Ostris
@ostrisai
AI / ML researcher and developer.
Creator of AI Toolkit -
Support my work -
参加 August 2023
338 フォロー中 15K ファン
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.
もっと見る
