processor_config.json
| 1 | { |
| 2 | "audio_ms_per_token": 40, |
| 3 | "audio_seq_length": 750, |
| 4 | "feature_extractor": { |
| 5 | "audio_samples_per_token": 640, |
| 6 | "feature_extractor_type": "Gemma4UnifiedAudioFeatureExtractor", |
| 7 | "feature_size": 640, |
| 8 | "padding_side": "right", |
| 9 | "padding_value": 0.0, |
| 10 | "return_attention_mask": true, |
| 11 | "sampling_rate": 16000 |
| 12 | }, |
| 13 | "image_processor": { |
| 14 | "do_convert_rgb": true, |
| 15 | "do_normalize": false, |
| 16 | "do_rescale": true, |
| 17 | "do_resize": true, |
| 18 | "image_mean": [ |
| 19 | 0.0, |
| 20 | 0.0, |
| 21 | 0.0 |
| 22 | ], |
| 23 | "image_processor_type": "Gemma4UnifiedImageProcessor", |
| 24 | "image_std": [ |
| 25 | 1.0, |
| 26 | 1.0, |
| 27 | 1.0 |
| 28 | ], |
| 29 | "max_soft_tokens": 280, |
| 30 | "patch_size": 16, |
| 31 | "pooling_kernel_size": 3, |
| 32 | "resample": 3, |
| 33 | "rescale_factor": 0.00392156862745098 |
| 34 | }, |
| 35 | "image_seq_length": 280, |
| 36 | "processor_class": "Gemma4UnifiedProcessor", |
| 37 | "video_processor": { |
| 38 | "do_convert_rgb": true, |
| 39 | "do_normalize": true, |
| 40 | "do_rescale": true, |
| 41 | "do_resize": true, |
| 42 | "do_sample_frames": true, |
| 43 | "image_mean": [ |
| 44 | 0.0, |
| 45 | 0.0, |
| 46 | 0.0 |
| 47 | ], |
| 48 | "image_std": [ |
| 49 | 1.0, |
| 50 | 1.0, |
| 51 | 1.0 |
| 52 | ], |
| 53 | "max_soft_tokens": 70, |
| 54 | "num_frames": 32, |
| 55 | "patch_size": 16, |
| 56 | "pooling_kernel_size": 3, |
| 57 | "resample": 3, |
| 58 | "rescale_factor": 0.00392156862745098, |
| 59 | "return_metadata": false, |
| 60 | "video_processor_type": "Gemma4UnifiedVideoProcessor" |
| 61 | } |
| 62 | } |
| 63 | |