|
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/Meiko |
|
check_val_every_n_epoch: 10 |
|
choose_test_manually: false |
|
clip_grad_norm: 1 |
|
config_path: training/config_nsf.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: 50000 |
|
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: checkpoints/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: 0.0006 |
|
max_beta: 0.02 |
|
max_epochs: 3000 |
|
max_eval_sentences: 1 |
|
max_eval_tokens: 60000 |
|
max_frames: 42000 |
|
max_input_tokens: 60000 |
|
max_sentences: 11 |
|
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: checkpoints/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/Meiko |
|
ref_norm_layer: bn |
|
rel_pos: true |
|
reset_phone_dict: true |
|
residual_channels: 384 |
|
residual_layers: 20 |
|
save_best: true |
|
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: Meiko |
|
spec_max: |
|
- 0.11616316437721252 |
|
- 0.009597139433026314 |
|
- 0.28568679094314575 |
|
- 0.5713539123535156 |
|
- 0.6507775187492371 |
|
- 0.6846900582313538 |
|
- 0.7684511542320251 |
|
- 0.7574314475059509 |
|
- 0.7267094254493713 |
|
- 0.8298212289810181 |
|
- 0.6814215183258057 |
|
- 0.7774385213851929 |
|
- 0.7883802056312561 |
|
- 0.7771736979484558 |
|
- 0.7607403993606567 |
|
- 0.8505979180335999 |
|
- 0.7654092311859131 |
|
- 0.7792922258377075 |
|
- 0.814899206161499 |
|
- 0.8058286905288696 |
|
- 0.839918851852417 |
|
- 0.8406909108161926 |
|
- 0.8339935541152954 |
|
- 0.9287465810775757 |
|
- 0.8166532516479492 |
|
- 0.8449192047119141 |
|
- 0.7643511891365051 |
|
- 0.8175668716430664 |
|
- 1.0239852666854858 |
|
- 0.920753002166748 |
|
- 0.8153243660926819 |
|
- 0.7587951421737671 |
|
- 0.7698416113853455 |
|
- 0.7247377634048462 |
|
- 0.6954795122146606 |
|
- 0.6807010173797607 |
|
- 0.8715915679931641 |
|
- 0.8993064761161804 |
|
- 0.90997314453125 |
|
- 0.7913641333580017 |
|
- 0.7065826058387756 |
|
- 0.6068118810653687 |
|
- 0.6278789639472961 |
|
- 0.6242763996124268 |
|
- 0.5978773236274719 |
|
- 0.651780366897583 |
|
- 0.7780635952949524 |
|
- 0.7565146684646606 |
|
- 0.5729265213012695 |
|
- 0.5707721710205078 |
|
- 0.5281876921653748 |
|
- 0.5579817891120911 |
|
- 0.6407540440559387 |
|
- 0.7233482003211975 |
|
- 0.5677092671394348 |
|
- 0.40926626324653625 |
|
- 0.4460923373699188 |
|
- 0.4058813750743866 |
|
- 0.4390961229801178 |
|
- 0.5553078055381775 |
|
- 0.5349165201187134 |
|
- 0.43830350041389465 |
|
- 0.4032619595527649 |
|
- 0.3253237009048462 |
|
- 0.30613574385643005 |
|
- 0.44174280762672424 |
|
- 0.3622792959213257 |
|
- 0.45337533950805664 |
|
- 0.3313130736351013 |
|
- 0.36956584453582764 |
|
- 0.4998202919960022 |
|
- 0.42133796215057373 |
|
- 0.28050243854522705 |
|
- 0.26571735739707947 |
|
- 0.20871540904045105 |
|
- 0.3416949510574341 |
|
- 0.3328045904636383 |
|
- 0.332925409078598 |
|
- 0.3000032603740692 |
|
- 0.08743463456630707 |
|
- 0.20726755261421204 |
|
- 0.1583203673362732 |
|
- 0.13275942206382751 |
|
- 0.066913902759552 |
|
- 0.1054723709821701 |
|
- -0.08983375877141953 |
|
- -0.12505969405174255 |
|
- -0.03509913384914398 |
|
- -0.11556489020586014 |
|
- -0.2324075847864151 |
|
- -0.06187695264816284 |
|
- 0.020108096301555634 |
|
- -0.009129349142313004 |
|
- -0.044059865176677704 |
|
- 0.0343453511595726 |
|
- 0.030609752982854843 |
|
- 0.11592991650104523 |
|
- 0.04611678794026375 |
|
- 0.016514429822564125 |
|
- -0.10608740150928497 |
|
- -0.18119606375694275 |
|
- -0.0764162689447403 |
|
- -0.005786585621535778 |
|
- -0.16699059307575226 |
|
- -0.1254500299692154 |
|
- -0.09370455145835876 |
|
- 0.015143157914280891 |
|
- 0.07289116084575653 |
|
- -0.006812357809394598 |
|
- -0.0280735082924366 |
|
- -0.0021705669350922108 |
|
- -0.1115487739443779 |
|
- -0.2423458993434906 |
|
- -0.116642065346241 |
|
- -0.1487213373184204 |
|
- -0.16707029938697815 |
|
- -0.25437667965888977 |
|
- -0.32499101758003235 |
|
- -0.2704009413719177 |
|
- -0.29621294140815735 |
|
- -0.42674311995506287 |
|
- -0.4650932848453522 |
|
- -0.5842434763908386 |
|
- -0.6859109401702881 |
|
- -0.9532108902931213 |
|
- -0.9863560199737549 |
|
- -1.220953106880188 |
|
- -1.3163429498672485 |
|
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 |
|
- -4.942144870758057 |
|
- -4.772783279418945 |
|
- -4.7206244468688965 |
|
- -4.5759992599487305 |
|
- -4.509932518005371 |
|
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: |
|
- test |
|
test_set_name: test |
|
timesteps: 1000 |
|
train_set_name: train |
|
use_crepe: false |
|
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: 1000 |
|
valid_num: 0 |
|
valid_set_name: valid |
|
vocoder: network.vocoders.nsf_hifigan.NsfHifiGAN |
|
vocoder_ckpt: checkpoints/nsf_hifigan/model |
|
warmup_updates: 2000 |
|
wav2spec_eps: 1e-6 |
|
weight_decay: 0 |
|
win_size: 2048 |
|
work_dir: checkpoints/Meiko |
|
|