Update model

README.md

@@ -0,0 +1,419 @@
+---
+tags:
+- espnet
+- audio
+- automatic-speech-recognition
+language: en
+datasets:
+- an4
+license: cc-by-4.0
+---
+
+## ESPnet2 ASR model 
+
+### `Fhrozen/test_an4`
+
+This model was trained by Fhrozen using an4 recipe in [espnet](https://github.com/espnet/espnet/).
+
+### Demo: How to use in ESPnet2
+
+```bash
+cd espnet
+git checkout b8df4c928e132acff78d196988bdb68a66987952
+pip install -e .
+cd egs2/an4/asr1
+./run.sh --skip_data_prep false --skip_train true --download_model Fhrozen/test_an4
+```
+
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Wed Oct 20 00:00:46 JST 2021`
+- python version: `3.9.7 (default, Sep 16 2021, 13:09:58)  [GCC 7.5.0]`
+- espnet version: `espnet 0.10.4a1`
+- pytorch version: `pytorch 1.9.0`
+- Git hash: `b8df4c928e132acff78d196988bdb68a66987952`
+  - Commit date: `Tue Oct 19 07:48:11 2021 -0400`
+
+## asr_train_raw_en_bpe30
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|inference_lm_lm_train_lm_en_bpe30_valid.loss.ave_asr_model_valid.acc.best/test|130|773|4.0|22.3|73.7|0.1|96.1|100.0|
+|inference_lm_lm_train_lm_en_bpe30_valid.loss.ave_asr_model_valid.acc.best/train_dev|100|591|2.7|21.8|75.5|0.0|97.3|100.0|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|inference_lm_lm_train_lm_en_bpe30_valid.loss.ave_asr_model_valid.acc.best/test|130|2565|17.2|16.4|66.4|1.0|83.8|100.0|
+|inference_lm_lm_train_lm_en_bpe30_valid.loss.ave_asr_model_valid.acc.best/train_dev|100|1915|15.5|16.4|68.1|0.9|85.5|100.0|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|inference_lm_lm_train_lm_en_bpe30_valid.loss.ave_asr_model_valid.acc.best/test|130|2695|21.1|15.6|63.3|0.9|79.9|100.0|
+|inference_lm_lm_train_lm_en_bpe30_valid.loss.ave_asr_model_valid.acc.best/train_dev|100|2015|19.4|15.6|65.0|0.9|81.5|100.0|
+
+## ASR config
+
+<details><summary>expand</summary>
+
+```
+config: null
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/asr_train_raw_en_bpe30
+ngpu: 0
+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: null
+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:
+-   - train
+    - loss
+    - min
+-   - valid
+    - loss
+    - min
+-   - train
+    - acc
+    - max
+-   - 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_bpe30/train/speech_shape
+- exp/asr_stats_raw_en_bpe30/train/text_shape.bpe
+valid_shape_file:
+- exp/asr_stats_raw_en_bpe30/valid/speech_shape
+- exp/asr_stats_raw_en_bpe30/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/wav.scp
+    - speech
+    - sound
+-   - dump/raw/train_nodev/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: adadelta
+optim_conf: {}
+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
+input_size: null
+ctc_conf:
+    dropout_rate: 0.0
+    ctc_type: builtin
+    reduce: true
+    ignore_nan_grad: true
+model_conf:
+    ctc_weight: 0.5
+    ignore_id: -1
+    lsm_weight: 0.0
+    length_normalized_loss: false
+    report_cer: true
+    report_wer: true
+    sym_space: <space>
+    sym_blank: <blank>
+    extract_feats_in_collect_stats: true
+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'
+frontend: default
+frontend_conf:
+    fs: 16k
+specaug: null
+specaug_conf: {}
+normalize: global_mvn
+normalize_conf:
+    stats_file: exp/asr_stats_raw_en_bpe30/train/feats_stats.npz
+preencoder: null
+preencoder_conf: {}
+encoder: rnn
+encoder_conf: {}
+postencoder: null
+postencoder_conf: {}
+decoder: rnn
+decoder_conf: {}
+required:
+- output_dir
+- token_list
+version: 0.10.4a1
+distributed: false
+```
+
+</details>
+
+## LM config
+    
+<details><summary>expand</summary>
+
+```
+  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: 0
+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: null
+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
+    - loss
+    - min
+keep_nbest_models: 1
+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: 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: 0.10.4a1
+distributed: false
+```
+
+</details>
+    

data/en_token_list/bpe_unigram30/bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37b8ea90f6f41bb62fa8f73850f8e1f40bf78987dadfe88567b3908c3e1751d1
+size 237994

exp/asr_train_raw_en_bpe30/2epoch.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6853bb9dad5af6eaca2ad7adb234ec7769cbe655bba9b38fe147e85cd116b53a
+size 33105716

