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/duckaloid
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: 60000
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: /content/diff-svc/pretrain/model_ckpt_steps_200000.ckpt
log_interval: 100
loud_norm: false
lr: 5.0e-05
max_beta: 0.02
max_epochs: 3000
max_eval_sentences: 1
max_eval_tokens: 60000
max_frames: 42000
max_input_tokens: 60000
max_sentences: 12
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: false
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/duckaloid
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: duckaloid
spec_max:
- 0.31781044602394104
- 0.23643149435520172
- 0.3626210689544678
- 0.3854254484176636
- 0.42850273847579956
- 0.44149714708328247
- 0.4209049344062805
- 0.3555622100830078
- 0.2809910476207733
- 0.27863848209381104
- 0.3248143494129181
- 0.2951713502407074
- 0.3265945613384247
- 0.35381320118904114
- 0.3171076774597168
- 0.214978888630867
- 0.2786235809326172
- 0.19925639033317566
- 0.163624569773674
- 0.2072090208530426
- 0.185895174741745
- 0.22331289947032928
- 0.2879233658313751
- 0.32632938027381897
- 0.35732847452163696
- 0.2702403664588928
- 0.2566107511520386
- 0.19432830810546875
- 0.15343080461025238
- 0.20222099125385284
- 0.13304749131202698
- 0.05277668684720993
- -0.07643222063779831
- -0.028486797586083412
- -0.06416790932416916
- -0.06962753087282181
- -0.11227447539567947
- -0.1221967339515686
- -0.16900566220283508
- -0.18083356320858002
- -0.12510593235492706
- -0.20988672971725464
- -0.1962517350912094
- -0.16290713846683502
- -0.25777187943458557
- -0.30785930156707764
- -0.3446635603904724
- -0.276061087846756
- -0.21626996994018555
- -0.2429492175579071
- -0.2969788610935211
- -0.2533876895904541
- -0.18988490104675293
- -0.23057228326797485
- -0.27699726819992065
- -0.166310653090477
- -0.3238593637943268
- -0.3475249409675598
- -0.2984049320220947
- -0.2591678500175476
- -0.33381229639053345
- -0.28111591935157776
- -0.2765443027019501
- -0.2617335617542267
- -0.35026833415031433
- -0.3533570468425751
- -0.10504872351884842
- -0.44001078605651855
- -0.5989624857902527
- -0.330731600522995
- -0.599812924861908
- -0.5182075500488281
- -0.5848872661590576
- -0.56633460521698
- -0.5030263066291809
- -0.3097822666168213
- -0.5560271143913269
- -0.6050411462783813
- -0.9396539330482483
- -1.6205432415008545
spec_min:
- -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
- -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
- -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
- -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
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: 1000
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: /content/drive/MyDrive/diff-svc/duckaloid