Hacker News Reader

Comment by lozenge | Hacker News Reader

Err, 16 hours just to read. Then you still need to deal with the inaccuracies of speech to text.

Have 4 people do it and you're done by lunch.

If their handwriting is like mine, i think it will take more time that way. The other people will be interrupting them every second to ask “what’s that word?”.

Eventually, they’ll learn and speed will go up, but with this amount of work, work will be finished before they make up for the learning curve.

Modern speech to text is, for me, extremely accurate. You also have the original audio and can rerun things as and when technology improves.

Yea, I use a cheapie voice recorder that only saves .wav files for ~10 memos per day, and Whisper transcripts are good. "Tiny" model, 4GB ram laptop. "Base" model runs too, but slower, and produces different inaccuracies.

But overall, if I were suggest an ideal process: 1) transcribe notes w/ Whisper, 2) play back the media in VLC with the transcripts and correct the errors. T = 16 hours of proofing/correction + ~8 hours of headless transcription of *.wav before hand.

I’d add that I had better luck using smaller chunks (about 20 seconds) per wav file for accuracy. Whisper seems to go berserk if you pump in lengthy audio (30+ seconds).

I’d be tempted to at least try breaking down the notes into one line long images (about a sentence) each and give it ago with Gemini. I haven’t tested their ocr, but even if it has errors, I bet you could just ask Gemini again to best fix the sentence.

Whisper works on 30s chunks iirc. You need to use something that's automatically splitting up your input if it's longer.

Do it over 2 weekends. Or an hour a night instead of TV.

Since OP is doing this deliberately for speech2text they will presumably enunciate very clearly and have a good mic. S2T has very good performance under ideal conditions like that

so what? it's 10 years of notes. even if you double or triple or quadruple the time editing it for inaccuracies it's still better than an ocr almost certainly.

Reply on news.ycombinator.com