Ask HN: How to transcribe 1000s of handwritten notes

Re:Ask HN: How to transcribe 1000s of handwritten notes by harlanji on Sunday June 02, 2024 @11:31AM (#40554949)

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.

[ Parent | on HN ]

Re:Ask HN: How to transcribe 1000s of handwritten notes by neverokay on Sunday June 02, 2024 @01:00PM (#40555572)

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.

[ Parent | on HN ]

Re:Ask HN: How to transcribe 1000s of handwritten notes by IanCal on Thursday June 06, 2024 @07:37AM (#40596225)

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

[ Parent | on HN ]