|
K_step: 1000 |
|
accumulate_grad_batches: 1 |
|
audio_num_mel_bins: 128 |
|
audio_sample_rate: 44100 |
|
binarization_args: |
|
shuffle: false |
|
with_align: true |
|
with_f0: true |
|
with_hubert: true |
|
with_spk_embed: false |
|
with_wav: false |
|
binarizer_cls: preprocessing.SVCpre.SVCBinarizer |
|
binary_data_dir: data/binary/mieru |
|
check_val_every_n_epoch: 10 |
|
choose_test_manually: true |
|
clip_grad_norm: 1 |
|
config_path: training/config_nsf_mieru.yaml |
|
content_cond_steps: [] |
|
cwt_add_f0_loss: false |
|
cwt_hidden_size: 128 |
|
cwt_layers: 2 |
|
cwt_loss: l1 |
|
cwt_std_scale: 0.8 |
|
datasets: |
|
- opencpop |
|
debug: false |
|
dec_ffn_kernel_size: 9 |
|
dec_layers: 4 |
|
decay_steps: 20000 |
|
decoder_type: fft |
|
dict_dir: '' |
|
diff_decoder_type: wavenet |
|
diff_loss_type: l2 |
|
dilation_cycle_length: 4 |
|
dropout: 0.1 |
|
ds_workers: 4 |
|
dur_enc_hidden_stride_kernel: |
|
- 0,2,3 |
|
- 0,2,3 |
|
- 0,1,3 |
|
dur_loss: mse |
|
dur_predictor_kernel: 3 |
|
dur_predictor_layers: 5 |
|
enc_ffn_kernel_size: 9 |
|
enc_layers: 4 |
|
encoder_K: 8 |
|
encoder_type: fft |
|
endless_ds: false |
|
f0_bin: 256 |
|
f0_max: 1100.0 |
|
f0_min: 40.0 |
|
ffn_act: gelu |
|
ffn_padding: SAME |
|
fft_size: 2048 |
|
fmax: 16000 |
|
fmin: 40 |
|
fs2_ckpt: '' |
|
gaussian_start: true |
|
gen_dir_name: '' |
|
gen_tgt_spk_id: -1 |
|
hidden_size: 256 |
|
hop_size: 512 |
|
hubert_gpu: true |
|
hubert_path: ckpt/hubert/hubert_soft.pt |
|
infer: false |
|
keep_bins: 128 |
|
lambda_commit: 0.25 |
|
lambda_energy: 0.0 |
|
lambda_f0: 1.0 |
|
lambda_ph_dur: 0.3 |
|
lambda_sent_dur: 1.0 |
|
lambda_uv: 1.0 |
|
lambda_word_dur: 1.0 |
|
load_ckpt: '' |
|
log_interval: 100 |
|
loud_norm: false |
|
lr: 0.0002 |
|
max_beta: 0.02 |
|
max_epochs: 3000 |
|
max_eval_sentences: 1 |
|
max_eval_tokens: 60000 |
|
max_frames: 42000 |
|
max_input_tokens: 60000 |
|
max_sentences: 44 |
|
max_tokens: 128000 |
|
max_updates: 1000000 |
|
mel_loss: ssim:0.5|l1:0.5 |
|
mel_vmax: 1.5 |
|
mel_vmin: -6.0 |
|
min_level_db: -120 |
|
no_fs2: true |
|
norm_type: gn |
|
num_ckpt_keep: 10 |
|
num_heads: 2 |
|
num_sanity_val_steps: 1 |
|
num_spk: 1 |
|
num_test_samples: 0 |
|
num_valid_plots: 10 |
|
optimizer_adam_beta1: 0.9 |
|
optimizer_adam_beta2: 0.98 |
|
out_wav_norm: false |
|
pe_ckpt: ckpt/0102_xiaoma_pe/model_ckpt_steps_60000.ckpt |
|
pe_enable: false |
|
perform_enhance: true |
|
pitch_ar: false |
|
pitch_enc_hidden_stride_kernel: |
|
- 0,2,5 |
|
- 0,2,5 |
|
- 0,2,5 |
|
pitch_extractor: parselmouth |
|
pitch_loss: l2 |
|
pitch_norm: log |
