preprocessor_config.json

{
  "crop_size": null,
  "data_format": "channels_first",
  "default_to_square": false,
  "device": null,
  "dither": 0.0,
  "do_center_crop": null,
  "do_convert_rgb": null,
  "do_normalize": false,
  "do_rescale": true,
  "do_resize": true,
  "feature_extractor_type": "Gemma3nAudioFeatureExtractor",
  "feature_size": 128,
  "fft_length": 1024,
  "fft_overdrive": true,
  "frame_length": 512,
  "hop_length": 160,
  "image_mean": [
    0.5,
    0.5,
    0.5
  ],
  "image_processor_type": "SiglipImageProcessorFast",
  "image_seq_length": 256,
  "image_std": [
    0.5,
    0.5,
    0.5
  ],
  "input_data_format": null,
  "input_scale_factor": 1.0,
  "max_frequency": 7600.0,
  "mel_floor": 1e-05,
  "min_frequency": 125.0,
  "padding_side": "right",
  "padding_value": 0.0,
  "per_bin_mean": null,
  "per_bin_stddev": null,
  "preemphasis": 0.97,
  "preemphasis_htk_flavor": true,
  "processor_class": "Gemma3nProcessor",
  "resample": 2,
  "rescale_factor": 0.00392156862745098,
  "return_attention_mask": false,
  "return_tensors": null,
  "sampling_rate": 16000,
  "size": {
    "height": 768,
    "width": 768
  }
}