←back to thread

Llama-OCR: Document to Markdown

(llamaocr.com)
293 points lapnect | 1 comments | 16 Nov 24 04:57 UTC | HN request time: 0.212s | source
Show context
notsylver ◴[16 Nov 24 06:34 UTC] No.42154841[source]▶
I've been doing a lot of OCR recently, mostly digitising text from family photos. Normal OCR models are terrible at it, LLMs do far better. Gemini Flash came out on top from the models I tested and it wasn't even close. It still had enough failures and hallucinations to make it faster to write it in by hand. Annoying considering how close it feels to working.

This seems worse. Sometimes it replies with just the text, sometimes it replies with a full "The image is a scanned document with handwritten text...". I was hoping for some fine tuning or something for it to beat Gemini Flash, it would save me a lot of time. :(

replies(7): >>42154901 #>>42155002 #>>42155087 #>>42155372 #>>42155438 #>>42156428 #>>42156646 #
og_kalu ◴[16 Nov 24 06:50 UTC] No.42154901[source]▶
>Normal OCR models are terrible at it, LLMs do far better. Gemini Flash came out on top from the models I tested and it wasn't even close.

For Normal models, the state of Open Source OCR is pretty terrible. Unfortunately, the closed options from Microsoft, Google etc are much better. Did you try those ?

Interesting about Flash, what LLMs did you test ?

replies(2): >>42155032 #>>42156731 #
1. pbhjpbhj ◴[16 Nov 24 14:56 UTC] No.42156731[source]▶
The OCR in OneNote is incredible IME. But, I've not tested in a wide range of fonts -- only that I have abysmal handwriting and it will find words that are almost unrecognisable.