vocoder_config.yaml

feature_extractor:
  class_path: vocos.feature_extractors.MelSpectrogramFeatures
  init_args:
    sample_rate: 24000
    n_fft: 1024
    hop_length: 256
    n_mels: 100
    padding: center

backbone:
  class_path: vocos.models.VocosBackbone
  init_args:
    input_channels: 100
    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: center

head_48k:
  class_path: vocos.heads.ISTFTHead
  init_args:
    dim: 512
    n_fft: 1024
    hop_length: 256
    padding: center

upsampler:
  class_path: linacodec.vocoder.upsampler_block.UpSamplerBlock
  init_args:
    in_channels: 512
    upsample_factors: [2, 1]
    kernel_sizes: [8, 8]