|
config: conf/tuning/train_gst_tacotron2.yaml |
|
print_config: false |
|
log_level: INFO |
|
dry_run: false |
|
iterator_type: sequence |
|
output_dir: exp/tts_train_gst_tacotron2_raw_phn_tacotron_g2p_en_no_space |
|
ngpu: 1 |
|
seed: 0 |
|
num_workers: 1 |
|
num_att_plot: 3 |
|
dist_backend: nccl |
|
dist_init_method: env:// |
|
dist_world_size: null |
|
dist_rank: null |
|
local_rank: 0 |
|
dist_master_addr: null |
|
dist_master_port: null |
|
dist_launcher: null |
|
multiprocessing_distributed: false |
|
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_noise: false |
|
accum_grad: 1 |
|
no_forward_run: false |
|
resume: true |
|
train_dtype: float32 |
|
log_interval: null |
|
pretrain_path: [] |
|
pretrain_key: [] |
|
num_iters_per_epoch: null |
|
batch_size: 20 |
|
valid_batch_size: null |
|
batch_bins: 3750000 |
|
valid_batch_bins: null |
|
train_shape_file: |
|
- exp/tts_stats_raw_phn_tacotron_g2p_en_no_space/train/text_shape.phn |
|
- exp/tts_stats_raw_phn_tacotron_g2p_en_no_space/train/speech_shape |
|
valid_shape_file: |
|
- exp/tts_stats_raw_phn_tacotron_g2p_en_no_space/valid/text_shape.phn |
|
- exp/tts_stats_raw_phn_tacotron_g2p_en_no_space/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 |
|
- - dump/raw/tr_no_dev/wav.scp |
|
- speech |
|
- sound |
|
valid_data_path_and_name_and_type: |
|
- - dump/raw/dev/text |
|
- text |
|
- text |
|
- - dump/raw/dev/wav.scp |
|
- speech |
|
- sound |
|
allow_variable_data_keys: false |
|
max_cache_size: 0.0 |
|
valid_max_cache_size: null |
|
optim: adam |
|
optim_conf: |
|
lr: 0.001 |
|
eps: 1.0e-06 |
|
weight_decay: 0.0 |
|
scheduler: null |
|
scheduler_conf: {} |
|
token_list: |
|
- <blank> |
|
- <unk> |
|
- OY0 |
|
- '''' |
|
- OY2 |
|
- ER2 |
|
- UH0 |
|
- '!' |
|
- EY0 |
|
- AW0 |
|
- AA0 |
|
- UH2 |
|
- UW2 |
|
- AY0 |
|
- AO2 |
|
- AO0 |
|
- AE2 |
|
- AH2 |
|
- AE0 |
|
- AA2 |
|
- IY2 |
|
- EH0 |
|
- AW2 |
|
- ZH |
|
- AY2 |
|
- OY1 |
|
- IH2 |
|
- UW0 |
|
- EY2 |
|
- EH2 |
|
- OW2 |
|
- OW0 |
|
- '?' |
|
- CH |
|
- ER1 |
|
- TH |
|
- UH1 |
|
- AW1 |
|
- JH |
|
- Y |
|
- SH |
|
- NG |
|
- ',' |
|
- G |
|
- OW1 |
|
- AO1 |
|
- IY0 |
|
- UW1 |
|
- EY1 |
|
- AY1 |
|
- HH |
|
- F |
|
- ER0 |
|
- V |
|
- P |
|
- B |
|
- AH1 |
|
- IY1 |
|
- IH0 |
|
- AA1 |
|
- EH1 |
|
- AE1 |
|
- M |
|
- W |
|
- K |
|
- DH |
|
- Z |
|
- . |
|
- L |
|
- D |
|
- IH1 |
|
- R |
|
- S |
|
- N |
|
- T |
|
- AH0 |
|
- <sos/eos> |
|
odim: null |
|
model_conf: {} |
|
use_preprocessor: true |
|
token_type: phn |
|
bpemodel: null |
|
non_linguistic_symbols: null |
|
cleaner: tacotron |
|
g2p: g2p_en_no_space |
|
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_stats_raw_phn_tacotron_g2p_en_no_space/train/feats_stats.npz |
|
tts: tacotron2 |
|
tts_conf: |
|
embed_dim: 512 |
|
elayers: 1 |
|
eunits: 512 |
|
econv_layers: 3 |
|
econv_chans: 512 |
|
econv_filts: 5 |
|
atype: location |
|
adim: 512 |
|
aconv_chans: 32 |
|
aconv_filts: 15 |
|
cumulate_att_w: true |
|
dlayers: 2 |
|
dunits: 1024 |
|
prenet_layers: 2 |
|
prenet_units: 256 |
|
postnet_layers: 5 |
|
postnet_chans: 512 |
|
postnet_filts: 5 |
|
output_activation: null |
|
use_batch_norm: true |
|
use_concate: true |
|
use_residual: false |
|
use_gst: true |
|
gst_heads: 8 |
|
gst_tokens: 128 |
|
dropout_rate: 0.5 |
|
zoneout_rate: 0.1 |
|
reduction_factor: 1 |
|
spk_embed_dim: null |
|
use_masking: true |
|
bce_pos_weight: 10.0 |
|
use_guided_attn_loss: true |
|
guided_attn_loss_sigma: 0.4 |
|
guided_attn_loss_lambda: 1.0 |
|
required: |
|
- output_dir |
|
- token_list |
|
distributed: false |
|
|