Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis — mentioned by ks2048

Thu, 01 May 2025 20:03:23 GMT

Odd that the page doesn't seem to link to either, paper: https://arxiv.org/abs/2502.04128 github: https://github.com/zhenye234/LLaSA_training

Paper and discussion history. A mention is not an endorsement.

Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis · HackerPapers discussions