Update model

README.md

@@ -1,3 +1,277 @@
 ---
+tags:
+- espnet
+- audio
+- audio-to-audio
+language: noinfo
+datasets:
+- clarity
 license: cc-by-4.0
 ---
+
+## ESPnet2 ENH model 
+
+### `popcornell/clarity21_train_enh_beamformer_mvdr`
+
+This model was trained by popcornell using clarity recipe in [espnet](https://github.com/espnet/espnet/).
+
+### Demo: How to use in ESPnet2
+
+```bash
+cd espnet
+
+pip install -e .
+cd egs2/clarity/enh_2021
+./run.sh --skip_data_prep false --skip_train true --download_model popcornell/clarity21_train_enh_beamformer_mvdr
+```
+
+<!-- Generated by ./scripts/utils/show_enh_score.sh -->
+# RESULTS
+## Environments
+- date: `Tue Apr 12 20:54:54 UTC 2022`
+- python version: `3.9.7 (default, Sep 16 2021, 13:09:58)  [GCC 7.5.0]`
+- espnet version: `espnet 0.10.5a1`
+- pytorch version: `pytorch 1.10.1`
+- Git hash: `46eaa5eb6bea11cc33927392dca7888921491d8c`
+  - Commit date: `Sat Mar 26 22:35:44 2022 +0100`
+
+
+## ..
+
+config: conf/tuning/train_enh_beamformer_mvdr.yaml
+
+|dataset|STOI|SAR|SDR|SIR|
+|---|---|---|---|---|
+|enhanced_dev|0.96|13.02|13.02|0.00|
+
+## 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: 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: 8
+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
+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: 1
+valid_batch_size: null
+batch_bins: 1000000
+valid_batch_bins: null
+train_shape_file:
+- exp/enh_stats_16000/train/speech_mix_shape
+- exp/enh_stats_16000/train/speech_ref1_shape
+- exp/enh_stats_16000/train/noise_ref1_shape
+valid_shape_file:
+- exp/enh_stats_16000/valid/speech_mix_shape
+- exp/enh_stats_16000/valid/speech_ref1_shape
+- exp/enh_stats_16000/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/train/wav.scp
+    - speech_mix
+    - sound
+-   - dump/raw/train/spk1.scp
+    - speech_ref1
+    - sound
+-   - dump/raw/train/noise1.scp
+    - noise_ref1
+    - sound
+valid_data_path_and_name_and_type:
+-   - dump/raw/dev/wav.scp
+    - speech_mix
+    - sound
+-   - dump/raw/dev/spk1.scp
+    - speech_ref1
+    - sound
+-   - dump/raw/dev/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:
+    stft_consistency: false
+    loss_type: mask_mse
+    mask_type: null
+criterions:
+-   name: snr
+    conf:
+        eps: 1e-8
+    wrapper: fixed_order
+    wrapper_conf:
+        weight: 1.0
+use_preprocessor: false
+encoder: stft
+encoder_conf:
+    n_fft: 1024
+    hop_length: 512
+    use_builtin_complex: false
+separator: wpe_beamformer
+separator_conf:
+    num_spk: 1
+    loss_type: spectrum
+    use_wpe: false
+    use_beamformer: true
+    bnet_type: blstmp
+    blayers: 3
+    bunits: 300
+    bprojs: 320
+    badim: 320
+    ref_channel: 0
+    use_noise_mask: true
+    bnonlinear: sigmoid
+    beamformer_type: mvdr_souden
+    rtf_iterations: 2
+    bdropout_rate: 0.0
+    shared_power: true
+    diagonal_loading: false
+    diag_eps_wpe: 1e-4
+    diag_eps_bf: 1e-4
+    mask_flooring: false
+    flooring_thres_wpe: 1e-6
+    flooring_thres_bf: 1e-6
+    use_torch_solver: true
+decoder: stft
+decoder_conf:
+    n_fft: 1024
+    hop_length: 512
+required:
+- output_dir
+version: 0.10.5a1
+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}
+}
+
+
+@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_enh_beamformer_mvdr_raw/8epoch.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22e4b012ae75d134a0f9fb1306106725bd13dd5e0219554f2f6f92f2c051218a
+size 23399166

