xcodec2

Papers using or citing this model 1

• Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis 128 citations · 2025 · arXiv (Cornell University) · arXiv

  Recent advances in text-based large language models (LLMs), particularly in the GPT series and the o1 model, have demonstrated the effectiveness of scaling both training-time and inference-time compute. However, current state-of-the-art...