File size: 6,234 Bytes
0c02046 |
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 |
config: conf/tuning/train_conformer_fastspeech2.yaml
print_config: false
log_level: INFO
dry_run: false
iterator_type: sequence
output_dir: exp/tts_train_conformer_fastspeech2_tacotron2_teacher_raw_phn_jaconv_pyopenjtalk_accent_with_pause
ngpu: 1
seed: 0
num_workers: 1
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: 55944
dist_launcher: null
multiprocessing_distributed: true
cudnn_enabled: true
cudnn_benchmark: false
cudnn_deterministic: true
collect_stats: false
write_collected_feats: false
max_epoch: 200
patience: null
val_scheduler_criterion:
- valid
- loss
early_stopping_criterion:
- valid
- loss
- min
best_model_criterion:
- - valid
- loss
- min
- - train
- loss
- min
keep_nbest_models: 5
grad_clip: 1.0
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
unused_parameters: false
use_tensorboard: true
use_wandb: false
wandb_project: null
wandb_id: null
pretrain_path: null
init_param: []
freeze_param: []
num_iters_per_epoch: 1000
batch_size: 20
valid_batch_size: null
batch_bins: 12000000
valid_batch_bins: null
train_shape_file:
- exp/tts_train_tacotron2_raw_phn_jaconv_pyopenjtalk_accent_with_pause/decode_use_teacher_forcingtrue_train.loss.ave/stats/train/text_shape.phn
- exp/tts_train_tacotron2_raw_phn_jaconv_pyopenjtalk_accent_with_pause/decode_use_teacher_forcingtrue_train.loss.ave/stats/train/speech_shape
valid_shape_file:
- exp/tts_train_tacotron2_raw_phn_jaconv_pyopenjtalk_accent_with_pause/decode_use_teacher_forcingtrue_train.loss.ave/stats/valid/text_shape.phn
- exp/tts_train_tacotron2_raw_phn_jaconv_pyopenjtalk_accent_with_pause/decode_use_teacher_forcingtrue_train.loss.ave/stats/valid/speech_shape
batch_type: numel
valid_batch_type: null
fold_length:
- 150
- 240000
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/raw/tr_no_dev/text
- text
- text
- - exp/tts_train_tacotron2_raw_phn_jaconv_pyopenjtalk_accent_with_pause/decode_use_teacher_forcingtrue_train.loss.ave/tr_no_dev/durations
- durations
- text_int
- - dump/raw/tr_no_dev/wav.scp
- speech
- sound
valid_data_path_and_name_and_type:
- - dump/raw/dev/text
- text
- text
- - exp/tts_train_tacotron2_raw_phn_jaconv_pyopenjtalk_accent_with_pause/decode_use_teacher_forcingtrue_train.loss.ave/dev/durations
- durations
- text_int
- - dump/raw/dev/wav.scp
- speech
- 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: 1.0
scheduler: noamlr
scheduler_conf:
model_size: 384
warmup_steps: 4000
token_list:
- <blank>
- <unk>
- '1'
- '2'
- '0'
- '3'
- '4'
- '-1'
- '5'
- a
- o
- '-2'
- i
- '-3'
- u
- e
- k
- n
- t
- '6'
- r
- '-4'
- s
- N
- m
- pau
- '7'
- sh
- d
- g
- w
- '8'
- U
- '-5'
- I
- cl
- h
- y
- b
- '9'
- j
- ts
- ch
- '-6'
- z
- p
- '-7'
- f
- ky
- ry
- '-8'
- gy
- '-9'
- hy
- ny
- '-10'
- by
- my
- '-11'
- '-12'
- '-13'
- py
- '-14'
- '-15'
- v
- '10'
- '-16'
- '-17'
- '11'
- '-21'
- '-20'
- '12'
- '-19'
- '13'
- '-18'
- '14'
- dy
- '15'
- ty
- '-22'
- '16'
- '18'
- '19'
- '17'
- <sos/eos>
odim: null
model_conf: {}
use_preprocessor: true
token_type: phn
bpemodel: null
non_linguistic_symbols: null
cleaner: jaconv
g2p: pyopenjtalk_accent_with_pause
feats_extract: fbank
feats_extract_conf:
fs: 24000
fmin: 80
fmax: 7600
n_mels: 80
hop_length: 300
n_fft: 2048
win_length: 1200
normalize: global_mvn
normalize_conf:
stats_file: exp/tts_train_tacotron2_raw_phn_jaconv_pyopenjtalk_accent_with_pause/decode_use_teacher_forcingtrue_train.loss.ave/stats/train/feats_stats.npz
tts: fastspeech2
tts_conf:
adim: 384
aheads: 2
elayers: 4
eunits: 1536
dlayers: 4
dunits: 1536
positionwise_layer_type: conv1d
positionwise_conv_kernel_size: 3
duration_predictor_layers: 2
duration_predictor_chans: 256
duration_predictor_kernel_size: 3
postnet_layers: 5
postnet_filts: 5
postnet_chans: 256
use_masking: true
encoder_normalize_before: true
decoder_normalize_before: true
reduction_factor: 1
encoder_type: conformer
decoder_type: conformer
conformer_pos_enc_layer_type: rel_pos
conformer_self_attn_layer_type: rel_selfattn
conformer_activation_type: swish
use_macaron_style_in_conformer: true
use_cnn_in_conformer: true
conformer_enc_kernel_size: 7
conformer_dec_kernel_size: 31
init_type: xavier_uniform
transformer_enc_dropout_rate: 0.2
transformer_enc_positional_dropout_rate: 0.2
transformer_enc_attn_dropout_rate: 0.2
transformer_dec_dropout_rate: 0.2
transformer_dec_positional_dropout_rate: 0.2
transformer_dec_attn_dropout_rate: 0.2
pitch_predictor_layers: 5
pitch_predictor_chans: 256
pitch_predictor_kernel_size: 5
pitch_predictor_dropout: 0.5
pitch_embed_kernel_size: 1
pitch_embed_dropout: 0.0
stop_gradient_from_pitch_predictor: true
energy_predictor_layers: 2
energy_predictor_chans: 256
energy_predictor_kernel_size: 3
energy_predictor_dropout: 0.5
energy_embed_kernel_size: 1
energy_embed_dropout: 0.0
stop_gradient_from_energy_predictor: false
pitch_extract: dio
pitch_extract_conf:
fs: 24000
n_fft: 2048
hop_length: 300
f0max: 400
f0min: 80
reduction_factor: 1
pitch_normalize: global_mvn
pitch_normalize_conf:
stats_file: exp/tts_train_tacotron2_raw_phn_jaconv_pyopenjtalk_accent_with_pause/decode_use_teacher_forcingtrue_train.loss.ave/stats/train/pitch_stats.npz
energy_extract: energy
energy_extract_conf:
fs: 24000
n_fft: 2048
hop_length: 300
win_length: 1200
reduction_factor: 1
energy_normalize: global_mvn
energy_normalize_conf:
stats_file: exp/tts_train_tacotron2_raw_phn_jaconv_pyopenjtalk_accent_with_pause/decode_use_teacher_forcingtrue_train.loss.ave/stats/train/energy_stats.npz
required:
- output_dir
- token_list
distributed: true
|