Live data from Hacker News

Llama-Scan: Convert PDFs to Text W Local LLMs

github.com

11–20 of 86 posts

Re: Llama-Scan: Convert PDFs to Text W Local LLMs

#11
By 1990 Omnipage 3 and its successors were 'good enough' and with their compact dictionaries and letter form recognition were miracles of their time at ~300MB installed.

In 2025 LLMs can 'fake it' using Trilobites of memory and Petaflops. It's funny actually, like a supercomputer being emulated in real time on a really fast Jacquard loom. By 2027 even simple hand held calculator addition will be billed in kilowatt-hours.

Re: Llama-Scan: Convert PDFs to Text W Local LLMs

#14

Looking at the code, this converts PDF pages to images, then transcribes each image. I might have expected a pdftotext post-processor. The complexity of PDF I guess ...

Saw this tweet the other day that helped me understand just how crazy PDF parsing can be

https://threadreaderapp.com/thread/1955355127818358929.html

Re: Llama-Scan: Convert PDFs to Text W Local LLMs

#18

I presume this doesn't handle handwriting. Does anyone have a suggestion for locally converting PDFs of handwriting into text, say on a recent Mac? Use case would be converting handwritten journals and daily note-taking.

+1. I have tried a bunch of local models (albeit the smaller end, b/c hardware limits), and I can't get handwriting recognition yet. But online Gemini and Claude do great. Hoping the local models catch up soon, as this is a wonderful LLM use case.

UPDATE: I just tried this with the default model on handwriting, and IT WORKED. Took about 5-10 minutes on my laptop, but it worked. I am so thrilled not to have to send my personal jottings into the cloud!

Re: Llama-Scan: Convert PDFs to Text W Local LLMs

#19

I presume this doesn't handle handwriting. Does anyone have a suggestion for locally converting PDFs of handwriting into text, say on a recent Mac? Use case would be converting handwritten journals and daily note-taking.

This one should handle handwriting - it's using Qwen 2.5 VL which is a vision LLM that is very good at handwritten text.

Re: Llama-Scan: Convert PDFs to Text W Local LLMs

#20

I presume this doesn't handle handwriting. Does anyone have a suggestion for locally converting PDFs of handwriting into text, say on a recent Mac? Use case would be converting handwritten journals and daily note-taking.

Author here, I tested it with this PDF of a handwritten doc [1], and it converted both pages accurately.

1. https://github.com/pnshiralkar/text-to-handwriting/blob/mast...

Post reply on HN