mitudesk's picture
Duplicate from ulysses115/diffsvc_test
05c77ed
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/raiden
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: 50000
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: checkpoints/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: 0.0012
max_beta: 0.02
max_epochs: 3000
max_eval_sentences: 1
max_eval_tokens: 60000
max_frames: 42000
max_input_tokens: 60000
max_sentences: 48
max_tokens: 128000
max_updates: 260000
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/raiden
ref_norm_layer: bn
rel_pos: true
reset_phone_dict: true
residual_channels: 384
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: raiden
spec_max:
- -0.4759584963321686
- -0.04242899641394615
- 0.2820039689540863
- 0.6635098457336426
- 0.7846556901931763
- 0.9242268800735474
- 1.0596446990966797
- 0.9890199303627014
- 0.8979427218437195
- 0.8635445237159729
- 0.8591453433036804
- 0.6987467408180237
- 0.717823326587677
- 0.7350517511367798
- 0.6464754939079285
- 0.6164345145225525
- 0.4986744523048401
- 0.3543139100074768
- 0.2876613438129425
- 0.3467520773410797
- 0.27083638310432434
- 0.4002445936203003
- 0.4222544729709625
- 0.4776916205883026
- 0.5299767255783081
- 0.6194124817848206
- 0.5802494287490845
- 0.6222044229507446
- 0.6124054193496704
- 0.6688933968544006
- 0.7368689179420471
- 0.7275264859199524
- 0.7448640465736389
- 0.5364857912063599
- 0.5867365002632141
- 0.48127084970474243
- 0.48270556330680847
- 0.45863038301467896
- 0.3647041916847229
- 0.3207940459251404
- 0.3352258801460266
- 0.2846287190914154
- 0.2674693465232849
- 0.3205840587615967
- 0.36074087023735046
- 0.40593528747558594
- 0.266417920589447
- 0.22159256041049957
- 0.19403372704982758
- 0.29326388239860535
- 0.29472747445106506
- 0.3801038861274719
- 0.3864395320415497
- 0.285959392786026
- 0.22213149070739746
- 0.19549456238746643
- 0.22238962352275848
- 0.15776650607585907
- 0.23960433900356293
- 0.3050341308116913
- 0.258531779050827
- 0.19573383033275604
- 0.2259710431098938
- 0.2110864669084549
- 0.24603094160556793
- 0.05981471762061119
- 0.17803697288036346
- 0.17807669937610626
- 0.18952223658561707
- 0.053435735404491425
- 0.1157914251089096
- 0.026514273136854172
- 0.16326436400413513
- 0.22839383780956268
- 0.08631942421197891
- 0.23315998911857605
- 0.162082701921463
- 0.1533375382423401
- 0.12668564915657043
- 0.08644244074821472
- 0.02113831788301468
- 0.3463006615638733
- 0.22695019841194153
- 0.14443305134773254
- 0.20211298763751984
- 0.07295431941747665
- -0.007622874341905117
- -0.02703588828444481
- -0.06394484639167786
- -0.09371187537908554
- -0.005024001933634281
- -0.013857427053153515
- -0.1372852921485901
- -0.10361140221357346
- -0.12665916979312897
- -0.20724378526210785
- -0.2142055779695511
- 0.19261693954467773
- 0.08877495676279068
- -0.21178629994392395
- -0.18947778642177582
- -0.2520659863948822
- -0.22880172729492188
- -0.14105628430843353
- -0.05572707951068878
- -0.26297450065612793
- -0.412873774766922
- -0.35086822509765625
- -0.36454305052757263
- -0.4511951208114624
- -0.3738810122013092
- -0.4491288959980011
- -0.5304299592971802
- -0.4495029151439667
- -0.4343602657318115
- -0.34189438819885254
- -0.5748119950294495
- -0.6650391817092896
- -0.6537092924118042
- -0.8302493691444397
- -0.7430973649024963
- -0.9170511364936829
- -1.0624077320098877
- -1.242630958557129
- -1.163043737411499
- -1.0178996324539185
- -1.4756207466125488
- -1.5275251865386963
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
- -4.9844536781311035
- -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: checkpoints/nsf_hifigan/model
warmup_updates: 2000
wav2spec_eps: 1e-6
weight_decay: 0
win_size: 2048
work_dir: checkpoints/raiden