Update model

README.md

@@ -1,3 +1,308 @@
 ---
-license: mit
+tags:
+- espnet
+- audio
+- automatic-speech-recognition
+language: en
+datasets:
+- an4
+license: cc-by-4.0
 ---
+
+## ESPnet2 ASR model 
+
+### `jkang/espnet2_an4_transformer`
+
+This model was trained by jaekookang using an4 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 c8f11ef7f5c571fbcc34d53da449353bd75037ce
+pip install -e .
+cd egs2/an4/asr1
+./run.sh --skip_data_prep false --skip_train true --download_model jkang/espnet2_an4_transformer
+```
+
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Fri Aug 19 17:38:46 KST 2022`
+- python version: `3.9.12 (main, Apr  5 2022, 06:56:58)  [GCC 7.5.0]`
+- espnet version: `espnet 202207`
+- pytorch version: `pytorch 1.10.1`
+- Git hash: `c8f11ef7f5c571fbcc34d53da449353bd75037ce`
+  - Commit date: `Fri Aug 19 17:20:13 2022 +0900`
+
+## asr_train_asr_transformer_raw_en_bpe30_sp
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_lm_lm_train_lm_en_bpe30_valid.loss.ave_asr_model_valid.acc.ave/test|130|773|92.0|5.8|2.2|0.4|8.4|33.1|
+|decode_asr_lm_lm_train_lm_en_bpe30_valid.loss.ave_asr_model_valid.acc.ave/train_dev|100|591|89.5|7.3|3.2|0.5|11.0|41.0|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_lm_lm_train_lm_en_bpe30_valid.loss.ave_asr_model_valid.acc.ave/test|130|2565|96.3|1.1|2.6|0.6|4.3|33.1|
+|decode_asr_lm_lm_train_lm_en_bpe30_valid.loss.ave_asr_model_valid.acc.ave/train_dev|100|1915|94.1|1.9|4.0|0.4|6.3|41.0|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_lm_lm_train_lm_en_bpe30_valid.loss.ave_asr_model_valid.acc.ave/test|130|2695|96.4|1.1|2.5|0.6|4.1|33.1|
+|decode_asr_lm_lm_train_lm_en_bpe30_valid.loss.ave_asr_model_valid.acc.ave/train_dev|100|2015|94.4|1.8|3.8|0.3|6.0|41.0|
+
+## ASR config
+
+<details><summary>expand</summary>
+
+```
+config: conf/train_asr_transformer.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/asr_train_asr_transformer_raw_en_bpe30_sp
+ngpu: 1
+seed: 0
+num_workers: 1
+num_att_plot: 3
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: 4
+dist_rank: 0
+local_rank: 0
+dist_master_addr: localhost
+dist_master_port: 43015
+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: 200
+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
+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_bpe30_sp/train/speech_shape
+- exp/asr_stats_raw_en_bpe30_sp/train/text_shape.bpe
+valid_shape_file:
+- exp/asr_stats_raw_en_bpe30_sp/valid/speech_shape
+- exp/asr_stats_raw_en_bpe30_sp/valid/text_shape.bpe
+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_nodev_sp/wav.scp
+    - speech
+    - sound
+-   - dump/raw/train_nodev_sp/text
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - dump/raw/train_dev/wav.scp
+    - speech
+    - sound
+-   - dump/raw/train_dev/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: 2500
+token_list:
+- <blank>
+- <unk>
+- ▁
+- T
+- E
+- O
+- R
+- Y
+- A
+- H
+- U
+- S
+- I
+- F
+- B
+- L
+- P
+- D
+- G
+- M
+- C
+- V
+- X
+- J
+- K
+- Z
+- W
+- N
+- Q
+- <sos/eos>
+init: xavier_uniform
+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: bpe
+bpemodel: data/en_token_list/bpe_unigram30/bpe.model
+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
+frontend: default
+frontend_conf:
+    fs: 16k
+specaug: null
+specaug_conf: {}
+normalize: global_mvn
+normalize_conf:
+    stats_file: exp/asr_stats_raw_en_bpe30_sp/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: transformer
+encoder_conf:
+    output_size: 256
+    attention_heads: 4
+    linear_units: 2048
+    num_blocks: 12
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.0
+    input_layer: conv2d
+    normalize_before: true
+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
+required:
+- output_dir
+- token_list
+version: '202207'
+distributed: true
+```
+
+</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/en_token_list/bpe_unigram30/bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:711fda202c8a36a6b2b7e2dfd9eea0b414397420cbd29ec7dafd107f62f5a0e9
+size 237994

