGE
+- ▁BASE
+- ▁COMING
+- UGH
+- ▁LIFT
+- ▁STA
+- ▁WORKING
+- ▁MU
+- ▁QUICK
+- ▁SOMETIMES
+- ▁HAPPEN
+- ▁YOURSELF
+- ▁TALKING
+- ▁DR
+- ▁TELL
+- ▁ANYTHING
+- ▁BRA
+- ▁LOOKING
+- ▁SLOW
+- ▁NE
+- ▁STAND
+- NER
+- ▁COMES
+- ▁GOES
+- ISE
+- BE
+- ▁USED
+- ▁UNDER
+- ▁BETWEEN
+- ▁HU
+- ▁CREATE
+- ▁NA
+- ▁USUALLY
+- ▁ARM
+- ▁DRY
+- ▁RUN
+- LING
+- ▁BRUSH
+- ▁COVER
+- ▁HEAR
+- ▁DOES
+- ▁STAY
+- ▁EN
+- ▁FOLD
+- ▁CHANGE
+- ▁LAST
+- ▁EASY
+- ▁US
+- ▁PER
+- ▁FACE
+- ▁EAR
+- ▁TIGHT
+- ▁FE
+- ▁PIN
+- ▁MAN
+- ▁BETTER
+- ▁CALL
+- ▁PRI
+- ▁BEST
+- ▁KI
+- ▁COUPLE
+- ▁WHILE
+- ▁SHAPE
+- ▁GAME
+- IV
+- ▁SHOT
+- ▁PAPER
+- ▁OWN
+- ▁ALRIGHT
+- ▁HAD
+- TIC
+- ▁BREATH
+- ▁TOOL
+- '2'
+- ▁ENOUGH
+- ▁COURSE
+- ▁SKIN
+- ▁SPIN
+- ▁VA
+- ▁ARMS
+- ▁TEA
+- ▁BREAK
+- ▁DOG
+- ▁1
+- QUE
+- ▁DROP
+- ▁NUMBER
+- IG
+- ▁RED
+- ▁NOTE
+- ▁WEIGHT
+- WARD
+- ▁PLAYING
+- ▁FINISH
+- ▁MINUTE
+- ▁R
+- ▁PRESS
+- ▁EITHER
+- ▁CHE
+- ▁PU
+- BER
+- ▁FEW
+- ▁SIZE
+- ▁MADE
+- ▁LEAVE
+- ▁GA
+- ▁ALREADY
+- ▁GUY
+- ▁FAR
+- ▁HOME
+- ▁BAR
+- UP
+- ▁GRAB
+- ▁MARK
+- ▁WHITE
+- ▁PROPER
+- ▁CAUSE
+- ▁OK
+- ▁ART
+- HI
+- ▁SORT
+- ▁EXERCISE
+- ▁LOWER
+- PORT
+- ▁PLANT
+- ▁BOARD
+- ▁CASE
+- ▁YEAR
+- CENT
+- ▁DU
+- ▁CHECK
+- ▁WHATEVER
+- ▁OIL
+- ▁IDEA
+- ▁SIMPLE
+- ▁PRACTICE
+- ▁FAST
+- '0'
+- ▁CONTROL
+- ▁J
+- ▁KEY
+- ▁MIDDLE
+- ▁FULL
+- ▁GLASS
+- ▁OUTSIDE
+- ▁LOW
+- ▁REST
+- ▁STUFF
+- ▁ACT
+- ▁UNTIL
+- ▁BLACK
+- ▁POP
+- ▁CLICK
+- ▁HOLE
+- ▁Z
+- ▁COUNT
+- ▁POT
+- ▁ALLOW
+- ▁HAVING
+- ▁TRYING
+- ▁MUSCLE
+- ▁GU
+- ▁BOX
+- ▁NOTICE
+- ▁EXAMPLE
+- UND
+- ▁ALONG
+- FUL
+- ISH
+- ▁STORE
+- ▁LU
+- ▁FLOOR
+- ▁MOVING
+- ▁LARGE
+- ▁STOP
+- ▁PH
+- ▁WALK
+- '5'
+- ▁QU
+- ▁TECHNIQUE
+- ▁SOFT
+- ▁GROUND
+- ▁JUMP
+- ▁JU
+- ▁FILL
+- ▁WHY
+- ▁BUY
+- ▁GREEN
+- ▁WALL
+- ▁HEEL
+- NESS
+- ▁LEVEL
+- ▁UNDERNEATH
+- ▁PATTERN
+- ▁BEHIND
+- ▁OLD
+- ▁TIP
+- ▁COMPLETE
+- ▁WON
+- ▁TEACH
+- ▁FIT
+- ▁NECK
+- ▁REMOVE
+- ▁TRICK
+- ▁MOVEMENT
+- ▁TOWARDS
+- ▁PARTICULAR
+- ▁CHI
+- ▁EFFECT
+- J
+- ▁FREE
+- ▁ACROSS
+- ▁BEND
+- ▁SAFE
+- ▁SLIDE
+- ▁PROBLEM
+- ▁BLOCK
+- ▁PAN
+- ▁NATURAL
+- ▁TOUCH
+- ▁CHILD
+- LINE
+- ▁CROSS
+- ▁REASON
+- '4'
+- ▁POWER
+- ▁APPLY
+- ▁FOLLOW
+- ▁DESIGN
+- ▁SPACE
+- ▁ORDER
+- ▁WOOD
+- ▁RID
+- '3'
+- ▁COOK
+- ▁BEGIN
+- ▁WATCH
+- ▁STYLE
+- QUA
+- ▁PRODUCT
+- ▁TAKING
+- ▁PUTTING
+- ▁EXHALE
+- ▁THOUGH
+- ▁DEEP
+- IAN
+- ▁REACH
+- ▁FOOD
+- ▁ALMOST
+- ▁COOL
+- ▁SECTION
+- ▁SAID
+- ▁ANGLE
+- ▁MUSIC
+- ▁RELAX
+- ▁CORNER
+- ▁DARK
+- ▁CHORD
+- ▁ESPECIALLY
+- ▁SCALE
+- ▁WARM
+- ▁WITHOUT
