milky-green-diff-svc / config.yaml
sparanoid's picture
Upload config.yaml
1ad6484
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/mqnl-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/mqnl-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: mqnl-covers
spec_max:
- 0.11258526891469955
- 0.029963258653879166
- 0.25167587399482727
- 0.3379969000816345
- 0.4209271967411041
- 0.4627160131931305
- 0.41560280323028564
- 0.3913577198982239
- 0.34750282764434814
- 0.29936230182647705
- 0.32207849621772766
- 0.3448757231235504
- 0.3113778233528137
- 0.35317060351371765
- 0.4166089594364166
- 0.3650610148906708
- 0.2879890203475952
- 0.21680839359760284
- 0.2509251832962036
- 0.25092849135398865
- 0.24402980506420135
- 0.28403371572494507
- 0.32604289054870605
- 0.3334726393222809
- 0.38054946064949036
- 0.41315314173698425
- 0.2945516109466553
- 0.350572794675827
- 0.4011584222316742
- 0.1728031039237976
- 0.17655976116657257
- 0.1981496810913086
- 0.11094453185796738
- 0.23602479696273804
- 0.06451099365949631
- 0.24015556275844574
- 0.01039820071309805
- 0.038468487560749054
- -0.03273174166679382
- 0.015290342271327972
- -0.0906442329287529
- -0.19544707238674164
- -0.03575506806373596
- -0.10758063197135925
- -0.12621892988681793
- -0.2831754982471466
- -0.2826099097728729
- -0.08007119596004486
- 0.09162873029708862
- -0.01513915229588747
- -0.131241112947464
- -0.2449709177017212
- -0.3528900146484375
- -0.2924903929233551
- -0.15330247581005096
- -0.1724396049976349
- -0.19285175204277039
- -0.11945571005344391
- -0.25330424308776855
- -0.27141112089157104
- -0.24878466129302979
- -0.18733099102973938
- -0.20597964525222778
- -0.23352883756160736
- -0.17950132489204407
- -0.24911648035049438
- -0.5155487656593323
- -0.49901074171066284
- -0.6347367763519287
- -0.7135335206985474
- -0.7645825743675232
- -0.8687030673027039
- -0.7830072641372681
- -0.7961702346801758
- -0.731216549873352
- -0.840649425983429
- -0.7183194756507874
- -0.663295328617096
- -1.1195011138916016
- -2.001723051071167
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
- -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
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/mqnl-covers