Update model

README.md

@@ -1,3 +1,258 @@
 ---
+tags:
+- espnet
+- audio
+- audio-to-audio
+language: noinfo
+datasets:
+- l3das22
 license: cc-by-4.0
 ---
+
+## ESPnet2 ENH model 
+
+### `espnet/Yen-Ju_Lu_l3das22_enh_train_enh_ineube_valid.loss.ave`
+
+This model was trained by neillu23 using l3das22 recipe in [espnet](https://github.com/espnet/espnet/).
+
+### Demo: How to use in ESPnet2
+
+```bash
+cd espnet
+git checkout 11d687844a544fcce6f6d0ce7a0a302e0e47d442
+pip install -e .
+cd egs2/l3das22/enh1
+./run.sh --skip_data_prep false --skip_train true --download_model espnet/Yen-Ju_Lu_l3das22_enh_train_enh_ineube_valid.loss.ave
+```
+
+<!-- Generated by ./scripts/utils/show_enh_score.sh -->
+# RESULTS
+## Environments
+- date: `Wed Jul  6 20:46:10 UTC 2022`
+- python version: `3.8.13 (default, Mar 28 2022, 11:38:47)  [GCC 7.5.0]`
+- espnet version: `espnet 202205`
+- pytorch version: `pytorch 1.8.1`
+- Git hash: `77e36afdd3f069567dd33d4b5b997a26b634772b`
+  - Commit date: `Fri Jun 17 18:32:56 2022 -0400`
+
+
+## enh_train_enh_ineube_raw
+
+config: conf/tuning/train_enh_ineube.yaml
+
+|dataset|STOI|SAR|SDR|SIR|SI_SNR|WER|STOI|TASK 1 METRIC|
+|---|---|---|---|---|---|---|---|---|
+|enhanced_dev_multich|95.62|15.00|15.00|0.00|13.64|5.93|0.956|0.948|
+|enhanced_test_multich|95.70|14.59|14.59|0.00|13.34|4.85|0.957|0.954|
+
+## ENH config
+
+<details><summary>expand</summary>
+
+```
+config: conf/tuning/train_enh_ineube.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: chunk
+output_dir: exp/enh_train_enh_ineube_raw
+ngpu: 1
+seed: 0
+num_workers: 4
+num_att_plot: 3
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: 3
+dist_rank: 0
+local_rank: 0
+dist_master_addr: localhost
+dist_master_port: 50409
+dist_launcher: null
+multiprocessing_distributed: true
+unused_parameters: true
+sharded_ddp: false
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: true
+collect_stats: false
+write_collected_feats: false
+max_epoch: 100
+patience: 20
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - si_snr
+    - max
+-   - valid
+    - loss
+    - min
+keep_nbest_models: 1
+nbest_averaging_interval: 0
+grad_clip: 5
+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_matplotlib: true
+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: 15
+valid_batch_size: null
+batch_bins: 1000000
+valid_batch_bins: null
+train_shape_file:
+- exp/enh_stats_16k/train/speech_mix_shape
+- exp/enh_stats_16k/train/speech_ref1_shape
+valid_shape_file:
+- exp/enh_stats_16k/valid/speech_mix_shape
+- exp/enh_stats_16k/valid/speech_ref1_shape
+batch_type: folded
+valid_batch_type: null
+fold_length:
+- 80000
+- 80000
+sort_in_batch: descending
+sort_batch: descending
+multiple_iterator: false
+chunk_length: 32000
+chunk_shift_ratio: 0.5
+num_cache_chunks: 1024
+train_data_path_and_name_and_type:
+-   - dump/raw/train_multich/wav.scp
+    - speech_mix
+    - sound
+-   - dump/raw/train_multich/spk1.scp
+    - speech_ref1
+    - sound
+valid_data_path_and_name_and_type:
+-   - dump/raw/dev_multich/wav.scp
+    - speech_mix
+    - sound
+-   - dump/raw/dev_multich/spk1.scp
+    - speech_ref1
+    - sound
+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
+    eps: 1.0e-08
+    weight_decay: 1.0e-07
+scheduler: reducelronplateau
+scheduler_conf:
+    mode: min
+    factor: 0.5
+    patience: 20
+init: xavier_uniform
+model_conf:
+    stft_consistency: false
+    loss_type: mask_mse
+    mask_type: null
+criterions:
+-   name: snr
+    conf: {}
+    wrapper: fixed_order
+    wrapper_conf:
+        weight: 1.0
+use_preprocessor: false
+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
+use_reverberant_ref: false
+num_spk: 1
+num_noise_type: 1
+sample_rate: 8000
+force_single_channel: false
+encoder: same
+encoder_conf: {}
+separator: ineube
+separator_conf:
+    n_fft: 512
+    stride: 128
+    window: hann
+    mic_channels: 8
+decoder: same
+decoder_conf: {}
+mask_module: multi_mask
+mask_module_conf: {}
+required:
+- output_dir
+version: '202205'
+distributed: true
+```
+
+</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}
+}
+
+
+@inproceedings{ESPnet-SE,
+  author = {Chenda Li and Jing Shi and Wangyou Zhang and Aswin Shanmugam Subramanian and Xuankai Chang and 
+  Naoyuki Kamo and Moto Hira and Tomoki Hayashi and Christoph B{"{o}}ddeker and Zhuo Chen and Shinji Watanabe},
+  title = {ESPnet-SE: End-To-End Speech Enhancement and Separation Toolkit Designed for {ASR} Integration},
+  booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021},
+  pages = {785--792},
+  publisher = {{IEEE}},
+  year = {2021},
+  url = {https://doi.org/10.1109/SLT48900.2021.9383615},
+  doi = {10.1109/SLT48900.2021.9383615},
+  timestamp = {Mon, 12 Apr 2021 17:08:59 +0200},
+  biburl = {https://dblp.org/rec/conf/slt/Li0ZSCKHHBC021.bib},
+  bibsource = {dblp computer science bibliography, https://dblp.org}
+}
+
+
+```
+
+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/enh_stats_16k/train/feats_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd36206f9254d1adfffa0dd03e2a53b6212bc6637a69a7451e651214a07bf414
+size 826

