import from zenodo

README.md

@@ -0,0 +1,43 @@
+---
+tags:
+- espnet
+- audio
+- <add_more_tags>
+language: en
+datasets:
+- slurp
+license: cc-by-4.0
+---
+## ESPnet2 ASR1 pretrained model 
+### `siddhana/slurp_new_asr_train_asr_conformer_raw_en_word_valid.acc.ave_10best`
+♻️ Imported from https://zenodo.org/record/5590384
+
+This model was trained by siddhana using slurp/asr11 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: `Fri Sep 24 01:51:48 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|108484|84.6|8.7|6.6|1.4|16.8|50.8|
+|inference_asr_model_valid.acc.ave_10best/test|13078|159666|84.4|8.9|6.7|1.4|17.0|49.3|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|inference_asr_model_valid.acc.ave_10best/devel|8690|512732|91.9|3.5|4.6|1.8|9.9|50.8|
+|inference_asr_model_valid.acc.ave_10best/test|13078|757056|91.7|3.5|4.7|1.8|10.1|49.3|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|

exp/asr_train_asr_conformer_raw_en_word/config.yaml

@@ -0,0 +1,754 @@
+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: 50
+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>
+- ▁the
+- s
+- ▁to
+- ▁i
+- ▁me
+- ▁you
+- ▁what
+- ▁a
+- ▁is
+- ▁my
+- ▁please
+- a
+- ''''
+- y
+- ▁in
+- ing
+- ▁s
+- e
+- ▁for
+- i
+- ▁on
+- d
+- t
+- o
+- u
+- er
+- p
+- ▁of
+- es
+- re
+- l
+- ▁it
+- ▁p
+- le
+- ▁f
+- ▁m
+- ▁email
+- ▁d
+- m
+- ▁c
+- st
+- r
+- n
+- ar
+- ▁h
+- b
+- ▁that
+- c
+- ▁this
+- h
+- an
+- email_query
+- ▁play
+- ▁re
+- ▁b
+- ▁do
+- ▁can
+- at
+- ▁have
+- g
+- ▁from
+- ▁and
+- en
+- email_sendemail
+- ▁olly
+- 'on'
+- ▁new
+- it
+- qa_factoid
+- calendar_set
+- ▁any
+- or
+- ▁g
+- ▁how
+- ▁t
+- ▁tell
+- ch
+- ▁not
+- ▁about
+- ▁at
+- ate
+- general_negate
+- f
+- ▁today
+- ▁e
+- ed
+- ▁list
+- ▁r
+- in
+- k
+- ic
+- social_post
+- ▁are
+- play_music
+- general_quirky
+- ▁l
+- al
+- v
+- ent
+- ▁n
+- ▁be
+- ▁an
+- ▁st
+- et
+- ▁am
+- general_praise
+- ▁time
+- weather_query
+- ▁up
+- ▁check
+- calendar_query
+- ▁w
+- om
+- ur
+- ▁send
+- ▁with
+- ly
+- w
+- general_explain
+- ad
+- ▁th
+- news_query
+- ▁one
+- ▁emails
+- day
+- ▁sh
+- ce
+- ▁last
+- ve
+- ▁he
+- z
+- ▁ch
+- ▁will
+- ▁set
+- ▁would
+- ▁was
+- x
+- general_repeat
+- ▁add
+- ou
+- ▁again
+- ▁ex
+- is
+- ct
+- general_affirm
+- general_confirm
+- ▁song
+- ▁next
+- ▁j
+- ▁meeting
+- um
+- ation
+- ▁turn
+- ▁did
+- if
+- ▁alarm
+- am
+- ▁like
+- datetime_query
+- ter
+- ▁remind
+- ▁o
+- qa_definition
+- ▁said
+- ▁calendar
+- ll
+- se
+- ers
+- th
+- ▁get
+- our
+- ▁need
+- ▁all
+- ot
+- ▁want
+- ▁off
+- and
+- ▁right
+- ▁de
+- ▁tr
+- ut
+- general_dontcare
+- ▁
+- ▁week
+- as
+- ▁tweet
+- ight
+- ir
+- ▁your
+- ▁event
+- ▁news
+- ▁se
+- ay
+- ion
+- ▁com
+- ▁there
+- ▁ye
+- ▁weather
+- un
+- ▁confirm
+- ld
+- calendar_remove
+- ▁y
+- ▁lights
+- ▁more
+- ▁v
+- play_radio
+- ▁does
+- ▁po
+- ▁now
+- id
+- email_querycontact
+- ▁show
+- ▁could
+- ery
+- op
+- ▁day
+- ▁pm
+- ▁music
+- ▁tomorrow
+- ▁train
+- ▁u
+- ine
+- ▁or
+- ange
+- qa_currency
+- ice
+- ▁contact
+- ▁just
+- ▁jo
+- ▁think
+- qa_stock
+- end
+- ss
+- ber
+- ▁tw
+- ▁command
+- ▁make
+- ▁no
+- ▁mo
+- pe
+- ▁find
+- general_commandstop
+- ▁when
+- social_query
+- ▁so
+- ong
+- ▁co
+- ant
+- ow
+- ▁much
+- ▁where
+- ul
