metadata
tags:
- espnet
- audio
- automatic-speech-recognition
language: en
datasets:
- slurp_entity
license: cc-by-4.0
ESPnet2 ASR model
Darshan7575/slurp_multiconvformer_conv_fusion
This model was trained by Darshan using slurp_entity recipe in espnet.
Demo: How to use in ESPnet2
Follow the ESPnet installation instructions
if you haven't done that already.
cd espnet
git checkout b8b31c06da081ee1690c8dc1bf102a7811124529
pip install -e .
cd egs2_imp/slurp_entity/asr1
./run.sh --skip_data_prep false --skip_train true --download_model Darshan7575/slurp_multiconvformer_conv_fusion
RESULTS
Environments
- date:
Wed Feb 21 01:04:03 EST 2024
- python version:
3.9.18 (main, Sep 11 2023, 13:41:44) [GCC 11.2.0]
- espnet version:
espnet 202310
- pytorch version:
pytorch 2.1.2+cu118
- Git hash:
edb6ec64bb5d4f2c68a3b81674f0c2822e2e5b58
- Commit date:
Fri Feb 9 21:26:35 2024 +0530
exp/slurp_multiconvformer_conv_fusion
WER
| dataset |
Snt |
Wrd |
Corr |
Sub |
Del |
Ins |
Err |
S.Err |
| decode_asr_asr_model_valid.acc.ave_10best/test |
13078 |
262176 |
84.1 |
7.5 |
8.5 |
2.7 |
18.7 |
47.0 |
CER
| dataset |
Snt |
Wrd |
Corr |
Sub |
Del |
Ins |
Err |
S.Err |
| decode_asr_asr_model_valid.acc.ave_10best/test |
13078 |
1245475 |
90.0 |
3.0 |
7.0 |
3.1 |
13.1 |
47.0 |
TER
| dataset |
Snt |
Wrd |
Corr |
Sub |
Del |
Ins |
Err |
S.Err |
exp/slurp_multiconvformer_conv_fusion/decode_asr_asr_model_valid.acc.ave_10best
WER
| dataset |
Snt |
Wrd |
Corr |
Sub |
Del |
Ins |
Err |
S.Err |
| org/devel |
8690 |
178058 |
84.9 |
7.4 |
7.7 |
3.1 |
18.1 |
48.7 |
CER
| dataset |
Snt |
Wrd |
Corr |
Sub |
Del |
Ins |
Err |
S.Err |
| org/devel |
8690 |
847400 |
90.9 |
2.9 |
6.2 |
3.4 |
12.5 |
48.7 |
TER
| dataset |
Snt |
Wrd |
Corr |
Sub |
Del |
Ins |
Err |
S.Err |
Intent Classification
- Valid Intent Classification Result:
0.8882623705408516
- Test Intent Classification Result:
0.8737574552683897
Entity
| Slu f1 |
Precision |
Recall |
F-Measure |
| test |
0.8076 |
0.7710 |
0.7889 |
ASR config
expand
config: conf/tuning/train_asr_multiconv_e12_mlp3072_linear2048_layerdrop.yaml
print_config: false
log_level: INFO
drop_last_iter: false
dry_run: false
iterator_type: sequence
valid_iterator_type: null
output_dir: exp/slurp_multiconvformer_conv_fusion
ngpu: 1
seed: 0
num_workers: 1
num_att_plot: 3
dist_backend: nccl
dist_init_method: env://
dist_world_size: 2
dist_rank: 0
local_rank: 0
dist_master_addr: localhost
dist_master_port: 40439
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: 60
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
use_lora: false
save_lora_only: true
lora_conf: {}
pretrain_path: null
init_param: []
ignore_init_mismatch: false
freeze_param: []
num_iters_per_epoch: null
batch_size: 64
valid_batch_size: null
batch_bins: 1000000
valid_batch_bins: null
train_shape_file:
