import from zenodo

README.md

@@ -0,0 +1,50 @@
+---
+tags:
+- espnet
+- audio
+- automatic-speech-recognition
+language: es
+datasets:
+- mls
+license: cc-by-4.0
+---
+## Example ESPnet2 ASR model 
+### `ftshijt/mls_asr_transformer_valid.acc.best`
+♻️ Imported from https://zenodo.org/record/4458452/
+
+This model was trained by ftshijt using mls/asr1 recipe in [espnet](https://github.com/espnet/espnet/).
+### Demo: How to use in ESPnet2
+```python
+# coming soon
+```
+### 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 {Enrique Yalta Soplin} 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}
+}
+@inproceedings{hayashi2020espnet,
+  title={{Espnet-TTS}: Unified, reproducible, and integratable open source end-to-end text-to-speech toolkit},
+  author={Hayashi, Tomoki and Yamamoto, Ryuichi and Inoue, Katsuki and Yoshimura, Takenori and Watanabe, Shinji and Toda, Tomoki and Takeda, Kazuya and Zhang, Yu and Tan, Xu},
+  booktitle={Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
+  pages={7654--7658},
+  year={2020},
+  organization={IEEE}
+}
+```
+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 Enrique Yalta Soplin 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_unigram150/bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f633bfbf3f726a1166cebdaddb9c4253ba3690d9d4461ad998fdd70211e2847f
+size 239455

exp/asr_transformer/29epoch.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e6f7f6542a536cd7658ab0539d1c23ba91c93ae66230649c63405898eb8ac0d
+size 109062285

exp/asr_transformer/RESULTS.md

@@ -0,0 +1,29 @@
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Fri Jan 22 04:56:26 EST 2021`
+- python version: `3.8.3 (default, May 19 2020, 18:47:26)  [GCC 7.3.0]`
+- espnet version: `espnet 0.9.2`
+- pytorch version: `pytorch 1.6.0`
+- Git hash: `c0c3724fe660abd205dbca9c9bbdffed1d2c79db`
+  - Commit date: `Tue Jan 12 23:00:11 2021 -0500`
+
+## asr_transformer
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_lm_lm_train_bpe150_valid.loss.ave_asr_model_valid.acc.best/es_test|2385|88499|81.3|15.6|3.1|2.5|21.2|98.6|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_lm_lm_train_bpe150_valid.loss.ave_asr_model_valid.acc.best/es_test|2385|474976|94.3|2.9|2.7|1.4|7.1|98.6|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_lm_lm_train_bpe150_valid.loss.ave_asr_model_valid.acc.best/es_test|2385|251160|88.6|7.9|3.5|2.1|13.6|98.6|
+

exp/asr_transformer/config.yaml

@@ -0,0 +1,297 @@
+config: conf/tuning/train_asr_transformer.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/asr_transformer
+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
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: true
+collect_stats: false
+write_collected_feats: false
+max_epoch: 100
+patience: 0
+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
+unused_parameters: false
+use_tensorboard: true
+use_wandb: false
+wandb_project: null
+wandb_id: null
+pretrain_path: null
+init_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_bpe150/train/speech_shape
+- exp/asr_stats_raw_bpe150/train/text_shape.bpe
+valid_shape_file:
+- exp/asr_stats_raw_bpe150/valid/speech_shape
+- exp/asr_stats_raw_bpe150/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/es_train/wav.scp
+    - speech
+    - sound
+-   - dump/raw/es_train/text
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - dump/raw/es_dev/wav.scp
+    - speech
+    - sound
+-   - dump/raw/es_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: 25000
+token_list:
+- <blank>
+- <unk>
+- ▁
+- s
+- n
+- r
+- o
+- a
+- ▁de
+- e
+- l
+- ▁a
+- u
+- ▁y
+- ▁que
+- ra
+- ta
+- do
+- ▁la
+- i
+- ▁en
+- re
+- to
+- ▁el
+- d
+- p
+- da
+- la
+- c
+- b
+- t
+- ro
+- ó
+- en
+- ri
+- g
+- ba
+- ▁se
+- os
+- er
+- te
+- ▁con
+- ci
+- ▁es
+- es
+- ▁no
+- ▁su
+- h
+- ti
+- é
+- mo
+- á
+- ▁ca
+- ▁ha
+- na
+- ▁los
+- lo
+- í
+- ía
+- de
+- me
+- ca
+- ▁al
+- le
+- ce
+- v
+- ma
+- nte
+- ▁di
+- ▁ma
+- ▁por
+- y
+- di
+- m
+- ▁pa
+- sa
+- ▁si
+- ▁pe
+- gu
+- z
+- ▁mi
+- ▁co
+- ▁me
+- ▁o
+- ▁e
+- ▁un
+- tra
+- ▁re
+- li
+- ▁f
+- co
+- ▁á
+- ndo
+- se
+- mi
+- ga
+- ni
+- ▁cu
+- ▁le
+- jo
+- ▁ve
+- mp
+- bi
+- f
+- va
+- ▁mu
+- go
+- ▁so
+- ñ
+- tu
+- si
+- ▁lo
+- ▁pu
+- ▁vi
+- ▁b
+- ▁las
+- ▁c
+- ▁sa
+- za
+- ▁del
+- ▁po
+- ▁in
+- vi
+- ▁te
+- tro
+- cia
+- ▁una
+- qui
+- pi
+- que
+- ja
+- pa
+- ▁para
+- cu
+- pe
+- ▁como
+- ▁esta
+- ve
+- je
+- lle
+- x
+- ú
+- j
+- q
+- ''''
+- k
+- w
+- ü
+- '-'
+- <sos/eos>
+init: chainer
+input_size: null
+ctc_conf:
+    dropout_rate: 0.0
+    ctc_type: builtin
+    reduce: true
+    ignore_nan_grad: false
+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_unigram150/bpe.model
+non_linguistic_symbols: null
+cleaner: null
+g2p: null
+frontend: default
+frontend_conf:
+    fs: 16k
+specaug: null
+specaug_conf: {}
+normalize: global_mvn
+normalize_conf:
+    stats_file: exp/asr_stats_raw_bpe150/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
+decoder: transformer
+decoder_conf:
+    input_layer: embed
+    num_blocks: 6
+    linear_units: 2048
+    dropout_rate: 0.1
+required:
+- output_dir
+- token_list
+distributed: false

