Update model

README.md

@@ -1,3 +1,241 @@
----
-license: cc-by-4.0
----
+---
+tags:
+- espnet
+- audio
+- audio-to-audio
+language: 
+datasets:
+- chime4
+license: cc-by-4.0
+---
+
+## ESPnet2 ENH model 
+
+### ``
+
+This model was trained by Wangyou Zhang using chime4 recipe in [espnet](https://github.com/espnet/espnet/).
+
+### Demo: How to use in ESPnet2
+
+```bash
+cd espnet
+
+pip install -e .
+cd wyz/Downloads/Wangyou_Zhang_chime4_enh_train_enh_beamformer_mvdr_raw
+./run.sh --skip_data_prep false --skip_train true --download_model 
+```
+
+
+
+## ENH config
+
+<details><summary>expand</summary>
+
+```
+config: conf/tuning/train_enh_beamformer_mvdr.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/enh_train_enh_beamformer_mvdr_raw
+ngpu: 1
+seed: 0
+num_workers: 4
+num_att_plot: 3
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: 2
+dist_rank: 0
+local_rank: 0
+dist_master_addr: localhost
+dist_master_port: 35841
+dist_launcher: null
+multiprocessing_distributed: true
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: true
+collect_stats: false
+write_collected_feats: false
+max_epoch: 70
+patience: 4
+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
+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: []
+freeze_param: []
+num_iters_per_epoch: null
+batch_size: 8
+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
+- exp/enh_stats_16k/train/noise_ref1_shape
+valid_shape_file:
+- exp/enh_stats_16k/valid/speech_mix_shape
+- exp/enh_stats_16k/valid/speech_ref1_shape
+- exp/enh_stats_16k/valid/noise_ref1_shape
+batch_type: folded
+valid_batch_type: null
+fold_length:
+- 80000
+- 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/tr05_simu_isolated_6ch_track/wav.scp
+    - speech_mix
+    - sound
+-   - dump/raw/tr05_simu_isolated_6ch_track/spk1.scp
+    - speech_ref1
+    - sound
+-   - dump/raw/tr05_simu_isolated_6ch_track/noise1.scp
+    - noise_ref1
+    - sound
+valid_data_path_and_name_and_type:
+-   - dump/raw/dt05_simu_isolated_6ch_track/wav.scp
+    - speech_mix
+    - sound
+-   - dump/raw/dt05_simu_isolated_6ch_track/spk1.scp
+    - speech_ref1
+    - sound
+-   - dump/raw/dt05_simu_isolated_6ch_track/noise1.scp
+    - noise_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: 0
+scheduler: reducelronplateau
+scheduler_conf:
+    mode: min
+    factor: 0.5
+    patience: 1
+init: xavier_uniform
+model_conf:
+    loss_type: mask_mse
+    mask_type: PSM^2
+use_preprocessor: false
+encoder: stft
+encoder_conf:
+    n_fft: 512
+    hop_length: 128
+separator: wpe_beamformer
+separator_conf:
+    num_spk: 1
+    loss_type: mask_mse
+    use_wpe: false
+    wnet_type: blstmp
+    wlayers: 3
+    wunits: 300
+    wprojs: 320
+    wdropout_rate: 0.0
+    taps: 5
+    delay: 3
+    use_dnn_mask_for_wpe: true
+    use_beamformer: true
+    bnet_type: blstmp
+    blayers: 3
+    bunits: 512
+    bprojs: 512
+    badim: 320
+    ref_channel: 3
+    use_noise_mask: true
+    beamformer_type: mvdr_souden
+    bdropout_rate: 0.0
+decoder: stft
+decoder_conf:
+    n_fft: 512
+    hop_length: 128
+required:
+- output_dir
+version: 0.9.7
+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{li2021espnetse,
+  title={{ESPnet-SE}: End-to-End Speech Enhancement and Separation Toolkit Designed for {ASR} Integration},
+  author={Li, Chenda and Shi, Jing and Zhang, Wangyou and Subramanian, Aswin Shanmugam and Chang, Xuankai and Kamo, Naoyuki and Hira, Moto and Hayashi, Tomoki and Boeddeker, Christoph and Chen, Zhuo and Watanabe, Shinji},
+  booktitle={Proc. IEEE Spoken Language Technology Workshop (SLT)},
+  pages={785--792},
+  year={2021},
+}
+
+```
+
+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}
+}
+
+@inproceedings{li2021espnetse,
+  title={{ESPnet-SE}: End-to-End Speech Enhancement and Separation Toolkit Designed for {ASR} Integration},
+  author={Li, Chenda and Shi, Jing and Zhang, Wangyou and Subramanian, Aswin Shanmugam and Chang, Xuankai and Kamo, Naoyuki and Hira, Moto and Hayashi, Tomoki and Boeddeker, Christoph and Chen, Zhuo and Watanabe, Shinji},
+  year={2020},
+  eprint={2011.03706},
+  archivePrefix={arXiv},
+  primaryClass={eess.AS}
+}
+```

