{
  "transformer": {"dim": 1536, "heads": 24, "ff_mult": 2, "text_hidden_dim": 2048, "latent_dim": 64, "num_layers": 10, "num_single_layers": 20},
  "vae": {
    "upsample_rates": [5, 4, 3, 2, 2, 2], "upsample_kernel_sizes": [10, 8, 6, 4, 4, 4], "upsample_initial_channel": 1536,
    "resblock_kernel_sizes": [3, 7, 11], "resblock_dilation_sizes": [[1, 3, 5], [1, 3, 5], [1, 3, 5]],
    "downsample_rates": [2, 2, 2, 3, 4, 5], "downsample_channels": [12, 24, 48, 96, 192, 384, 768],
    "snake_logscale": true, "latent_dim": 64, "use_vae": true, "causal": true, "flow_hidden_channels": 256, "act_causal": true
  }
}
