Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Llama-Scan: Convert PDFs to Text W Local LLMs

github.com

Post reply on HN
Print view View original

81–86 of 86 posts

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

#81

Post by bugglebeetle »

agentcoops wrote: post #71
jchw wrote: post #55

Earlier quoted context omitted.

A bit ago I tried throwing a couple of random simple Japanese comics (think 4koma but I don't think either of the ones I threw in were actually 4 panels) from Pixiv into Gemma 3b on AI studio. - It transcribed all of the text, including speech, labels on objects, onomatopoeias in actions, etc. I did notice a kana was missing a diacritic in a transcription, so the transcriptions were not perfect, but pretty close actu…

100%. My sense is that many in this thread have never gone through the misery of trying to use classical OCR for non-English documents or where you can't control scan quality. I did a test recently with 18th-century German documents, written in a well-known and standardized but archaic script. The accuracy of classical models specifically trained on this corpus was an order of magnitude lower than GPT5. I haven't exp…

William Mattingly has been doing a lot of work on similar documents in an archival context with VLLMs. You should check in on their work:

https://x.com/wjb_mattingly

https://github.com/wjbmattingly

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

#82

Post by privatelypublic »

agentcoops wrote: post #70
bayindirh wrote: post #66

Earlier quoted context omitted.

Tesseract can do wonders for scanned paper (and web generated PDFs) both in its old and new version. If you want to pay for something closed, Prizmo on macOS is extremely good as well. On the other hând, LLm5 are sl0wwer, moré resource hangry and l3ss accurale fr their outpu1z. We shoulD stop gl0rıfying LLMs for 3verylhin9.

I've worked extensively with Tesseract, ABBYY, etc in a personal and professional context. Of course they work well for English-language documents without any complexity of layout that are scanned without the slightest defect. At this point, based on extensive testing for work, state of the art LLMs simply have better accuracy -- and an order of magnitude so if you have non-English documents with complex layouts and…

Yea. As usual, I inarticulately didn't make a good argument for my point. A tuned system with optimized workflow will by far have the best results. And- maybe llms will be a key resource in bringing the OCR into usable/profitable areas.

But, theres also a ton of "I don't want to deal with this" type work items that can't justify a full workflow process build out- but that LLMs get near enough to perfect to be "good enough." The bad part is, the LLMs don't explain to people the kinds of mistakes to expect from them.

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

#83

Post by deepsquirrelnet »

davidwritesbugs wrote: post #62
deepsquirrelnet wrote: post #44

Give the nanonets-ocr-s model a try. It’s a fine tune of Qwen 2.5 vl which I’ve had good success with for markdown and latex with image captioning. It uses a simple tagging scheme for page numbers, captions and tables.

I've tried nanonets but it seems very sensitive to the prompt, changing it slightly turned the output to rubbish. When it worked it was pretty good.

This is true. It’s not meant to be run with any prompt but the one they trained with. I found that out as well. It’s only meant for ocr. Qwen 2.5vl is better if you need that option.

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

#84

Post by jdthedisciple »

If its not nearly as accurate as state of the art OCR (such as GPT's), then I'm not sure it being offline is worth the tradeoff to me personally.

I'm personally on the watchout for the absolute best possible multilingual OCR performance, local or not, cost it what it may (almost).

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

#85

Post by dreamcompiler »

firesteelrain wrote: post #4
david_draco wrote: post #3

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 ...

There is a very popular Python module called ocrmypdf. I used it to help my HOA and OCR’ing of old PDFs. https://github.com/ocrmypdf/OCRmyPDF No LLMs required.

20 years ago I tried in vain to get my HOA to use the virtual printer for PDF documents so they'd be searchable. The capability was built in to both Mac and Windows even way back then.

No luck. They just could not grasp it. So they kept using their process of printing out the file on paper and then scanning it back in as a PDF image file.

I finally quit trying. Now of course they've seen the light and are painstakingly OCRing all that old stuff.

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

#86

Post by firesteelrain »

dreamcompiler wrote: post #85
firesteelrain wrote: post #4

Earlier quoted context omitted.

There is a very popular Python module called ocrmypdf. I used it to help my HOA and OCR’ing of old PDFs. https://github.com/ocrmypdf/OCRmyPDF No LLMs required.

20 years ago I tried in vain to get my HOA to use the virtual printer for PDF documents so they'd be searchable. The capability was built in to both Mac and Windows even way back then. No luck. They just could not grasp it. So they kept using their process of printing out the file on paper and then scanning it back in as a PDF image file. I finally quit trying. Now of course they've seen the light and are painstaking…

Ouch! I am on the BOD so as an IT/Engineering Professional I can influence things better
Post reply on HN