exp/lm_train_bpe150/config.yaml

@@ -0,0 +1,265 @@
+config: null
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/lm_train_bpe150
+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
+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
+unused_parameters: false
+use_tensorboard: true
+use_wandb: false
+wandb_project: null
+wandb_id: null
+pretrain_path: null
+init_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_bpe150/train/text_shape.bpe
+valid_shape_file:
+- exp/lm_stats_bpe150/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/es_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>
+- ▁
+- s
+- n
+- r
+- o
+- a
+- ▁de
+- e
+- l
+- ▁a
+- u
+- ▁y
+- ▁que
+- ra
+- ta
+- do
+- ▁la
+- i
+- ▁en
+- re
+- to
+- ▁el
+- d
+- p
+- da
+- la
+- c
+- b
+- t
+- ro
+- ó
+- en
+- ri
+- g
+- ba
+- ▁se
+- os
+- er
+- te
+- ▁con
+- ci
+- ▁es
+- es
+- ▁no
+- ▁su
+- h
+- ti
+- é
+- mo
+- á
+- ▁ca
+- ▁ha
+- na
+- ▁los
+- lo
+- í
+- ía
+- de
+- me
+- ca
+- ▁al
+- le
+- ce
+- v
+- ma
+- nte
+- ▁di
+- ▁ma
+- ▁por
+- y
+- di
+- m
+- ▁pa
+- sa
+- ▁si
+- ▁pe
+- gu
+- z
+- ▁mi
+- ▁co
+- ▁me
+- ▁o
+- ▁e
+- ▁un
+- tra
+- ▁re
+- li
+- ▁f
+- co
+- ▁á
+- ndo
+- se
+- mi
+- ga
+- ni
+- ▁cu
+- ▁le
+- jo
+- ▁ve
+- mp
+- bi
+- f
+- va
+- ▁mu
+- go
+- ▁so
+- ñ
+- tu
+- si
+- ▁lo
+- ▁pu
+- ▁vi
+- ▁b
+- ▁las
+- ▁c
+- ▁sa
+- za
+- ▁del
+- ▁po
+- ▁in
+- vi
+- ▁te
+- tro
+- cia
+- ▁una
+- qui
+- pi
+- que
+- ja
+- pa
+- ▁para
+- cu
+- pe
+- ▁como
+- ▁esta
+- ve
+- je
+- lle
+- x
+- ú
+- j
+- q
+- ''''
+- k
+- w
+- ü
+- '-'
+- <sos/eos>
+init: null
+model_conf:
+    ignore_id: 0
+use_preprocessor: true
+token_type: bpe
+bpemodel: data/token_list/bpe_unigram150/bpe.model
+non_linguistic_symbols: null
+cleaner: null
+g2p: null
+lm: seq_rnn
+lm_conf: {}
+required:
+- output_dir
+- token_list
+distributed: false

exp/lm_train_bpe150/perplexity_test/ppl

@@ -0,0 +1 @@
+8.779000113188225

exp/lm_train_bpe150/valid.loss.ave_10best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b44c99e0c9ba7be39a8234c384d302f686b4058a93f748d72165686ce73ed01b
+size 27865874

meta.yaml

@@ -0,0 +1,10 @@
+espnet: 0.9.2
+files:
+  asr_model_file: exp/asr_transformer/29epoch.pth
+  lm_file: exp/lm_train_bpe150/valid.loss.ave_10best.pth
+python: "3.8.3 (default, May 19 2020, 18:47:26) \n[GCC 7.3.0]"
+timestamp: 1611336069.625217
+torch: 1.6.0
+yaml_files:
+  asr_train_config: exp/asr_transformer/config.yaml
+  lm_train_config: exp/lm_train_bpe150/config.yaml