Update model

README.md

@@ -0,0 +1,526 @@
+---
+tags:
+- espnet
+- audio
+- automatic-speech-recognition
+language: noinfo
+datasets:
+- totonac
+license: cc-by-4.0
+---
+
+## ESPnet2 ASR model 
+
+### `espnet/ftshijt_espnet2_asr_totonac_transformer`
+
+This model was trained by ftshijt using totonac recipe in [espnet](https://github.com/espnet/espnet/).
+
+### Demo: How to use in ESPnet2
+
+```bash
+cd espnet
+
+pip install -e .
+cd els/totonac/asr1
+./run.sh --skip_data_prep false --skip_train true --download_model espnet/ftshijt_espnet2_asr_totonac_transformer
+```
+
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Sun Nov  7 09:22:09 EST 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: ``
+  - Commit date: ``
+
+## asr_train_asr_transformer_specaug_raw_bpe250_sp
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_lm_lm_train_bpe250_valid.loss.ave_asr_model_valid.acc.best/dev|530|3547|59.8|32.9|7.3|6.5|46.7|87.4|
+|decode_asr_lm_lm_train_bpe250_valid.loss.ave_asr_model_valid.acc.best/test|704|5018|55.5|35.7|8.8|6.1|50.6|92.0|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_lm_lm_train_bpe250_valid.loss.ave_asr_model_valid.acc.best/dev|530|22510|88.1|4.4|7.4|3.9|15.8|87.4|
+|decode_asr_lm_lm_train_bpe250_valid.loss.ave_asr_model_valid.acc.best/test|704|32990|86.9|4.3|8.8|4.0|17.1|92.0|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_lm_lm_train_bpe250_valid.loss.ave_asr_model_valid.acc.best/dev|530|9360|70.3|15.8|13.8|4.3|34.0|87.4|
+|decode_asr_lm_lm_train_bpe250_valid.loss.ave_asr_model_valid.acc.best/test|704|13835|70.5|16.0|13.6|4.4|33.9|92.0|
+
+## ASR config
+
+<details><summary>expand</summary>
+
+```
+config: conf/tuning/train_asr_transformer_specaug.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/asr_train_asr_transformer_specaug_raw_bpe250_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: 100
+patience: 15
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - acc
+    - max
+keep_nbest_models: 10
+grad_clip: 5
+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_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: 32
+valid_batch_size: null
+batch_bins: 1000000
+valid_batch_bins: null
+train_shape_file:
+- exp/asr_stats_raw_bpe250_sp/train/speech_shape
+- exp/asr_stats_raw_bpe250_sp/train/text_shape.bpe
+valid_shape_file:
+- exp/asr_stats_raw_bpe250_sp/valid/speech_shape
+- exp/asr_stats_raw_bpe250_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:
+-   - /tmp/jiatong-7359.okvPvI3Z/raw/train_sp/wav.scp
+    - speech
+    - kaldi_ark
+-   - /tmp/jiatong-7359.okvPvI3Z/raw/train_sp/text
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - /tmp/jiatong-7359.okvPvI3Z/raw/dev/wav.scp
+    - speech
+    - kaldi_ark
+-   - /tmp/jiatong-7359.okvPvI3Z/raw/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: 1.0
+scheduler: noamlr
+scheduler_conf:
+    warmup_steps: 4000
+token_list:
+- <blank>
+- <unk>
+- ':'
+- ▁N
+- NI
+- N
+- ▁IYMA
+- ▁NA
+- NA
+- ▁WA
+- WA
+- ▁
+- ''''
+- KA
+- ▁MA
+- MA
+- T
+- ▁XA
+- TA
+- NCHU
+- WI
+- ▁LI
+- ▁NI
+- PA
+- YI
