logoalt Hacker News

lkm0today at 3:06 PM3 repliesview on HN

So I'm trying to OCR 1000s of pages of old french dictionaries from the 1700s, has anything popped up that doesn't cost an arm and a leg, and works pretty decently?


Replies

grumbeltoday at 6:10 PM

I use Gemini for that. Split the PDF into 50 page chunks, throw it into aistudio and ask it to convert it. A couple of 1000 pages can be done with the free tier.

ks2048today at 5:13 PM

Take a look at Mistral, https://mistral.ai/news/mistral-ocr-3

speedgoosetoday at 3:08 PM

Qwen3 VL.

show 1 reply