preprocessor_config.json

{
  "audio_pool_step": 5,
  "auto_map": {
    "AutoFeatureExtractor": "processing_minicpmo.MiniCPMAAudioProcessor",
    "AutoImageProcessor": "processing_minicpmo.MiniCPMVImageProcessor",
    "AutoProcessor": "processing_minicpmo.MiniCPMOProcessor"
  },
  "chunk_length": 30,
  "dither": 0.0,
  "dynamic_log_norm": true,
  "dynamic_range_db": 8.0,
  "feature_extractor_type": "MiniCPMAAudioProcessor",
  "feature_size": 80,
  "hop_length": 160,
  "im_end": "</image>",
  "im_id_end": "</image_id>",
  "im_id_start": "<image_id>",
  "im_start": "<image>",
  "image_feature_size": 64,
  "image_processor_type": "MiniCPMVImageProcessor",
  "log_floor_db": -10.0,
  "max_slice_nums": 9,
  "n_fft": 400,
  "n_samples": 480000,
  "nb_max_frames": 3000,
  "norm_mean": [
    0.5,
    0.5,
    0.5
  ],
  "norm_std": [
    0.5,
    0.5,
    0.5
  ],
  "padding_side": "right",
  "padding_value": 0.0,
  "patch_size": 14,
  "processor_class": "MiniCPMOProcessor",
  "return_attention_mask": false,
  "sampling_rate": 16000,
  "scale_resolution": 448,
  "slice_end": "</slice>",
  "slice_mode": true,
  "slice_start": "<slice>",
  "unk": "<unk>",
  "use_image_id": true,
  "version": 4.5
}