Update model

README.md

@@ -0,0 +1,255 @@
+---
+tags:
+- espnet
+- audio
+- audio-to-audio
+language: en
+datasets:
+- dns_icassp21
+license: cc-by-4.0
+---
+
+## ESPnet2 ENH model 
+
+### `espnet/dns_icassp21_enh_train_enh_tcn_tf_raw`
+
+This model was trained by Yoshiki using dns_icassp21 recipe in [espnet](https://github.com/espnet/espnet/).
+
+### Demo: How to use in ESPnet2
+
+```bash
+cd espnet
+
+pip install -e .
+cd egs2/dns_icassp21/enh1
+./run.sh --skip_data_prep false --skip_train true --download_model espnet/dns_icassp21_enh_train_enh_tcn_tf_raw
+```
+
+<!-- Generated by ./scripts/utils/show_enh_score.sh -->
+# RESULTS
+## Environments
+- date: `Thu Apr 21 21:49:46 UTC 2022`
+- python version: `3.7.4 (default, Aug 13 2019, 20:35:49)  [GCC 7.3.0]`
+- espnet version: `espnet 202204`
+- pytorch version: `pytorch 1.10.1+cu111`
+- Git hash: ``
+  - Commit date: ``
+
+
+## ..
+
+config: ./conf/train.yaml
+
+|dataset|STOI|SAR|SDR|SIR|SI_SNR|
+|---|---|---|---|---|---|
+|enhanced_cv_synthetic|0.93|18.96|18.96|0.00|18.79|
+|enhanced_tt_synthetic_track_1|0.77|14.19|14.19|0.00|12.15|
+
+## ENH config
+
+<details><summary>expand</summary>
+
+```
+config: ./conf/train.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/enh_train_raw
+ngpu: 1
+seed: 0
+num_workers: 4
+num_att_plot: 3
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: 4
+dist_rank: 0
+local_rank: 0
+dist_master_addr: localhost
+dist_master_port: 32787
+dist_launcher: null
+multiprocessing_distributed: true
+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: 10
+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: 5.0
+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_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: 128
+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: 500
+chunk_shift_ratio: 0.5
+num_cache_chunks: 1024
+train_data_path_and_name_and_type:
+-   - dump/raw/tr_synthetic/wav.scp
+    - speech_mix
+    - sound
+-   - dump/raw/tr_synthetic/spk1.scp
+    - speech_ref1
+    - sound
+valid_data_path_and_name_and_type:
+-   - dump/raw/cv_synthetic/wav.scp
+    - speech_mix
+    - sound
+-   - dump/raw/cv_synthetic/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: 0.7
+    patience: 1
+init: xavier_uniform
+model_conf:
+    stft_consistency: false
+    loss_type: mask_mse
+    mask_type: null
+criterions:
+-   name: si_snr
+    conf:
+        eps: 1.0e-07
+    wrapper: pit
+    wrapper_conf:
+        weight: 1.0
+        independent_perm: true
+use_preprocessor: false
+encoder: stft
+encoder_conf:
+    n_fft: 320
+    hop_length: 160
+separator: tcn
+separator_conf:
+    num_spk: 1
+    layer: 4
+    stack: 3
+    bottleneck_dim: 128
+    hidden_dim: 512
+    kernel: 3
+    causal: true
+    norm_type: gLN
+    nonlinear: relu
+decoder: stft
+decoder_conf:
+    n_fft: 320
+    hop_length: 160
+required:
+- output_dir
+version: '202204'
+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_train_raw/53epoch.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47b7401135abff7b761436573e5216ba9fdf8978d44d5a4ec7ef12bebfe144f2
+size 6675681

exp/enh_train_raw/RESULTS.md

@@ -0,0 +1,20 @@
+<!-- Generated by ./scripts/utils/show_enh_score.sh -->
+# RESULTS
+## Environments
+- date: `Thu Apr 21 21:49:46 UTC 2022`
+- python version: `3.7.4 (default, Aug 13 2019, 20:35:49)  [GCC 7.3.0]`
+- espnet version: `espnet 202204`
+- pytorch version: `pytorch 1.10.1+cu111`
+- Git hash: ``
+  - Commit date: ``
+
+
+## ..
+
+config: ./conf/train.yaml
+
+|dataset|STOI|SAR|SDR|SIR|SI_SNR|
+|---|---|---|---|---|---|
+|enhanced_cv_synthetic|0.93|18.96|18.96|0.00|18.79|
+|enhanced_tt_synthetic_track_1|0.77|14.19|14.19|0.00|12.15|
+

exp/enh_train_raw/config.yaml

@@ -0,0 +1,153 @@
+config: ./conf/train.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/enh_train_raw
+ngpu: 1
+seed: 0
+num_workers: 4
+num_att_plot: 3
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: 4
+dist_rank: 0
+local_rank: 0
+dist_master_addr: localhost
+dist_master_port: 32787
+dist_launcher: null
+multiprocessing_distributed: true
+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: 10
+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: 5.0
+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_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: 128
+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: 500
+chunk_shift_ratio: 0.5
+num_cache_chunks: 1024
+train_data_path_and_name_and_type:
+-   - dump/raw/tr_synthetic/wav.scp
+    - speech_mix
+    - sound
+-   - dump/raw/tr_synthetic/spk1.scp
+    - speech_ref1
+    - sound
+valid_data_path_and_name_and_type:
+-   - dump/raw/cv_synthetic/wav.scp
+    - speech_mix
+    - sound
+-   - dump/raw/cv_synthetic/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: 0.7
+    patience: 1
+init: xavier_uniform
+model_conf:
+    stft_consistency: false
+    loss_type: mask_mse
+    mask_type: null
+criterions:
+-   name: si_snr
+    conf:
+        eps: 1.0e-07
+    wrapper: pit
+    wrapper_conf:
+        weight: 1.0
+        independent_perm: true
+use_preprocessor: false
+encoder: stft
+encoder_conf:
+    n_fft: 320
+    hop_length: 160
+separator: tcn
+separator_conf:
+    num_spk: 1
+    layer: 4
+    stack: 3
+    bottleneck_dim: 128
+    hidden_dim: 512
+    kernel: 3
+    causal: true
+    norm_type: gLN
+    nonlinear: relu
+decoder: stft
+decoder_conf:
+    n_fft: 320
+    hop_length: 160
+required:
+- output_dir
+version: '202204'
+distributed: true

meta.yaml

@@ -0,0 +1,8 @@
+espnet: '202204'
+files:
+  model_file: exp/enh_train_raw/53epoch.pth
+python: "3.7.4 (default, Aug 13 2019, 20:35:49) \n[GCC 7.3.0]"
+timestamp: 1650738852.952602
+torch: 1.10.1+cu111
+yaml_files:
+  train_config: exp/enh_train_raw/config.yaml