| | --- |
| | tags: |
| | - espnet |
| | - audio |
| | - audio-to-audio |
| | language: en |
| | datasets: |
| | - wsj_kinect |
| | license: cc-by-4.0 |
| | --- |
| | |
| | ## ESPnet2 ENH model |
| |
|
| | ### `atharva253/tfgridnetv2_wsj_kinect` |
| |
|
| | This model was trained by Atharva Anand Joshi using wsj_kinect 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 |
| | git checkout 37828ea9708cd2f541220fdfe180457c7f7d67f1 |
| | pip install -e . |
| | cd egs2/wsj_kinect/enh1 |
| | ./run.sh --skip_data_prep false --skip_train true --download_model atharva253/tfgridnetv2_wsj_kinect |
| | ``` |
| | |
| | <!-- Generated by ./scripts/utils/show_enh_score.sh --> |
| | # RESULTS |
| | ## Environments |
| | - date: `Mon Apr 22 17:21:05 EDT 2024` |
| | - python version: `3.9.18 (main, Sep 11 2023, 13:41:44) [GCC 11.2.0]` |
| | - espnet version: `espnet 202402` |
| | - pytorch version: `pytorch 2.1.0` |
| | - Git hash: `37828ea9708cd2f541220fdfe180457c7f7d67f1` |
| | - Commit date: `Thu Mar 21 22:52:57 2024 -0400` |
| | |
| | |
| | ## enh_train_enh_tfgridnetv2_tf_lr-patience3_patience5_I_1_J_1_D_128_batch_8_raw |
| | |
| | config: conf/tuning/train_enh_tfgridnetv2_tf_lr-patience3_patience5_I_1_J_1_D_128_batch_8.yaml |
| | |
| | |dataset|STOI|SAR|SDR|SIR|SI_SNR| |
| | |---|---|---|---|---|---| |
| | |enhanced_cv|85.97|10.51|10.07|21.63|9.61| |
| | |enhanced_tt|88.76|11.22|10.69|21.36|10.26| |
| | |
| | ## ENH config |
| | |
| | <details><summary>expand</summary> |
| | |
| | ``` |
| | config: conf/tuning/train_enh_tfgridnetv2_tf_lr-patience3_patience5_I_1_J_1_D_128_batch_8.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_tfgridnetv2_tf_lr-patience3_patience5_I_1_J_1_D_128_batch_8_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: 45443 |
| | 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: 150 |
| | patience: 5 |
| | 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 |
| | 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: 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/speech_ref2_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/speech_ref2_shape |
| | batch_type: folded |
| | valid_batch_type: null |
| | fold_length: |
| | - 80000 |
| | - 80000 |
| | - 80000 |
| | sort_in_batch: descending |
| | shuffle_within_batch: false |
| | sort_batch: descending |
| | multiple_iterator: false |
| | chunk_length: 32000 |
| | chunk_shift_ratio: 0.5 |
| | num_cache_chunks: 1024 |
| | chunk_excluded_key_prefixes: [] |
| | chunk_default_fs: null |
| | train_data_path_and_name_and_type: |
| | - - dump/raw/tr/wav.scp |
| | - speech_mix |
| | - sound |
| | - - dump/raw/tr/spk1.scp |
| | - speech_ref1 |
| | - sound |
| | - - dump/raw/tr/spk2.scp |
| | - speech_ref2 |
| | - sound |
| | valid_data_path_and_name_and_type: |
| | - - dump/raw/cv/wav.scp |
| | - speech_mix |
| | - sound |
| | - - dump/raw/cv/spk1.scp |
| | - speech_ref1 |
| | - sound |
| | - - dump/raw/cv/spk2.scp |
| | - speech_ref2 |
| | - sound |
| | allow_variable_data_keys: false |
| | max_cache_size: 0.0 |
| | max_cache_fd: 32 |
| | allow_multi_rates: false |
| | 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: 0 |
| | scheduler: reducelronplateau |
| | scheduler_conf: |
| | mode: min |
| | factor: 0.5 |
| | patience: 3 |
| | init: xavier_uniform |
| | model_conf: |
| | stft_consistency: false |
| | loss_type: mask_mse |
| | mask_type: null |
| | flexible_numspk: false |
| | extract_feats_in_collect_stats: false |
| | normalize_variance: false |
| | normalize_variance_per_ch: false |
| | categories: [] |
| | category_weights: [] |
| | criterions: |
| | - name: si_snr |
| | conf: |
| | eps: 1.0e-07 |
| | wrapper: pit |
| | wrapper_conf: |
| | weight: 1.0 |
| | independent_perm: true |
| | 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 |
| | channel_reordering: false |
| | categories: [] |
| | speech_segment: null |
| | avoid_allzero_segment: true |
| | flexible_numspk: false |
| | dynamic_mixing: false |
| | utt2spk: null |
| | dynamic_mixing_gain_db: 0.0 |
| | encoder: same |
| | encoder_conf: {} |
| | separator: tfgridnetv2 |
| | separator_conf: |
| | n_srcs: 2 |
| | n_fft: 128 |
| | stride: 64 |
| | window: hann |
| | n_imics: 4 |
| | n_layers: 6 |
| | lstm_hidden_units: 192 |
| | attn_n_head: 4 |
| | attn_approx_qk_dim: 512 |
| | emb_dim: 128 |
| | emb_ks: 1 |
| | emb_hs: 1 |
| | activation: prelu |
| | eps: 1.0e-05 |
| | decoder: same |
| | decoder_conf: {} |
| | mask_module: multi_mask |
| | mask_module_conf: {} |
| | preprocessor: null |
| | 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} |
| | } |
| | ``` |
| |
|
