News for hackers. Stuff that matters.
Re:Cleaning Up Speech Recognition with GPT by aragonite on Friday April 26, 2024 @09:51PM (#40176388)
I take a lot of long voice notes thinking out loud during my walks. I use this prompt when I give the Whisper output to GPT-4. I've found it to be pretty reliable:

> Punctuate the following transcript of a voice note I took. Insert periods, commas, and paragraph breaks where appropriate. Remove filler words such as 'right?' 'you know', and 'uh'. But do retain my original wording! Do not paraphrase my sentences beyond recognition: this is not a rewriting task! The transcript now follows:

Re:Cleaning Up Speech Recognition with GPT by BeetleB on Friday April 26, 2024 @10:21PM (#40176559)
Thanks! I'll give it a try. My current prompt is much longer (lists many things Whisper misrecognizes so GPT can replace them).

Did not think of telling it to remove filler words, but I find it usually removes them anyway.