add model files

README.md

@@ -0,0 +1,371 @@
+---
+tags:
+- espnet
+- audio
+- automatic-speech-recognition
+language: en
+datasets:
+- chime4
+license: cc-by-4.0
+---
+
+## ESPnet2 ASR model 
+
+### `pyf98/chime4_conformer_e12_linear1024`
+
+This model was trained by Yifan Peng using chime4 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 ad91279f0108d54bd22abe29671b376f048822c5
+pip install -e .
+cd egs2/chime4/asr1
+./run.sh --skip_data_prep false --skip_train true --download_model pyf98/chime4_conformer_e12_linear1024
+```
+
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Wed Dec 28 15:49:24 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: `f9a8009aef6ff9ba192a78c19b619ae4a9f3b9d2`
+  - Commit date: `Wed Dec 28 00:30:54 2022 -0500`
+
+## asr_train_asr_conformer_e12_linear1024_raw_en_char_sp
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_lm_lm_train_lm_transformer_en_char_valid.loss.ave_asr_model_valid.acc.ave/dt05_real_beamformit_5mics|1640|27119|92.8|5.8|1.5|0.6|7.8|56.5|
+|decode_asr_lm_lm_train_lm_transformer_en_char_valid.loss.ave_asr_model_valid.acc.ave/dt05_simu_beamformit_5mics|1640|27120|91.3|6.7|2.0|0.8|9.5|60.5|
+|decode_asr_lm_lm_train_lm_transformer_en_char_valid.loss.ave_asr_model_valid.acc.ave/et05_real_beamformit_5mics|1320|21409|88.6|9.2|2.1|1.2|12.5|63.8|
+|decode_asr_lm_lm_train_lm_transformer_en_char_valid.loss.ave_asr_model_valid.acc.ave/et05_simu_beamformit_5mics|1320|21416|86.5|10.4|3.1|1.3|14.8|70.9|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_lm_lm_train_lm_transformer_en_char_valid.loss.ave_asr_model_valid.acc.ave/dt05_real_beamformit_5mics|1640|160390|96.9|1.6|1.5|0.7|3.8|56.5|
+|decode_asr_lm_lm_train_lm_transformer_en_char_valid.loss.ave_asr_model_valid.acc.ave/dt05_simu_beamformit_5mics|1640|160400|96.0|2.0|2.0|1.0|4.9|60.5|
+|decode_asr_lm_lm_train_lm_transformer_en_char_valid.loss.ave_asr_model_valid.acc.ave/et05_real_beamformit_5mics|1320|126796|94.8|2.8|2.3|1.2|6.4|63.9|
+|decode_asr_lm_lm_train_lm_transformer_en_char_valid.loss.ave_asr_model_valid.acc.ave/et05_simu_beamformit_5mics|1320|126812|93.1|3.4|3.4|1.5|8.4|70.9|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+
+## ASR config
+
+<details><summary>expand</summary>
+
+```
+config: conf/tuning/train_asr_conformer_e12_linear1024.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/asr_train_asr_conformer_e12_linear1024_raw_en_char_sp
+ngpu: 1
+seed: 2022
+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: 60
+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: true
+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: 15000000
+valid_batch_bins: null
+train_shape_file:
+- exp/asr_stats_raw_en_char_sp/train/speech_shape
+- exp/asr_stats_raw_en_char_sp/train/text_shape.char
+valid_shape_file:
+- exp/asr_stats_raw_en_char_sp/valid/speech_shape
+- exp/asr_stats_raw_en_char_sp/valid/text_shape.char
+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/tr05_multi_noisy_si284_sp/wav.scp
+    - speech
+    - kaldi_ark
+-   - dump/raw/tr05_multi_noisy_si284_sp/text
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - dump/raw/dt05_multi_isolated_1ch_track/wav.scp
+    - speech
+    - kaldi_ark
+-   - dump/raw/dt05_multi_isolated_1ch_track/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
+    weight_decay: 1.0e-06
+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
+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:
+    n_fft: 512
+    win_length: 400
+    hop_length: 160
+    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
+    - 27
+    num_freq_mask: 2
+    apply_time_mask: true
+    time_mask_width_ratio_range:
+    - 0.0
+    - 0.05
+    num_time_mask: 2
+normalize: global_mvn
+normalize_conf:
+    stats_file: exp/asr_stats_raw_en_char_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: conformer
+encoder_conf:
+    output_size: 256
+    attention_heads: 4
+    linear_units: 1024
+    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
+    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: 0.1
+    src_attention_dropout_rate: 0.1
+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_sp/train/feats_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2aca9a9d9bf95ba2222dd91ed8d62655135d2637bf76704cf984b7d0e90756c
+size 1402

