moetts / diff_svc /sena441 /config.yaml
luoyi
sort files
8a599b3
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/sena
check_val_every_n_epoch: 10
choose_test_manually: true
clip_grad_norm: 1
config_path: training/config_nsf_sena.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: 10000
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: ckpt/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: 128
max_tokens: 42000
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: ckpt/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/sena
ref_norm_layer: bn
rel_pos: true
reset_phone_dict: true
residual_channels: 512
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: sena
spec_max:
- 0.17097608745098114
- 0.3397301733493805
- 0.6082707047462463
- 0.7658080458641052
- 0.9264223575592041
- 1.1378915309906006
- 1.2659214735031128
- 1.231523036956787
- 1.2456761598587036
- 1.2685513496398926
- 1.1583133935928345
- 1.1537851095199585
- 1.2560111284255981
- 1.1849987506866455
- 1.1610959768295288
- 1.2605981826782227
- 1.226485013961792
- 1.1268006563186646
- 1.137515664100647
- 1.177683711051941
- 1.170212745666504
- 1.1891556978225708
- 1.204882025718689
- 1.151033878326416
- 1.1880069971084595
- 1.2375954389572144
- 1.1038519144058228
- 1.1212972402572632
- 1.197728157043457
- 1.1437523365020752
- 1.0745612382888794
- 1.1244035959243774
- 1.1003185510635376
- 1.106966257095337
- 1.1127562522888184
- 1.0868451595306396
- 1.0899468660354614
- 1.0303136110305786
- 1.04606294631958
- 1.03463876247406
- 1.016716480255127
- 1.0034751892089844
- 1.0667635202407837
- 1.0440107583999634
- 0.9983909130096436
- 0.9837781190872192
- 0.9780927300453186
- 0.9547947645187378
- 1.0833947658538818
- 1.0186176300048828
- 1.0262666940689087
- 0.9818507432937622
- 0.9809918403625488
- 0.9516422748565674
- 0.9858482480049133
- 0.8438718914985657
- 0.9086287617683411
- 0.8336443901062012
- 0.8408522009849548
- 0.7966897487640381
- 0.7060108184814453
- 0.6853682398796082
- 0.6755683422088623
- 0.6235848665237427
- 0.6333395838737488
- 0.6069809198379517
- 0.5742683410644531
- 0.665706217288971
- 0.6048570275306702
- 0.7021833062171936
- 0.7196664810180664
- 0.5961004495620728
- 0.5049697756767273
- 0.49245569109916687
- 0.5433599352836609
- 0.6448594331741333
- 0.731346607208252
- 0.524942934513092
- 0.44391942024230957
- 0.5200350880622864
- 0.4035450220108032
- 0.4356535077095032
- 0.49859124422073364
- 0.48476505279541016
- 0.5568605661392212
- 0.45708560943603516
- 0.4374412000179291
- 0.45580312609672546
- 0.4294637441635132
- 0.3111153542995453
- 0.2814539670944214
- 0.2886189818382263
- 0.2661425471305847
- 0.20193226635456085
- 0.38692978024482727
- 0.3419096767902374
- 0.48901742696762085
- 0.4254615008831024
- 0.38061267137527466
- 0.35519418120384216
- 0.35050907731056213
- 0.5192219018936157
- 0.4214952886104584
- 0.4718898832798004
- 0.428811639547348
- 0.5504823327064514
- 0.5378233194351196
- 0.49835407733917236
- 0.40051230788230896
- 0.34427186846733093
- 0.46247372031211853
- 0.3569100499153137
- 0.4144101142883301
- 0.4045094847679138
- 0.45712941884994507
- 0.43897101283073425
- 0.47350218892097473
- 0.5039759874343872
- 0.4046401381492615
- 0.354009747505188
- 0.3337729573249817
- 0.3514827489852905
- 0.19709141552448273
- 0.09294259548187256
- -0.09443746507167816
- 0.13250915706157684
- -0.014945651404559612
- -0.06271237879991531
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:
- data\raw\sena\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.nsf_hifigan.NsfHifiGAN
vocoder_ckpt: ckpt/nsf_hifigan/model
warmup_updates: 2000
wav2spec_eps: 1e-6
weight_decay: 0
win_size: 2048
work_dir: ckpt/sena