add model files

README.md

@@ -0,0 +1,350 @@
+---
+tags:
+- espnet
+- audio
+- automatic-speech-recognition
+language: en
+datasets:
+- wsj
+license: cc-by-4.0
+---
+
+## ESPnet2 ASR model 
+
+### `pyf98/wsj_conformer_e15_linear1024`
+
+This model was trained by Yifan Peng using wsj recipe in [espnet](https://github.com/espnet/espnet/).
+
+### Demo: How to use in ESPnet2
+
+Follow the [ESPnet installation instructions](https://espnet.github.io/espnet/installation.html)
+if you haven't done that already.
+
+```bash
+cd espnet
+git checkout 0aa06d0535323aabc1d8b057f8769da377f4d9ff
+pip install -e .
+cd egs2/wsj/asr1
+./run.sh --skip_data_prep false --skip_train true --download_model pyf98/wsj_conformer_e15_linear1024
+```
+
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Wed Dec 28 00:25:25 EST 2022`
+- python version: `3.9.15 (main, Nov 24 2022, 14:31:59)  [GCC 11.2.0]`
+- espnet version: `espnet 202211`
+- pytorch version: `pytorch 1.12.1`
+- Git hash: `0aa06d0535323aabc1d8b057f8769da377f4d9ff`
+  - Commit date: `Tue Dec 27 15:08:25 2022 -0600`
+
+## asr_train_asr_conformer_e15_linear1024_raw_en_char
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_lm_lm_train_lm_transformer_en_char_valid.loss.ave_asr_model_valid.acc.ave/test_dev93|503|8234|94.2|5.1|0.8|0.7|6.5|52.5|
+|decode_lm_lm_train_lm_transformer_en_char_valid.loss.ave_asr_model_valid.acc.ave/test_eval92|333|5643|96.4|3.3|0.3|0.6|4.1|37.2|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_lm_lm_train_lm_transformer_en_char_valid.loss.ave_asr_model_valid.acc.ave/test_dev93|503|48634|97.8|1.0|1.2|0.6|2.8|58.3|
+|decode_lm_lm_train_lm_transformer_en_char_valid.loss.ave_asr_model_valid.acc.ave/test_eval92|333|33341|98.6|0.7|0.7|0.5|1.9|46.8|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+
+## ASR config
+
+<details><summary>expand</summary>
+
+```
+config: conf/tuning/train_asr_conformer_e15_linear1024.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/asr_train_asr_conformer_e15_linear1024_raw_en_char
+ngpu: 1
+seed: 0
+num_workers: 4
+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: 100
+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: 2
+no_forward_run: false
+resume: true
+train_dtype: float32
+use_amp: true
+log_interval: 100
+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
+pretrain_path: null
+init_param: []
+ignore_init_mismatch: false
+freeze_param: []
+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_char/train/speech_shape
+- exp/asr_stats_raw_en_char/train/text_shape.char
+valid_shape_file:
+- exp/asr_stats_raw_en_char/valid/speech_shape
+- exp/asr_stats_raw_en_char/valid/text_shape.char
+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_si284/wav.scp
+    - speech
+    - sound
+-   - dump/raw/train_si284/text
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - dump/raw/test_dev93/wav.scp
+    - speech
+    - sound
+-   - dump/raw/test_dev93/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: 0.005
+scheduler: warmuplr
+scheduler_conf:
+    warmup_steps: 30000
+token_list:
+- <blank>
+- <unk>
+- <space>
+- E
+- T
+- A
+- N
+- I
+- O
+- S
+- R
+- H
+- L
+- D
+- C
+- U
+- M
+- P
+- F
+- G
+- Y
+- W
+- B
+- V
+- K
+- .
+- X
+- ''''
+- J
+- Q
+- Z
+- <NOISE>
+- ','
+- '-'
+- '"'
+- '*'
+- ':'
+- (
+- )
+- '?'
+- '!'
+- '&'
+- ;
+- '1'
+- '2'
+- '0'
+- /
+- $
+- '{'
+- '}'
+- '8'
+- '9'
+- '6'
+- '3'
+- '5'
+- '7'
+- '4'
+- '~'
+- '`'
+- _
+- <*IN*>
+- <*MR.*>
+- \
+- ^
+- <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
+joint_net_conf: null
+use_preprocessor: true
+token_type: char
+bpemodel: null
+non_linguistic_symbols: data/nlsyms.txt
+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
+frontend: default
+frontend_conf:
+    fs: 16k
+specaug: null
+specaug_conf: {}
+normalize: global_mvn
+normalize_conf:
+    stats_file: exp/asr_stats_raw_en_char/train/feats_stats.npz
+model: espnet
+model_conf:
+    ctc_weight: 0.3
+    lsm_weight: 0.1
+    length_normalized_loss: false
+preencoder: null
+preencoder_conf: {}
+encoder: conformer
+encoder_conf:
+    output_size: 256
+    attention_heads: 4
+    linear_units: 1024
+    num_blocks: 15
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.1
+    input_layer: conv2d
+    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: {}
+decoder: transformer
+decoder_conf:
+    attention_heads: 4
+    linear_units: 2048
+    num_blocks: 6
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    self_attention_dropout_rate: 0.0
+    src_attention_dropout_rate: 0.0
+preprocessor: default
+preprocessor_conf: {}
+required:
+- output_dir
+- token_list
+version: '202211'
+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}
+}
+```

