Siddhant
Update model
b046f80
config: conf/train_asr2_hubert_lr0.002.yaml
print_config: false
log_level: INFO
dry_run: false
iterator_type: sequence
output_dir: exp/asr_train_asr2_hubert_lr0.002_raw_en_bpe500
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: 57197
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: 50
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
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:
- frontend.upstream
num_iters_per_epoch: null
batch_size: 128
valid_batch_size: null
batch_bins: 1000000
valid_batch_bins: null
train_shape_file:
- exp/asr_stats_raw_en_bpe500/train/speech_shape
- exp/asr_stats_raw_en_bpe500/train/text_shape.bpe
valid_shape_file:
- exp/asr_stats_raw_en_bpe500/valid/speech_shape
- exp/asr_stats_raw_en_bpe500/valid/text_shape.bpe
batch_type: folded
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/train/wav.scp
- speech
- sound
- - dump/raw/train/text
- text
- text
valid_data_path_and_name_and_type:
- - dump/raw/valid/wav.scp
- speech
- sound
- - dump/raw/valid/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: 0.0004
weight_decay: 1.0e-06
scheduler: warmuplr
scheduler_conf:
warmup_steps: 25000
token_list:
- <blank>
- <unk>
- ▁[
- ':'
- ▁]
- _
- SL
- IN
- GET
- S
- TIME
- DATE
- ▁THE
- ▁TO
- ▁FOR
-
- E
- LOCATION
- A
- WEATHER
- O
- ▁ME
- MUSIC
- ▁MY
- CREATE
- ALARM
- Y
- D
- ▁I
- T
- ▁AT
- I
- ▁A
- TIMER
- ▁IS
- U
- ▁IN
- ▁ON
- EVENT
- M
- ▁TIMER
- TODO
- REMINDER
- R
- ▁PM
- P
- ING
- ▁WHAT
- ▁THIS
- ▁TODAY
- ▁AM
- N
- ▁ALARM
- ▁SET
- NT
- METHOD
- ▁TOMORROW
- ER
- TYPE
- B
- ATTRIBUTE
- DESTINATION
- ▁MINUTES
- REMINDED
- PERSON
- L
- ▁HOW
- NAME
- K
- ▁FIVE
- ▁BE
- ▁'
- G
- ▁NEXT
- 'ON'
- ▁IT
- MESSAGE
- H
- ▁WILL
- ▁S
- ▁WEEK
- ST
- C
- INFO
- EN
- CATEGORY
- TRAFFIC
- ▁F
- LE
- ▁AND
- AR
- SEND
- RE
- ▁P
- ▁D
- ▁FROM
- RECIPIE
- PLAY
- ▁DO
- ▁TRAFFIC
- AN
- ▁AN
- AL
- ▁SIX
- ▁SONG
- ▁ALL
- ▁UP
- CONTENT
- ▁REMINDER
- ▁WEEKEND
- ▁REMIND
- ▁OF
- ▁T
- RA
- ▁WEATHER
- ▁SEVEN
- ▁PLEASE
- ▁RE
- ▁TONIGHT
- EXACT
- ▁EIGHT
- ▁W
- W
- ▁TEN
- F
- SOURCE
- ▁TIME
- ESTIMATED
- RECURRING
- TH
- DELETE
- VE
- ▁NEW
- LL
- ▁EVERY
- ▁PLAY
- ES
- ▁THIRTY
- ▁GET
- ▁RAIN
- CK
- ▁TWO
- ▁C
- ▁CO
- ▁ARE
- ▁MESSAGE
- RI
- ▁G
- ▁MORNING
- CONTACT
- ▁CAN
- ▁NOW
- ▁THREE
- ▁THERE
- ET
- ▁MUSIC
- TER
- ▁TAKE
- IC
- CH
- ▁J
- V
- ED
- ▁FOUR
- DURATION
- LY
- ▁E
- ▁FRIDAY
- UR
- ▁YOU
- ▁ANY
- ▁NINE
- ▁GO
- UNSUPPORTED
- OR
- ▁SHOW
- ▁O
- ▁BA
- ▁PA
- ▁LONG
- AT
- ▁ONE
- ND
- ▁MA
- ▁ST
- ▁GOING
- ▁LIKE
- ▁ALARMS
- ▁BY
- ▁THAT
- ▁TWENTY
- ▁DAY
- ▁CH
- ▁MONTH
- ▁K
- ▁SH
- UPDATE
- ▁MONDAY
- CE
- IT
- IL
- AMOUNT
- ▁SATURDAY
- ▁BR
- ▁NEED
- ▁WORK
- ID
- ▁DRIVE
- LA
- ▁MO
- ▁HAVE
- ▁TUESDAY
- ▁TELL
- IR
- HA
- ''''
- ▁IF
- HOME
- ▁HE
- ▁LO
- ▁LA
- ▁WHEN
- LO
- ▁TH
- ▁REMINDERS
- IE
- DISTANCE
- ▁WE
- ▁SA
- ▁HOUR
- OULD
- NE
- DEPARTURE
- ▁HI
- ▁LI
- ARTIST
- Z
- TRAVEL
- ▁OUT
- PAUSE
- EST
- ARRIVAL
- ▁CANCEL
- ▁MI
- ▁OFF
- ▁FIFTEEN
- POINT
- ▁SNOW
- NA
- EL
- ▁EVENTS
- ▁CA
- ▁SUNDAY
- ▁LEAVE
- TRACK
- ▁SEND
- ▁DELETE
- ▁APPOINTMENT
- ▁BO
- RDINAL
- ▁MAKE
- ▁NEAR
- ▁BEFORE
- GE
- ▁HOME
- RELATION
- ▁V
- FR