exp/enh_train_enh_ineube_raw/99epoch.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa75dbe6a394a608fc9a2c514baba2169b345789696d9a19c9a7340d435901b9
+size 62103895

exp/enh_train_enh_ineube_raw/RESULTS.md

@@ -0,0 +1,20 @@
+<!-- Generated by ./scripts/utils/show_enh_score.sh -->
+# RESULTS
+## Environments
+- date: `Wed Jul  6 20:46:10 UTC 2022`
+- python version: `3.8.13 (default, Mar 28 2022, 11:38:47)  [GCC 7.5.0]`
+- espnet version: `espnet 202205`
+- pytorch version: `pytorch 1.8.1`
+- Git hash: `77e36afdd3f069567dd33d4b5b997a26b634772b`
+  - Commit date: `Fri Jun 17 18:32:56 2022 -0400`
+
+
+## enh_train_enh_ineube_raw
+
+config: conf/tuning/train_enh_ineube.yaml
+
+|dataset|STOI|SAR|SDR|SIR|SI_SNR|
+|---|---|---|---|---|---|
+|enhanced_dev_multich|95.62|15.00|15.00|0.00|13.64|
+|enhanced_test_multich|95.70|14.59|14.59|0.00|13.34|
+

exp/enh_train_enh_ineube_raw/config.yaml

@@ -0,0 +1,156 @@
+config: conf/tuning/train_enh_ineube.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: chunk
+output_dir: exp/enh_train_enh_ineube_raw
+ngpu: 1
+seed: 0
+num_workers: 4
+num_att_plot: 3
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: 3
+dist_rank: 0
+local_rank: 0
+dist_master_addr: localhost
+dist_master_port: 50409
+dist_launcher: null
+multiprocessing_distributed: true
+unused_parameters: true
+sharded_ddp: false
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: true
+collect_stats: false
+write_collected_feats: false
+max_epoch: 100
+patience: 20
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - si_snr
+    - max
+-   - valid
+    - loss
+    - min
+keep_nbest_models: 1
+nbest_averaging_interval: 0
+grad_clip: 5
+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_matplotlib: true
+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: 15
+valid_batch_size: null
+batch_bins: 1000000
+valid_batch_bins: null
+train_shape_file:
+- exp/enh_stats_16k/train/speech_mix_shape
+- exp/enh_stats_16k/train/speech_ref1_shape
+valid_shape_file:
+- exp/enh_stats_16k/valid/speech_mix_shape
+- exp/enh_stats_16k/valid/speech_ref1_shape
+batch_type: folded
+valid_batch_type: null
+fold_length:
+- 80000
+- 80000
+sort_in_batch: descending
+sort_batch: descending
+multiple_iterator: false
+chunk_length: 32000
+chunk_shift_ratio: 0.5
+num_cache_chunks: 1024
+train_data_path_and_name_and_type:
+-   - dump/raw/train_multich/wav.scp
+    - speech_mix
+    - sound
+-   - dump/raw/train_multich/spk1.scp
+    - speech_ref1
+    - sound
+valid_data_path_and_name_and_type:
+-   - dump/raw/dev_multich/wav.scp
+    - speech_mix
+    - sound
+-   - dump/raw/dev_multich/spk1.scp
+    - speech_ref1
+    - sound
+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
+    eps: 1.0e-08
+    weight_decay: 1.0e-07
+scheduler: reducelronplateau
+scheduler_conf:
+    mode: min
+    factor: 0.5
+    patience: 20
+init: xavier_uniform
+model_conf:
+    stft_consistency: false
+    loss_type: mask_mse
+    mask_type: null
+criterions:
+-   name: snr
+    conf: {}
+    wrapper: fixed_order
+    wrapper_conf:
+        weight: 1.0
+use_preprocessor: false
+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
+use_reverberant_ref: false
+num_spk: 1
+num_noise_type: 1
+sample_rate: 8000
+force_single_channel: false
+encoder: same
+encoder_conf: {}
+separator: ineube
+separator_conf:
+    n_fft: 512
+    stride: 128
+    window: hann
+    mic_channels: 8
+decoder: same
+decoder_conf: {}
+mask_module: multi_mask
+mask_module_conf: {}
+required:
+- output_dir
+version: '202205'
+distributed: true

meta.yaml

@@ -0,0 +1,8 @@
+espnet: '202205'
+files:
+  model_file: exp/enh_train_enh_ineube_raw/99epoch.pth
+python: "3.8.13 (default, Mar 28 2022, 11:38:47) \n[GCC 7.5.0]"
+timestamp: 1657140371.541695
+torch: 1.8.1
+yaml_files:
+  train_config: exp/enh_train_enh_ineube_raw/config.yaml