Import from zenodo

README.md

@@ -0,0 +1,43 @@
+---
+tags:
+- espnet
+- audio
+- automatic-speech-recognition
+language: en
+datasets:
+- fsc
+license: cc-by-4.0
+---
+## ESPnet2 ASR pretrained model 
+### `siddhana/slurp_entity_asr_train_asr_conformer_raw_en_word_valid.acc.ave_10best`
+♻️ Imported from https://zenodo.org/record/5590204
+
+This model was trained by siddhana using fsc/asr1 recipe in [espnet](https://github.com/espnet/espnet/).
+### Demo: How to use in ESPnet2
+```python
+# coming soon
+```
+### 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 {Enrique Yalta Soplin} 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 Enrique Yalta Soplin 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}
+}
+```

exp/asr_train_asr_conformer_raw_en_word/RESULTS.md

@@ -0,0 +1,29 @@
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Wed Oct  6 23:32:47 EDT 2021`
+- python version: `3.9.5 (default, Jun  4 2021, 12:28:51)  [GCC 7.5.0]`
+- espnet version: `espnet 0.10.3a2`
+- pytorch version: `pytorch 1.8.1+cu102`
+- Git hash: `8ef7bd675815ae2fbaba930a53c8ad4ae0ad19af`
+  - Commit date: `Sat Sep 11 10:05:59 2021 +0900`
+
+## asr_train_asr_conformer_raw_en_word
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|inference_asr_model_valid.acc.ave_10best/devel|8690|177293|80.1|8.9|10.9|3.1|23.0|59.7|
+|inference_asr_model_valid.acc.ave_10best/test|13078|261300|79.3|9.1|11.6|2.8|23.5|58.7|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|inference_asr_model_valid.acc.ave_10best/devel|8690|846635|87.8|3.5|8.7|3.7|16.0|59.7|
+|inference_asr_model_valid.acc.ave_10best/test|13078|1244599|86.8|3.5|9.6|3.4|16.6|58.7|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|

exp/asr_train_asr_conformer_raw_en_word/config.yaml

@@ -0,0 +1,793 @@
+config: conf/tuning/train_asr_conformer.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/asr_train_asr_conformer_raw_en_word
+ngpu: 1
+seed: 0
+num_workers: 1
+num_att_plot: 3
+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
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: true
+collect_stats: false
+write_collected_feats: false
+max_epoch: 40
+patience: null
+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: 1
+no_forward_run: false
+resume: true
+train_dtype: float32
+use_amp: false
+log_interval: null
+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: []
+num_iters_per_epoch: null
+batch_size: 20
+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
+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/devel/wav.scp
+    - speech
+    - sound
+-   - dump/raw/devel/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: 0.0002
+scheduler: warmuplr
+scheduler_conf:
+    warmup_steps: 25000
+token_list:
+- <blank>
+- <unk>
+- ▁SEP
+- ▁FILL
+- s
+- ▁the
+- ▁to
+- a
+- ▁i
+- ▁me
+- ▁s
+- ▁a
+- i
+- e
+- ▁you
+- ▁what
+- er
+- u
+- ▁is
+- ''''
+- o
+- ing
+- p
+- ▁in
+- ▁p
+- y
+- ▁my
+- ▁please
+- d
+- m
+- ▁b
+- l
+- ▁c
+- date
+- n
+- ▁d
+- c
+- le
+- b
+- ▁m
+- ▁for
+- re
+- st
+- ▁on
+- t
+- 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
+- v
+- et
+- ck
+- ▁any
+- calendar_set
+- ly
+- se
+- th
+- ▁how
+- ▁meeting
+- ed
+- ▁tell
+- ▁st
+- x
+- ur
+- ▁at
+- ro
+- nd
+- ▁list
+- ou
+- w
+- ▁u
+- ▁not
+- ▁about
+- ▁an
+- ▁o
+- general_negate
+- ut
+- ▁time
+- ▁be
+- ▁ch
+- ▁are
+- social_post
+- business_name
+- ty
+- la
+- 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
+- ▁go
+- ▁ha
+- 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
+- ss
+- ▁day
+- pla
+- ume
+- ▁get
+- pp
+- ail
+- 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
+- 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
+- li
+- ag
+- ▁sto
+- ▁contact
+- cket
+- email_querycontact
+- ▁ev
+- ▁could
+- ▁just
+- ange
+- out
+- ame
+- .
+- ▁ja
+- ▁confirm
+- qa_currency
+- ▁man
+- ▁some
+- ▁late
+- ▁think
+- 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
+- ard
+- ▁te
+- ▁by
+- social_query
+- ul
+- ▁tw
+- 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
+- ac
+- ▁morning
+- ▁ti
+- est
+- ▁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
+- ort
+- player_setting
+- 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
+- orn
+- 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
+- set
+- 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
+- music_dislikeness
+- ather
+- 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'
+- '0'
+- ▁dol
+- vice
+- ▁pers
+- '&'
+- T
+- ▁appoint
+- A
+- '7'
+- '3'
+- '-'
+- game_type
+- ▁pod
+- _
+- list
+- music_album
+- dio
+- ▁transport
+- qa_query
+- C
+- O
+- U
+- query_detail
+- spon
+- <sos/eos>
+init: null
+input_size: null
+ctc_conf:
+    dropout_rate: 0.0
+    ctc_type: builtin
+    reduce: true
+    ignore_nan_grad: true
+model_conf:
+    ctc_weight: 0.3
+    lsm_weight: 0.1
+    length_normalized_loss: false
+    extract_feats_in_collect_stats: false
+use_preprocessor: true
+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'
+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: {}
+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: rel_pos
+    selfattention_layer_type: rel_selfattn
+    activation_type: swish
+    use_cnn_module: true
+    cnn_module_kernel: 31
+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
+required:
+- output_dir
+- token_list
+version: 0.10.3a2
+distributed: false

exp/asr_train_asr_conformer_raw_en_word/valid.acc.ave_10best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f85bd4f2c885c262e6fb1e3eb214e000eb6f69cf4846e7d530635c71c7783646
+size 437939867

meta.yaml

@@ -0,0 +1,8 @@
+espnet: 0.10.3a2
+files:
+  asr_model_file: exp/asr_train_asr_conformer_raw_en_word/valid.acc.ave_10best.pth
+python: "3.9.5 (default, Jun  4 2021, 12:28:51) \n[GCC 7.5.0]"
+timestamp: 1636234622.134315
+torch: 1.8.1+cu102
+yaml_files:
+  asr_train_config: exp/asr_train_asr_conformer_raw_en_word/config.yaml