data/nlsyms.txt

@@ -0,0 +1,3 @@
+<*IN*>
+<*MR.*>
+<NOISE>

exp/asr_stats_raw_en_char/train/feats_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ea03fa4eea91ad6b7e047a7572be73ed998be1896e389935de240c68ccc1931
+size 1402

exp/asr_train_asr_conformer_e15_linear1024_raw_en_char/RESULTS.md

@@ -0,0 +1,29 @@
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Wed Dec 28 00:25:25 EST 2022`
+- python version: `3.9.15 (main, Nov 24 2022, 14:31:59)  [GCC 11.2.0]`
+- espnet version: `espnet 202211`
+- pytorch version: `pytorch 1.12.1`
+- Git hash: `0aa06d0535323aabc1d8b057f8769da377f4d9ff`
+  - Commit date: `Tue Dec 27 15:08:25 2022 -0600`
+
+## asr_train_asr_conformer_e15_linear1024_raw_en_char
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_lm_lm_train_lm_transformer_en_char_valid.loss.ave_asr_model_valid.acc.ave/test_dev93|503|8234|94.2|5.1|0.8|0.7|6.5|52.5|
+|decode_lm_lm_train_lm_transformer_en_char_valid.loss.ave_asr_model_valid.acc.ave/test_eval92|333|5643|96.4|3.3|0.3|0.6|4.1|37.2|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_lm_lm_train_lm_transformer_en_char_valid.loss.ave_asr_model_valid.acc.ave/test_dev93|503|48634|97.8|1.0|1.2|0.6|2.8|58.3|
+|decode_lm_lm_train_lm_transformer_en_char_valid.loss.ave_asr_model_valid.acc.ave/test_eval92|333|33341|98.6|0.7|0.7|0.5|1.9|46.8|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|

exp/asr_train_asr_conformer_e15_linear1024_raw_en_char/config.yaml

@@ -0,0 +1,249 @@
+config: conf/tuning/train_asr_conformer_e15_linear1024.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/asr_train_asr_conformer_e15_linear1024_raw_en_char
+ngpu: 1
+seed: 0
+num_workers: 4
+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: 100
+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: 2
+no_forward_run: false
+resume: true
+train_dtype: float32
+use_amp: true
+log_interval: 100
+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
+pretrain_path: null
+init_param: []
+ignore_init_mismatch: false
+freeze_param: []
+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_char/train/speech_shape
+- exp/asr_stats_raw_en_char/train/text_shape.char
+valid_shape_file:
+- exp/asr_stats_raw_en_char/valid/speech_shape
+- exp/asr_stats_raw_en_char/valid/text_shape.char
+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_si284/wav.scp
+    - speech
+    - sound
+-   - dump/raw/train_si284/text
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - dump/raw/test_dev93/wav.scp
+    - speech
+    - sound
+-   - dump/raw/test_dev93/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: 0.005
+scheduler: warmuplr
+scheduler_conf:
+    warmup_steps: 30000
+token_list:
+- <blank>
+- <unk>
+- <space>
+- E
+- T
+- A
+- N
+- I
+- O
+- S
+- R
+- H
+- L
+- D
+- C
+- U
+- M
+- P
+- F
+- G
+- Y
+- W
+- B
+- V
+- K
+- .
+- X
+- ''''
+- J
+- Q
+- Z
+- <NOISE>
+- ','
+- '-'
+- '"'
+- '*'
+- ':'
+- (
+- )
+- '?'
+- '!'
+- '&'
+- ;
+- '1'
+- '2'
+- '0'
+- /
+- $
+- '{'
+- '}'
+- '8'
+- '9'
+- '6'
+- '3'
+- '5'
+- '7'
+- '4'
+- '~'
+- '`'
+- _
+- <*IN*>
+- <*MR.*>
+- \
+- ^
+- <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
+joint_net_conf: null
+use_preprocessor: true
+token_type: char
+bpemodel: null
+non_linguistic_symbols: data/nlsyms.txt
+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
+frontend: default
+frontend_conf:
+    fs: 16k
+specaug: null
+specaug_conf: {}
+normalize: global_mvn
+normalize_conf:
+    stats_file: exp/asr_stats_raw_en_char/train/feats_stats.npz
+model: espnet
+model_conf:
+    ctc_weight: 0.3
+    lsm_weight: 0.1
+    length_normalized_loss: false
+preencoder: null
+preencoder_conf: {}
+encoder: conformer
+encoder_conf:
+    output_size: 256
+    attention_heads: 4
+    linear_units: 1024
+    num_blocks: 15
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.1
+    input_layer: conv2d
+    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: {}
+decoder: transformer
+decoder_conf:
+    attention_heads: 4
+    linear_units: 2048
+    num_blocks: 6
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    self_attention_dropout_rate: 0.0
+    src_attention_dropout_rate: 0.0
+preprocessor: default
+preprocessor_conf: {}
+required:
+- output_dir
+- token_list
+version: '202211'
+distributed: false