- ▁THURSDAY
- ▁LAST
- DIRECTIONS
- ▁WEDNESDAY
- ▁START
- ▁FORECAST
- ▁YORK
- ▁RIGHT
- UM
- ▁WITH
- USE
- ▁MEETING
- UT
- LI
- ▁CHANGE
- ▁CAR
- GENRE
- ATION
- X
- ▁PICK
- ▁WANT
- ▁NIGHT
- SKIP
- ▁DE
- ▁RO
- ▁ABOUT
- MAP
- CO
- MA
- ▁HOUSE
- ▁HOT
- ▁PARTY
- ▁WA
- UNIT
- ▁HERE
- ▁SU
- ▁AFTERNOON
- ▁MUCH
- ▁MOM
- ▁TEMPERATURE
- EQUENC
- ▁ADD
- ▁SAN
- ▁HER
- ▁CONCERTS
- ▁CHRISTMAS
- ▁DINNER
- ▁MAR
- LAND
- ▁HOURS
- ▁CURRENT
- ▁TRACK
- ▁SOME
- ▁CITY
- ▁FORTY
- ATE
- ▁ROUTE
- SNOOZE
- ▁TEXT
- WORK
- ▁COLD
- RELATED
- ▁OR
- ▁NO
- Q
- ▁WAY
- WAY
- ▁MANY
- ▁BIRTHDAY
- ▁MINUTE
- ▁PLAYLIST
- ▁NOON
- ▁ROAD
- TITLE
- PATH
- ▁ASK
- NAVIGATION
- ▁LEFT
- ▁ALBUM
- ▁TURN
- ▁LATE
- ▁ELEVEN
- NEW
- ▁CELSIUS
- ▁BUY
- AVOID
- LOW
- NCE
- SEARCH
- ▁GAME
- ▁STOP
- ▁JO
- ▁FIRST
- ▁SHE
- ▁DOCTOR
- ▁BU
- PERIOD
- ▁WAKE
- CONDITION
- ▁EVENING
- RADIUS
- MODIFIE
- ▁REPEAT
- ▁SECOND
- ▁CONCERT
- ▁ANGELES
- ▁DOWNTOWN
- ▁UMBRELLA
- TEMPERATURE
- ASH
- ▁YEAR
- GROUP
- ▁DRIVING
- ▁GIVE
- ▁HUNDRED
- ▁HO
- ▁MILES
- PLAYLIST
- ADD
- RETRIEV
- ▁TWELVE
- EAD
- ▁CLASS
- ▁FREE
- PORT
- VILLE
- ▁BETWEEN
- ▁KNOW
- ▁AROUND
- ▁SCHOOL
- ▁NINETY
- PROVIDER
- SILENCE
- RESUME
- ▁LET
- TION
- ▁AUGUST
- ▁HAPPENING
- ▁AFTER
- ▁FAHRENHEIT
- ▁EX
- ▁VIDEO
- ROAD
- ▁PARK
- ▁CHICAGO
- ▁DAILY
- ▁CHECK
- ▁BEACH
- ▁WHERE
- ▁JUNE
- ▁STREET
- ▁FESTIVAL
- ▁FLORIDA
- ▁JOHN
- ▁HAS
- ▁SPOTIFY
- ▁BILL
- RESTART
- ▁HIGHWAY
- ▁SEATTLE
- J
- ▁LUNCH
- ▁LOOK
- ▁FRIEND
- ▁COMING
- ▁ALERT
- IGHT
- ▁PANDORA
- ▁HEAVY
- ▁KIDS
- ▁MOVIE
- ▁SOUTH
- REACT
- ▁CONSTRUCTION
- PREVIOUS
- ▁ORLANDO
- ▁OVER
- ▁MIAMI
- REACTION
- ▁ATLANTA
- ▁ACCIDENT
- ▁COUNTRY
- ▁NORTH
- ▁LIGHT
- RADIO
- ▁READ
- ▁FAMILY
- ▁AIRPORT
- ▁EXPECT
- ▁DEGREE
- ▁PRO
- ▁PARTIES
- ▁FIFTY
- ▁HIGH
- ▁PLAN
- ▁FOOD
- ▁WARM
- ▁SUNNY
- ▁VEGAS
- ▁HOLIDAY
- ▁SCHEDULE
- ▁STORM
- ▁FIFTH
- ▁BOSTON
- ▁FRANCISCO
- ▁LONDON
- ATTENDEE
- ▁JULY
- ▁WALK
- ▁COMMUTE
- ▁CLEAN
- ▁DENTIST
- TOWN
- ▁AGAIN
- ▁DALLAS
- ▁PORTLAND
- ▁SEPTEMBER
- ▁ARRIVE
- ▁SISTER
- ▁HOUSTON
- Ã
- É
- Í
- '*'
- Á
- Ç
- Ó
- ']'
- '['
- Ú
- Ü
- <sos/eos>
transcript_token_list: null
two_pass: false
pre_postencoder_norm: false
init: null
input_size: null
ctc_conf:
dropout_rate: 0.0
ctc_type: builtin
reduce: true
ignore_nan_grad: true
joint_net_conf: null
use_preprocessor: true
token_type: bpe
bpemodel: data/en_token_list/bpe_unigram500/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'
frontend: s3prl
frontend_conf:
frontend_conf:
upstream: hubert_large_ll60k
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
- 30
num_freq_mask: 2
apply_time_mask: true
time_mask_width_range:
- 0
- 40
num_time_mask: 2
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: 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: conv2d2
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
postencoder: null
postencoder_conf: {}
deliberationencoder: null
deliberationencoder_conf: {}
decoder: transformer
decoder_conf:
attention_heads: 8
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
decoder2: null
decoder2_conf: {}
postdecoder: null
postdecoder_conf: {}
required:
- output_dir
- token_list
version: '202205'
distributed: true