processor_config.json

{
  "audio_token": "<|unused_200053|>",
  "audio_bos_token": "<|content_audio_input|>",
  "dmel_max_value": 2.0,
  "dmel_min_value": -7.0,
  "feature_extractor": {
    "audio_token_duration_s": 0.05,
    "feature_extractor_type": "InklingFeatureExtractor",
    "feature_size": 80,
    "hop_length": 800,
    "n_fft": 1600,
    "padding_side": "right",
    "padding_value": 0.0,
    "return_attention_mask": true,
    "sampling_rate": 16000,
    "window_size": 1600,
    "window_size_multiplier": 2.0
  },
  "image_processor": {
    "do_convert_rgb": true,
    "do_normalize": true,
    "do_rescale": true,
    "do_resize": true,
    "image_mean": [
      0.48145466,
      0.4578275,
      0.40821073
    ],
    "image_processor_type": "InklingImageProcessor",
    "image_std": [
      0.26862954,
      0.26130258,
      0.27577711
    ],
    "resample": 3,
    "rescale_factor": 0.00392156862745098,
    "size": {
      "height": 40,
      "width": 40
    }
  },
  "image_token": "<|unused_200054|>",
  "image_bos_token": "<|content_image|>",
  "num_dmel_bins": 16,
  "processor_class": "InklingProcessor"
}