Upload 7 files

README.md

@@ -1,3 +1,58 @@
----
-license: cc-by-nc-4.0
----
+---
+{}
+---
+## ESPnet2 ASR model 
+
+### `ouktlab/espnet_asr-ja-kc_am-transformer-robustcorpus10_lm-transformer-corpus10-bccwj-wiki40b`
+
+This model was trained using csj recipe in [espnet](https://github.com/espnet/espnet/).
+
+### 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}
+}
+```
+
+### Katakana model
+```BibTex
+@inproceedings{rtakeda2024:iwsds,
+  author={Ryu Takeda and Kazunori Komatani},
+  title={Toward OOV-word Acquisition during Spoken Dialogue using Syllable-based ASR and Word Segmentation},
+  year={2024},
+  booktitle={Proceedings of International Workshop on Spoken Dialogue Systems Technology (IWSDS)},
+}
+
+@inproceedings{oshio2023:apsipa,
+  author={Miki Oshio, Hokuto Munakata, Ryu Takeda and Kazunori Komatani},
+  title={Out-Of-Vocabulary Word Detection in Spoken Dialogues Based on Joint Decoding with User Response Patterns},
+  year={2023},
+  booktitle={Proceedings of Asia Pacific Signal and Information Processing Association (APSIPA)},
+  pages={1753-1759}  
+}
+
+```
+
+license: cc-by-nc-4.0
+

exp/asr_stats_raw_jp_char_sp/train/feats_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d77903ab1c6159cb627d842db7a7c2503a5d4138e5f1ddac81353d59354157b1
+size 1402

exp/asr_train_asr_transformer_ja_raw_jp_char_sp/config.yaml

@@ -0,0 +1,368 @@
+config: 
+print_config: false
+log_level: INFO
+drop_last_iter: false
+dry_run: false
+iterator_type: sequence
+valid_iterator_type: null
+output_dir: 
+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: 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: 20
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - cer
+    - min
+keep_nbest_models: 10
+nbest_averaging_interval: 0
+grad_clip: 5.0
+grad_clip_type: 2.0
+grad_noise: false
+accum_grad: 6
+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: 20
+valid_batch_size: null
+batch_bins: 10000000
+valid_batch_bins: null
+train_shape_file:
+- model/stats//train/speech_shape
+- model/stats//train/text_shape.char
+valid_shape_file:
+- model/stats//valid/speech_shape
+- model/stats//valid/text_shape.char
+batch_type: numel
+valid_batch_type: null
+fold_length:
+- 80000
+- 150
+sort_in_batch: descending
+shuffle_within_batch: false
+sort_batch: descending
+multiple_iterator: false
+chunk_length: 500
+chunk_shift_ratio: 0.5
+num_cache_chunks: 1024
+chunk_excluded_key_prefixes: []
+train_data_path_and_name_and_type:
+-   - 
+    - speech
+    - sound
+-   - 
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - 
+    - speech
+    - sound
+-   - 
+    - text
+    - text
+allow_variable_data_keys: false
+max_cache_size: 0.0
+max_cache_fd: 32
+valid_max_cache_size: null
+exclude_weight_decay: false
+exclude_weight_decay_conf: {}
+optim: adam
+optim_conf:
+    lr: 2.0e-05
+scheduler: null
+scheduler_conf: {}
+token_list:
+- <blank>
+- <unk>
+- <b>
+- <e>
+- <o>
+- <i>
+- </>
+- '!'
+- '#'
+- $
+- '%'
+- '&'
+- (
+- )
+- '*'
+- '='
+- +
+- '-'
+- /
+- ':'
+- <
+- '>'
+- '?'
+- '@'
+- A
+- B
+- C
+- D
+- E
+- F
+- G
+- H
+- I
+- J
+- K
+- L
+- M
+- N
+- O
+- P
+- Q
+- R
+- S
+- T
+- U
+- V
+- W
+- X
+- Y
+- Z
+- '['
+- ']'
+- ^
+- _
+- a
+- b
+- c
+- d
+- e
+- f
+- g
+- h
+- i
+- j
+- k
+- l
+- m
+- n
+- o
+- p
+- q
+- r
+- s
+- t
+- u
+- v
+- w
+- x
+- y
+- z
+- '{'
+- '|'
+- '}'
+- 、
+- 。
+- ？
+- ！
+- …
+- ー
+- ァ
+- ア
+- ィ
+- イ
+- ゥ
+- ウ
+- ェ
+- エ
+- ォ
+- オ
+- カ
+- ガ
+- キ
+- ギ
+- ク
+- グ
+- ケ
+- ゲ
+- コ
+- ゴ
+- サ
+- ザ
+- シ
+- ジ
+- ス
+- ズ
+- セ
+- ゼ
+- ソ
+- ゾ
+- タ
+- ダ
+- チ
+- ヂ
+- ッ
+- ツ
+- ヅ
+- テ
+- デ
+- ト
+- ド
+- ナ
+- ニ
+- ヌ
+- ネ
+- ノ
+- ハ
+- バ
+- パ
+- ヒ
+- ビ
+- ピ
+- フ
+- ブ
+- プ
+- ヘ
+- ベ
+- ペ
+- ホ
+- ボ
+- ポ
+- マ
+- ミ
+- ム
+- メ
+- モ
+- ャ
+- ヤ
+- ュ
+- ユ
+- ョ
+- ヨ
+- ラ
+- リ
+- ル
+- レ
+- ロ
+- ヮ
+- ワ
+- ヲ
+- ン
+- ヴ
+- <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: char
+bpemodel: null
+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
+aux_ctc_tasks: []
+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_jp_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: transformer
+encoder_conf:
+    output_size: 512
+    attention_heads: 8
+    linear_units: 2048
+    num_blocks: 18
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.1
+    input_layer: conv2d6
+    normalize_before: true
+postencoder: null
+postencoder_conf: {}
+decoder: transformer
+decoder_conf:
+    attention_heads: 8
+    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: '202308'
+distributed: false

