ESPnet2 pretrained model, neillu23/dns_ins20_enh_train_enh_blstm_tf_raw_valid.loss.best, fs=16k, lang=en

This model was trained by neillu23 using dns_ins20 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 f484fd3a94ac4565af2cea52f59627a4cfe3b16a
  pip install -e .
  cd egs2/dns_ins20/enh1
  ./run.sh --skip_data_prep false --skip_train true --download_model neillu23/dns_ins20_enh_train_enh_blstm_tf_raw_valid.loss.best
  

• Results

  
  # RESULTS
  ## Environments
  - date: `Wed Jun  9 09:49:34 CST 2021`
  - python version: `3.8.10 (default, May 19 2021, 18:05:58)  [GCC 7.3.0]`
  - espnet version: `espnet 0.9.9`
  - pytorch version: `pytorch 1.4.0`
  - Git hash: `c1dfefb98bf59f654e0907b9681668eaca8ddfcc`
    - Commit date: `Tue Jun 8 17:23:26 2021 +0800`
  
  
  ## enh_train_enh_blstm_tf_raw
  
  config: ./conf/tuning/train_enh_blstm_tf.yaml
  
  |dataset|STOI|SAR|SDR|SIR|
  |---|---|---|---|---|
  |enhanced_cv_synthetic|0.98|23.87|23.87|0.00|
  |enhanced_tt_synthetic_no_reverb|0.96|15.94|15.94|0.00|
  |enhanced_tt_synthetic_with_reverb|0.84|11.86|11.86|0.00|

• Enhancement config

  config: ./conf/tuning/train_enh_blstm_tf.yaml
  print_config: false
  log_level: INFO
  dry_run: false
  iterator_type: sequence
  output_dir: exp/enh_train_enh_blstm_tf_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: 45398
  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: 100
  patience: 10
  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
  use_tensorboard: true
  use_wandb: false
  wandb_project: null
  wandb_id: null
  detect_anomaly: false
  pretrain_path: null
  init_param: []
  ignore_init_mismatch: false
  freeze_param: []
  num_iters_per_epoch: null
  batch_size: 64
  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/noise_ref1_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/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/tr_synthetic/wav.scp
      - speech_mix
      - sound
  -   - dump/raw/tr_synthetic/spk1.scp
      - speech_ref1
      - sound
  -   - dump/raw/tr_synthetic/noise1.scp
      - noise_ref1
      - sound
  valid_data_path_and_name_and_type:
  -   - dump/raw/cv_synthetic/wav.scp
      - speech_mix
      - sound
  -   - dump/raw/cv_synthetic/spk1.scp
      - speech_ref1
      - sound
  -   - dump/raw/cv_synthetic/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: 1.0e-07
  scheduler: reducelronplateau
  scheduler_conf:
      mode: min
      factor: 0.7
      patience: 1
  init: xavier_uniform
  model_conf:
      loss_type: mask_mse
      mask_type: psm
  use_preprocessor: false
  encoder: stft
  encoder_conf:
      n_fft: 256
      hop_length: 128
  separator: rnn
  separator_conf:
      rnn_type: blstm
      num_spk: 1
      nonlinear: relu
      layer: 3
      unit: 896
      dropout: 0.5
  decoder: stft
  decoder_conf:
      n_fft: 256
      hop_length: 128
  required:
  - output_dir
  version: 0.9.9
  distributed: true