exp/asr_train_asr_conformer_e15_linear1024_raw_en_char/valid.acc.ave_10best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91ec12d91bb5144564f260c2391126e9edc6546205dd10d28b36c2a9fb61d785
+size 141181493

exp/lm_train_lm_transformer_en_char/config.yaml

@@ -0,0 +1,190 @@
+config: conf/train_lm_transformer.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/lm_train_lm_transformer_en_char
+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: 44469
+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: 25
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - loss
+    - min
+keep_nbest_models: 10
+nbest_averaging_interval: 0
+grad_clip: 5.0
+grad_clip_type: 2.0
+grad_noise: false
+accum_grad: 2
+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
+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: 350000
+valid_batch_bins: null
+train_shape_file:
+- exp/lm_stats_en_char/train/text_shape.char
+valid_shape_file:
+- exp/lm_stats_en_char/valid/text_shape.char
+batch_type: numel
+valid_batch_type: null
+fold_length:
+- 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/lm_train.txt
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - dump/raw/test_dev93/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: 0.001
+scheduler: warmuplr
+scheduler_conf:
+    warmup_steps: 25000
+token_list:
+- <blank>
+- <unk>
+- <space>
+- E
+- T
+- A
+- N
+- I
+- O
+- S
+- R
+- H
+- L
+- D
+- C
+- U
+- M
+- P
+- F
+- G
+- Y
+- W
+- B
+- V
+- K
+- .
+- X
+- ''''
+- J
+- Q
+- Z
+- <NOISE>
+- ','
+- '-'
+- '"'
+- '*'
+- ':'
+- (
+- )
+- '?'
+- '!'
+- '&'
+- ;
+- '1'
+- '2'
+- '0'
+- /
+- $
+- '{'
+- '}'
+- '8'
+- '9'
+- '6'
+- '3'
+- '5'
+- '7'
+- '4'
+- '~'
+- '`'
+- _
+- <*IN*>
+- <*MR.*>
+- \
+- ^
+- <sos/eos>
+init: null
+model_conf:
+    ignore_id: 0
+use_preprocessor: true
+token_type: char
+bpemodel: null
+non_linguistic_symbols: data/nlsyms.txt
+cleaner: null
+g2p: null
+lm: transformer
+lm_conf:
+    pos_enc: null
+    embed_unit: 128
+    att_unit: 512
+    head: 8
+    unit: 2048
+    layer: 16
+    dropout_rate: 0.1
+required:
+- output_dir
+- token_list
+version: '202211'
+distributed: true

exp/lm_train_lm_transformer_en_char/perplexity_test/ppl

@@ -0,0 +1 @@
+2.2880849662126233

exp/lm_train_lm_transformer_en_char/valid.loss.ave_10best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e700b5a85868956df7aae5581f76e3a66115d1bdf2ee031b51454dc21a7010db
+size 202290031

meta.yaml

@@ -0,0 +1,10 @@
+espnet: '202211'
+files:
+  asr_model_file: exp/asr_train_asr_conformer_e15_linear1024_raw_en_char/valid.acc.ave_10best.pth
+  lm_file: exp/lm_train_lm_transformer_en_char/valid.loss.ave_10best.pth
+python: "3.9.15 (main, Nov 24 2022, 14:31:59) \n[GCC 11.2.0]"
+timestamp: 1672205127.39957
+torch: 1.12.1
+yaml_files:
+  asr_train_config: exp/asr_train_asr_conformer_e15_linear1024_raw_en_char/config.yaml
+  lm_train_config: exp/lm_train_lm_transformer_en_char/config.yaml