Having worked with Whisper for quite some time now, it's true that hallucinations can be a real pain point. Long pauses between sentences / silence and background noise make it worse, among other factors. Good news is, there are ways to mitigate and solve this.
> if these transcriptions are used in the context of AI-based hiring, in courtroom trials or patient notes in medical settings
I expect courtroom trials to listen to the actual sound. But I'm worried and ininteligible part may be magicaly "translated" by the AI to a death threat.
About medical notes, in a recent task they asked me the same thing like 5 times by different doctors. It didn't look like they were double checking, but just not reading the previous notes.
I expect courtroom trials to listen to the actual sound. But I'm worried and ininteligible part may be magicaly "translated" by the AI to a death threat.
About medical notes, in a recent task they asked me the same thing like 5 times by different doctors. It didn't look like they were double checking, but just not reading the previous notes.