ESPnet2 pretrained model, Chenda Li/wsj0_2mix_enh_train_enh_conv_tasnet_raw_valid.si_snr.ave, fs=8k, lang=en

This model was trained by Chenda Li using wsj0_2mix recipe in espnet.

• Python API

  See https://github.com/espnet/espnet_model_zoo

• Evaluate in the recipe

  git clone https://github.com/espnet/espnet
  cd espnet
  git checkout a3334220b0352931677946d178fade3313cf82bb
  pip install -e .
  cd egs2/wsj0_2mix/enh1
  ./run.sh --skip_data_prep false --skip_train true --download_model Chenda Li/wsj0_2mix_enh_train_enh_conv_tasnet_raw_valid.si_snr.ave
  

• Results

  
  # RESULTS
  ## Environments
  - date: `Thu Feb  4 01:16:18 CST 2021`
  - python version: `3.7.6 (default, Jan  8 2020, 19:59:22)  [GCC 7.3.0]`
  - espnet version: `espnet 0.9.7`
  - pytorch version: `pytorch 1.5.0`
  - Git hash: `a3334220b0352931677946d178fade3313cf82bb`
    - Commit date: `Fri Jan 29 23:35:47 2021 +0800`
  
  
  ## enh_train_enh_conv_tasnet_raw
  
  config: ./conf/tuning/train_enh_conv_tasnet.yaml
  
  |dataset|STOI|SAR|SDR|SIR|
  |---|---|---|---|---|
  |enhanced_cv_min_8k|0.949205|17.3785|16.8028|26.9785|
  |enhanced_tt_min_8k|0.95349|16.6221|15.9494|25.9032|

• ASR config

  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: null
  dist_rank: null
  local_rank: 0
  dist_master_addr: null
  dist_master_port: null
  dist_launcher: null
  multiprocessing_distributed: false
  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_8k/train/speech_mix_shape
  - exp/enh_stats_8k/train/speech_ref1_shape
  - exp/enh_stats_8k/train/speech_ref2_shape
  valid_shape_file:
  - exp/enh_stats_8k/valid/speech_mix_shape
  - exp/enh_stats_8k/valid/speech_ref1_shape
  - exp/enh_stats_8k/valid/speech_ref2_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: 32000
  chunk_shift_ratio: 0.5
  num_cache_chunks: 1024
  train_data_path_and_name_and_type:
  -   - dump/raw/tr_min_8k/wav.scp
      - speech_mix
      - sound
  -   - dump/raw/tr_min_8k/spk1.scp
      - speech_ref1
      - sound
  -   - dump/raw/tr_min_8k/spk2.scp
      - speech_ref2
      - sound
  valid_data_path_and_name_and_type:
  -   - dump/raw/cv_min_8k/wav.scp
      - speech_mix
      - sound
  -   - dump/raw/cv_min_8k/spk1.scp
      - speech_ref1
      - sound
  -   - dump/raw/cv_min_8k/spk2.scp
      - speech_ref2
      - 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: si_snr
  use_preprocessor: false
  encoder: conv
  encoder_conf:
      channel: 256
      kernel_size: 20
      stride: 10
  separator: tcn
  separator_conf:
      num_spk: 2
      layer: 8
      stack: 4
      bottleneck_dim: 256
      hidden_dim: 512
      kernel: 3
      causal: false
      norm_type: gLN
      nonlinear: relu
  decoder: conv
  decoder_conf:
      channel: 256
      kernel_size: 20
      stride: 10
  required:
  - output_dir
  version: 0.9.7
  distributed: false