configs/model/audioldm.yaml

########################
# audioldm autoencoder #
########################


audioldm_autoencoder:
  type: audioldm_autoencoder
  args:
    embed_dim: 8
    monitor: val/rec_loss
    ddconfig:
      double_z: True
      z_channels: 8
      resolution: 256
      downsample_time: False
      in_channels: 1
      out_ch: 1
      ch: 128
      ch_mult: [1, 2, 4]
      num_res_blocks: 2
      attn_resolutions: []
      dropout: 0.0
    lossconfig:
      target: torch.nn.Identity