add model files

README.md

@@ -0,0 +1,332 @@
+---
+tags:
+- espnet
+- audio
+- automatic-speech-recognition
+language: it
+datasets:
+- voxforge
+license: cc-by-4.0
+---
+
+## ESPnet2 ASR model 
+
+### `pyf98/voxforge_it_e_branchformer`
+
+This model was trained by Yifan Peng using voxforge recipe in [espnet](https://github.com/espnet/espnet/).
+
+References:
+- [E-Branchformer: Branchformer with Enhanced merging for speech recognition (SLT 2022)](https://arxiv.org/abs/2210.00077)
+- [Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding (ICML 2022)](https://proceedings.mlr.press/v162/peng22a.html)
+
+### 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 bf8c8f00194bdfed8ca388d8b20d14791b7d270e
+pip install -e .
+cd egs2/voxforge/asr1
+./run.sh --skip_data_prep false --skip_train true --download_model pyf98/voxforge_it_e_branchformer
+```
+
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Thu Dec 29 01:48:29 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: `bf8c8f00194bdfed8ca388d8b20d14791b7d270e`
+  - Commit date: `Wed Dec 28 22:43:13 2022 -0500`
+
+## asr_train_asr_e_branchformer_e12_mlp1024_linear1024_raw_it_char_normalize_confnorm_varsFalse
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_asr_model_valid.acc.ave/dt_it|1035|12587|71.3|24.0|4.7|3.8|32.5|95.5|
+|decode_asr_asr_model_valid.acc.ave/et_it|1103|13699|72.8|22.7|4.5|3.1|30.2|91.7|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_asr_model_valid.acc.ave/dt_it|1035|75494|93.2|3.7|3.1|2.0|8.8|95.5|
+|decode_asr_asr_model_valid.acc.ave/et_it|1103|81228|93.8|3.5|2.7|1.8|8.0|91.7|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+
+## ASR config
+
+<details><summary>expand</summary>
+
+```
+config: conf/tuning/train_asr_e_branchformer_e12_mlp1024_linear1024.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/asr_train_asr_e_branchformer_e12_mlp1024_linear1024_raw_it_char_normalize_confnorm_varsFalse
+ngpu: 1
+seed: 0
+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: 100
+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: 128
+valid_batch_size: null
+batch_bins: 1000000
+valid_batch_bins: null
+train_shape_file:
+- exp/asr_stats_raw_it_char/train/speech_shape
+- exp/asr_stats_raw_it_char/train/text_shape.char
+valid_shape_file:
+- exp/asr_stats_raw_it_char/valid/speech_shape
+- exp/asr_stats_raw_it_char/valid/text_shape.char
+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/tr_it/wav.scp
+    - speech
+    - sound
+-   - dump/raw/tr_it/text
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - dump/raw/dt_it/wav.scp
+    - speech
+    - sound
+-   - dump/raw/dt_it/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: 0.002
+scheduler: warmuplr
+scheduler_conf:
+    warmup_steps: 10000
+token_list:
+- <blank>
+- <unk>
+- <space>
+- A
+- E
+- I
+- O
+- R
+- N
+- L
+- S
+- T
+- C
+- D
+- U
+- M
+- P
+- V
+- G
+- F
+- H
+- B
+- Q
+- Z
+- ''''
+- Ò
+- À
+- È
+- Ú
+- X
+- W
+- Í
+- É
+- Y
+- K
+- J
+- '1'
+- <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: 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
+frontend: default
+frontend_conf:
+    fs: 16k
+specaug: null
+specaug_conf: {}
+normalize: global_mvn
+normalize_conf:
+    stats_file: exp/asr_stats_raw_it_char/train/feats_stats.npz
+    norm_vars: false
+model: espnet
+model_conf:
+    ctc_weight: 0.3
+    lsm_weight: 0.1
+    length_normalized_loss: false
+preencoder: null
+preencoder_conf: {}
+encoder: e_branchformer
+encoder_conf:
+    output_size: 256
+    attention_heads: 4
+    attention_layer_type: rel_selfattn
+    pos_enc_layer_type: rel_pos
+    rel_pos_type: latest
+    cgmlp_linear_units: 1024
+    cgmlp_conv_kernel: 31
+    use_linear_after_conv: false
+    gate_activation: identity
+    num_blocks: 12
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.1
+    input_layer: conv2d
+    layer_drop_rate: 0.0
+    linear_units: 1024
+    positionwise_layer_type: linear
+    use_ffn: true
+    macaron_ffn: true
+    merge_conv_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: 0.0
+    src_attention_dropout_rate: 0.0
+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}
+}
+```

exp/asr_stats_raw_it_char/train/feats_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ac4c6cee9a2bbf0175bb92bc350e21038c874b9d01b537b2688f5c8e1bae3d6
+size 1402

exp/asr_train_asr_e_branchformer_e12_mlp1024_linear1024_raw_it_char_normalize_confnorm_varsFalse/RESULTS.md