+- ▁WHEEL
+- ▁SEGMENT
+- ▁TABLE
+- ▁BOOK
+- ▁PASS
+- ▁ELBOW
+- ▁ROUND
+- ▁INHALE
+- ▁SMOOTH
+- ▁ROOM
+- /
+- ▁NINE
+- ▁SHORT
+- ▁MEASURE
+- ▁LESS
+- ▁TWIST
+- ▁BALANCE
+- ▁PROCESS
+- ▁SWITCH
+- ▁GENERAL
+- ▁CLAY
+- ▁CERTAIN
+- ▁NEVER
+- ▁BLUE
+- ▁CUP
+- ▁HOUSE
+- ▁EXTRA
+- ▁MOTION
+- ▁PRESSURE
+- ▁FIRE
+- ▁SIMPLY
+- ▁DOUBLE
+- ▁TWENTY
+- ▁CATCH
+- ▁BECOME
+- ▁BUILD
+- ▁SPEED
+- ▁TRANS
+- ▁DRUM
+- ▁CHEST
+- ▁PICTURE
+- ▁LENGTH
+- ▁CONTINUE
+- ▁COMFORTABLE
+- ▁FISH
+- ▁PHOTO
+- ▁LOOSE
+- ▁SKI
+- ▁LIFE
+- ▁DEGREE
+- ▁OPTION
+- ▁WORD
+- ▁SHARP
+- ▁SHOOT
+- ▁FOUND
+- ▁STRONG
+- ▁QUITE
+- ▁THIRD
+- ▁GLUE
+- ▁MIND
+- ▁DEFINITELY
+- ▁EASIER
+- GRAPH
+- ▁HOOK
+- ▁CLEAR
+- ▁POSE
+- ▁BUTTON
+- ▁CHOOSE
+- ▁THICK
+- ▁SYSTEM
+- ▁PERFECT
+- ▁BEAUTIFUL
+- ▁SPOT
+- ▁GROW
+- ▁SIGN
+- ▁ELSE
+- ▁CONNECT
+- ▁SELECT
+- ▁PUNCH
+- ▁DIRECTION
+- ▁WRAP
+- ▁RELEASE
+- QUI
+- SIDE
+- ▁CAREFUL
+- ▁VIDEO
+- ▁INSTEAD
+- ▁CIRCLE
+- ▁WIRE
+- ▁NOSE
+- ▁AMOUNT
+- ▁FOCUS
+- ▁NORMAL
+- ▁MAJOR
+- ▁WHETHER
+- ▁SURFACE
+- ▁THUMB
+- ▁DRIVE
+- ▁SCREW
+- ▁POSSIBLE
+- ▁OBVIOUSLY
+- ▁COMMON
+- ▁REGULAR
+- ▁ADJUST
+- ▁WIDE
+- ▁BLADE
+- ▁FRET
+- ▁RECOMMEND
+- ▁BOWL
+- BOARD
+- ▁IMAGE
+- ▁DEPENDING
+- ▁PROTECT
+- ▁CLOTH
+- ▁HEALTH
+- ▁WRIST
+- ▁CLUB
+- ▁DRINK
+- ▁SINCE
+- ▁FRIEND
+- '00'
+- ▁RUNNING
+- ▁ITSELF
+- ▁RECORD
+- ▁SWING
+- ▁DIRECT
+- ▁MATERIAL
+- ▁YO
+- ▁LEAST
+- ▁EXACTLY
+- ▁BEGINNING
+- ▁SLIGHTLY
+- ▁TREAT
+- ▁CAMERA
+- ▁QUARTER
+- ▁WINDOW
+- '8'
+- ▁SOMEBODY
+- ▁BURN
+- ▁DEMONSTRATE
+- ▁DIFFERENCE
+- ▁COMPUTER
+- IBLE
+- ▁SHOE
+- ▁PERFORM
+- ▁SQUARE
+- ▁CONSIDER
+- ▁DRILL
+- ▁TEXT
+- ▁FILE
+- ▁RUB
+- ▁FABRIC
+- ▁HUNDRED
+- ▁GRIP
+- ▁CHARACTER
+- ▁SPECIFIC
+- ▁KNOT
+- ▁CURL
+- ▁STITCH
+- ▁BLEND
+- ▁FRAME
+- ▁THIRTY
+- '1'
+- ▁HORSE
+- ▁ATTACH
+- ▁GROUP
+- ▁STROKE
+- ▁GUITAR
+- ▁APART
+- ▁MACHINE
+- ▁CLASS
+- ▁COMB
+- ▁ROOT
+- ▁HELLO
+- ▁ENERGY
+- ▁ATTACK
+- ▁CORRECT
+- ▁EXTEND
+- ▁MINOR
+- ▁PROFESSIONAL
+- ▁MONEY
+- ▁STRIP
+- ▁FLAVOR
+- ▁EVERYBODY
+- ▁RULE
+- ▁DIFFICULT
+- ▁PROJECT
+- ▁DISCUSS
+- ▁FIGURE
+- ▁HOWEVER
+- ▁FINAL
+- ▁STRENGTH
+- ▁ENTIRE
+- ▁FIELD
+- ▁CONTACT
+- ▁SUPPORT
+- ▁PALM
+- ▁SERIES
+- ▁ENJOY
+- '6'
+- ▁WORLD
+- ▁DECIDE
+- ▁SPEAK
+- ▁SEVERAL
+- ▁WRITE
+- ▁PROGRAM
+- ABILITY
+- ▁KNIFE
+- ▁PLASTIC
+- ▁ORGAN
+- '7'
+- ▁UNDERSTAND
+- ▁FIFTEEN
+- ▁FLEX
+- ▁INFORMATION
+- ▁TWELVE
+- ▁DETAIL
+- ▁STRIKE
+- ▁ACTUAL
+- ▁SPRAY
+- ▁LOCAL
+- ▁MOUTH
+- ▁NIGHT
+- ▁VEHICLE
+- ▁OPPOSITE
+- ▁SCHOOL
+- '9'
+- ▁QUESTION
+- ▁SPECIAL
