training/config.yaml

K_step: 1000
accumulate_grad_batches: 1
audio_num_mel_bins: 80
audio_sample_rate: 24000
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/atri
check_val_every_n_epoch: 10
choose_test_manually: false
clip_grad_norm: 1
config_path: training/config.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: 50.0
ffn_act: gelu
ffn_padding: SAME
fft_size: 512
fmax: 12000
fmin: 30
fs2_ckpt: ''
gaussian_start: true
gen_dir_name: ''
gen_tgt_spk_id: -1
hidden_size: 256
hop_size: 128
hubert_gpu: true
hubert_path: checkpoints/hubert/hubert_soft.pt
infer: false
keep_bins: 80
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: 0.0004
max_beta: 0.02
max_epochs: 3000
max_eval_sentences: 1
max_eval_tokens: 60000
max_frames: 42000
max_input_tokens: 60000
max_sentences: 88
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
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/atri
ref_norm_layer: bn
rel_pos: true
reset_phone_dict: true
residual_channels: 256
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: atri
spec_max:
- -1.5451143980026245
- -1.5177826881408691
- -1.1807013750076294
- -0.6732071042060852
- -0.47006210684776306
- -0.271837055683136
- -0.27174147963523865
- -0.3395537734031677
- -0.2529868483543396
- -0.22453370690345764
- -0.24767500162124634
- -0.22861438989639282
- -0.28668588399887085
- -0.335957795381546
- -0.3118636906147003
- -0.34530898928642273
- -0.35274678468704224
- -0.4730182886123657
- -0.45395755767822266
- -0.4338522255420685
- -0.41395917534828186
- -0.29468369483947754
- -0.16852207481861115
- -0.3900046646595001
- -0.6241626739501953
- -0.5899035930633545
- -0.6534764170646667
- -0.6667397022247314
- -0.6992383003234863
- -0.7867978811264038
- -0.8457596302032471
- -0.43350857496261597
- -0.629216730594635
- -0.9135912656784058
- -0.9230040311813354
- -0.6756577491760254
- -0.8399246335029602
- -0.8495144248008728
- -0.781493067741394
- -1.0347247123718262
- -1.0051935911178589
- -1.1246198415756226
- -1.021154522895813
- -0.851677417755127
- -0.8443652987480164
- -0.9016147255897522
- -0.7618780732154846
- -1.0490750074386597
- -1.2046996355056763
- -1.2022035121917725
- -0.9753153324127197
- -1.2503044605255127
- -1.0664823055267334
- -1.1236635446548462
- -1.2223032712936401
- -1.0116488933563232
- -1.2263423204421997
- -1.2552075386047363
- -1.3846945762634277
- -1.2681812047958374
- -1.3416036367416382
- -1.264938235282898
- -1.2763726711273193
- -1.4651004076004028
- -1.4880361557006836
- -1.5735552310943604
- -1.4097294807434082
- -1.468385100364685
- -1.3768259286880493
- -1.3312186002731323
- -1.3547866344451904
- -1.4387739896774292
- -1.1861546039581299
- -1.1709729433059692
- -1.1812609434127808
- -1.1489264965057373
- -1.5605546236038208
- -2.2702553272247314
- -4.064557075500488
- -5.809507846832275
spec_min:
- -5.740882873535156
- -6.0
- -6.0
- -6.0
- -6.0
- -6.0
- -6.0
- -6.0
- -5.959110260009766
- -6.0
- -6.0
- -6.0
- -6.0
- -6.0
- -6.0
- -6.0
- -6.0
- -6.0
- -6.0
- -6.0
- -6.0
- -6.0
- -6.0
- -6.0
- -6.0
- -6.0
- -6.0
- -6.0
- -6.0
- -6.0
- -6.0
- -5.999546527862549
- -6.0
- -5.995517730712891
- -6.0
- -6.0
- -6.0
- -6.0
- -6.0
- -6.0
- -6.0
- -5.960205078125
- -5.93423318862915
- -6.0
- -5.933608531951904
- -6.0
- -6.0
- -6.0
- -5.953958511352539
- -5.908934593200684
- -5.911312580108643
- -5.882552623748779
- -5.932425498962402
- -5.91495943069458
- -5.826524257659912
- -5.777952671051025
- -5.775007724761963
- -5.849961280822754
- -5.7793660163879395
- -5.781087875366211
- -5.818603992462158
- -5.765895366668701
- -5.834509372711182
- -5.817623615264893
- -5.855445384979248
- -5.844409465789795
- -5.760529518127441
- -5.713063716888428
- -5.74588680267334
- -5.855954647064209
- -5.874588489532471
- -5.81571626663208
- -5.849369049072266
- -5.963766574859619
- -5.8541646003723145
- -5.922942161560059
- -6.0
- -6.0
- -6.0
- -6.0
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_vec: false
use_var_enc: false
val_check_interval: 2000
valid_num: 0
valid_set_name: valid
vocoder: network.vocoders.hifigan.HifiGAN
vocoder_ckpt: checkpoints/0109_hifigan_bigpopcs_hop128
warmup_updates: 2000
wav2spec_eps: 1e-6
weight_decay: 0
win_size: 512
work_dir: checkpoints/atri
no_fs2: true