配置: conf/tuning/train_enh_skim_causal_small.yaml
print_config: false
log_level: INFO
dry_run: false
iterator_type: chunk
output_dir: exp/enh_train_enh_skim_causal_small_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
unused_parameters: false
sharded_ddp: false
cudnn_enabled: true
cudnn_benchmark: false
cudnn_deterministic: true
collect_stats: false
write_collected_feats: false
max_epoch: 150
patience: 50
val_scheduler_criterion:
- valid
- loss
early_stopping_criterion:
- valid
- loss
- min
best_model_criterion:
-   - valid
    - si_snr_loss
    - min
-   - valid
    - loss
    - min
keep_nbest_models: 1
nbest_averaging_interval: 0
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_matplotlib: true
use_tensorboard: true
create_graph_in_tensorboard: false
use_wandb: false
wandb_project: null
wandb_id: null
wandb_entity: null
wandb_name: null
wandb_model_log_interval: -1
detect_anomaly: false
pretrain_path: null
init_param: []
ignore_init_mismatch: false
freeze_param: []
num_iters_per_epoch: null
batch_size: 16
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: 32000,16000,8000
chunk_shift_ratio: 0.5
num_cache_chunks: 1024
chunk_excluded_key_prefixes: []
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
exclude_weight_decay: false
exclude_weight_decay_conf: {}
optim: adam
optim_conf:
    lr: 0.001
    eps: 1.0e-08
    weight_decay: 0
scheduler: steplr
scheduler_conf:
    step_size: 2
    gamma: 0.97
init: xavier_uniform
model_conf:
    stft_consistency: false
    loss_type: mask_mse
    mask_type: null
criterions:
-   name: si_snr
    conf: {}
    wrapper: pit
    wrapper_conf:
        weight: 1.0
        independent_perm: true
speech_volume_normalize: null
rir_scp: null
rir_apply_prob: 1.0
noise_scp: null
noise_apply_prob: 1.0
noise_db_range: '13_15'
short_noise_thres: 0.5
use_reverberant_ref: false
num_spk: 1
num_noise_type: 1
sample_rate: 8000
force_single_channel: false
dynamic_mixing: false
utt2spk: null
dynamic_mixing_gain_db: 0.0
encoder: conv
encoder_conf:
    channel: 128
    kernel_size: 8
    stride: 4
separator: skim
separator_conf:
    causal: true
    num_spk: 2
    layer: 3
    nonlinear: relu
    unit: 384
    segment_size: 50
    dropout: 0.0
    mem_type: hc
    seg_overlap: false
decoder: conv
decoder_conf:
    channel: 128
    kernel_size: 8
    stride: 4
mask_module: multi_mask
mask_module_conf: {}
preprocessor: null
preprocessor_conf: {}
required:
- output_dir
version: '202304'
distributed: false