exp/asr_train_asr_conformer_e12_linear1024_raw_en_char_sp/RESULTS.md

@@ -0,0 +1,57 @@
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Wed Dec 28 15:49:24 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: `f9a8009aef6ff9ba192a78c19b619ae4a9f3b9d2`
+  - Commit date: `Wed Dec 28 00:30:54 2022 -0500`
+
+## asr_train_asr_conformer_e12_linear1024_raw_en_char_sp
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_lm_lm_train_lm_en_char_valid.loss.ave_asr_model_valid.acc.ave/dt05_real_beamformit_2mics|1640|27119|87.9|9.8|2.3|0.9|13.0|77.7|
+|decode_asr_lm_lm_train_lm_en_char_valid.loss.ave_asr_model_valid.acc.ave/dt05_real_beamformit_5mics|1640|27119|89.5|8.6|1.9|0.8|11.3|74.0|
+|decode_asr_lm_lm_train_lm_en_char_valid.loss.ave_asr_model_valid.acc.ave/dt05_real_isolated_1ch_track|1640|27119|86.6|10.8|2.6|1.0|14.4|79.4|
+|decode_asr_lm_lm_train_lm_en_char_valid.loss.ave_asr_model_valid.acc.ave/dt05_simu_beamformit_2mics|1640|27120|85.6|11.5|3.0|1.2|15.7|78.9|
+|decode_asr_lm_lm_train_lm_en_char_valid.loss.ave_asr_model_valid.acc.ave/dt05_simu_beamformit_5mics|1640|27120|87.6|9.9|2.5|1.0|13.4|76.5|
+|decode_asr_lm_lm_train_lm_en_char_valid.loss.ave_asr_model_valid.acc.ave/dt05_simu_isolated_1ch_track|1640|27120|84.2|12.8|3.0|1.3|17.1|80.5|
+|decode_asr_lm_lm_train_lm_en_char_valid.loss.ave_asr_model_valid.acc.ave/et05_real_beamformit_2mics|1320|21409|81.8|15.0|3.1|1.6|19.8|82.2|
+|decode_asr_lm_lm_train_lm_en_char_valid.loss.ave_asr_model_valid.acc.ave/et05_real_beamformit_5mics|1320|21409|84.6|12.7|2.6|1.4|16.7|78.7|
+|decode_asr_lm_lm_train_lm_en_char_valid.loss.ave_asr_model_valid.acc.ave/et05_real_isolated_1ch_track|1320|21409|79.7|16.7|3.6|2.0|22.3|84.1|
+|decode_asr_lm_lm_train_lm_en_char_valid.loss.ave_asr_model_valid.acc.ave/et05_simu_beamformit_2mics|1320|21416|79.6|16.3|4.1|1.8|22.2|84.7|
+|decode_asr_lm_lm_train_lm_en_char_valid.loss.ave_asr_model_valid.acc.ave/et05_simu_beamformit_5mics|1320|21416|82.2|14.3|3.4|1.5|19.3|83.0|
+|decode_asr_lm_lm_train_lm_en_char_valid.loss.ave_asr_model_valid.acc.ave/et05_simu_isolated_1ch_track|1320|21416|78.1|17.9|4.0|2.3|24.2|84.6|
+|decode_asr_lm_lm_train_lm_transformer_en_char_valid.loss.ave_asr_model_valid.acc.ave/dt05_real_beamformit_5mics|1640|27119|92.8|5.8|1.5|0.6|7.8|56.5|
+|decode_asr_lm_lm_train_lm_transformer_en_char_valid.loss.ave_asr_model_valid.acc.ave/dt05_simu_beamformit_5mics|1640|27120|91.3|6.7|2.0|0.8|9.5|60.5|
+|decode_asr_lm_lm_train_lm_transformer_en_char_valid.loss.ave_asr_model_valid.acc.ave/et05_real_beamformit_5mics|1320|21409|88.6|9.2|2.1|1.2|12.5|63.8|
+|decode_asr_lm_lm_train_lm_transformer_en_char_valid.loss.ave_asr_model_valid.acc.ave/et05_simu_beamformit_5mics|1320|21416|86.5|10.4|3.1|1.3|14.8|70.9|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_lm_lm_train_lm_en_char_valid.loss.ave_asr_model_valid.acc.ave/dt05_real_beamformit_2mics|1640|160390|95.1|2.6|2.3|1.1|6.0|77.7|
+|decode_asr_lm_lm_train_lm_en_char_valid.loss.ave_asr_model_valid.acc.ave/dt05_real_beamformit_5mics|1640|160390|95.9|2.1|2.0|1.0|5.1|74.0|
+|decode_asr_lm_lm_train_lm_en_char_valid.loss.ave_asr_model_valid.acc.ave/dt05_real_isolated_1ch_track|1640|160390|94.4|2.9|2.6|1.3|6.9|79.4|
+|decode_asr_lm_lm_train_lm_en_char_valid.loss.ave_asr_model_valid.acc.ave/dt05_simu_beamformit_2mics|1640|160400|93.6|3.4|3.1|1.4|7.9|78.9|
+|decode_asr_lm_lm_train_lm_en_char_valid.loss.ave_asr_model_valid.acc.ave/dt05_simu_beamformit_5mics|1640|160400|94.8|2.7|2.5|1.2|6.4|76.5|
+|decode_asr_lm_lm_train_lm_en_char_valid.loss.ave_asr_model_valid.acc.ave/dt05_simu_isolated_1ch_track|1640|160400|92.9|3.9|3.2|1.7|8.8|80.5|
+|decode_asr_lm_lm_train_lm_en_char_valid.loss.ave_asr_model_valid.acc.ave/et05_real_beamformit_2mics|1320|126796|91.9|4.5|3.6|1.9|10.0|82.2|
+|decode_asr_lm_lm_train_lm_en_char_valid.loss.ave_asr_model_valid.acc.ave/et05_real_beamformit_5mics|1320|126796|93.5|3.6|2.9|1.6|8.0|78.7|
+|decode_asr_lm_lm_train_lm_en_char_valid.loss.ave_asr_model_valid.acc.ave/et05_real_isolated_1ch_track|1320|126796|90.7|5.2|4.1|2.3|11.6|84.1|
+|decode_asr_lm_lm_train_lm_en_char_valid.loss.ave_asr_model_valid.acc.ave/et05_simu_beamformit_2mics|1320|126812|90.1|5.2|4.7|2.2|12.0|84.7|
+|decode_asr_lm_lm_train_lm_en_char_valid.loss.ave_asr_model_valid.acc.ave/et05_simu_beamformit_5mics|1320|126812|91.8|4.2|4.0|1.9|10.1|83.0|
+|decode_asr_lm_lm_train_lm_en_char_valid.loss.ave_asr_model_valid.acc.ave/et05_simu_isolated_1ch_track|1320|126812|89.3|6.0|4.8|2.7|13.5|84.6|
+|decode_asr_lm_lm_train_lm_transformer_en_char_valid.loss.ave_asr_model_valid.acc.ave/dt05_real_beamformit_5mics|1640|160390|96.9|1.6|1.5|0.7|3.8|56.5|
+|decode_asr_lm_lm_train_lm_transformer_en_char_valid.loss.ave_asr_model_valid.acc.ave/dt05_simu_beamformit_5mics|1640|160400|96.0|2.0|2.0|1.0|4.9|60.5|
+|decode_asr_lm_lm_train_lm_transformer_en_char_valid.loss.ave_asr_model_valid.acc.ave/et05_real_beamformit_5mics|1320|126796|94.8|2.8|2.3|1.2|6.4|63.9|
+|decode_asr_lm_lm_train_lm_transformer_en_char_valid.loss.ave_asr_model_valid.acc.ave/et05_simu_beamformit_5mics|1320|126812|93.1|3.4|3.4|1.5|8.4|70.9|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|

