Initial commit

README.md

@@ -1,3 +1,317 @@
 ---
+tags:
+- audio
+- audio-to-audio
+language: en
+datasets:
+- urgent24
 license: cc-by-4.0
+library_name: espnet
 ---
+
+## ESPnet2 ENH model
+
+### `wyz/tfgridnet_for_urgent24`
+
+This model was trained by Wangyou Zhang using the wsj0_2mix recipe in [espnet](https://github.com/espnet/espnet/).
+
+### 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
+
+pip install -e .
+cd egs2/urgent24/enh1
+./run.sh --skip_data_prep false --skip_train true --is_tse_task true --download_model wyz/tfgridnet_for_urgent24
+```
+
+## ENH config
+
+<details><summary>expand</summary>
+
+```
+config: conf/tuning/train_enh_tfgridnet.yaml
+print_config: false
+log_level: INFO
+drop_last_iter: false
+dry_run: false
+iterator_type: chunk
+valid_iterator_type: null
+output_dir: exp/enh_train_enh_tfgridnet_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: 54825
+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: 40
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - loss
+    - min
+keep_nbest_models: 1
+nbest_averaging_interval: 0
+grad_clip: 1.0
+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
+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
+use_adapter: false
+adapter: lora
+save_strategy: all
+adapter_conf: {}
+pretrain_path: null
+init_param: []
+ignore_init_mismatch: false
+freeze_param: []
+num_iters_per_epoch: 8000
+batch_size: 4
+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
+shuffle_within_batch: false
+sort_batch: descending
+multiple_iterator: false
+chunk_length: 200
+chunk_shift_ratio: 0.5
+num_cache_chunks: 1024
+chunk_excluded_key_prefixes: []
+chunk_default_fs: 50
+chunk_max_abs_length: 100000
+chunk_discard_short_samples: true
+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/utt2category
+    - category
+    - text
+-   - dump/raw/train/utt2fs
+    - fs
+    - text_int
+valid_data_path_and_name_and_type:
+-   - dump/raw/validation/wav.scp
+    - speech_mix
+    - sound
+-   - dump/raw/validation/spk1.scp
+    - speech_ref1
+    - sound
+-   - dump/raw/validation/utt2category
+    - category
+    - text
+-   - dump/raw/validation/utt2fs
+    - fs
+    - text_int
+allow_variable_data_keys: false
+max_cache_size: 0.0
+max_cache_fd: 32
+allow_multi_rates: true
+valid_max_cache_size: null
+exclude_weight_decay: false
+exclude_weight_decay_conf: {}
+optim: adam
+optim_conf:
+    lr: 0.001
+    eps: 1.0e-08
+    weight_decay: 1.0e-05
+scheduler: steplr
+scheduler_conf:
+    step_size: 2
+    gamma: 0.99
+init: null
+model_conf:
+    normalize_variance_per_ch: true
+    categories:
+    - 1ch_8000Hz
+    - 1ch_16000Hz
+    - 1ch_22050Hz
+    - 1ch_24000Hz
+    - 1ch_32000Hz
+    - 1ch_44100Hz
+    - 1ch_48000Hz
+criterions:
+-   name: mr_l1_tfd
+    conf:
+        window_sz:
+        - 256
+        - 512
+        - 768
+        - 1024
+        hop_sz: null
+        eps: 1.0e-08
+        time_domain_weight: 0.5
+        normalize_variance: true
+    wrapper: fixed_order
+    wrapper_conf:
+        weight: 1.0
+-   name: si_snr
+    conf:
+        eps: 1.0e-07
+    wrapper: fixed_order
+    wrapper_conf:
+        weight: 0.0
+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: true
+channel_reordering: true
+categories:
+- 1ch_8000Hz
+- 1ch_16000Hz
+- 1ch_22050Hz
+- 1ch_24000Hz
+- 1ch_32000Hz
+- 1ch_44100Hz
+- 1ch_48000Hz
+speech_segment: null
+avoid_allzero_segment: true
+flexible_numspk: false
+dynamic_mixing: false
+utt2spk: null
+dynamic_mixing_gain_db: 0.0
+encoder: stft
+encoder_conf:
+    n_fft: 256
+    hop_length: 128
+    use_builtin_complex: true
+    default_fs: 8000
+separator: tfgridnetv3
+separator_conf:
+    n_srcs: 1
+    n_imics: 1
+    n_layers: 6
+    lstm_hidden_units: 200
+    attn_n_head: 4
+    attn_qk_output_channel: 2
+    emb_dim: 48
+    emb_ks: 4
+    emb_hs: 1
+    activation: prelu
+    eps: 1.0e-05
+decoder: stft
+decoder_conf:
+    n_fft: 256
+    hop_length: 128
+    default_fs: 8000
+mask_module: multi_mask
+mask_module_conf: {}
+preprocessor: enh
+preprocessor_conf: {}
+diffusion_model: null
+diffusion_model_conf: {}
+required:
+- output_dir
+version: '202402'
+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_enh_tfgridnet_raw/21epoch.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be416f78659998e8196fd6565adb50b35e2645cea23d15d28c081fda40504751
+size 34175373

exp/enh_train_enh_tfgridnet_raw/RESULTS.md

@@ -0,0 +1 @@
+This model was trained on simulated data (based on DNS5 Engligh speech, CommonVoice 11.0 English portion, LibriTTS, VCTK, and WSJ) for 21 epochs.

