Update model

README.md

@@ -0,0 +1,338 @@
+---
+tags:
+- espnet
+- audio
+- automatic-speech-recognition
+language: en
+datasets:
+- swbd_da
+license: cc-by-4.0
+---
+
+## ESPnet2 ASR model 
+
+### `akreal/espnet2_swbd_da_hubert_conformer`
+
+This model was trained by Pavel Denisov using swbd_da recipe in [espnet](https://github.com/espnet/espnet/).
+
+### Demo: How to use in ESPnet2
+
+```bash
+cd espnet
+git checkout 08c6efbc6299c972301236625f9abafe087c9f9c
+pip install -e .
+cd egs2/swbd_da/asr1
+./run.sh --skip_data_prep false --skip_train true --download_model akreal/espnet2_swbd_da_hubert_conformer
+```
+
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Thu Jan 20 19:31:21 CET 2022`
+- python version: `3.8.12 (default, Aug 30 2021, 00:00:00)  [GCC 11.2.1 20210728 (Red Hat 11.2.1-1)]`
+- espnet version: `espnet 0.10.6a1`
+- pytorch version: `pytorch 1.10.1+cu113`
+- Git hash: `08c6efbc6299c972301236625f9abafe087c9f9c`
+  - Commit date: `Tue Jan 4 13:40:33 2022 +0100`
+
+## asr_train_asr_raw_en_word_sp
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_asr_model_valid.loss.ave/test_context3|2379|2379|66.3|33.7|0.0|0.0|33.7|33.7|
+|decode_asr_asr_model_valid.loss.ave/valid_context3|8116|8116|69.5|30.5|0.0|0.0|30.5|30.5|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_asr_model_valid.loss.ave/test_context3|2379|19440|76.1|17.7|6.2|8.1|32.0|33.7|
+|decode_asr_asr_model_valid.loss.ave/valid_context3|8116|66353|79.5|16.1|4.4|8.0|28.5|30.5|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+
+## ASR config
+
+<details><summary>expand</summary>
+
+```
+config: conf/tuning/train_asr_conformer_hubert_context3.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/asr_train_asr_conformer_hubert_context3_raw_en_word_sp
+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: 35
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - loss
+    - min
+keep_nbest_models: 7
+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: 20
+valid_batch_size: null
+batch_bins: 4000000
+valid_batch_bins: null
+train_shape_file:
+- exp/asr_stats_context3_raw_en_word_sp/train/speech_shape
+- exp/asr_stats_context3_raw_en_word_sp/train/text_shape.word
+valid_shape_file:
+- exp/asr_stats_context3_raw_en_word_sp/valid/speech_shape
+- exp/asr_stats_context3_raw_en_word_sp/valid/text_shape.word
+batch_type: numel
+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_context3_sp/wav.scp
+    - speech
+    - sound
+-   - dump/raw/train_context3_sp/text
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - dump/raw/valid_context3/wav.scp
+    - speech
+    - sound
+-   - dump/raw/valid_context3/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: 0.0001
+scheduler: warmuplr
+scheduler_conf:
+    warmup_steps: 25000
+token_list:
+- <blank>
+- <unk>
+- statement
+- backchannel
+- opinion
+- abandon
+- agree
+- yn_q
+- apprec
+- 'yes'
+- uninterp
+- close
+- wh_q
+- acknowledge
+- 'no'
+- yn_decl_q
+- hedge
+- backchannel_q
+- sum
+- quote
+- affirm
+- other
+- directive
+- repeat
+- open_q
+- completion
+- rhet_q
+- hold
+- reject
+- answer
+- neg
+- ans_dispref
+- repeat_q
+- open
+- or
+- commit
+- maybe
+- decl_q
+- third_pty
+- self_talk
+- thank
+- apology
+- tag_q
+- downplay
+- <sos/eos>
+init: null
+input_size: null
+ctc_conf:
+    dropout_rate: 0.0
+    ctc_type: builtin
+    reduce: true
+    ignore_nan_grad: true
+joint_net_conf: null
+model_conf:
+    ctc_weight: 0.0
+    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: 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: {}
+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: 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: 0.10.5a1
+distributed: false
+```
+
+</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}
+}
+```

