checkpoints/acestep-transcriber/preprocessor_config.json

{
  "chunk_length": 300,
  "dither": 0.0,
  "feature_extractor_type": "WhisperFeatureExtractor",
  "feature_size": 128,
  "hop_length": 160,
  "image_mean": [
    0.48145466,
    0.4578275,
    0.40821073
  ],
  "image_processor_type": "Qwen2VLImageProcessor",
  "image_std": [
    0.26862954,
    0.26130258,
    0.27577711
  ],
  "max_pixels": 12845056,
  "merge_size": 2,
  "min_pixels": 3136,
  "n_fft": 400,
  "n_samples": 4800000,
  "nb_max_frames": 30000,
  "padding_side": "right",
  "padding_value": 0.0,
  "patch_size": 14,
  "processor_class": "Qwen2_5OmniProcessor",
  "return_attention_mask": true,
  "sampling_rate": 16000,
  "temporal_patch_size": 2
}