Ostris
@ostrisai
AI / ML researcher and developer.
Creator of AI Toolkit -
Support my work -
加入 August 2023
338 正在关注 15K 粉丝
Captioning music is difficult. The LLM has to be greedy because you need to be precise, but this makes it susceptible to fall into loops. Lyrics often repeat over and over, which makes it want to loop more. You can penalize this, but that breaks real loops.
显示更多
