Other Open Access

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

Yen-Ju Lu

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
Files (190.9 MB)
Name Size
enh_train_enh_blstm_tf_raw_valid.loss.best.zip
md5:a09107025a7876d44933a74fd67a556e
190.9 MB Download
155
906
views
downloads
All versions This version
Views 155155
Downloads 906906
Data volume 173.0 GB173.0 GB
Unique views 141141
Unique downloads 121121

Share

Cite as