Wangyou Zhang Chime4 Enh Train Enh Conv Tasnet Raw

--- tags: - espnet - audio - audio-to-audio language: datasets: - chime4 license: cc-by-4.0 --- ## ESPnet2 ENH model ### `espnet/Wangyou_Zhang_chime4_enh_train_enh_conv_tasnet_raw` 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 egs2/chime4/enh1 ./run.sh --skip_data_prep false --skip_train true --download_model espnet/Wangyou_Zhang_chime4_enh_train_enh_conv_tasnet_raw ``` ## ENH config <details><summary>expand</summary> ``` config: conf/tuning/train_enh_conv_tasnet.yaml print_config: false log_level: INFO dry_run: false iterator_type: chunk output_dir: exp/enh_train_enh_conv_tasnet_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: 57680 dist_launcher: null multiprocessing_distributed: true cudnn_enabled: true cudnn_benchmark: false cudnn_deterministic: true collect_stats: false write_collected_feats: false max_epoch: 100 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 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: 32000 chunk_shift_ratio: 0.5 num_cache_chunks: 1024 train_data_path_and_name_and_type: - - dump/raw/tr05_simu_isolated_1ch_track/wav.scp - speech_mix - sound - - dump/raw/tr05_simu_isolated_1ch_track/spk1.scp - speech_ref1 - sound valid_data_path_and_name_and_type: - - dump/raw/dt05_simu_isolated_1ch_track...

Source context: 13 downloads · 1 likes · Pipeline audio-to-audio · Library espnet · Repo espnet/Wangyou_Zhang_chime4_enh_train_enh_conv_tasnet_raw