File size: 4,865 Bytes
db03c34 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 |
config: ./conf/train.yaml
print_config: false
log_level: INFO
dry_run: false
iterator_type: chunk
output_dir: exp/enh_train_raw
ngpu: 1
seed: 0
num_workers: 2
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: 43837
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: 100
patience: 20
val_scheduler_criterion:
- valid
- loss
early_stopping_criterion:
- valid
- loss
- min
best_model_criterion:
- - valid
- snr
- max
- - 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_train_dev_16k/train/speech_mix_shape
- exp/enh_stats_train_dev_16k/train/speech_ref1_shape
- exp/enh_stats_train_dev_16k/train/enroll_ref1_shape
- exp/enh_stats_train_dev_16k/train/speech_ref2_shape
- exp/enh_stats_train_dev_16k/train/enroll_ref2_shape
valid_shape_file:
- exp/enh_stats_train_dev_16k/valid/speech_mix_shape
- exp/enh_stats_train_dev_16k/valid/speech_ref1_shape
- exp/enh_stats_train_dev_16k/valid/enroll_ref1_shape
- exp/enh_stats_train_dev_16k/valid/speech_ref2_shape
- exp/enh_stats_train_dev_16k/valid/enroll_ref2_shape
batch_type: folded
valid_batch_type: null
fold_length:
- 80000
- 80000
- 80000
- 80000
- 80000
sort_in_batch: descending
sort_batch: descending
multiple_iterator: false
chunk_length: 48000
chunk_shift_ratio: 0.5
num_cache_chunks: 1024
chunk_excluded_key_prefixes:
- enroll_ref
train_data_path_and_name_and_type:
- - dump/raw/train/wav.scp
- speech_mix
- sound
- - dump/raw/train/spk1.scp
- speech_ref1
- sound
- - dump/raw/train/enroll_spk1.scp
- enroll_ref1
- text
- - dump/raw/train/spk2.scp
- speech_ref2
- sound
- - dump/raw/train/enroll_spk2.scp
- enroll_ref2
- text
valid_data_path_and_name_and_type:
- - dump/raw/dev/wav.scp
- speech_mix
- sound
- - dump/raw/dev/spk1.scp
- speech_ref1
- sound
- - dump/raw/dev/enroll_spk1.scp
- enroll_ref1
- text
- - dump/raw/dev/spk2.scp
- speech_ref2
- sound
- - dump/raw/dev/enroll_spk2.scp
- enroll_ref2
- text
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: reducelronplateau
scheduler_conf:
mode: min
factor: 0.7
patience: 3
init: null
model_conf:
num_spk: 2
share_encoder: true
criterions:
- name: snr
conf:
eps: 1.0e-07
wrapper: fixed_order
wrapper_conf:
weight: 1.0
- name: l1_fd
conf:
only_for_test: true
wrapper: fixed_order
wrapper_conf:
weight: 0.0
- name: l1_td
conf:
only_for_test: true
wrapper: fixed_order
wrapper_conf:
weight: 0.0
- name: mse_fd
conf:
only_for_test: true
wrapper: fixed_order
wrapper_conf:
weight: 0.0
- name: mse_td
conf:
only_for_test: true
wrapper: fixed_order
wrapper_conf:
weight: 0.0
train_spk2enroll: data/train-100/spk2enroll.json
enroll_segment: 48000
load_spk_embedding: false
load_all_speakers: false
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
speech_volume_normalize: null
use_reverberant_ref: false
num_spk: 1
num_noise_type: 1
sample_rate: 8000
force_single_channel: false
channel_reordering: false
categories: []
encoder: conv
encoder_conf:
channel: 256
kernel_size: 32
stride: 16
extractor: td_speakerbeam
extractor_conf:
layer: 8
stack: 4
bottleneck_dim: 256
hidden_dim: 512
skip_dim: 256
kernel: 3
causal: false
norm_type: gLN
pre_nonlinear: prelu
nonlinear: relu
i_adapt_layer: 7
adapt_layer_type: mul
adapt_enroll_dim: 256
use_spk_emb: false
decoder: conv
decoder_conf:
channel: 256
kernel_size: 32
stride: 16
preprocessor: tse
preprocessor_conf: {}
required:
- output_dir
version: '202301'
distributed: true
|