@@ -0,0 +1,29 @@
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Thu Dec 29 01:48:29 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: `bf8c8f00194bdfed8ca388d8b20d14791b7d270e`
+  - Commit date: `Wed Dec 28 22:43:13 2022 -0500`
+
+## asr_train_asr_e_branchformer_e12_mlp1024_linear1024_raw_it_char_normalize_confnorm_varsFalse
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_asr_model_valid.acc.ave/dt_it|1035|12587|71.3|24.0|4.7|3.8|32.5|95.5|
+|decode_asr_asr_model_valid.acc.ave/et_it|1103|13699|72.8|22.7|4.5|3.1|30.2|91.7|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_asr_model_valid.acc.ave/dt_it|1035|75494|93.2|3.7|3.1|2.0|8.8|95.5|
+|decode_asr_asr_model_valid.acc.ave/et_it|1103|81228|93.8|3.5|2.7|1.8|8.0|91.7|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|

exp/asr_train_asr_e_branchformer_e12_mlp1024_linear1024_raw_it_char_normalize_confnorm_varsFalse/config.yaml

@@ -0,0 +1,227 @@
+config: conf/tuning/train_asr_e_branchformer_e12_mlp1024_linear1024.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/asr_train_asr_e_branchformer_e12_mlp1024_linear1024_raw_it_char_normalize_confnorm_varsFalse
+ngpu: 1
+seed: 0
+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: 100
+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: 128
+valid_batch_size: null
+batch_bins: 1000000
+valid_batch_bins: null
+train_shape_file:
+- exp/asr_stats_raw_it_char/train/speech_shape
+- exp/asr_stats_raw_it_char/train/text_shape.char
+valid_shape_file:
+- exp/asr_stats_raw_it_char/valid/speech_shape
+- exp/asr_stats_raw_it_char/valid/text_shape.char
+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/tr_it/wav.scp
+    - speech
+    - sound
+-   - dump/raw/tr_it/text
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - dump/raw/dt_it/wav.scp
+    - speech
+    - sound
+-   - dump/raw/dt_it/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: 0.002
+scheduler: warmuplr
+scheduler_conf:
+    warmup_steps: 10000
+token_list:
+- <blank>
+- <unk>
+- <space>
+- A
+- E
+- I
+- O
+- R
+- N
+- L
+- S
+- T
+- C
+- D
+- U
+- M
+- P
+- V
+- G
+- F
+- H
+- B
+- Q
+- Z
+- ''''
+- Ò
+- À
+- È
+- Ú
+- X
+- W
+- Í
+- É
+- Y
+- K
+- J
+- '1'
+- <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: 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
+frontend: default
+frontend_conf:
+    fs: 16k
+specaug: null
+specaug_conf: {}
+normalize: global_mvn
+normalize_conf:
+    stats_file: exp/asr_stats_raw_it_char/train/feats_stats.npz
+    norm_vars: false
+model: espnet
+model_conf:
+    ctc_weight: 0.3
+    lsm_weight: 0.1
+    length_normalized_loss: false
+preencoder: null
+preencoder_conf: {}
+encoder: e_branchformer
+encoder_conf:
+    output_size: 256
+    attention_heads: 4
+    attention_layer_type: rel_selfattn
+    pos_enc_layer_type: rel_pos
+    rel_pos_type: latest
+    cgmlp_linear_units: 1024
+    cgmlp_conv_kernel: 31
+    use_linear_after_conv: false
+    gate_activation: identity
+    num_blocks: 12
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.1
+    input_layer: conv2d
+    layer_drop_rate: 0.0
+    linear_units: 1024
+    positionwise_layer_type: linear
+    use_ffn: true
+    macaron_ffn: true
+    merge_conv_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: 0.0
+    src_attention_dropout_rate: 0.0
+preprocessor: default
+preprocessor_conf: {}
+required:
+- output_dir
+- token_list
+version: '202211'
+distributed: false

exp/asr_train_asr_e_branchformer_e12_mlp1024_linear1024_raw_it_char_normalize_confnorm_varsFalse/valid.acc.ave_10best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ab27c2b3cebd3d0ab4762bc63084250bd22543239310e71d41fca00db19b6c0
+size 138931213

meta.yaml

@@ -0,0 +1,8 @@
+espnet: '202211'
+files:
+  asr_model_file: exp/asr_train_asr_e_branchformer_e12_mlp1024_linear1024_raw_it_char_normalize_confnorm_varsFalse/valid.acc.ave_10best.pth
+python: "3.9.15 (main, Nov 24 2022, 14:31:59) \n[GCC 11.2.0]"
+timestamp: 1672296511.658743
+torch: 1.12.1
+yaml_files:
+  asr_train_config: exp/asr_train_asr_e_branchformer_e12_mlp1024_linear1024_raw_it_char_normalize_confnorm_varsFalse/config.yaml