exp/asr_stats_raw_en_bpe30_sp/train/feats_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a09378a62d433d3db78f20ed9f1cc3189aa381fb84756c161d2fb9731976412
+size 1402

exp/asr_train_asr_transformer_raw_en_bpe30_sp/RESULTS.md

@@ -0,0 +1,32 @@
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Fri Aug 19 17:38:46 KST 2022`
+- python version: `3.9.12 (main, Apr  5 2022, 06:56:58)  [GCC 7.5.0]`
+- espnet version: `espnet 202207`
+- pytorch version: `pytorch 1.10.1`
+- Git hash: `c8f11ef7f5c571fbcc34d53da449353bd75037ce`
+  - Commit date: `Fri Aug 19 17:20:13 2022 +0900`
+
+## asr_train_asr_transformer_raw_en_bpe30_sp
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_lm_lm_train_lm_en_bpe30_valid.loss.ave_asr_model_valid.acc.ave/test|130|773|92.0|5.8|2.2|0.4|8.4|33.1|
+|decode_asr_lm_lm_train_lm_en_bpe30_valid.loss.ave_asr_model_valid.acc.ave/train_dev|100|591|89.5|7.3|3.2|0.5|11.0|41.0|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_lm_lm_train_lm_en_bpe30_valid.loss.ave_asr_model_valid.acc.ave/test|130|2565|96.3|1.1|2.6|0.6|4.3|33.1|
+|decode_asr_lm_lm_train_lm_en_bpe30_valid.loss.ave_asr_model_valid.acc.ave/train_dev|100|1915|94.1|1.9|4.0|0.4|6.3|41.0|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_lm_lm_train_lm_en_bpe30_valid.loss.ave_asr_model_valid.acc.ave/test|130|2695|96.4|1.1|2.5|0.6|4.1|33.1|
+|decode_asr_lm_lm_train_lm_en_bpe30_valid.loss.ave_asr_model_valid.acc.ave/train_dev|100|2015|94.4|1.8|3.8|0.3|6.0|41.0|
+

exp/asr_train_asr_transformer_raw_en_bpe30_sp/config.yaml

@@ -0,0 +1,205 @@
+config: conf/train_asr_transformer.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/asr_train_asr_transformer_raw_en_bpe30_sp
+ngpu: 1
+seed: 0
+num_workers: 1
+num_att_plot: 3
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: 4
+dist_rank: 0
+local_rank: 0
+dist_master_addr: localhost
+dist_master_port: 43015
+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: 200
+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
+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_bpe30_sp/train/speech_shape
+- exp/asr_stats_raw_en_bpe30_sp/train/text_shape.bpe
+valid_shape_file:
+- exp/asr_stats_raw_en_bpe30_sp/valid/speech_shape
+- exp/asr_stats_raw_en_bpe30_sp/valid/text_shape.bpe
+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_nodev_sp/wav.scp
+    - speech
+    - sound
+-   - dump/raw/train_nodev_sp/text
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - dump/raw/train_dev/wav.scp
+    - speech
+    - sound
+-   - dump/raw/train_dev/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: 2500
+token_list:
+- <blank>
+- <unk>
+- ▁
+- T
+- E
+- O
+- R
+- Y
+- A
+- H
+- U
+- S
+- I
+- F
+- B
+- L
+- P
+- D
+- G
+- M
+- C
+- V
+- X
+- J
+- K
+- Z
+- W
+- N
+- Q
+- <sos/eos>
+init: xavier_uniform
+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: bpe
+bpemodel: data/en_token_list/bpe_unigram30/bpe.model
+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
+frontend: default
+frontend_conf:
+    fs: 16k
+specaug: null
+specaug_conf: {}
+normalize: global_mvn
+normalize_conf:
+    stats_file: exp/asr_stats_raw_en_bpe30_sp/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: transformer
+encoder_conf:
+    output_size: 256
+    attention_heads: 4
+    linear_units: 2048
+    num_blocks: 12
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.0
+    input_layer: conv2d
+    normalize_before: true
+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
+required:
+- output_dir
+- token_list
+version: '202207'
+distributed: true

