train:

batch_size: 18

lr: 0.00003

weight_decay: 0.00

num_workers: 64

gpus: 2 #ddp

opt_eps: 1e-9

beta1: 0.5

beta2: 0.999

data:

dir: '/DATA1/VCTK/VCTK-Corpus/wav48' #dir/spk/format

format: '*mic1.pt'

cv_ratio: (100./108., 8./108., 0.00) #train/val/test

audio:

sr: 48000

nfft: 1024

hop: 256

ratio: 2 #upscale_ratio

length: 32768 #32*1024 ~ 1sec

arch:

residual_layers: 30 #

residual_channels: 64

dilation_cycle_length: 10

pos_emb_dim: 512

ddpm:

max_step: 1000

noise_schedule: "torch.linspace(1e-6, 0.006, hparams.ddpm.max_step)"

pos_emb_scale: 50000

pos_emb_channels: 128

infer_step: 8

infer_schedule: "torch.tensor([1e-6,2e-6,1e-5,1e-4,1e-3,1e-2,1e-1,9e-1])"

log:

name: 'nuwave_x2'

checkpoint_dir: 'checkpoint'

tensorboard_dir: 'tensorboard'

test_result_dir: 'test_sample/result'