{
  "architectures": [
    "SparkTTSModel"
  ],
  "audio_tokenizer_type": "BiCodec",
  "hidden_size": 896,
  "intermediate_size": 4864,
  "max_audio_length": 30.0,
  "max_new_tokens": 1536,
  "max_position_embeddings": 32768,
  "model_type": "spark-tts",
  "num_attention_heads": 14,
  "num_hidden_layers": 24,
  "rms_norm_eps": 1e-06,
  "sample_rate": 16000,
  "temperature": 0.8,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.52.4",
  "use_cache": true,
  "vocab_size": 152064
}