moetts / diff_svc /mori /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/mori
check_val_every_n_epoch: 10
choose_test_manually: false
clip_grad_norm: 1
config_path: training/config_nsf.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: 20000
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: 0.0004
max_beta: 0.02
max_epochs: 3000
max_eval_sentences: 1
max_eval_tokens: 60000
max_frames: 42000
max_input_tokens: 60000
max_sentences: 44
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: 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/mori
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: mori
spec_max:
- -0.019330784678459167
- 0.06567800790071487
- 0.228793203830719
- 0.11802903562784195
- 0.10110537707805634
- 0.4689864218235016
- 0.7036661505699158
- 0.8703911900520325
- 0.9361032843589783
- 0.8655202388763428
- 0.7785714864730835
- 0.8148141503334045
- 0.679547131061554
- 0.7320918440818787
- 0.8978622555732727
- 0.784517765045166
- 0.7389000058174133
- 0.9378820657730103
- 0.924305260181427
- 0.9783570766448975
- 0.9135251045227051
- 1.0022618770599365
- 1.0694200992584229
- 1.1138495206832886
- 1.089599609375
- 1.2263946533203125
- 1.1603796482086182
- 1.1704267263412476
- 1.1352192163467407
- 0.9894201159477234
- 0.8867910504341125
- 1.1269314289093018
- 1.0692254304885864
- 1.0560897588729858
- 0.9916731119155884
- 0.8903139233589172
- 0.8455407619476318
- 0.8520137071609497
- 0.9605215787887573
- 0.816070556640625
- 0.9223976731300354
- 0.5765433311462402
- 0.7290225625038147
- 0.5933732986450195
- 0.5727764964103699
- 0.7514742016792297
- 0.4809681475162506
- 0.4641554355621338
- 0.5157797336578369
- 0.5645105838775635
- 0.6428343057632446
- 0.5405521392822266
- 0.473175972700119
- 0.44530436396598816
- 0.4342418909072876
- 0.44113707542419434
- 0.49833279848098755
- 0.48190838098526
- 0.44705429673194885
- 0.3638623356819153
- 0.30654290318489075
- 0.4154691696166992
- 0.34633904695510864
- 0.35942935943603516
- 0.39546000957489014
- 0.2380419671535492
- 0.328754723072052
- 0.3026845455169678
- 0.24524439871311188
- 0.25909164547920227
- 0.1833379566669464
- 0.14229395985603333
- 0.200522318482399
- 0.15264283120632172
- 0.1986929476261139
- 0.060403868556022644
- 0.0036014982033520937
- 0.12869416177272797
- 0.05505308136343956
- -0.031196756288409233
- -0.0574474036693573
- -0.0543854720890522
- -0.036599062383174896
- -0.06735989451408386
- -0.09748432785272598
- 0.00449156342074275
- 0.05749598145484924
- 0.08902159333229065
- -0.11218735575675964
- -0.011491273529827595
- -0.11833566427230835
- -0.010254009626805782
- -0.06703109294176102
- -0.09058596193790436
- -0.039965495467185974
- -0.10134681314229965
- 0.07939088344573975
- 0.13496151566505432
- -0.002308185212314129
- 0.18585674464702606
- -0.03961731120944023
- -0.1287146657705307
- -0.22040295600891113
- -0.23626138269901276
- -0.17821004986763
- -0.04868573695421219
- -0.11022017896175385
- -0.23770904541015625
- -0.1830531656742096
- -0.2001497745513916
- -0.3840283453464508
- -0.32347947359085083
- -0.12253516912460327
- -0.22939082980155945
- -0.43113377690315247
- -0.3798638880252838
- -0.23814789950847626
- -0.39345860481262207
- -0.4185469448566437
- -0.5147720575332642
- -0.5336534380912781
- -0.6215676665306091
- -0.6951723098754883
- -0.7364555597305298
- -0.7716941833496094
- -0.7262001633644104
- -0.8554714918136597
- -0.9651122093200684
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:
- 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.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/mori