processor_config.json

{
  "feature_extractor": {
    "auto_map": {
      "AutoProcessor": "processing_bidirlm_omni.BidirLMOmniProcessor"
    },
    "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": "Qwen2VLImageProcessorFast",
    "image_std": [
      0.5,
      0.5,
      0.5
    ],
    "merge_size": 2,
    "n_fft": 400,
    "n_samples": 480000,
    "nb_max_frames": 3000,
    "padding_side": "right",
    "padding_value": 0.0,
    "patch_size": 16,
    "return_attention_mask": true,
    "sampling_rate": 16000,
    "size": {
      "longest_edge": 1048576,
      "shortest_edge": 65536
    },
    "temporal_patch_size": 2
  },
  "image_processor": {
    "auto_map": {
      "AutoProcessor": "processing_bidirlm_omni.BidirLMOmniProcessor"
    },
    "chunk_length": 30,
    "dither": 0.0,
    "do_convert_rgb": true,
    "do_normalize": true,
    "do_rescale": true,
    "do_resize": true,
    "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
    ],
    "merge_size": 2,
    "n_fft": 400,
    "n_samples": 480000,
    "nb_max_frames": 3000,
    "padding_side": "right",
    "padding_value": 0.0,
    "patch_size": 16,
    "resample": 3,
    "rescale_factor": 0.00392156862745098,
    "return_attention_mask": true,
    "sampling_rate": 16000,
    "size": {
      "longest_edge": 1048576,
      "shortest_edge": 65536
    },
    "temporal_patch_size": 2
  },
  "processor_class": "ColQwen3OmniProcessor",
  "video_processor": {
    "auto_map": {
      "AutoProcessor": "processing_bidirlm_omni.BidirLMOmniProcessor"
    },
    "data_format": "channels_first",
    "default_to_square": true,
    "do_convert_rgb": true,
    "do_normalize": true,
    "do_rescale": true,
    "do_resize": true,
    "do_sample_frames": true,
    "fps": 2,
    "image_mean": [
      0.5,
      0.5,
      0.5
    ],
    "image_std": [
      0.5,
      0.5,
      0.5
    ],
    "max_frames": 768,
    "merge_size": 2,
    "min_frames": 4,
    "patch_size": 16,
    "resample": 3,
    "rescale_factor": 0.00392156862745098,
    "return_metadata": false,
    "size": {
      "longest_edge": 25165824,
      "shortest_edge": 4096
    },
    "temporal_patch_size": 2,
    "video_processor_type": "Qwen3VLVideoProcessor"
  }
}