Faster Speech-LLaMA Inference with Multi-token Prediction.
Desh Raj, Gil Keren, Junteng Jia, Jay Mahadeokar, Ozlem Kalinli
Browse the full ICASSP paper archive.
Desh Raj, Gil Keren, Junteng Jia, Jay Mahadeokar, Ozlem Kalinli
Browse the full ICASSP paper archive.