Wangyou Zhang
Add model files
90acba8
config: conf/tuning/train_enh_dc_crn_mapping_snr.yaml
print_config: false
log_level: INFO
dry_run: false
iterator_type: chunk
output_dir: exp/enh_train_enh_dc_crn_mapping_snr_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: 43524
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: 200
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
nbest_averaging_interval: 0
grad_clip: 5
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
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_16k/train/speech_mix_shape
- exp/enh_stats_16k/train/speech_ref1_shape
valid_shape_file:
- exp/enh_stats_16k/valid/speech_mix_shape
- exp/enh_stats_16k/valid/speech_ref1_shape
batch_type: folded
valid_batch_type: null
fold_length:
- 80000
- 80000
sort_in_batch: descending
sort_batch: descending
multiple_iterator: false
chunk_length: 32000
chunk_shift_ratio: 0.5
num_cache_chunks: 1024
train_data_path_and_name_and_type:
- - dump/raw/tr05_simu_isolated_6ch_track/wav.scp
- speech_mix
- sound
- - dump/raw/tr05_simu_isolated_6ch_track/spk1.scp
- speech_ref1
- sound
valid_data_path_and_name_and_type:
- - dump/raw/dt05_simu_isolated_6ch_track/wav.scp
- speech_mix
- sound
- - dump/raw/dt05_simu_isolated_6ch_track/spk1.scp
- speech_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
amsgrad: true
scheduler: steplr
scheduler_conf:
step_size: 2
gamma: 0.98
init: xavier_uniform
model_conf:
stft_consistency: false
loss_type: mask_mse
mask_type: null
criterions:
- name: snr
conf:
eps: 1.0e-07
wrapper: pit
wrapper_conf:
weight: 1.0
use_preprocessor: false
encoder: stft
encoder_conf:
n_fft: 256
hop_length: 128
separator: dc_crn
separator_conf:
num_spk: 1
input_channels:
- 10
- 16
- 32
- 64
- 128
- 256
enc_hid_channels: 8
enc_layers: 5
glstm_groups: 2
glstm_layers: 2
glstm_bidirectional: true
glstm_rearrange: false
mode: mapping
ref_channel: 3
decoder: stft
decoder_conf:
n_fft: 256
hop_length: 128
required:
- output_dir
version: 0.10.7a1
distributed: true