exp/asr_train_asr_conformer_e12_linear1024_raw_en_char_sp/config.yaml

@@ -0,0 +1,266 @@
+config: conf/tuning/train_asr_conformer_e12_linear1024.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/asr_train_asr_conformer_e12_linear1024_raw_en_char_sp
+ngpu: 1
+seed: 2022
+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: 60
+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: true
+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: 15000000
+valid_batch_bins: null
+train_shape_file:
+- exp/asr_stats_raw_en_char_sp/train/speech_shape
+- exp/asr_stats_raw_en_char_sp/train/text_shape.char
+valid_shape_file:
+- exp/asr_stats_raw_en_char_sp/valid/speech_shape
+- exp/asr_stats_raw_en_char_sp/valid/text_shape.char
+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/tr05_multi_noisy_si284_sp/wav.scp
+    - speech
+    - kaldi_ark
+-   - dump/raw/tr05_multi_noisy_si284_sp/text
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - dump/raw/dt05_multi_isolated_1ch_track/wav.scp
+    - speech
+    - kaldi_ark
+-   - dump/raw/dt05_multi_isolated_1ch_track/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
+    weight_decay: 1.0e-06
+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
+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:
+    n_fft: 512
+    win_length: 400
+    hop_length: 160
+    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
+    - 27
+    num_freq_mask: 2
+    apply_time_mask: true
+    time_mask_width_ratio_range:
+    - 0.0
+    - 0.05
+    num_time_mask: 2
+normalize: global_mvn
+normalize_conf:
+    stats_file: exp/asr_stats_raw_en_char_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: conformer
+encoder_conf:
+    output_size: 256
+    attention_heads: 4
+    linear_units: 1024
+    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
+    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: 0.1
+    src_attention_dropout_rate: 0.1
+preprocessor: default
+preprocessor_conf: {}
+required:
+- output_dir
+- token_list
+version: '202211'
+distributed: false