+- ▁PUS
+- K
+- ▁PI
+- ▁X
+- S
+- ▁TA
+- YA
+- ▁LA
+- Q
+- QA
+- TI
+- ▁KA
+- QO
+- W
+- ▁KAH
+- ▁PALA
+- H
+- X
+- XA
+- ▁KI
+- A
+- LH
+- I
+- LA
+- ▁CHA
+- ▁A
+- ▁XLI
+- ▁LHI
+- U
+- ▁K
+- KANI
+- KU
+- Y
+- ▁LU
+- Á
+- ▁CHU
+- O
+- KI
+- ▁KIWI
+- NTLA
+- ▁TLA
+- M
+- ▁TAWA
+- ▁TI
+- ▁S
+- WANI
+- CHA
+- LHI
+- LI
+- ▁TU
+- ▁PALHA
+- Í
+- ▁CHANÁ
+- ▁KILHWAMPA
+- KÁN
+- ▁WAYMA
+- E
+- SA
+- ▁E
+- ▁LHU
+- LHA
+- PU
+- ▁LHA
+- ▁PA
+- ▁LAK
+- ▁ANTA
+- ▁KITI
+- NCHÚ
+- SI
+- TLA
+- PI
+- ▁KINI
+- CHI
+- ▁PEROH
+- ▁PU
+- QÓ
+- QALHCHIWINA
+- TU
+- ▁TLHA
+- ▁WI
+- NÁ
+- ▁KAN
+- ▁NAYI
+- CH
+- 'NO'
+- ▁U
+- TSA
+- MÁ
+- NQO
+- ▁ANA
+- ▁LIKWA
+- ▁XTA
+- J
+- ▁QALH
+- TO
+- TÁ
+- ▁USA
+- ▁PORQUE
+- ▁MI
+- L
+- ▁TAWÁ
+- XI
+- LHAQAPASA
+- P
+- CHIWI
+- WÁ
+- NTI
+- ▁JKA
+- Ú
+- NTLHA
+- R
+- TSI
+- C
+- STA
+- ▁LH
+- LHU
+- MPI
+- ▁I
+- ▁NILH
+- ▁KATSI
+- ▁LHAK
+- MAKLHAKASKI
+- ▁WANIKÁN
+- ▁WIXI
+- ▁TSI
+- KÚ
+- NÍ
+- ▁PAKS
+- NU
+- TLHA
+- YÁ
+- KUCHAN
+- XAQATLI
+- ▁MAX
+- ▁LAQAPASA
+- ▁LAQ
+- QALH
+- KATSI
+- Ó
+- LAQAPASA
+- ▁J
+- ▁QAMA
+- NTU
+- MI
+- KIWI
+- ▁KIN
+- ▁XANAT
+- ▁CHI
+- JA
+- ▁IY
+- ▁TSU
+- MAKLAKAS
+- ▁MAQA
+- LÁ
+- ▁KATSIYA
+- ▁TLANKA
+- ▁STAK
+- ▁XLA
+- ▁LHIKWA
+- ▁SQA
+- ▁P
+- TAHNA
+- ▁TLAQ
+- ▁JKATSI
+- MAKLAKASKINKA
+- YÁW
+- WATIYA
+- CHÁ
+- ▁IPORQUEI
+- ▁AKXNI
+- TSU
+- ▁TSINÓ
+- ▁STAKA
+- ▁AKXNÍ
+- LAKATA
+- KATSÍ
+- ▁XALHAK
+- TLAWAYA
+- SPUT
+- ▁XATAWA
+- QALHCHIWI
+- PÁ
+- JU
+- ▁XAXANAT
+- ▁PÉREZ
+- ▁AKTSU
+- ▁JKI
+- NTÚ
+- ▁KATSIYÁ
+- ▁IESTEI
+- LAQAPASÁ
+- ▁MASKI
+- ▁LAQSQATÁ
+- ▁TLHANKA
+- ▁WANIKANI
+- ▁LÓPEZ
+- MAKLAKASKINKÁN
+- ▁ANTÁ
+- ▁TACHIWÍ
+- ▁SEBAST
+- ▁CANO
+- ▁XKUTNI
+- ▁UKXILH
+- TANKAH
+- LAKASKINQO
+- LAKAPASTAK
+- ▁XCHACHAT
+- TAKAWANÍ
+- ▁TLÁ
+- ▁TSINOH
+- KAXTLAWA
+- ▁NÚÑEZ
+- ▁XLAKASKINKA
+- ▁WÁTIYA
+- ONCE
+- Z
+- É
+- D
+- Ñ
+- V
+- F
+- G
+- '1'
+- B
+- <sos/eos>
+init: xavier_uniform
+input_size: null
+ctc_conf:
+    dropout_rate: 0.0
+    ctc_type: builtin
+    reduce: true
+    ignore_nan_grad: true
+model_conf:
+    ctc_weight: 0.3
+    lsm_weight: 0.1
+    length_normalized_loss: false
+use_preprocessor: true
+token_type: bpe
+bpemodel: data/token_list/bpe_unigram250/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: 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: global_mvn
+normalize_conf:
+    stats_file: exp/asr_stats_raw_bpe250_sp/train/feats_stats.npz
+preencoder: null
+preencoder_conf: {}
+encoder: transformer
+encoder_conf:
+    input_layer: conv2d
+    num_blocks: 12
+    linear_units: 2048
+    dropout_rate: 0.1
+    output_size: 256
+    attention_heads: 4
+    attention_dropout_rate: 0.0
+postencoder: null
+postencoder_conf: {}
+decoder: transformer
+decoder_conf:
+    input_layer: embed
+    num_blocks: 6
+    linear_units: 2048
+    dropout_rate: 0.1
+required:
+- output_dir
+- token_list
+version: 0.10.4a1
+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/token_list/bpe_unigram250/bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28c4aa9cc4fb4f2dcc54e7a91661189d4985730af7d75468f84baa98ceebd157
+size 241202