+- ue
+- ri
+- ap
+- ▁start
+- ▁mar
+- ▁by
+- one
+- ▁know
+- ▁wor
+- oo
+- ▁give
+- ▁let
+- ▁events
+- der
+- ▁ro
+- ▁pr
+- ▁pl
+- play_podcasts
+- art
+- us
+- ▁work
+- ▁current
+- ol
+- cooking_recipe
+- nt
+- ▁correct
+- transport_query
+- ia
+- ▁stock
+- ▁br
+- ive
+- ▁app
+- ▁two
+- ▁latest
+- lists_query
+- ▁some
+- recommendation_events
+- ab
+- ▁go
+- ▁but
+- ook
+- ke
+- alarm_set
+- play_audiobook
+- ▁k
+- ▁response
+- ▁wr
+- cast
+- ▁open
+- ▁cle
+- ▁done
+- ▁got
+- ▁ca
+- ite
+- ase
+- ▁thank
+- iv
+- ah
+- ag
+- ▁answer
+- ie
+- ▁five
+- ▁book
+- ist
+- ▁rec
+- ore
+- ▁john
+- ment
+- ▁appreci
+- ▁fri
+- ack
+- ▁remove
+- ated
+- ock
+- ree
+- j
+- ▁good
+- ▁many
+- orn
+- fe
+- ▁radio
+- ▁we
+- int
+- ▁facebook
+- ▁cl
+- ▁sev
+- ▁schedule
+- ard
+- ▁per
+- ▁li
+- ▁going
+- nd
+- ain
+- recommendation_locations
+- ▁post
+- lists_createoradd
+- ff
+- ▁su
+- red
+- iot_hue_lightoff
+- lists_remove
+- ▁ar
+- een
+- ▁say
+- ro
+- ▁volume
+- ▁le
+- ▁reply
+- ▁complaint
+- ▁out
+- ▁delete
+- ▁ne
+- ame
+- ▁detail
+- ▁if
+- im
+- ▁happ
+- orr
+- ich
+- em
+- ▁ev
+- ction
+- ▁dollar
+- ▁as
+- alarm_query
+- audio_volume_mute
+- ac
+- music_query
+- ▁mon
+- ther
+- ▁thanks
+- cel
+- ▁who
+- ave
+- ▁service
+- ▁mail
+- ty
+- ▁hear
+- de
+- ▁si
+- ▁wh
+- ood
+- ell
+- ▁con
+- ▁once
+- ound
+- ▁don
+- ▁loc
+- ▁light
+- ▁birthday
+- ▁inf
+- ort
+- ffe
+- ▁playlist
+- el
+- ening
+- ▁us
+- ▁un
+- ▁has
+- own
+- ▁inc
+- ai
+- ▁speak
+- age
+- ▁mess
+- ast
+- ci
+- ver
+- ▁ten
+- ▁underst
+- ▁pro
+- ▁q
+- enty
+- ▁ticket
+- gh
+- audio_volume_up
+- ▁take
+- ▁bo
+- ally
+- ome
+- transport_ticket
+- ind
+- iot_hue_lightchange
+- pp
+- iot_coffee
+- ▁res
+- plain
+- io
+- lar
+- takeaway_query
+- ge
+- takeaway_order
+- email_addcontact
+- play_game
+- ak
+- ▁fa
+- transport_traffic
+- music_likeness
+- ▁rep
+- act
+- ust
+- transport_taxi
+- iot_hue_lightdim
+- ▁mu
+- ▁ti
+- ick
+- ▁ha
+- ould
+- general_joke
+- '1'
+- qa_maths
+- ▁lo
+- iot_cleaning
+- q
+- ake
+- ill
+- her
+- iot_hue_lightup
+- pl
+- '2'
+- alarm_remove
+- orrect
+- ▁cont
+- mail
+- out
+- audio_volume_down
+- book
+- ail
+- recommendation_movies
+- ck
+- ▁man
+- ▁mus
+- ▁che
+- me
+- ume
+- ▁answ
+- datetime_convert
+- ▁late
+- iot_wemo_on
+- ▁twe
+- music_settings
+- iot_wemo_off
+- orre
+- ith
+- ▁tom
+- ▁fr
+- ere
+- ▁ad
+- xt
+- ▁ab
+- ank
+- general_greet
+- now
+- ▁meet
+- ▁curre
+- ▁respon
+- ▁ag
+- ght
+- audio_volume_other
+- ink
+- ▁spe
+- iot_hue_lighton
+- ▁rem
+- lly
+- '?'
+- urn
+- ▁op
+- ▁complain
+- ▁comm
+- let
+- music_dislikeness
+- ove
+- ▁sch
+- ather
+- ▁rad
+- edule
+- ▁under
+- icket
+- lease
+- ▁bir
+- erv
+- ▁birth
+- ▁face
+- ▁cur
+- sw
+- ▁serv
+- ek
+- aid
+- '9'
+- ▁vol
+- edu
+- '5'
+- cooking_query
+- lete
+- ▁joh
+- ▁det
+- firm
+- nder
+- '0'
+- irm
+- '8'
+- '&'
+- _
+- list
+- pon
+- qa_query
+- '7'
+- '3'
+- '-'
+- reci
+- ▁doll
+- <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 sha256:0b2144a9a26a71d820fd5923124e33cf8be4accf7e731e3c72526805350806d9
+size 437699867

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: 1634835292.734022
+torch: 1.8.1+cu102
+yaml_files:
+  asr_train_config: exp/asr_train_asr_conformer_raw_en_word/config.yaml