News for hackers. Stuff that matters.

A comment on Show HN: Ocrbase – pdf → .md/.json document OCR and structured extraction API.

Re:Show HN: Ocrbase – pdf → .md/.json document OCR and struc... by sgc on Tuesday January 20, 2026 @09:55AM (#46692425)
How does this compare to dots.ocr? I got fantastic results when I tested dots.

https://github.com/rednote-hilab/dots.ocr

[ Parent | on HN ]
Re:Show HN: Ocrbase – pdf → .md/.json document OCR and struc... by mjrpes on Tuesday January 20, 2026 @10:15AM (#46692640)
Ocrbase is CUDA only while dots.ocr uses vLLM, so should support ROCm/AMD cards?
[ Parent | on HN ]
Re:Show HN: Ocrbase – pdf → .md/.json document OCR and struc... by actionfromafar on Tuesday January 20, 2026 @11:05AM (#46693389)
How about CPU?
[ Parent | on HN ]
Re:Show HN: Ocrbase – pdf → .md/.json document OCR and struc... by jasonni on Wednesday January 21, 2026 @12:06AM (#46701364)
dots.ocr requires requires a considerable amount of computational resources. If you have Mac device with ARM CPU(M series), you can try my dots.ocr.runner(https://github.com/jason-ni/app.dots.ocr.runner).

There is a pipeline solution with multiple small specific models that can run only with CPU: https://github.com/RapidAI/RapidOCR

[ Parent | on HN ]
Re:Show HN: Ocrbase – pdf → .md/.json document OCR and struc... by sgc on Wednesday January 21, 2026 @02:22AM (#46702201)
Jason, your runner looks interesting. I am using debian linux on my laptop with an intel cpu and nvidia gpu (proprietary nvidia cuda drivers). Should I be able to get it working? What is your speed per page at this point? Thank you
[ Parent | on HN ]