audio_vae/config.json

{
  "audio_vae": {
    "model": {
      "params": {
        "ddconfig": {
          "double_z": true,
          "mel_bins": 64,
          "z_channels": 8,
          "resolution": 256,
          "downsample_time": false,
          "in_channels": 2,
          "out_ch": 2,
          "ch": 128,
          "ch_mult": [
            1,
            2,
            4
          ],
          "num_res_blocks": 2,
          "attn_resolutions": [],
          "dropout": 0.0,
          "mid_block_add_attention": false,
          "norm_type": "pixel",
          "causality_axis": "height"
        },
        "sampling_rate": 16000
      }
    },
    "preprocessing": {
      "audio": {
        "sampling_rate": 16000,
        "max_wav_value": 32768.0,
        "duration": 5.12,
        "stereo": true,
        "causal_padding": 3
      },
      "stft": {
        "filter_length": 1024,
        "hop_length": 160,
        "win_length": 1024,
        "causal": true
      },
      "mel": {
        "n_mel_channels": 64,
        "mel_fmin": 0,
        "mel_fmax": 8000
      }
    }
  },
  "_class_name": "LTX2AudioDecoder"
}