exp/asr_train_raw_en_bpe30/RESULTS.md

@@ -0,0 +1,32 @@
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Wed Oct 20 00:00:46 JST 2021`
+- python version: `3.9.7 (default, Sep 16 2021, 13:09:58)  [GCC 7.5.0]`
+- espnet version: `espnet 0.10.4a1`
+- pytorch version: `pytorch 1.9.0`
+- Git hash: `b8df4c928e132acff78d196988bdb68a66987952`
+  - Commit date: `Tue Oct 19 07:48:11 2021 -0400`
+
+## asr_train_raw_en_bpe30
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|inference_lm_lm_train_lm_en_bpe30_valid.loss.ave_asr_model_valid.acc.best/test|130|773|4.0|22.3|73.7|0.1|96.1|100.0|
+|inference_lm_lm_train_lm_en_bpe30_valid.loss.ave_asr_model_valid.acc.best/train_dev|100|591|2.7|21.8|75.5|0.0|97.3|100.0|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|inference_lm_lm_train_lm_en_bpe30_valid.loss.ave_asr_model_valid.acc.best/test|130|2565|17.2|16.4|66.4|1.0|83.8|100.0|
+|inference_lm_lm_train_lm_en_bpe30_valid.loss.ave_asr_model_valid.acc.best/train_dev|100|1915|15.5|16.4|68.1|0.9|85.5|100.0|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|inference_lm_lm_train_lm_en_bpe30_valid.loss.ave_asr_model_valid.acc.best/test|130|2695|21.1|15.6|63.3|0.9|79.9|100.0|
+|inference_lm_lm_train_lm_en_bpe30_valid.loss.ave_asr_model_valid.acc.best/train_dev|100|2015|19.4|15.6|65.0|0.9|81.5|100.0|
+

exp/asr_train_raw_en_bpe30/config.yaml

@@ -0,0 +1,196 @@
+config: null
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/asr_train_raw_en_bpe30
+ngpu: 0
+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: null
+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:
+-   - train
+    - loss
+    - min
+-   - valid
+    - loss
+    - min
+-   - train
+    - acc
+    - max
+-   - 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_bpe30/train/speech_shape
+- exp/asr_stats_raw_en_bpe30/train/text_shape.bpe
+valid_shape_file:
+- exp/asr_stats_raw_en_bpe30/valid/speech_shape
+- exp/asr_stats_raw_en_bpe30/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/wav.scp
+    - speech
+    - sound
+-   - dump/raw/train_nodev/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: adadelta
+optim_conf: {}
+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
+input_size: null
+ctc_conf:
+    dropout_rate: 0.0
+    ctc_type: builtin
+    reduce: true
+    ignore_nan_grad: true
+model_conf:
+    ctc_weight: 0.5
+    ignore_id: -1
+    lsm_weight: 0.0
+    length_normalized_loss: false
+    report_cer: true
+    report_wer: true
+    sym_space: <space>
+    sym_blank: <blank>
+    extract_feats_in_collect_stats: true
+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'
+frontend: default
+frontend_conf:
+    fs: 16k
+specaug: null
+specaug_conf: {}
+normalize: global_mvn
+normalize_conf:
+    stats_file: exp/asr_stats_raw_en_bpe30/train/feats_stats.npz
+preencoder: null
+preencoder_conf: {}
+encoder: rnn
+encoder_conf: {}
+postencoder: null
+postencoder_conf: {}
+decoder: rnn
+decoder_conf: {}
+required:
+- output_dir
+- token_list
+version: 0.10.4a1
+distributed: false

exp/lm_train_lm_en_bpe30/39epoch.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e588e2a3843cd37c3880170e99b0d0f60fb36aed888dc501f2a8aaace230b5d
+size 27240836

exp/lm_train_lm_en_bpe30/config.yaml

@@ -0,0 +1,146 @@
+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: 0
+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: null
+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
+    - loss
+    - min
+keep_nbest_models: 1
+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: 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: 0.10.4a1
+distributed: false

exp/lm_train_lm_en_bpe30/perplexity_test/ppl

@@ -0,0 +1 @@
+8.770004779236807

meta.yaml

@@ -0,0 +1,10 @@
+espnet: 0.10.4a1
+files:
+  asr_model_file: exp/asr_train_raw_en_bpe30/2epoch.pth
+  lm_file: exp/lm_train_lm_en_bpe30/39epoch.pth
+python: "3.9.7 (default, Sep 16 2021, 13:09:58) \n[GCC 7.5.0]"
+timestamp: 1634655646.769093
+torch: 1.9.0
+yaml_files:
+  asr_train_config: exp/asr_train_raw_en_bpe30/config.yaml
+  lm_train_config: exp/lm_train_lm_en_bpe30/config.yaml