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/aqua-covers
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
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/aqua-covers
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: aqua-covers
spec_max:
- 0.30652669072151184
- 0.08383000642061234
- 0.1723981499671936
- 0.3240015506744385
- 0.39965277910232544
- 0.44550102949142456
- 0.38052627444267273
- 0.32977527379989624
- 0.3479712903499603
- 0.34630587697029114
- 0.3231307864189148
- 0.38071632385253906
- 0.4098763167858124
- 0.4250231385231018
- 0.47273561358451843
- 0.4468965232372284
- 0.4200228452682495
- 0.3831767439842224
- 0.37592482566833496
- 0.3783853352069855
- 0.4049440622329712
- 0.37970447540283203
- 0.40022099018096924
- 0.41112345457077026
- 0.46689096093177795
- 0.4474470615386963
- 0.39477235078811646
- 0.36646541953086853
- 0.3191830515861511
- 0.33559781312942505
- 0.3327852189540863
- 0.34980878233909607
- 0.3240199685096741
- 0.3037862181663513
- 0.29198917746543884
- 0.36840683221817017
- 0.2427365928888321
- 0.2464374154806137
- 0.29265183210372925
- 0.2961692810058594
- 0.1467614769935608
- 0.0934368446469307
- 0.06043912097811699
- 0.05212782323360443
- 0.058152664452791214
- 0.10727789998054504
- 0.037161730229854584
- 0.01805332489311695
- 0.014705522917211056
- -0.005861940328031778
- -0.00127512332983315
- -0.10097749531269073
- -0.09864751249551773
- -0.0720948874950409
- -0.12240472435951233
- -0.22892576456069946
- -0.19455470144748688
- -0.2074085921049118
- -0.16607750952243805
- -0.3007032871246338
- -0.22413626313209534
- -0.36319100856781006
- -0.2630736529827118
- -0.4355252683162689
- -0.4011249542236328
- -0.4347180128097534
- -0.36945652961730957
- -0.39407187700271606
- -0.47727906703948975
- -0.45892977714538574
- -0.34440308809280396
- -0.4578149616718292
- -0.5542540550231934
- -0.2935250997543335
- -0.3627168536186218
- -0.5405836701393127
- -0.6675882935523987
- -0.7014155983924866
- -0.9406138062477112
- -1.8107411861419678
spec_min:
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -6.000000476837158
- -5.8976850509643555
- -5.985969066619873
- -5.844642639160156
- -5.920450687408447
- -5.921976566314697
- -5.874476432800293
- -5.934454441070557
- -5.875627040863037
- -5.845851898193359
- -5.956720352172852
- -5.952122211456299
- -5.828412055969238
- -5.834786891937256
- -5.867711544036865
- -5.819331645965576
- -5.861200332641602
- -5.8309478759765625
- -5.837533473968506
- -5.745879173278809
- -5.765843868255615
- -5.7412519454956055
- -5.756224632263184
- -5.7770514488220215
- -5.83022928237915
- -6.000000476837158
- -6.000000476837158
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.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/aqua-covers