PyTorch
ONNX
vocoder
mel
vocos
hifigan
tts
vocos-mel-22khz / config.yaml
wetdog's picture
Upload config.yaml
ddd22f9 verified
raw
history blame
558 Bytes
# pytorch_lightning==1.8.6
feature_extractor:
class_path: vocos.feature_extractors.MelSpectrogramFeatures
init_args:
sample_rate: 22050
n_fft: 1024
hop_length: 256
n_mels: 80
padding: same
f_min: 0
f_max: 8000
norm: "slaney"
mel_scale: "slaney"
backbone:
class_path: vocos.models.VocosBackbone
init_args:
input_channels: 80
dim: 512
intermediate_dim: 1536
num_layers: 8
head:
class_path: vocos.heads.ISTFTHead
init_args:
dim: 512
n_fft: 1024
hop_length: 256
padding: same