exp/asr_train_asr_transformer_raw_en_bpe30_sp/valid.acc.ave_10best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fa42f575245ed4af7176e4393ec048c6cc65dc06d42c9f8441a9ad33e02959b
+size 108678629

exp/lm_train_lm_en_bpe30/23epoch.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9354b3d36b3da2d2a0f54a8efe50fa6df1f696c260a80854614809d835f85fab
+size 27239903

exp/lm_train_lm_en_bpe30/config.yaml

@@ -0,0 +1,149 @@
+config: conf/train_lm.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/lm_train_lm_en_bpe30
+ngpu: 1
+seed: 0
+num_workers: 1
+num_att_plot: 3
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: 4
+dist_rank: 0
+local_rank: 0
+dist_master_addr: localhost
+dist_master_port: 42755
+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: 40
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - loss
+    - min
+keep_nbest_models: 1
+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
+pretrain_path: null
+init_param: []
+ignore_init_mismatch: false
+freeze_param: []
+num_iters_per_epoch: null
+batch_size: 256
+valid_batch_size: null
+batch_bins: 1000000
+valid_batch_bins: null
+train_shape_file:
+- exp/lm_stats_en_bpe30/train/text_shape.bpe
+valid_shape_file:
+- exp/lm_stats_en_bpe30/valid/text_shape.bpe
+batch_type: folded
+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/train_dev/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: 0.1
+scheduler: null
+scheduler_conf: {}
+token_list:
+- <blank>
+- <unk>
+- ▁
+- T
+- E
+- O
+- R
+- Y
+- A
+- H
+- U
+- S
+- I
+- F
+- B
+- L
+- P
+- D
+- G
+- M
+- C
+- V
+- X
+- J
+- K
+- Z
+- W
+- N
+- Q
+- <sos/eos>
+init: null
+model_conf:
+    ignore_id: 0
+use_preprocessor: true
+token_type: bpe
+bpemodel: data/en_token_list/bpe_unigram30/bpe.model
+non_linguistic_symbols: null
+cleaner: null
+g2p: null
+lm: seq_rnn
+lm_conf:
+    unit: 650
+    nlayers: 2
+required:
+- output_dir
+- token_list
+version: '202207'
+distributed: true

exp/lm_train_lm_en_bpe30/perplexity_test/ppl

@@ -0,0 +1 @@
+7.336515906190722

meta.yaml

@@ -0,0 +1,10 @@
+espnet: '202207'
+files:
+  asr_model_file: exp/asr_train_asr_transformer_raw_en_bpe30_sp/valid.acc.ave_10best.pth
+  lm_file: exp/lm_train_lm_en_bpe30/23epoch.pth
+python: "3.9.12 (main, Apr  5 2022, 06:56:58) \n[GCC 7.5.0]"
+timestamp: 1660898327.418722
+torch: 1.10.1
+yaml_files:
+  asr_train_config: exp/asr_train_asr_transformer_raw_en_bpe30_sp/config.yaml
+  lm_train_config: exp/lm_train_lm_en_bpe30/config.yaml