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/xiaxiaobai
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: 40000
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: 0.0008
max_beta: 0.02
max_epochs: 3000
max_eval_sentences: 1
max_eval_tokens: 60000
max_frames: 42000
max_input_tokens: 60000
max_sentences: 75
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/xiaxiaobai
ref_norm_layer: bn
rel_pos: true
reset_phone_dict: true
residual_channels: 384
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: xiaxiaobai
spec_max:
- -0.03524341061711311
- -0.22983506321907043
- 0.14042672514915466
- 0.24598221480846405
- 0.38769328594207764
- 0.403020977973938
- 0.4710584282875061
- 0.46678662300109863
- 0.38870999217033386
- 0.6632387638092041
- 0.6111851334571838
- 0.6690583229064941
- 0.7419546842575073
- 0.737534761428833
- 0.7382131218910217
- 0.8168102502822876
- 0.8108615279197693
- 0.8472557067871094
- 0.8082121014595032
- 0.9421120882034302
- 0.9718508124351501
- 0.9050439596176147
- 0.9559441208839417
- 0.9039924740791321
- 0.8825679421424866
- 0.8896527290344238
- 0.9281688928604126
- 0.9495793581008911
- 0.9456884860992432
- 0.8448024392127991
- 0.706383228302002
- 0.8815341591835022
- 0.8132895827293396
- 0.6926009058952332
- 0.7048583626747131
- 0.7063571810722351
- 0.6628313064575195
- 0.6794947385787964
- 0.5719707608222961
- 0.5986276268959045
- 0.8701962232589722
- 0.6562694311141968
- 0.5677947998046875
- 0.617889404296875
- 0.6444329023361206
- 0.8564671874046326
- 0.81944340467453
- 0.5799424052238464
- 0.4977129399776459
- 0.39452463388442993
- 0.46540209650993347
- 0.3466089963912964
- 0.43464744091033936
- 0.3072132170200348
- 0.2883022129535675
- 0.13554586470127106
- 0.1449982076883316
- 0.06144052743911743
- 0.032265570014715195
- -0.0411582849919796
- -0.03320876136422157
- 0.09776383638381958
- -0.10860992968082428
- -0.16577060520648956
- -0.25543949007987976
- -0.15455809235572815
- -0.16559940576553345
- -0.08075764775276184
- -0.16779740154743195
- -0.13772723078727722
- -0.20297837257385254
- -0.29985055327415466
- -0.32260239124298096
- -0.3287070095539093
- -0.4775390326976776
- -0.5171418190002441
- -0.3881285488605499
- -0.3670082092285156
- -0.4483766555786133
- -0.4888381361961365
- -0.3579249382019043
- -0.3966373801231384
- -0.39407745003700256
- -0.42390042543411255
- -0.5861775875091553
- -0.380365252494812
- -0.6373982429504395
- -0.6403031945228577
- -0.6271409392356873
- -0.42471981048583984
- -0.660955011844635
- -0.566235363483429
- -0.6491592526435852
- -0.6828501224517822
- -0.5224244594573975
- -0.48923757672309875
- -0.5497328042984009
- -0.5110473036766052
- -0.5995211005210876
- -0.6271748542785645
- -0.6996229887008667
- -0.7070512771606445
- -0.6818519234657288
- -0.6255654692649841
- -0.5862824320793152
- -0.41896769404411316
- -0.4821942150592804
- -0.6815913915634155
- -0.8292946219444275
- -0.787152111530304
- -0.7727371454238892
- -0.6443832516670227
- -0.6990486979484558
- -0.7400271892547607
- -0.7830663919448853
- -0.8243145942687988
- -0.8491696119308472
- -0.765605092048645
- -1.025327205657959
- -1.0541386604309082
- -1.113960862159729
- -1.1958088874816895
- -1.2482109069824219
- -1.336235523223877
- -1.4202933311462402
- -1.4578213691711426
- -1.4341062307357788
- -1.4737169742584229
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:
- 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: checkpoints/nsf_hifigan/model
warmup_updates: 2000
wav2spec_eps: 1e-6
weight_decay: 0
win_size: 2048
work_dir: checkpoints/xiaxiaobai