{
  "crop_size": {
    "height": 384,
    "width": 384
  },
  "data_format": "channels_first",
  "image_mean": [
    0.5,
    0.5,
    0.5
  ],
  "image_processor_type": "SigLipImageProcessor",
  "image_std": [
    0.5,
    0.5,
    0.5
  ],
  "processor_class": "Qwen2VLProcessor",
  "resample": 3,
  "rescale_factor": 0.00392156862745098,
  "size": [
    384,
    384
  ],
  "chunk_length": 30,
  "feature_extractor_type": "WhisperFeatureExtractor",
  "feature_size": 128,
  "hop_length": 160,
  "n_fft": 400,
  "n_samples": 480000,
  "nb_max_frames": 3000,
  "padding_side": "right",
  "padding_value": 0.0,
  "return_attention_mask": false,
  "sampling_rate": 16000
}