exp/asr_train_asr_raw_en_word_sp/RESULTS.md

@@ -0,0 +1,29 @@
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Thu Jan 20 19:24:54 CET 2022`
+- python version: `3.8.12 (default, Aug 30 2021, 00:00:00)  [GCC 11.2.1 20210728 (Red Hat 11.2.1-1)]`
+- espnet version: `espnet 0.10.6a1`
+- pytorch version: `pytorch 1.10.1+cu113`
+- Git hash: `08c6efbc6299c972301236625f9abafe087c9f9c`
+  - Commit date: `Tue Jan 4 13:40:33 2022 +0100`
+
+## asr_train_asr_raw_en_word_sp
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_asr_model_valid.loss.ave/test_context3|2379|2379|66.3|33.7|0.0|0.0|33.7|33.7|
+|decode_asr_asr_model_valid.loss.ave/valid_context3|8116|8116|69.5|30.5|0.0|0.0|30.5|30.5|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_asr_model_valid.loss.ave/test_context3|2379|19440|76.1|17.7|6.2|8.1|32.0|33.7|
+|decode_asr_asr_model_valid.loss.ave/valid_context3|8116|66353|79.5|16.1|4.4|8.0|28.5|30.5|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|

exp/asr_train_asr_raw_en_word_sp/config.yaml

@@ -0,0 +1,240 @@
+config: conf/tuning/train_asr_conformer_hubert_context3.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/asr_train_asr_conformer_hubert_context3_raw_en_word_sp
+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: 35
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - loss
+    - min
+keep_nbest_models: 7
+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: 20
+valid_batch_size: null
+batch_bins: 4000000
+valid_batch_bins: null
+train_shape_file:
+- exp/asr_stats_context3_raw_en_word_sp/train/speech_shape
+- exp/asr_stats_context3_raw_en_word_sp/train/text_shape.word
+valid_shape_file:
+- exp/asr_stats_context3_raw_en_word_sp/valid/speech_shape
+- exp/asr_stats_context3_raw_en_word_sp/valid/text_shape.word
+batch_type: numel
+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_context3_sp/wav.scp
+    - speech
+    - sound
+-   - dump/raw/train_context3_sp/text
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - dump/raw/valid_context3/wav.scp
+    - speech
+    - sound
+-   - dump/raw/valid_context3/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: 0.0001
+scheduler: warmuplr
+scheduler_conf:
+    warmup_steps: 25000
+token_list:
+- <blank>
+- <unk>
+- statement
+- backchannel
+- opinion
+- abandon
+- agree
+- yn_q
+- apprec
+- 'yes'
+- uninterp
+- close
+- wh_q
+- acknowledge
+- 'no'
+- yn_decl_q
+- hedge
+- backchannel_q
+- sum
+- quote
+- affirm
+- other
+- directive
+- repeat
+- open_q
+- completion
+- rhet_q
+- hold
+- reject
+- answer
+- neg
+- ans_dispref
+- repeat_q
+- open
+- or
+- commit
+- maybe
+- decl_q
+- third_pty
+- self_talk
+- thank
+- apology
+- tag_q
+- downplay
+- <sos/eos>
+init: null
+input_size: null
+ctc_conf:
+    dropout_rate: 0.0
+    ctc_type: builtin
+    reduce: true
+    ignore_nan_grad: true
+joint_net_conf: null
+model_conf:
+    ctc_weight: 0.0
+    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: 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: {}
+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: 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: 0.10.5a1
+distributed: false

exp/asr_train_asr_raw_en_word_sp/valid.loss.ave_7best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f90363a91d0bec8dad19f036a0c72a8d223b03846ebf5a55255bde1f7a98ec9c
+size 1701237227

meta.yaml

@@ -0,0 +1,8 @@
+espnet: 0.10.6a1
+files:
+  asr_model_file: exp/asr_train_asr_raw_en_word_sp/valid.loss.ave_7best.pth
+python: "3.8.12 (default, Aug 30 2021, 00:00:00) \n[GCC 11.2.1 20210728 (Red Hat 11.2.1-1)]"
+timestamp: 1642703096.443818
+torch: 1.10.1+cu113
+yaml_files:
+  asr_train_config: exp/asr_train_asr_raw_en_word_sp/config.yaml