Other Open Access

ESPnet2 pretrained model, Chenda Li/wsj0_2mix_enh_train_enh_rnn_tf_raw_valid.si_snr.ave, fs=8k, lang=en

Chenda Li

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_rnn_tf_raw_valid.si_snr.ave
    
  • Results
    
    # RESULTS
    ## Environments
    - date: `Thu Feb  4 01:08:19 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_rnn_tf_raw
    
    config: conf/tuning/train_enh_rnn_tf.yaml
    
    |dataset|STOI|SAR|SDR|SIR|
    |---|---|---|---|---|
    |enhanced_cv_min_8k|0.891065|11.556|10.3982|18.0655|
    |enhanced_tt_min_8k|0.896373|11.4086|10.2433|18.0496|
  • ASR config
    config: conf/tuning/train_enh_rnn_tf.yaml
    print_config: false
    log_level: INFO
    dry_run: false
    iterator_type: sequence
    output_dir: exp/enh_train_enh_rnn_tf_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: 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
    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: 500
    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: 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: 2
        nonlinear: relu
        layer: 3
        unit: 896
        dropout: 0.5
    decoder: stft
    decoder_conf:
        n_fft: 256
        hop_length: 128
    required:
    - output_dir
    version: 0.9.7
    distributed: false
Files (191.4 MB)
Name Size
enh_train_enh_rnn_tf_raw_valid.si_snr.ave.zip
md5:a9a0e1641631890c70dc0cce1e647fac
191.4 MB Download
336
113
views
downloads
All versions This version
Views 336336
Downloads 113113
Data volume 21.6 GB21.6 GB
Unique views 322322
Unique downloads 7575

Share

Cite as