preprocessor_config.json

{
  "audio_compression_rate": 8,
  "audio_downsample_rate": 1,
  "audio_feat_stride": 1,
  "auto_map": {
    "AutoFeatureExtractor": "feature_extraction_phi4_multimodal.Phi4MultimodalFeatureExtractor",
    "AutoImageProcessor": "image_processing_phi4_multimodal_fast.Phi4MultimodalImageProcessorFast",
    "AutoProcessor": "processing_phi4_multimodal.Phi4MultimodalProcessor"
  },
  "feature_extractor_type": "Phi4MultimodalFeatureExtractor",
  "feature_size": 80,
  "hop_length": 160,
  "n_fft": 512,
  "padding_side": "right",
  "padding_value": 0.0,
  "preemphasis": 0.97,
  "processor_class": "Phi4MultimodalProcessor",
  "return_attention_mask": true,
  "sampling_rate": 16000,
  "win_length": 400
}