exp/enh_train_enh_beamformer_mvdr_raw/RESULTS.md

@@ -0,0 +1,19 @@
+<!-- Generated by ./scripts/utils/show_enh_score.sh -->
+# RESULTS
+## Environments
+- date: `Tue Apr 12 20:54:54 UTC 2022`
+- python version: `3.9.7 (default, Sep 16 2021, 13:09:58)  [GCC 7.5.0]`
+- espnet version: `espnet 0.10.5a1`
+- pytorch version: `pytorch 1.10.1`
+- Git hash: `46eaa5eb6bea11cc33927392dca7888921491d8c`
+  - Commit date: `Sat Mar 26 22:35:44 2022 +0100`
+
+
+## ..
+
+config: conf/tuning/train_enh_beamformer_mvdr.yaml
+
+|dataset|STOI|SAR|SDR|SIR|
+|---|---|---|---|---|
+|enhanced_dev|0.96|13.02|13.02|0.00|
+

exp/enh_train_enh_beamformer_mvdr_raw/config.yaml

@@ -0,0 +1,176 @@
+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: 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: 8
+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
+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: 1
+valid_batch_size: null
+batch_bins: 1000000
+valid_batch_bins: null
+train_shape_file:
+- exp/enh_stats_16000/train/speech_mix_shape
+- exp/enh_stats_16000/train/speech_ref1_shape
+- exp/enh_stats_16000/train/noise_ref1_shape
+valid_shape_file:
+- exp/enh_stats_16000/valid/speech_mix_shape
+- exp/enh_stats_16000/valid/speech_ref1_shape
+- exp/enh_stats_16000/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/train/wav.scp
+    - speech_mix
+    - sound
+-   - dump/raw/train/spk1.scp
+    - speech_ref1
+    - sound
+-   - dump/raw/train/noise1.scp
+    - noise_ref1
+    - sound
+valid_data_path_and_name_and_type:
+-   - dump/raw/dev/wav.scp
+    - speech_mix
+    - sound
+-   - dump/raw/dev/spk1.scp
+    - speech_ref1
+    - sound
+-   - dump/raw/dev/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:
+    stft_consistency: false
+    loss_type: mask_mse
+    mask_type: null
+criterions:
+-   name: snr
+    conf:
+        eps: 1e-8
+    wrapper: fixed_order
+    wrapper_conf:
+        weight: 1.0
+use_preprocessor: false
+encoder: stft
+encoder_conf:
+    n_fft: 1024
+    hop_length: 512
+    use_builtin_complex: false
+separator: wpe_beamformer
+separator_conf:
+    num_spk: 1
+    loss_type: spectrum
+    use_wpe: false
+    use_beamformer: true
+    bnet_type: blstmp
+    blayers: 3
+    bunits: 300
+    bprojs: 320
+    badim: 320
+    ref_channel: 0
+    use_noise_mask: true
+    bnonlinear: sigmoid
+    beamformer_type: mvdr_souden
+    rtf_iterations: 2
+    bdropout_rate: 0.0
+    shared_power: true
+    diagonal_loading: false
+    diag_eps_wpe: 1e-4
+    diag_eps_bf: 1e-4
+    mask_flooring: false
+    flooring_thres_wpe: 1e-6
+    flooring_thres_bf: 1e-6
+    use_torch_solver: true
+decoder: stft
+decoder_conf:
+    n_fft: 1024
+    hop_length: 512
+required:
+- output_dir
+version: 0.10.5a1
+distributed: false

meta.yaml

@@ -0,0 +1,8 @@
+espnet: 0.10.5a1
+files:
+  model_file: exp/enh_train_enh_beamformer_mvdr_raw/8epoch.pth
+python: "3.9.7 (default, Sep 16 2021, 13:09:58) \n[GCC 7.5.0]"
+timestamp: 1649796895.876417
+torch: 1.10.1
+yaml_files:
+  train_config: exp/enh_train_enh_beamformer_mvdr_raw/config.yaml