News for hackers. Stuff that matters.
Re:Show HN: Self-host Whisper As a Service with GUI and queu... by graderjs on Monday February 13, 2023 @11:23AM (#34775561)
Can you not separate into two phases? Speech separation to get source per speaker, and then whisper on each in isolation (maybe interlacing prompts)?

There are no comments on this comment yet.