exp/enh_train_enh_beamformer_mvdr_raw/11epoch.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:418c3c7ab136dea6ae4cfbd9084493dc8e18e95b68b60af9368d194955063eff
+size 53613220

exp/enh_train_enh_beamformer_mvdr_raw/RESULTS.TXT

@@ -0,0 +1,20 @@
+<!-- Generated by ./scripts/utils/show_enh_score.sh -->
+# RESULTS
+## Environments
+- date: `Thu Jan 28 22:28:34 CST 2021`
+- python version: `3.6.3 |Anaconda, Inc.| (default, Nov 20 2017, 20:41:42)  [GCC 7.2.0]`
+- espnet version: `espnet 0.9.7`
+- pytorch version: `pytorch 1.6.0`
+- Git hash: `eddccfa7a296fcf8fd744200d7e8113f9a3c7e69`
+  - Commit date: `Thu Jan 21 21:42:24 2021 +0800`
+
+
+## enh_train_enh_beamformer_mvdr_raw
+
+config: conf/tuning/train_enh_beamformer_mvdr.yaml
+
+|dataset|PESQ|STOI|SAR|SDR|SIR|SI_SNR|
+|---|---|---|---|---|---|---|
+|enhanced_dt05_simu_isolated_6ch_track|2.60262|0.945147|13.6748|13.6748|0|12.5195|
+|enhanced_et05_simu_isolated_6ch_track|2.63531|0.950153|15.5108|15.5108|0|14.6525|
+

exp/enh_train_enh_beamformer_mvdr_raw/config.yaml

@@ -0,0 +1,157 @@
+config: conf/tuning/train_enh_beamformer_mvdr.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/enh_train_enh_beamformer_mvdr_raw
+ngpu: 1
+seed: 0
+num_workers: 4
+num_att_plot: 3
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: 2
+dist_rank: 0
+local_rank: 0
+dist_master_addr: localhost
+dist_master_port: 35841
+dist_launcher: null
+multiprocessing_distributed: true
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: true
+collect_stats: false
+write_collected_feats: false
+max_epoch: 70
+patience: 4
+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
+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: []
+freeze_param: []
+num_iters_per_epoch: null
+batch_size: 8
+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
+- exp/enh_stats_16k/train/noise_ref1_shape
+valid_shape_file:
+- exp/enh_stats_16k/valid/speech_mix_shape
+- exp/enh_stats_16k/valid/speech_ref1_shape
+- exp/enh_stats_16k/valid/noise_ref1_shape
+batch_type: folded
+valid_batch_type: null
+fold_length:
+- 80000
+- 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/tr05_simu_isolated_6ch_track/wav.scp
+    - speech_mix
+    - sound
+-   - dump/raw/tr05_simu_isolated_6ch_track/spk1.scp
+    - speech_ref1
+    - sound
+-   - dump/raw/tr05_simu_isolated_6ch_track/noise1.scp
+    - noise_ref1
+    - sound
+valid_data_path_and_name_and_type:
+-   - dump/raw/dt05_simu_isolated_6ch_track/wav.scp
+    - speech_mix
+    - sound
+-   - dump/raw/dt05_simu_isolated_6ch_track/spk1.scp
+    - speech_ref1
+    - sound
+-   - dump/raw/dt05_simu_isolated_6ch_track/noise1.scp
+    - noise_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: 0
+scheduler: reducelronplateau
+scheduler_conf:
+    mode: min
+    factor: 0.5
+    patience: 1
+init: xavier_uniform
+model_conf:
+    loss_type: mask_mse
+    mask_type: PSM^2
+use_preprocessor: false
+encoder: stft
+encoder_conf:
+    n_fft: 512
+    hop_length: 128
+separator: wpe_beamformer
+separator_conf:
+    num_spk: 1
+    loss_type: mask_mse
+    use_wpe: false
+    wnet_type: blstmp
+    wlayers: 3
+    wunits: 300
+    wprojs: 320
+    wdropout_rate: 0.0
+    taps: 5
+    delay: 3
+    use_dnn_mask_for_wpe: true
+    use_beamformer: true
+    bnet_type: blstmp
+    blayers: 3
+    bunits: 512
+    bprojs: 512
+    badim: 320
+    ref_channel: 3
+    use_noise_mask: true
+    beamformer_type: mvdr_souden
+    bdropout_rate: 0.0
+decoder: stft
+decoder_conf:
+    n_fft: 512
+    hop_length: 128
+required:
+- output_dir
+version: 0.9.7
+distributed: true

meta.yaml

@@ -0,0 +1,8 @@
+espnet: 0.9.7
+files:
+  model_file: exp/enh_train_enh_beamformer_mvdr_raw/11epoch.pth
+python: "3.6.3 |Anaconda, Inc.| (default, Nov 20 2017, 20:41:42) \n[GCC 7.2.0]"
+timestamp: 1644422365.226252
+torch: 1.6.0
+yaml_files:
+  train_config: exp/enh_train_enh_beamformer_mvdr_raw/config.yaml