processor_config.json

{
  "feature_extractor": {
    "feature_extractor_type": "PeAudioFeatureExtractor",
    "feature_size": 1,
    "hop_length": 1920,
    "padding_side": "right",
    "padding_value": 0.0,
    "processor_class": "PeAudioVideoProcessor",
    "return_attention_mask": true,
    "sampling_rate": 48000
  },
  "processor_class": "PeAudioVideoProcessor",
  "video_processor": {
    "crop_size": null,
    "data_format": "channels_first",
    "default_to_square": true,
    "device": null,
    "do_center_crop": null,
    "do_convert_rgb": true,
    "do_normalize": true,
    "do_pad": null,
    "do_rescale": true,
    "do_resize": true,
    "do_sample_frames": true,
    "fps": null,
    "image_mean": [
      0.5,
      0.5,
      0.5
    ],
    "image_std": [
      0.5,
      0.5,
      0.5
    ],
    "input_data_format": null,
    "num_frames": 16,
    "pad_size": null,
    "processor_class": "PeAudioVideoProcessor",
    "resample": 2,
    "rescale_factor": 0.00392156862745098,
    "return_metadata": false,
    "return_tensors": null,
    "size": {
      "height": 336,
      "width": 336
    },
    "video_metadata": null,
    "video_processor_type": "PeVideoVideoProcessor"
  }
}