{
    "llm_models": {
        "sample_rate": 16000,
        "backbone_flavor": "qwen-1.5b",
        "decoder_flavor": "qwen-200m",
        "text_vocab_size": 151936,
        "audio_vocab_size": 2051,
        "audio_num_codebooks": 16,
        "decoder_loss_weight": 0.6
    }
}