{
  "feature_extractor": {
    "feature_extractor_type": "WavTokenizerFeatureExtractor",
    "feature_size": 1,
    "hop_length": 600,
    "padding_side": "right",
    "padding_value": 0.0,
    "return_attention_mask": true,
    "sampling_rate": 24000
  },
  "image_processor": {
    "do_convert_rgb": true,
    "do_normalize": true,
    "do_pad": true,
    "do_rescale": true,
    "do_resize": true,
    "image_mean": [
      0.5,
      0.5,
      0.5
    ],
    "image_processor_type": "Apertus1p5ImageProcessor",
    "image_std": [
      0.5,
      0.5,
      0.5
    ],
    "max_pixels": 1960000,
    "min_pixels": 65536,
    "resample": 3,
    "rescale_factor": 0.00392156862745098,
    "spatial_factor": 16
  },
  "processor_class": "Apertus1p5Processor"
}