AudioVisual-Caption/ASID-Captioner-3B

1{2  "chunk_length": 300,3  "dither": 0.0,4  "feature_extractor_type": "WhisperFeatureExtractor",5  "feature_size": 128,6  "hop_length": 160,7  "image_mean": [8    0.48145466,9    0.4578275,10    0.4082107311  ],12  "image_processor_type": "Qwen2VLImageProcessor",13  "image_std": [14    0.26862954,15    0.26130258,16    0.2757771117  ],18  "max_pixels": 12845056,19  "merge_size": 2,20  "min_pixels": 3136,21  "n_fft": 400,22  "n_samples": 4800000,23  "nb_max_frames": 30000,24  "padding_side": "right",25  "padding_value": 0.0,26  "patch_size": 14,27  "processor_class": "Qwen2_5OmniProcessor",28  "return_attention_mask": true,29  "sampling_rate": 16000,30  "temporal_patch_size": 231}32