- exp/asr_stats_raw_en_word/train/speech_shape
- exp/asr_stats_raw_en_word/train/text_shape.word
valid_shape_file:
- exp/asr_stats_raw_en_word/valid/speech_shape
- exp/asr_stats_raw_en_word/valid/text_shape.word
batch_type: folded
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/wav.scp
- speech
- kaldi_ark
- - dump/raw/train/text
- text
- text
valid_data_path_and_name_and_type:
- - dump/raw/devel/wav.scp
- speech
- kaldi_ark
- - 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: 0.001
weight_decay: 1.0e-06
scheduler: warmuplr
scheduler_conf:
warmup_steps: 35000
token_list:
- <blank>
- <unk>
- ▁SEP
- ▁FILL
- s
- ▁the
- a
- ▁to
- ▁i
- ▁me
- e
- ▁s
- ▁a
- i
- ▁you
- ▁what
- er
- ing
- u
- ▁is
- ''''
- o
- p
- ▁in
- ▁p
- y
- ▁my
- ▁please
- d
- c
- m
- ▁b
- l
- ▁m
- ▁c
- st
- date
- n
- ▁d
- le
- b
- ▁for
- re
- t
- ▁on
- en
- h
- 'on'
- ar
- person
- ▁re
- ▁f
- ▁g
- ▁of
- an
- ▁
- g
- ▁today
- ▁t
- or
- ▁it
- ▁this
- ▁h
- r
- f
- at
- ch
- ce
- place_name
- ▁email
- ▁do
- es
- ri
- ▁e
- ▁w
- ic
- in
- ▁that
- event_name
- ▁play
- ▁and
- al
- ▁n
- ▁can
- email_query
- ve
- ▁new
- day
- it
- ate
- ▁from
- ▁have
- k
- time
- ▁am
- media_type
- email_sendemail
- ent
- ▁olly
- qa_factoid
- se
- v
- et
- ck
- ▁any
- calendar_set
- ly
- th
- ▁how
- ▁meeting
- ed
- ▁tell
- ▁st
- x
- ur
- ro
- ▁at
- nd
- ▁list
- w
- ▁u
- ou
- ▁not
- ▁about
- ▁an
- ▁o
- general_negate
- ut
- ▁time
- ▁be
- ▁ch
- ▁are
- social_post
- business_name
- la
- ty
- play_music
- ot
- general_quirky
- ▁l
- ▁sh
- ▁tweet
- om
- ▁week
- um
- ▁one
- ter
- ▁he
- ▁up
- ▁com
- general_praise
- weather_query
- ▁next
- ▁th
- ▁check
- calendar_query
- ▁last
- ▁ro
- ad
- is
- ▁with
- ay
- ▁send
- pe
- ▁pm
- ▁tomorrow
- ▁j
- un
- ▁train
- general_explain
- ▁v
- one
- ▁r
- ra
- news_query
- ation
- ▁emails
- us
- if
- ct
- ▁co
- ▁add
- ▁will
- ▁se
- nt
- ▁was
- ine
- ▁de
- ▁set
- ▁ex
- ▁would
- ir
- ow
- ber
- general_repeat
- ight
- ook
- ▁again
- ▁song
- currency_name
- ll
- ▁ha
- ▁go
- relation
- te
- ion
- and
- ▁y
- ▁ye
- general_affirm
- general_confirm
- ery
- ▁po
- ff
- ▁we
- ▁turn
- ▁did
- ▁mar
- ▁alarm
- ▁like
- datetime_query
- ers
- ▁all
- ▁remind
- ▁so
- qa_definition
- ▁calendar
- end
- ▁said
- ci
- ▁off
- ▁john
- ▁day
- ss
- pla
- ume
- ▁get
- ail
- pp
- z
- ry
- am
- ▁need
- as
- ▁thank
- ▁wh
- ▁want
- ▁right
- ▁jo
- ▁facebook
- ▁k
- ge
- ld
- ▁fri
- ▁two
- general_dontcare
- ▁news
- ol
- oo
- ant
- ▁five
- ▁event
- ake
- definition_word
- transport_type
- ▁your
- vi
- orn
- op
- ▁weather
- ome
- ▁app
- ▁lo
- de
- ▁music
- weather_descriptor
- ak
- ke
- ▁there
- ▁si
- ▁lights
- ▁now
- ▁mo
- calendar_remove
- our
- ▁dollar
- food_type
- me
- ▁more
- ▁no
- ▁birthday
- orrect
- ▁rep
- ▁show
- play_radio
- ▁mon
- ▁does
- ood
- ag
- li
- ▁sto
- ▁contact
- cket
- email_querycontact
- ▁ev
- ▁could
- ange
- ▁just
- out
- ame
- .