|
pitch_type: frame |
|
pndm_speedup: 10 |
|
pre_align_args: |
|
allow_no_txt: false |
|
denoise: false |
|
forced_align: mfa |
|
txt_processor: zh_g2pM |
|
use_sox: true |
|
use_tone: false |
|
pre_align_cls: data_gen.singing.pre_align.SingingPreAlign |
|
predictor_dropout: 0.5 |
|
predictor_grad: 0.1 |
|
predictor_hidden: -1 |
|
predictor_kernel: 5 |
|
predictor_layers: 5 |
|
prenet_dropout: 0.5 |
|
prenet_hidden_size: 256 |
|
pretrain_fs_ckpt: '' |
|
processed_data_dir: xxx |
|
profile_infer: false |
|
raw_data_dir: data/raw/mieru |
|
ref_norm_layer: bn |
|
rel_pos: true |
|
reset_phone_dict: true |
|
residual_channels: 512 |
|
residual_layers: 20 |
|
save_best: false |
|
save_ckpt: true |
|
save_codes: |
|
- configs |
|
- modules |
|
- src |
|
- utils |
|
save_f0: true |
|
save_gt: false |
|
schedule_type: linear |
|
seed: 1234 |
|
sort_by_len: true |
|
speaker_id: mieru |
|
spec_max: |
|
- -0.07798238843679428 |
|
- 0.26933982968330383 |
|
- 0.534960925579071 |
|
- 0.6316468715667725 |
|
- 0.7611492872238159 |
|
- 0.8967669606208801 |
|
- 1.206213355064392 |
|
- 1.1772220134735107 |
|
- 1.2176483869552612 |
|
- 1.2086814641952515 |
|
- 1.1052502393722534 |
|
- 1.1271764039993286 |
|
- 1.2594239711761475 |
|
- 1.2077986001968384 |
|
- 1.174630880355835 |
|
- 1.2514570951461792 |
|
- 1.2161906957626343 |
|
- 1.1831343173980713 |
|
- 1.1852372884750366 |
|
- 1.2100788354873657 |
|
- 1.1555075645446777 |
|
- 1.1737077236175537 |
|
- 1.17905592918396 |
|
- 1.1453087329864502 |
|
- 1.139377474784851 |
|
- 1.2360846996307373 |
|
- 1.1950435638427734 |
|
- 1.2026022672653198 |
|
- 1.2503693103790283 |
|
- 1.1509045362472534 |
|
- 1.1815613508224487 |
|
- 1.2241206169128418 |
|
- 1.1905879974365234 |
|
- 1.1836503744125366 |
|
- 1.1992517709732056 |
|
- 1.174208164215088 |
|
- 1.1604502201080322 |
|
- 1.1240005493164062 |
|
- 1.1267870664596558 |
|
- 1.1273980140686035 |
|
- 1.0988750457763672 |
|
- 1.1005706787109375 |
|
- 1.0876210927963257 |
|
- 1.0774418115615845 |
|
- 1.0573620796203613 |
|
- 1.1072624921798706 |
|
- 1.0700596570968628 |
|
- 1.0841786861419678 |
|
- 0.9595680236816406 |
|
- 0.9211053848266602 |
|
- 0.9691729545593262 |
|
- 0.8628745675086975 |
|
- 0.9731287360191345 |
|
- 0.8603856563568115 |
|
- 0.8312976956367493 |
|
- 0.7979366183280945 |
|
- 0.7976928353309631 |
|
- 0.8139990568161011 |
|
- 0.8054372072219849 |
|
- 0.7865338921546936 |
|
- 0.6887863874435425 |
|
- 0.7727973461151123 |
|
- 0.6160252094268799 |
|
- 0.6462228894233704 |
|
- 0.7076483368873596 |
|
- 0.6195215582847595 |
|
