File size: 8,066 Bytes
907c0f4 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 |
config: conf/tuning/train_full_band_vits.yaml
print_config: false
log_level: INFO
dry_run: false
iterator_type: sequence
output_dir: exp/44k/tts_train_full_band_vits_raw_phn_tacotron_g2p_en
ngpu: 1
seed: 777
num_workers: 4
num_att_plot: 3
dist_backend: nccl
dist_init_method: env://
dist_world_size: 3
dist_rank: 0
local_rank: 0
dist_master_addr: localhost
dist_master_port: 59741
dist_launcher: null
multiprocessing_distributed: true
unused_parameters: true
sharded_ddp: false
cudnn_enabled: true
cudnn_benchmark: false
cudnn_deterministic: false
collect_stats: false
write_collected_feats: false
max_epoch: 100
patience: null
val_scheduler_criterion:
- valid
- loss
early_stopping_criterion:
- valid
- loss
- min
best_model_criterion:
- - train
- total_count
- max
keep_nbest_models: 10
nbest_averaging_interval: 0
grad_clip: -1
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: 50
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: 1000
batch_size: 20
valid_batch_size: null
batch_bins: 10000000
valid_batch_bins: null
train_shape_file:
- exp/44k/tts_stats_raw_linear_spectrogram_phn_tacotron_g2p_en/train/text_shape.phn
- exp/44k/tts_stats_raw_linear_spectrogram_phn_tacotron_g2p_en/train/speech_shape
valid_shape_file:
- exp/44k/tts_stats_raw_linear_spectrogram_phn_tacotron_g2p_en/valid/text_shape.phn
- exp/44k/tts_stats_raw_linear_spectrogram_phn_tacotron_g2p_en/valid/speech_shape
batch_type: numel
valid_batch_type: null
fold_length:
- 150
- 409600
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/44k/raw/train/text
- text
- text
- - dump/44k/raw/train/wav.scp
- speech
- sound
valid_data_path_and_name_and_type:
- - dump/44k/raw/valid/text
- text
- text
- - dump/44k/raw/valid/wav.scp
- speech
- sound
allow_variable_data_keys: false
max_cache_size: 0.0
max_cache_fd: 32
valid_max_cache_size: null
optim: adamw
optim_conf:
lr: 0.0002
betas:
- 0.8
- 0.99
eps: 1.0e-09
weight_decay: 0.0
scheduler: exponentiallr
scheduler_conf:
gamma: 0.999875
optim2: adamw
optim2_conf:
lr: 0.0002
betas:
- 0.8
- 0.99
eps: 1.0e-09
weight_decay: 0.0
scheduler2: exponentiallr
scheduler2_conf:
gamma: 0.999875
generator_first: false
token_list:
- <blank>
- <unk>
- ''
- AA1
- AH0
- N
- K
- OW0
- M
- B
- IY0
- L
- T
- Y
- S
- OW1
- IY1
- G
- P
- IH0
- EY1
- Z
- NG
- AA0
- EH1
- UW1
- D
- AE1
- OY1
- AE2
- OW2
- AY1
- W
- IH1
- UW0
- AO1
- EH0
- AA2
- JH
- EH2
- R
- V
- F
- AH1
- UW2
- SH
- AE0
- '?'