- ▁ja
- ▁confirm
- qa_currency
- ▁man
- ▁late
- ▁think
- ▁some
- timeofday
- ▁bo
- qa_stock
- ong
- ▁start
- ▁work
- ▁ten
- int
- ▁command
- all
- ▁make
- ▁la
- j
- ▁answ
- ▁hour
- ▁cle
- ah
- ▁find
- ▁service
- ▁fa
- qu
- general_commandstop
- ai
- ▁when
- ▁te
- ▁by
- social_query
- ard
- ▁tw
- ul
- id
- ▁seven
- ▁where
- ▁much
- art
- ▁appointment
- ver
- artist_name
- el
- device_type
- ▁know
- ▁three
- ▁events
- ▁tr
- ▁li
- ork
- red
- ect
- ▁let
- ▁respon
- ▁par
- zz
- ▁give
- ▁twenty
- ▁ti
- ▁curre
- play_podcasts
- ▁radio
- cooking_recipe
- transport_query
- ▁con
- gh
- ▁le
- lists_query
- ▁rem
- recommendation_events
- house_place
- alarm_set
- play_audiobook
- ist
- ase
- music_genre
- ive
- ast
- player_setting
- ort
- lly
- news_topic
- list_name
- ▁playlist
- ▁ne
- business_type
- personal_info
- ind
- ust
- di
- ress
- recommendation_locations
- lists_createoradd
- iot_hue_lightoff
- lists_remove
- ord
- ▁light
- ere
- alarm_query
- audio_volume_mute
- music_query
- ▁audio
- rain
- ▁date
- ▁order
- audio_volume_up
- ▁ar
- ▁podcast
- transport_ticket
- mail
- iot_hue_lightchange
- iot_coffee
- radio_name
- ill
- ▁ri
- '@'
- takeaway_query
- song_name
- takeaway_order
- ▁ra
- email_addcontact
- play_game
- book
- transport_traffic
- ▁house
- music_likeness
- her
- transport_taxi
- iot_hue_lightdim
- ment
- ght
- fo
- order_type
- color_type
- '1'
- ven
- ould
- general_joke
- ess
- ain
- qa_maths
- ▁place
- ▁twe
- cast
- iot_cleaning
- ▁che
- ▁cont
- ith
- audiobook_name
- email_address
- game_name
- ▁cal
- general_frequency
- ▁tom
- ▁food
- act
- iot_hue_lightup
- '2'
- alarm_remove
- podcast_descriptor
- ▁definition
- audio_volume_down
- ▁media
- email_folder
- dia
- meal_type
- ▁mus
- recommendation_movies
- ▁ad
- ree
- pt
- now
- playlist_name
- ▁person
- change_amount
- ▁pla
- escri
- datetime_convert
- podcast_name
- ▁ab
- time_zone
- ▁def
- ting
- iot_wemo_on
- music_settings
- iot_wemo_off
- orre
- cy
- ank
- music_descriptor
- lar
- app_name
- row
- joke_type
- xt
- of
- ition
- ▁meet
- ink
- ▁confir
- transport_agency
- general_greet
- ▁business
- ▁art
- ▁ag
- urn
- escript
- rom
- ▁rel
- ▁au
- ▁currency
- audio_volume_other
- iot_hue_lighton
- ▁artist
- '?'
- ▁bus
- cooking_type
- movie_name
- coffee_type
- ingredient
- ather
- music_dislikeness
- sp
- q
- ▁ser
- esc
- ▁bir
- ▁cur
- name
- ▁tran
- ▁hou
- ek
- uch
- ▁conf
- ▁face
- '9'
- ▁birth
- I
- sw
- transport_descriptor
- ▁comm
- lease
- transport_name
- aid
- movie_type
- ▁device
- alarm_type
- audiobook_author
- '5'
- drink_type
- ▁joh
- ▁defin
- word
- ▁curren
- order
- iness
- W
- cooking_query
- sport_type
- ▁relation
- oint
- H
- '8'
- A
- '0'
- ▁dol
- vice
- ▁pers
- '&'
- T
- ▁appoint
- _
- '7'
- '3'
- '-'
- game_type
- ▁pod
- N
- M
- E
- list
- music_album
- dio
- ▁transport
- qa_query
- C
- O
- U
- query_detail
- ']'
- '['
- descriptor
- ':'
- spon
- <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: 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
aux_ctc_tasks: []
frontend: default
frontend_conf:
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: null
preencoder_conf: {}
encoder: multiconv_conformer
encoder_conf:
output_size: 512
attention_heads: 8
selfattention_layer_type: rel_selfattn
pos_enc_layer_type: rel_pos
rel_pos_type: latest
cgmlp_linear_units: 3072
multicgmlp_type: concat_fusion
multicgmlp_kernel_sizes: 7,15,23,31
multicgmlp_merge_conv_kernel: 31
use_linear_after_conv: false
gate_activation: identity
num_blocks: 12
dropout_rate: 0.1
positional_dropout_rate: 0.1
attention_dropout_rate: 0.1
input_layer: conv2d
layer_drop_rate: 0.1
linear_units: 1152
positionwise_layer_type: linear
macaron_style: true
use_cnn_module: true
postencoder: null
postencoder_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
layer_drop_rate: 0.2
preprocessor: default
preprocessor_conf: {}
required:
- output_dir
- token_list
version: '202310'
distributed: true
Citing ESPnet
@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:
@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}
}