exp/asr_train_asr_conformer_e12_linear1024_raw_en_char_sp/valid.acc.ave_10best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:315c57ff4f30a06e6b1632a994fb1b84820aafcd6a267eb17ef25c90ea24ef32
+size 122063653

exp/lm_train_lm_transformer_en_char/12epoch.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13dc5af025af5be3560922587402820207a78d258eb78fe1d47553a62b4b5895
+size 202293743

exp/lm_train_lm_transformer_en_char/config.yaml

@@ -0,0 +1,189 @@
+accum_grad: 4
+allow_variable_data_keys: false
+batch_bins: 150000
+batch_size: 20
+batch_type: numel
+best_model_criterion:
+- - valid
+  - loss
+  - min
+bpemodel: null
+chunk_length: 500
+chunk_shift_ratio: 0.5
+cleaner: null
+collect_stats: false
+config: conf/train_lm_transformer.yaml
+cudnn_benchmark: false
+cudnn_deterministic: true
+cudnn_enabled: true
+detect_anomaly: false
+dist_backend: nccl
+dist_init_method: env://
+dist_launcher: null
+dist_master_addr: null
+dist_master_port: null
+dist_rank: null
+dist_world_size: null
+distributed: false
+dry_run: false
+early_stopping_criterion:
+- valid
+- loss
+- min
+fold_length:
+- 150
+freeze_param: []
+g2p: null
+grad_clip: 5.0
+grad_clip_type: 2.0
+grad_noise: false
+ignore_init_mismatch: false
+init: null
+init_param: []
+iterator_type: sequence
+keep_nbest_models: 10
+lm: transformer
+lm_conf:
+  att_unit: 512
+  dropout_rate: 0.1
+  embed_unit: 128
+  head: 8
+  layer: 16
+  pos_enc: null
+  unit: 2048
+local_rank: 0
+log_interval: null
+log_level: INFO
+max_cache_fd: 32
+max_cache_size: 0.0
+max_epoch: 30
+model_conf:
+  ignore_id: 0
+multiple_iterator: false
+multiprocessing_distributed: false
+nbest_averaging_interval: 0
+ngpu: 1
+no_forward_run: false
+non_linguistic_symbols: data/nlsyms.txt
+num_att_plot: 3
+num_cache_chunks: 1024
+num_iters_per_epoch: null
+num_workers: 1
+optim: adam
+optim_conf:
+  lr: 0.001
+output_dir: exp_real2/lm_train_lm_transformer_en_char
+patience: null
+pretrain_path: null
+print_config: false
+required:
+- output_dir
+- token_list
+resume: true
+scheduler: warmuplr
+scheduler_conf:
+  warmup_steps: 25000
+seed: 0
+sharded_ddp: false
+sort_batch: descending
+sort_in_batch: descending
+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>
+token_type: char
+train_data_path_and_name_and_type:
+- - dump/raw/lm_train.txt
+  - text
+  - text
+train_dtype: float32
+train_shape_file:
+- exp_real2/lm_stats_en_char/train/text_shape.char
+unused_parameters: false
+use_amp: false
+use_matplotlib: true
+use_preprocessor: true
+use_tensorboard: true
+use_wandb: false
+val_scheduler_criterion:
+- valid
+- loss
+valid_batch_bins: null
+valid_batch_size: null
+valid_batch_type: null
+valid_data_path_and_name_and_type:
+- - dump/raw/dt05_multi_isolated_1ch_track/text
+  - text
+  - text
+valid_max_cache_size: null
+valid_shape_file:
+- exp_real2/lm_stats_en_char/valid/text_shape.char
+version: 0.10.7a1
+wandb_entity: null
+wandb_id: null
+wandb_model_log_interval: -1
+wandb_name: null
+wandb_project: null
+write_collected_feats: false

exp/lm_train_lm_transformer_en_char/perplexity_test/ppl

@@ -0,0 +1 @@
+1.8016810278173603

meta.yaml

@@ -0,0 +1,10 @@
+espnet: '202211'
+files:
+  asr_model_file: exp/asr_train_asr_conformer_e12_linear1024_raw_en_char_sp/valid.acc.ave_10best.pth
+  lm_file: exp/lm_train_lm_transformer_en_char/12epoch.pth
+python: "3.9.15 (main, Nov 24 2022, 14:31:59) \n[GCC 11.2.0]"
+timestamp: 1672282073.431392
+torch: 1.12.1
+yaml_files:
+  asr_train_config: exp/asr_train_asr_conformer_e12_linear1024_raw_en_char_sp/config.yaml
+  lm_train_config: exp/lm_train_lm_transformer_en_char/config.yaml