|
config: conf/tuning/train_enh_uses_refch0_2mem.yaml |
|
print_config: false |
|
log_level: INFO |
|
dry_run: false |
|
iterator_type: chunk |
|
output_dir: exp/enh_train_enh_uses_refch0_2mem_raw |
|
ngpu: 1 |
|
seed: 0 |
|
num_workers: 4 |
|
num_att_plot: 3 |
|
dist_backend: nccl |
|
dist_init_method: env:// |
|
dist_world_size: 4 |
|
dist_rank: 0 |
|
local_rank: 0 |
|
dist_master_addr: localhost |
|
dist_master_port: 33702 |
|
dist_launcher: null |
|
multiprocessing_distributed: true |
|
unused_parameters: true |
|
sharded_ddp: false |
|
cudnn_enabled: true |
|
cudnn_benchmark: false |
|
cudnn_deterministic: true |
|
collect_stats: false |
|
write_collected_feats: false |
|
skip_stats_npz: false |
|
max_epoch: 150 |
|
patience: 20 |
|
val_scheduler_criterion: |
|
- valid |
|
- loss |
|
early_stopping_criterion: |
|
- valid |
|
- loss |
|
- min |
|
best_model_criterion: |
|
- - 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: 8000 |
|
batch_size: 4 |
|
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/dereverb_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/dereverb_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: 32000 |
|
chunk_shift_ratio: 0.5 |
|
num_cache_chunks: 1024 |
|
chunk_excluded_key_prefixes: [] |
|
chunk_discard_short_samples: false |
|
train_data_path_and_name_and_type: |
|
- - dump/raw/train_dns20_vctk_whamr_chime4_reverb/wav.scp |
|
- speech_mix |
|
- sound |
|
- - dump/raw/train_dns20_vctk_whamr_chime4_reverb/spk1.scp |
|
- speech_ref1 |
|
- sound |
|
- - dump/raw/train_dns20_vctk_whamr_chime4_reverb/dereverb1.scp |
|
- dereverb_ref1 |
|
- sound |
|
- - dump/raw/train_dns20_vctk_whamr_chime4_reverb/utt2category |
|
- category |
|
- text |
|
- - dump/raw/train_dns20_vctk_whamr_chime4_reverb/utt2fs |
|
- fs |
|
- text_int |
|
valid_data_path_and_name_and_type: |
|
- - dump/raw/valid_dns20_vctk_whamr_chime4/wav.scp |
|
- speech_mix |
|
- sound |
|
- - dump/raw/valid_dns20_vctk_whamr_chime4/spk1.scp |
|
- speech_ref1 |
|
- sound |
|
- - dump/raw/valid_dns20_vctk_whamr_chime4/dereverb1.scp |
|
- dereverb_ref1 |
|
- sound |
|
- - dump/raw/valid_dns20_vctk_whamr_chime4/utt2category |
|
- category |
|
- text |
|
- - dump/raw/valid_dns20_vctk_whamr_chime4/utt2fs |
|
- fs |
|
- text_int |
|
allow_variable_data_keys: false |
|
max_cache_size: 0.0 |
|
max_cache_fd: 32 |
|
allow_multi_rates: true |
|
valid_max_cache_size: null |
|
exclude_weight_decay: false |
|
exclude_weight_decay_conf: {} |
|
optim: adam |
|
optim_conf: |
|
lr: 0.0004 |
|
eps: 1.0e-08 |
|
weight_decay: 1.0e-05 |
|
scheduler: warmupreducelronplateau |
|
scheduler_conf: |
|
warmup_steps: 25000 |
|
mode: min |
|
factor: 0.5 |
|
patience: 2 |
|
init: null |
|
model_conf: |
|
normalize_variance: true |
|
categories: |
|
- 1ch_48k |
|
- 1ch_16k |
|
- 1ch_16k_r |
|
- 2ch_16k |
|
- 2ch_16k_r |
|
- 5ch_16k |
|
- 8ch_16k_r |
|
criterions: |
|
- name: mr_l1_tfd |
|
conf: |
|
window_sz: |
|
- 256 |
|
- 512 |
|
- 768 |
|
- 1024 |
|
hop_sz: null |
|
eps: 1.0e-08 |
|
time_domain_weight: 0.5 |
|
normalize_variance: true |
|
wrapper: fixed_order |
|
wrapper_conf: |
|
weight: 1.0 |
|
- name: si_snr |
|
conf: |
|
eps: 1.0e-07 |
|
wrapper: fixed_order |
|
wrapper_conf: |
|
weight: 0.0 |
|
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 |
|
channel_reordering: true |
|
categories: |
|
- 1ch_48k |
|
- 1ch_16k |
|
- 1ch_16k_r |
|
- 2ch_16k |
|
- 2ch_16k_r |
|
- 5ch_16k |
|
- 8ch_16k_r |
|
dynamic_mixing: false |
|
utt2spk: null |
|
dynamic_mixing_gain_db: 0.0 |
|
encoder: stft |
|
encoder_conf: |
|
n_fft: 256 |
|
hop_length: 128 |
|
use_builtin_complex: false |
|
separator: uses |
|
separator_conf: |
|
num_spk: 1 |
|
enc_channels: 256 |
|
bottleneck_size: 64 |
|
num_blocks: 6 |
|
num_spatial_blocks: 3 |
|
segment_size: 64 |
|
memory_size: 20 |
|
memory_types: 2 |
|
rnn_type: lstm |
|
bidirectional: true |
|
hidden_size: 128 |
|
att_heads: 4 |
|
dropout: 0.0 |
|
norm_type: cLN |
|
activation: relu |
|
ch_mode: tac |
|
ch_att_dim: 256 |
|
eps: 1.0e-05 |
|
ref_channel: 0 |
|
decoder: stft |
|
decoder_conf: |
|
n_fft: 256 |
|
hop_length: 128 |
|
mask_module: multi_mask |
|
mask_module_conf: {} |
|
preprocessor: enh |
|
preprocessor_conf: {} |
|
required: |
|
- output_dir |
|
version: '202301' |
|
distributed: true |
|
|