processor_config.json

{
  "audio_end_token": "<|audio_end|>",
  "audio_length_per_tok": 8,
  "audio_start_token": "<|audio_start|>",
  "audio_token": "<|audio_pad|>",
  "chunk_audio": true,
  "downsample_factor": 4,
  "feature_extractor": {
    "feature_extractor_type": "VoxtralRealtimeFeatureExtractor",
    "feature_size": 128,
    "global_log_mel_max": 1.5,
    "hop_length": 160,
    "n_fft": 400,
    "padding_side": "right",
    "padding_value": 0.0,
    "return_attention_mask": true,
    "sampling_rate": 16000,
    "win_length": 400
  },
  "image_processor": {
    "do_convert_rgb": true,
    "do_normalize": true,
    "do_rescale": true,
    "do_resize": true,
    "image_mean": [
      0.5,
      0.5,
      0.5
    ],
    "image_processor_type": "Qwen2VLImageProcessor",
    "image_std": [
      0.5,
      0.5,
      0.5
    ],
    "max_pixels": 360448,
    "merge_size": 2,
    "min_pixels": 28800,
    "patch_size": 16,
    "resample": 3,
    "rescale_factor": 0.00392156862745098,
    "size": {
      "longest_edge": 360448,
      "shortest_edge": 28800
    },
    "temporal_patch_size": 2
  },
  "image_token": "<|image_pad|>",
  "processor_class": "AeroRealtimeProcessor",
  "rt_end_token": "<|rt_end|>",
  "rt_pad_token": "<|rt_pad|>",
  "rt_speak_token": "<|rt_speak|>",
  "rt_start_token": "<|rt_start|>",
  "video_processor": {
    "do_convert_rgb": true,
    "do_normalize": true,
    "do_rescale": true,
    "do_resize": true,
    "do_sample_frames": true,
    "fps": 2,
    "image_mean": [
      0.5,
      0.5,
      0.5
    ],
    "image_std": [
      0.5,
      0.5,
      0.5
    ],
    "max_frames": 768,
    "max_pixels": 360448,
    "merge_size": 2,
    "min_frames": 4,
    "min_pixels": 28800,
    "patch_size": 16,
    "resample": 3,
    "rescale_factor": 0.00392156862745098,
    "return_metadata": false,
    "size": {
      "longest_edge": 25165824,
      "shortest_edge": 4096
    },
    "temporal_patch_size": 2,
    "video_processor_type": "Qwen3VLVideoProcessor"
  },
  "video_token": "<|video_pad|>",
  "vision_end_token": "<|vision_end|>",
  "vision_start_token": "<|vision_start|>"
}