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