config.yaml

feature_extractor:
  class_path: vocos.feature_extractors.MelSpectrogramFeatures
  init_args:
    sample_rate: 44100
    n_fft: 2048
    hop_length: 512
    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: 2048
    hop_length: 512
    padding: same