exp/asr_train_asr_transformer_ja_raw_jp_char_sp/valid.cer.ave_10best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41d25a35e5a07422de19fec39a70a946620ce7a030610eeacb8db70b8f92aafb
+size 368015872

exp/lm_train_lm_ja_char/config.yaml

@@ -0,0 +1,303 @@
+config: train_lm_transformer.yaml
+print_config: false
+log_level: INFO
+drop_last_iter: false
+dry_run: false
+iterator_type: sequence
+valid_iterator_type: null
+output_dir: 
+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: 25
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - loss
+    - min
+keep_nbest_models: 10
+nbest_averaging_interval: 0
+grad_clip: 5.0
+grad_clip_type: 2.0
+grad_noise: false
+accum_grad: 2
+no_forward_run: false
+resume: false
+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: 20
+valid_batch_size: null
+batch_bins: 4000000
+valid_batch_bins: null
+train_shape_file:
+- 
+valid_shape_file:
+- 
+batch_type: numel
+valid_batch_type: null
+fold_length:
+- 150
+sort_in_batch: descending
+shuffle_within_batch: false
+sort_batch: descending
+multiple_iterator: false
+chunk_length: 500
+chunk_shift_ratio: 0.5
+num_cache_chunks: 1024
+chunk_excluded_key_prefixes: []
+train_data_path_and_name_and_type:
+-   - 
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - 
+    - text
+    - text
+allow_variable_data_keys: false
+max_cache_size: 0.0
+max_cache_fd: 32
+valid_max_cache_size: null
+exclude_weight_decay: false
+exclude_weight_decay_conf: {}
+optim: adam
+optim_conf:
+    lr: 0.001
+scheduler: warmuplr
+scheduler_conf:
+    warmup_steps: 25000
+token_list:
+- <blank>
+- <unk>
+- <b>
+- <e>
+- <o>
+- <i>
+- </>
+- '!'
+- '#'
+- $
+- '%'
+- '&'
+- (
+- )
+- '*'
+- '='
+- +
+- '-'
+- /
+- ':'
+- <
+- '>'
+- '?'
+- '@'
+- A
+- B
+- C
+- D
+- E
+- F
+- G
+- H
+- I
+- J
+- K
+- L
+- M
+- N
+- O
+- P
+- Q
+- R
+- S
+- T
+- U
+- V
+- W
+- X
+- Y
+- Z
+- '['
+- ']'
+- ^
+- _
+- a
+- b
+- c
+- d
+- e
+- f
+- g
+- h
+- i
+- j
+- k
+- l
+- m
+- n
+- o
+- p
+- q
+- r
+- s
+- t
+- u
+- v
+- w
+- x
+- y
+- z
+- '{'
+- '|'
+- '}'
+- 、
+- 。
+- ？
+- ！
+- …
+- ー
+- ァ
+- ア
+- ィ
+- イ
+- ゥ
+- ウ
+- ェ
+- エ
+- ォ
+- オ
+- カ
+- ガ
+- キ
+- ギ
+- ク
+- グ
+- ケ
+- ゲ
+- コ
+- ゴ
+- サ
+- ザ
+- シ
+- ジ
+- ス
+- ズ
+- セ
+- ゼ
+- ソ
+- ゾ
+- タ
+- ダ
+- チ
+- ヂ
+- ッ
+- ツ
+- ヅ
+- テ
+- デ
+- ト
+- ド
+- ナ
+- ニ
+- ヌ
+- ネ
+- ノ
+- ハ
+- バ
+- パ
+- ヒ
+- ビ
+- ピ
+- フ
+- ブ
+- プ
+- ヘ
+- ベ
+- ペ
+- ホ
+- ボ
+- ポ
+- マ
+- ミ
+- ム
+- メ
+- モ
+- ャ
+- ヤ
+- ュ
+- ユ
+- ョ
+- ヨ
+- ラ
+- リ
+- ル
+- レ
+- ロ
+- ヮ
+- ワ
+- ヲ
+- ン
+- ヴ
+- <sos/eos>
+init: null
+model_conf:
+    ignore_id: 0
+use_preprocessor: true
+token_type: char
+bpemodel: null
+non_linguistic_symbols: null
+cleaner: null
+g2p: null
+lm: transformer
+lm_conf:
+    pos_enc: null
+    embed_unit: 256
+    att_unit: 512
+    head: 8
+    unit: 2048
+    layer: 16
+    dropout_rate: 0.1
+required:
+- output_dir
+- token_list
+version: '202308'
+distributed: false

exp/lm_train_lm_ja_char/valid.loss.ave_5best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d9c4920e781f8323bca07939d006d8fd41fda69d482e6bc165d352d3ca1fde0
+size 202919113

meta.yaml

@@ -0,0 +1,6 @@
+files:
+  asr_model_file: exp/asr_train_asr_transformer_ja_raw_jp_char_sp/valid.cer.ave_10best.pth
+  lm_file: exp/lm_train_lm_ja_char/valid.loss.ave_5best.pth
+yaml_files:
+  asr_train_config: exp/asr_train_asr_transformer_ja_raw_jp_char_sp/config.yaml
+  lm_train_config: exp/lm_train_lm_ja_char/config.yaml