exp/asr_train_asr_transformer_specaug_raw_bpe250_sp/73epoch.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62e89e5b8cea7c5337d0945d576728edea3f495fc94e3212449028ee94aa6610
+size 109361573

exp/asr_train_asr_transformer_specaug_raw_bpe250_sp/RESULTS.md

@@ -0,0 +1,32 @@
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Sun Nov  7 09:22:09 EST 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: ``
+  - Commit date: ``
+
+## asr_train_asr_transformer_specaug_raw_bpe250_sp
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_lm_lm_train_bpe250_valid.loss.ave_asr_model_valid.acc.best/dev|530|3547|59.8|32.9|7.3|6.5|46.7|87.4|
+|decode_asr_lm_lm_train_bpe250_valid.loss.ave_asr_model_valid.acc.best/test|704|5018|55.5|35.7|8.8|6.1|50.6|92.0|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_lm_lm_train_bpe250_valid.loss.ave_asr_model_valid.acc.best/dev|530|22510|88.1|4.4|7.4|3.9|15.8|87.4|
+|decode_asr_lm_lm_train_bpe250_valid.loss.ave_asr_model_valid.acc.best/test|704|32990|86.9|4.3|8.8|4.0|17.1|92.0|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_lm_lm_train_bpe250_valid.loss.ave_asr_model_valid.acc.best/dev|530|9360|70.3|15.8|13.8|4.3|34.0|87.4|
+|decode_asr_lm_lm_train_bpe250_valid.loss.ave_asr_model_valid.acc.best/test|704|13835|70.5|16.0|13.6|4.4|33.9|92.0|
+