- EY0
- CH
- AY2
- AY0
- EY2
- ER0
- IH2
- TH
- AW2
- OY0
- IY2
- AO0
- HH
- AO2
- OY2
- UH0
- ZH
- ER1
- AW1
- ''''
- AW0
- UH1
- AH2
- <sos/eos>
odim: null
model_conf: {}
use_preprocessor: true
token_type: phn
bpemodel: null
non_linguistic_symbols: null
cleaner: tacotron
g2p: g2p_en
feats_extract: linear_spectrogram
feats_extract_conf:
n_fft: 2048
hop_length: 512
win_length: null
normalize: null
normalize_conf: {}
tts: vits
tts_conf:
generator_type: vits_generator
generator_params:
hidden_channels: 192
spks: -1
global_channels: -1
segment_size: 32
text_encoder_attention_heads: 2
text_encoder_ffn_expand: 4
text_encoder_blocks: 6
text_encoder_positionwise_layer_type: conv1d
text_encoder_positionwise_conv_kernel_size: 3
text_encoder_positional_encoding_layer_type: rel_pos
text_encoder_self_attention_layer_type: rel_selfattn
text_encoder_activation_type: swish
text_encoder_normalize_before: true
text_encoder_dropout_rate: 0.1
text_encoder_positional_dropout_rate: 0.0
text_encoder_attention_dropout_rate: 0.1
use_macaron_style_in_text_encoder: true
use_conformer_conv_in_text_encoder: false
text_encoder_conformer_kernel_size: -1
decoder_kernel_size: 7
decoder_channels: 512
decoder_upsample_scales:
- 8
- 8
- 2
- 2
- 2
decoder_upsample_kernel_sizes:
- 16
- 16
- 4
- 4
- 4
decoder_resblock_kernel_sizes:
- 3
- 7
- 11
decoder_resblock_dilations:
- - 1
- 3
- 5
- - 1
- 3
- 5
- - 1
- 3
- 5
use_weight_norm_in_decoder: true
posterior_encoder_kernel_size: 5
posterior_encoder_layers: 16
posterior_encoder_stacks: 1
posterior_encoder_base_dilation: 1
posterior_encoder_dropout_rate: 0.0
use_weight_norm_in_posterior_encoder: true
flow_flows: 4
flow_kernel_size: 5
flow_base_dilation: 1
flow_layers: 4
flow_dropout_rate: 0.0
use_weight_norm_in_flow: true
use_only_mean_in_flow: true
stochastic_duration_predictor_kernel_size: 3
stochastic_duration_predictor_dropout_rate: 0.5
stochastic_duration_predictor_flows: 4
stochastic_duration_predictor_dds_conv_layers: 3
vocabs: 72
aux_channels: 1025
discriminator_type: hifigan_multi_scale_multi_period_discriminator
discriminator_params:
scales: 1
scale_downsample_pooling: AvgPool1d
scale_downsample_pooling_params:
kernel_size: 4
stride: 2
padding: 2
scale_discriminator_params:
in_channels: 1
out_channels: 1
kernel_sizes:
- 15
- 41
- 5
- 3
channels: 128
max_downsample_channels: 1024
max_groups: 16
bias: true
downsample_scales:
- 2
- 2
- 4
- 4
- 1
nonlinear_activation: LeakyReLU
nonlinear_activation_params:
negative_slope: 0.1
use_weight_norm: true
use_spectral_norm: false
follow_official_norm: false
periods:
- 2
- 3
- 5
- 7
- 11
period_discriminator_params:
in_channels: 1
out_channels: 1
kernel_sizes:
- 5
- 3
channels: 32
downsample_scales:
- 3
- 3
- 3
- 3
- 1
max_downsample_channels: 1024
bias: true
nonlinear_activation: LeakyReLU
nonlinear_activation_params:
negative_slope: 0.1
use_weight_norm: true
use_spectral_norm: false
generator_adv_loss_params:
average_by_discriminators: false
loss_type: mse
discriminator_adv_loss_params:
average_by_discriminators: false
loss_type: mse
feat_match_loss_params:
average_by_discriminators: false
average_by_layers: false
include_final_outputs: true
mel_loss_params:
fs: 44100
n_fft: 2048
hop_length: 512
win_length: null
window: hann
n_mels: 80
fmin: 0
fmax: null
log_base: null
lambda_adv: 1.0
lambda_mel: 45.0
lambda_feat_match: 2.0
lambda_dur: 1.0
lambda_kl: 1.0
sampling_rate: 44100
cache_generator_outputs: true
pitch_extract: null
pitch_extract_conf: {}
pitch_normalize: null
pitch_normalize_conf: {}
energy_extract: null
energy_extract_conf: {}
energy_normalize: null
energy_normalize_conf: {}
required:
- output_dir
- token_list
version: '202209'
distributed: true
|