processor_config.json

{
  "feature_extractor": {
    "chunk_length": 30,
    "dither": 0.0,
    "feature_extractor_type": "WhisperFeatureExtractor",
    "feature_size": 128,
    "hop_length": 160,
    "image_mean": [
      0.5,
      0.5,
      0.5
    ],
    "image_processor_type": "Qwen2VLImageProcessor",
    "image_std": [
      0.5,
      0.5,
      0.5
    ],
    "max_pixels": 12845056,
    "merge_size": 2,
    "min_pixels": 3136,
    "n_fft": 400,
    "n_samples": 480000,
    "nb_max_frames": 3000,
    "padding_side": "right",
    "padding_value": 0.0,
    "patch_size": 16,
    "processor_class": "Qwen3OmniMoeProcessor",
    "return_attention_mask": true,
    "sampling_rate": 16000,
    "temporal_patch_size": 2
  },
  "image_processor": {
    "crop_size": null,
    "data_format": "channels_first",
    "device": null,
    "disable_grouping": null,
    "dither": 0.0,
    "do_center_crop": null,
    "do_convert_rgb": true,
    "do_normalize": true,
    "do_pad": null,
    "do_rescale": true,
    "do_resize": true,
    "feature_size": 128,
    "hop_length": 160,
    "image_mean": [
      0.5,
      0.5,
      0.5
    ],
    "image_processor_type": "Qwen2VLImageProcessorFast",
    "image_std": [
      0.5,
      0.5,
      0.5
    ],
    "input_data_format": null,
    "max_pixels": 12845056,
    "merge_size": 2,
    "min_pixels": 3136,
    "n_fft": 400,
    "n_samples": 4800000,
    "nb_max_frames": 30000,
    "pad_size": null,
    "padding_side": "right",
    "padding_value": 0.0,
    "patch_size": 16,
    "processor_class": "Qwen3OmniMoeProcessor",
    "resample": 3,
    "rescale_factor": 0.00392156862745098,
    "return_attention_mask": true,
    "return_tensors": null,
    "sampling_rate": 16000,
    "size": {
      "longest_edge": 12845056,
      "shortest_edge": 3136
    },
    "temporal_patch_size": 2
  },
  "processor_class": "Qwen3OmniMoeProcessor",
  "video_processor": {
    "crop_size": null,
    "data_format": "channels_first",
    "default_to_square": true,
    "device": null,
    "dither": 0.0,
    "do_center_crop": null,
    "do_convert_rgb": true,
    "do_normalize": true,
    "do_pad": null,
    "do_rescale": true,
    "do_resize": true,
    "do_sample_frames": false,
    "feature_extractor_type": "WhisperFeatureExtractor",
    "feature_size": 128,
    "fps": null,
    "hop_length": 160,
    "image_mean": [
      0.5,
      0.5,
      0.5
    ],
    "image_std": [
      0.5,
      0.5,
      0.5
    ],
    "input_data_format": null,
    "max_frames": 768,
    "max_pixels": 12845056,
    "merge_size": 2,
    "min_frames": 4,
    "min_pixels": 3136,
    "n_fft": 400,
    "n_samples": 4800000,
    "nb_max_frames": 30000,
    "num_frames": null,
    "pad_size": null,
    "padding_side": "right",
    "padding_value": 0.0,
    "patch_size": 16,
    "processor_class": "Qwen3OmniMoeProcessor",
    "resample": 3,
    "rescale_factor": 0.00392156862745098,
    "return_attention_mask": true,
    "return_metadata": false,
    "return_tensors": null,
    "sampling_rate": 16000,
    "size": {
      "longest_edge": 12845056,
      "shortest_edge": 3136
    },
    "temporal_patch_size": 2,
    "video_metadata": null,
    "video_processor_type": "Qwen2VLVideoProcessor"
  }
}