exp/asr_train_asr_transformer_specaug_raw_bpe250_sp/config.yaml

@@ -0,0 +1,426 @@
+config: conf/tuning/train_asr_transformer_specaug.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/asr_train_asr_transformer_specaug_raw_bpe250_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: 100
+patience: 15
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - acc
+    - max
+keep_nbest_models: 10
+grad_clip: 5
+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_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: 32
+valid_batch_size: null
+batch_bins: 1000000
+valid_batch_bins: null
+train_shape_file:
+- exp/asr_stats_raw_bpe250_sp/train/speech_shape
+- exp/asr_stats_raw_bpe250_sp/train/text_shape.bpe
+valid_shape_file:
+- exp/asr_stats_raw_bpe250_sp/valid/speech_shape
+- exp/asr_stats_raw_bpe250_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:
+-   - /tmp/jiatong-7359.okvPvI3Z/raw/train_sp/wav.scp
+    - speech
+    - kaldi_ark
+-   - /tmp/jiatong-7359.okvPvI3Z/raw/train_sp/text
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - /tmp/jiatong-7359.okvPvI3Z/raw/dev/wav.scp
+    - speech
+    - kaldi_ark
+-   - /tmp/jiatong-7359.okvPvI3Z/raw/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: 1.0
+scheduler: noamlr
+scheduler_conf:
+    warmup_steps: 4000
+token_list:
+- <blank>
+- <unk>
+- ':'
+- ▁N
+- NI
+- N
+- ▁IYMA
+- ▁NA
+- NA
+- ▁WA
+- WA
+- ▁
+- ''''
+- KA
+- ▁MA
+- MA
+- T
+- ▁XA
+- TA
+- NCHU
+- WI
+- ▁LI
+- ▁NI
+- PA
+- YI
+- ▁PUS
+- K
+- ▁PI
+- ▁X
+- S
+- ▁TA
+- YA
+- ▁LA
+- Q
+- QA
+- TI
+- ▁KA
+- QO
+- W
+- ▁KAH
+- ▁PALA
+- H
+- X
+- XA
+- ▁KI
+- A
+- LH
+- I
+- LA
+- ▁CHA
+- ▁A
+- ▁XLI
+- ▁LHI
+- U
+- ▁K
+- KANI
+- KU
+- Y
+- ▁LU
+- Á
+- ▁CHU
+- O
+- KI
+- ▁KIWI
+- NTLA
+- ▁TLA
+- M
+- ▁TAWA
+- ▁TI
+- ▁S
+- WANI
+- CHA
+- LHI
+- LI
+- ▁TU
+- ▁PALHA
+- Í
+- ▁CHANÁ
+- ▁KILHWAMPA
+- KÁN
+- ▁WAYMA
+- E
+- SA
+- ▁E
+- ▁LHU
+- LHA
+- PU
+- ▁LHA
+- ▁PA
+- ▁LAK
+- ▁ANTA
+- ▁KITI
+- NCHÚ
+- SI
+- TLA
+- PI
+- ▁KINI
+- CHI
+- ▁PEROH
+- ▁PU
+- QÓ
+- QALHCHIWINA
+- TU
+- ▁TLHA
+- ▁WI
+- NÁ
+- ▁KAN
+- ▁NAYI
+- CH
+- 'NO'
+- ▁U
+- TSA
+- MÁ
+- NQO
+- ▁ANA
+- ▁LIKWA
+- ▁XTA
+- J
+- ▁QALH
+- TO
+- TÁ
+- ▁USA
