processor_config.json

{
  "audio_context_size": 3000,
  "audio_padding": "longest",
  "audio_placeholder": "<|audio|>",
  "audio_processor": {
    "auto_map": {
      "AutoProcessor": "ultravox_processing.UltravoxProcessor"
    },
    "chunk_length": 30,
    "dither": 0.0,
    "feature_extractor_type": "WhisperFeatureExtractor",
    "feature_size": 128,
    "hop_length": 160,
    "n_fft": 400,
    "n_samples": 480000,
    "nb_max_frames": 3000,
    "padding_side": "right",
    "padding_value": 0.0,
    "return_attention_mask": false,
    "sampling_rate": 16000
  },
  "auto_map": {
    "AutoProcessor": "ultravox_processing.UltravoxProcessor"
  },
  "encoder_ds_factor": 2,
  "processor_class": "UltravoxProcessor",
  "stack_factor": 8
}