- 0.6210001111030579 |
|
- 0.645635187625885 |
|
- 0.5153771042823792 |
|
- 0.6078693270683289 |
|
- 0.4183902442455292 |
|
- 0.3647494316101074 |
|
- 0.3318658173084259 |
|
- 0.37621980905532837 |
|
- 0.3409509062767029 |
|
- 0.40003079175949097 |
|
- 0.5052263140678406 |
|
- 0.2630102336406708 |
|
- 0.32661110162734985 |
|
- 0.38820746541023254 |
|
- 0.45013752579689026 |
|
- 0.387237548828125 |
|
- 0.40396344661712646 |
|
- 0.43512699007987976 |
|
- 0.4810633957386017 |
|
- 0.4886694848537445 |
|
- 0.3818564713001251 |
|
- 0.46548202633857727 |
|
- 0.42557549476623535 |
|
- 0.41637828946113586 |
|
- 0.4002314507961273 |
|
- 0.3845779001712799 |
|
- 0.3366483449935913 |
|
- 0.42071297764778137 |
|
- 0.4211159348487854 |
|
- 0.46399375796318054 |
|
- 0.2527320683002472 |
|
- 0.2950391471385956 |
|
- 0.19637906551361084 |
|
- 0.2465660572052002 |
|
- 0.16044391691684723 |
|
- 0.17868264019489288 |
|
- 0.2509983479976654 |
|
- 0.1478097140789032 |
|
- 0.18556511402130127 |
|
- 0.2730163633823395 |
|
- 0.16532213985919952 |
|
- 0.2402658760547638 |
|
- 0.10384183377027512 |
|
- 0.18026986718177795 |
|
- 0.15106868743896484 |
|
- 0.2155972272157669 |
|
- 0.1567213237285614 |
|
- 0.18318375945091248 |
|
- 0.19110459089279175 |
|
- 0.11672339588403702 |
|
- 0.02623329684138298 |
|
- 0.018039697781205177 |
|
- -0.07879792153835297 |
|
- -0.1182454526424408 |
|
- -0.04759000614285469 |
|
- -0.06419961154460907 |
|
- -0.1695338785648346 |
|
- -0.16710501909255981 |
|
- -0.21242910623550415 |
|
- -0.3622243106365204 |
|
- -0.3296288251876831 |
|
- -0.2035948485136032 |
|
spec_min: |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
- -4.999994277954102 |
|
spk_cond_steps: [] |
|
stop_token_weight: 5.0 |
|
task_cls: training.task.SVC_task.SVCTask |
|
test_ids: [] |
|
test_input_dir: '' |
|
test_num: 0 |
|
test_prefixes: |
|
- data\raw\mieru\test |
|
test_set_name: test |
|
timesteps: 1000 |
|
train_set_name: train |
|
use_crepe: true |
|
use_denoise: false |
|
use_energy_embed: false |
|
use_gt_dur: false |
|
use_gt_f0: false |
|
use_midi: false |
|
use_nsf: true |
|
use_pitch_embed: true |
|
use_pos_embed: true |
|
use_spk_embed: false |
|
use_spk_id: false |
|
use_split_spk_id: false |
|
use_uv: false |
|
use_var_enc: false |
|
use_vec: false |
|
val_check_interval: 2000 |
|
valid_num: 0 |
|
valid_set_name: valid |
|
vocoder: network.vocoders.nsf_hifigan.NsfHifiGAN |
|
vocoder_ckpt: ckpt/nsf_hifigan/model |
|
warmup_updates: 2000 |
|
wav2spec_eps: 1e-6 |
|
weight_decay: 0 |
|
win_size: 2048 |
|
work_dir: ckpt/mieru |
|
|