+- ▁PORQUE
+- ▁MI
+- L
+- ▁TAWÁ
+- XI
+- LHAQAPASA
+- P
+- CHIWI
+- WÁ
+- NTI
+- ▁JKA
+- Ú
+- NTLHA
+- R
+- TSI
+- C
+- STA
+- ▁LH
+- LHU
+- MPI
+- ▁I
+- ▁NILH
+- ▁KATSI
+- ▁LHAK
+- MAKLHAKASKI
+- ▁WANIKÁN
+- ▁WIXI
+- ▁TSI
+- KÚ
+- NÍ
+- ▁PAKS
+- NU
+- TLHA
+- YÁ
+- KUCHAN
+- XAQATLI
+- ▁MAX
+- ▁LAQAPASA
+- ▁LAQ
+- QALH
+- KATSI
+- Ó
+- LAQAPASA
+- ▁J
+- ▁QAMA
+- NTU
+- MI
+- KIWI
+- ▁KIN
+- ▁XANAT
+- ▁CHI
+- JA
+- ▁IY
+- ▁TSU
+- MAKLAKAS
+- ▁MAQA
+- LÁ
+- ▁KATSIYA
+- ▁TLANKA
+- ▁STAK
+- ▁XLA
+- ▁LHIKWA
+- ▁SQA
+- ▁P
+- TAHNA
+- ▁TLAQ
+- ▁JKATSI
+- MAKLAKASKINKA
+- YÁW
+- WATIYA
+- CHÁ
+- ▁IPORQUEI
+- ▁AKXNI
+- TSU
+- ▁TSINÓ
+- ▁STAKA
+- ▁AKXNÍ
+- LAKATA
+- KATSÍ
+- ▁XALHAK
+- TLAWAYA
+- SPUT
+- ▁XATAWA
+- QALHCHIWI
+- PÁ
+- JU
+- ▁XAXANAT
+- ▁PÉREZ
+- ▁AKTSU
+- ▁JKI
+- NTÚ
+- ▁KATSIYÁ
+- ▁IESTEI
+- LAQAPASÁ
+- ▁MASKI
+- ▁LAQSQATÁ
+- ▁TLHANKA
+- ▁WANIKANI
+- ▁LÓPEZ
+- MAKLAKASKINKÁN
+- ▁ANTÁ
+- ▁TACHIWÍ
+- ▁SEBAST
+- ▁CANO
+- ▁XKUTNI
+- ▁UKXILH
+- TANKAH
+- LAKASKINQO
+- LAKAPASTAK
+- ▁XCHACHAT
+- TAKAWANÍ
+- ▁TLÁ
+- ▁TSINOH
+- KAXTLAWA
+- ▁NÚÑEZ
+- ▁XLAKASKINKA
+- ▁WÁTIYA
+- ONCE
+- Z
+- É
+- D
+- Ñ
+- V
+- F
+- G
+- '1'
+- B
+- <sos/eos>
+init: xavier_uniform
+input_size: null
+ctc_conf:
+    dropout_rate: 0.0
+    ctc_type: builtin
+    reduce: true
+    ignore_nan_grad: true
+model_conf:
+    ctc_weight: 0.3
+    lsm_weight: 0.1
+    length_normalized_loss: false
+use_preprocessor: true
+token_type: bpe
+bpemodel: data/token_list/bpe_unigram250/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: 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: global_mvn
+normalize_conf:
+    stats_file: exp/asr_stats_raw_bpe250_sp/train/feats_stats.npz
+preencoder: null
+preencoder_conf: {}
+encoder: transformer
+encoder_conf:
+    input_layer: conv2d
+    num_blocks: 12
+    linear_units: 2048
+    dropout_rate: 0.1
+    output_size: 256
+    attention_heads: 4
+    attention_dropout_rate: 0.0
+postencoder: null
+postencoder_conf: {}
+decoder: transformer
+decoder_conf:
+    input_layer: embed
+    num_blocks: 6
+    linear_units: 2048
+    dropout_rate: 0.1
+required:
+- output_dir
+- token_list
+version: 0.10.4a1
+distributed: false