exp/enh_train_enh_tfgridnet_raw/config.yaml

@@ -0,0 +1,232 @@
+config: conf/tuning/train_enh_tfgridnet.yaml
+print_config: false
+log_level: INFO
+drop_last_iter: false
+dry_run: false
+iterator_type: chunk
+valid_iterator_type: null
+output_dir: exp/enh_train_enh_tfgridnet_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: 54825
+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: 40
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - loss
+    - min
+keep_nbest_models: 1
+nbest_averaging_interval: 0
+grad_clip: 1.0
+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
+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
+use_adapter: false
+adapter: lora
+save_strategy: all
+adapter_conf: {}
+pretrain_path: null
+init_param: []
+ignore_init_mismatch: false
+freeze_param: []
+num_iters_per_epoch: 8000
+batch_size: 4
+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
+shuffle_within_batch: false
+sort_batch: descending
+multiple_iterator: false
+chunk_length: 200
+chunk_shift_ratio: 0.5
+num_cache_chunks: 1024
+chunk_excluded_key_prefixes: []
+chunk_default_fs: 50
+chunk_max_abs_length: 100000
+chunk_discard_short_samples: true
+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/utt2category
+    - category
+    - text
+-   - dump/raw/train/utt2fs
+    - fs
+    - text_int
+valid_data_path_and_name_and_type:
+-   - dump/raw/validation/wav.scp
+    - speech_mix
+    - sound
+-   - dump/raw/validation/spk1.scp
+    - speech_ref1
+    - sound
+-   - dump/raw/validation/utt2category
+    - category
+    - text
+-   - dump/raw/validation/utt2fs
+    - fs
+    - text_int
+allow_variable_data_keys: false
+max_cache_size: 0.0
+max_cache_fd: 32
+allow_multi_rates: true
+valid_max_cache_size: null
+exclude_weight_decay: false
+exclude_weight_decay_conf: {}
+optim: adam
+optim_conf:
+    lr: 0.001
+    eps: 1.0e-08
+    weight_decay: 1.0e-05
+scheduler: steplr
+scheduler_conf:
+    step_size: 2
+    gamma: 0.99
+init: null
+model_conf:
+    normalize_variance_per_ch: true
+    categories:
+    - 1ch_8000Hz
+    - 1ch_16000Hz
+    - 1ch_22050Hz
+    - 1ch_24000Hz
+    - 1ch_32000Hz
+    - 1ch_44100Hz
+    - 1ch_48000Hz
+criterions:
+-   name: mr_l1_tfd
+    conf:
+        window_sz:
+        - 256
+        - 512
+        - 768
+        - 1024
+        hop_sz: null
+        eps: 1.0e-08
+        time_domain_weight: 0.5
+        normalize_variance: true
+    wrapper: fixed_order
+    wrapper_conf:
+        weight: 1.0
+-   name: si_snr
+    conf:
+        eps: 1.0e-07
+    wrapper: fixed_order
+    wrapper_conf:
+        weight: 0.0
+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: true
+channel_reordering: true
+categories:
+- 1ch_8000Hz
+- 1ch_16000Hz
+- 1ch_22050Hz
+- 1ch_24000Hz
+- 1ch_32000Hz
+- 1ch_44100Hz
+- 1ch_48000Hz
+speech_segment: null
+avoid_allzero_segment: true
+flexible_numspk: false
+dynamic_mixing: false
+utt2spk: null
+dynamic_mixing_gain_db: 0.0
+encoder: stft
+encoder_conf:
+    n_fft: 256
+    hop_length: 128
+    use_builtin_complex: true
+    default_fs: 8000
+separator: tfgridnetv3
+separator_conf:
+    n_srcs: 1
+    n_imics: 1
+    n_layers: 6
+    lstm_hidden_units: 200
+    attn_n_head: 4
+    attn_qk_output_channel: 2
+    emb_dim: 48
+    emb_ks: 4
+    emb_hs: 1
+    activation: prelu
+    eps: 1.0e-05
+decoder: stft
+decoder_conf:
+    n_fft: 256
+    hop_length: 128
+    default_fs: 8000
+mask_module: multi_mask
+mask_module_conf: {}
+preprocessor: enh
+preprocessor_conf: {}
+diffusion_model: null
+diffusion_model_conf: {}
+required:
+- output_dir
+version: '202402'
+distributed: true

exp/enh_train_enh_tfgridnet_raw/valid.loss.best.pth

@@ -0,0 +1 @@
+21epoch.pth

meta.yaml

@@ -0,0 +1,8 @@
+espnet: '202402'
+files:
+  model_file: exp/enh_train_enh_tfgridnet_raw/21epoch.pth
+python: "3.8.19 (default, Mar 20 2024, 19:58:24) \n[GCC 11.2.0]"
+timestamp: 1719552816.976782
+torch: 2.0.1
+yaml_files:
+  train_config: exp/enh_train_enh_tfgridnet_raw/config.yaml