+- ▁BIGGER
+- ▁DEVELOP
+- ▁PEPPER
+- ▁PREFER
+- Q
+- '%'
+- ']'
+- '['
+- '&'
+- ','
+- _
+- '#'
+- '='
+- '@'
+- +
+- '*'
+- $
+- '~'
+- <sos/eos>
+init: null
+input_size: null
+ctc_conf:
+    ignore_nan_grad: true
+model_conf:
+    ctc_weight: 0.0
+    lsm_weight: 0.15
+    length_normalized_loss: false
+use_preprocessor: true
+token_type: bpe
+bpemodel: data/en_token_list/bpe_unigram1000/bpe.model
+non_linguistic_symbols: data/nlsyms
+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'
+frontend: default
+frontend_conf:
+    n_fft: 512
+    hop_length: 256
+    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
+    - 30
+    num_freq_mask: 2
+    apply_time_mask: true
+    time_mask_width_range:
+    - 0
+    - 40
+    num_time_mask: 2
+normalize: global_mvn
+normalize_conf:
+    stats_file: exp/asr_stats_raw_vid_sum/train/feats_stats.npz
+preencoder: null
+preencoder_conf: {}
+encoder: conformer
+encoder_conf:
+    output_size: 512
+    attention_heads: 8
+    linear_units: 2048
+    num_blocks: 12
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.1
+    input_layer: conv2d
+    normalize_before: true
+    macaron_style: true
+    pos_enc_layer_type: abs_pos
+    selfattention_layer_type: lf_selfattn
+    activation_type: swish
+    use_cnn_module: true
+    cnn_module_kernel: 31
+    attention_windows:
+    - 40
+    - 40
+    - 40
+    - 40
+    - 40
+    - 40
+    - 40
+    - 40
+    - 40
+    - 40
+    - 40
+    - 40
+    attention_dilation:
+    - 1
+    - 1
+    - 1
+    - 1
+    - 1
+    - 1
+    - 1
+    - 1
+    - 1
+    - 1
+    - 1
+    - 1
+    attention_mode: tvm
+decoder: transformer
+decoder_conf:
+    attention_heads: 4
+    linear_units: 512
+    num_blocks: 6
+    dropout_rate: 0.15
+    positional_dropout_rate: 0.15
+    self_attention_dropout_rate: 0.15
+    src_attention_dropout_rate: 0.15
+required:
+- output_dir
+- token_list
+version: 0.10.0
+distributed: true

exp/roshansh_how2_asr_raw_ft_sum/valid.acc.ave_10best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:309db0e004a1922b28a3a74b3173412b156167dcf08b816fe45f9c7406547808
+size 413117831

meta.yaml

@@ -0,0 +1,8 @@
+espnet: 0.10.7a1
+files:
+  asr_model_file: exp/roshansh_how2_asr_raw_ft_sum/valid.acc.ave_10best.pth
+python: "3.8.12 (default, Oct 12 2021, 13:49:34) \n[GCC 7.5.0]"
+timestamp: 1644953744.151672
+torch: 1.10.1
+yaml_files:
+  asr_train_config: exp/roshansh_how2_asr_raw_ft_sum/config.yaml