exp/lm_train_bpe250/config.yaml

@@ -0,0 +1,373 @@
+config: null
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/lm_train_bpe250
+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: 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/lm_stats_bpe250/train/text_shape.bpe
+valid_shape_file:
+- exp/lm_stats_bpe250/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/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>
+- ':'
+- ▁N
+- NI
+- N
+- ▁IYMA
+- ▁NA
+- NA
+- ▁WA
+- WA
+- ▁
+- ''''
+- KA
+- ▁MA
+- MA
+- T
+- ▁XA
+- TA
+- NCHU
+- WI
+- ▁LI
+- ▁NI
+- PA
+- YI
+- ▁PUS
+- K
+- ▁PI
+- ▁X
+- S
+- ▁TA
+- YA
+- ▁LA
+- Q
+- QA
+- TI
+- ▁KA
+- QO
+- W
+- ▁KAH
+- ▁PALA
+- H
+- X
+- XA
+- ▁KI
+- A
+- LH
+- I
+- LA
+- ▁CHA
+- ▁A
+- ▁XLI
+- ▁LHI
+- U
+- ▁K
+- KANI
+- KU
+- Y
+- ▁LU
+- Á
+- ▁CHU
+- O
+- KI
+- ▁KIWI
+- NTLA
+- ▁TLA
+- M
+- ▁TAWA
+- ▁TI
+- ▁S
+- WANI
+- CHA
+- LHI
+- LI
+- ▁TU
+- ▁PALHA
+- Í
+- ▁CHANÁ
+- ▁KILHWAMPA
+- KÁN
+- ▁WAYMA
+- E
+- SA
+- ▁E
+- ▁LHU
+- LHA
+- PU
+- ▁LHA
+- ▁PA
+- ▁LAK
+- ▁ANTA
+- ▁KITI
+- NCHÚ
+- SI
+- TLA
+- PI
+- ▁KINI
+- CHI
+- ▁PEROH
+- ▁PU
+- QÓ
+- QALHCHIWINA
+- TU
+- ▁TLHA
+- ▁WI
+- NÁ
+- ▁KAN
+- ▁NAYI
+- CH
+- 'NO'
+- ▁U
+- TSA
+- MÁ
+- NQO
+- ▁ANA
+- ▁LIKWA
+- ▁XTA
+- J
+- ▁QALH
+- TO
+- TÁ
+- ▁USA
+- ▁PORQUE
+- ▁MI
+- L
+- ▁TAWÁ
+- XI
+- LHAQAPASA
+- P
+- CHIWI
+- WÁ
+- NTI
+- ▁JKA
+- Ú
+- NTLHA
+- R
+- TSI
+- C
+- STA
+- ▁LH
+- LHU
+- MPI
+- ▁I
+- ▁NILH
+- ▁KATSI
+- ▁LHAK
+- MAKLHAKASKI
+- ▁WANIKÁN
+- ▁WIXI
+- ▁TSI
+- KÚ
+- NÍ
+- ▁PAKS
+- NU
+- TLHA
+- YÁ
+- KUCHAN
+- XAQATLI
+- ▁MAX
+- ▁LAQAPASA
+- ▁LAQ
+- QALH
+- KATSI
+- Ó
+- LAQAPASA
+- ▁J
+- ▁QAMA
+- NTU
+- MI
+- KIWI
+- ▁KIN
+- ▁XANAT
+- ▁CHI
+- JA
+- ▁IY
+- ▁TSU
+- MAKLAKAS
+- ▁MAQA
+- LÁ
+- ▁KATSIYA
+- ▁TLANKA
+- ▁STAK
+- ▁XLA
+- ▁LHIKWA
+- ▁SQA
+- ▁P
+- TAHNA
+- ▁TLAQ
+- ▁JKATSI
+- MAKLAKASKINKA
+- YÁW
+- WATIYA
+- CHÁ
+- ▁IPORQUEI
+- ▁AKXNI
+- TSU
+- ▁TSINÓ
+- ▁STAKA
+- ▁AKXNÍ
+- LAKATA
+- KATSÍ
+- ▁XALHAK
+- TLAWAYA
+- SPUT
+- ▁XATAWA
+- QALHCHIWI
+- PÁ
+- JU
+- ▁XAXANAT
+- ▁PÉREZ
+- ▁AKTSU
+- ▁JKI
+- NTÚ
+- ▁KATSIYÁ
+- ▁IESTEI
+- LAQAPASÁ
+- ▁MASKI
+- ▁LAQSQATÁ
+- ▁TLHANKA
+- ▁WANIKANI
+- ▁LÓPEZ
+- MAKLAKASKINKÁN
+- ▁ANTÁ
+- ▁TACHIWÍ
+- ▁SEBAST
+- ▁CANO
+- ▁XKUTNI
+- ▁UKXILH
+- TANKAH
+- LAKASKINQO
+- LAKAPASTAK
+- ▁XCHACHAT
+- TAKAWANÍ
+- ▁TLÁ
+- ▁TSINOH
+- KAXTLAWA
+- ▁NÚÑEZ
+- ▁XLAKASKINKA
+- ▁WÁTIYA
+- ONCE
+- Z
+- É
+- D
+- Ñ
+- V
+- F
+- G
+- '1'
+- B
+- <sos/eos>
+init: null
+model_conf:
+    ignore_id: 0
+use_preprocessor: true
+token_type: bpe
+bpemodel: data/token_list/bpe_unigram250/bpe.model
+non_linguistic_symbols: null
+cleaner: null
+g2p: null
+lm: seq_rnn
+lm_conf: {}
+required:
+- output_dir
+- token_list
+version: 0.10.3a3
+distributed: false

exp/lm_train_bpe250/perplexity_test/ppl

@@ -0,0 +1 @@
+18.3045965777891

exp/lm_train_bpe250/valid.loss.ave_10best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b143d75fce3b31b97930dab08414419abaf4f90edca5797f22a5d8eb5b79e5c8
+size 28385796

meta.yaml

@@ -0,0 +1,10 @@
+espnet: 0.10.5a1
+files:
+  asr_model_file: exp/asr_train_asr_transformer_specaug_raw_bpe250_sp/73epoch.pth
+  lm_file: exp/lm_train_bpe250/valid.loss.ave_10best.pth
+python: "3.9.7 (default, Sep 16 2021, 13:09:58) \n[GCC 7.5.0]"
+timestamp: 1640102996.550734
+torch: 1.9.0
+yaml_files:
+  asr_train_config: exp/asr_train_asr_transformer_specaug_raw_bpe250_sp/config.yaml
+  lm_train_config: exp/lm_train_bpe250/config.yaml