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

DeepSeek OCR

github.com

Post reply on HN
Print view View original

211–220 of 252 posts

Re: DeepSeek OCR

#211

Post by cheema33 »

breadislove wrote: post #98

For everyone wondering how good this and other benchmarks are: - the OmniAI benchmark is bad - Instead check OmniDocBench[1] out - Mistral OCR is far far behind most Open Source OCR models and even further behind then Gemini - End to End OCR is still extremely tricky - composed pipelines work better (layout detection -> reading order -> OCR every element) - complex table parsing is still extremely difficult [1]: http…

> the OmniAI benchmark is bad

According to Omni OCR benchmark, Omni OCR is the best OCR. I am sure you all will find no issues with these findings.

Re: DeepSeek OCR

#213

Post by hakunin »

wahnfrieden wrote: post #212
thekid314 wrote: post #134

Earlier quoted context omitted.

Yeah, and fails quickly at anything handwritten.

LiveText too? It has a newer engine

This is the second comment of yours about LiveText (this is the older one https://news.ycombinator.com/item?id=43192141) — I found that one by complete coincidence because I'm trying to provide a Ruby API for these frameworks. However, I can't find much info on LiveText? What framework is it part of? Do you have any links or any additional info? I found a source where they say it's specifically for screen and camera capturing.

Re: DeepSeek OCR

#214

Post by wahnfrieden »

hakunin wrote: post #213
wahnfrieden wrote: post #212

Earlier quoted context omitted.

LiveText too? It has a newer engine

This is the second comment of yours about LiveText (this is the older one https://news.ycombinator.com/item?id=43192141 ) — I found that one by complete coincidence because I'm trying to provide a Ruby API for these frameworks. However, I can't find much info on LiveText? What framework is it part of? Do you have any links or any additional info? I found a source where they say it's specifically for screen and camera…

https://developer.apple.com/documentation/visionkit/imageana... VisionKit. Swift-only (as with many new APIs) so lots of people stuck on ObjC bridges simply ignore it.

It does not provide bounding boxes but you can get text.

Re: DeepSeek OCR

#215

Post by prats226 »

Top 3 models on huggingface are all OCR models. Most automation projects involve documents where you need a model finetuned to understand all elements inside documents and provide grounding and confidence scores etc which is why these subset of models are gaining popularity

Re: DeepSeek OCR

#216

Post by prats226 »

singularity2001 wrote: post #58

Instead of downloading a specific OCR model how would one fare just downloading the currently best multi-modal foundation model? And what would that be at less than 30 GB?

Then you can just download finetuned version of same multi-modal foundation model that's trained on documents?

Re: DeepSeek OCR

#217

Post by hakunin »

wahnfrieden wrote: post #214
hakunin wrote: post #213

Earlier quoted context omitted.

This is the second comment of yours about LiveText (this is the older one https://news.ycombinator.com/item?id=43192141 ) — I found that one by complete coincidence because I'm trying to provide a Ruby API for these frameworks. However, I can't find much info on LiveText? What framework is it part of? Do you have any links or any additional info? I found a source where they say it's specifically for screen and camera…

https://developer.apple.com/documentation/visionkit/imageana... VisionKit. Swift-only (as with many new APIs) so lots of people stuck on ObjC bridges simply ignore it. It does not provide bounding boxes but you can get text.

That's great, I'm going to give this a shot. If you have any more resources please do share. I don't mind Swift-only, because I'm writing little shims with `@_cdecl` for the bridge (don't have much experience here, but hoping this is going to work, leaning on AI for support).

Re: DeepSeek OCR

#218

Post by prats226 »

2big2fail_47 wrote: post #80

I find it interesting that there's all these independent AI-OCR Projects but still no commercial offering. Is it still too inaccurate, too complex or simply too expensive?

https://docstrange.nanonets.com/ as well, wrapper on top of 7B version of https://huggingface.co/nanonets/Nanonets-OCR2-3B

Re: DeepSeek OCR

#219

Post by djmips »

jjcm wrote: post #200
simonw wrote: post #199

I figured out how to get this running on the NVIDIA Spark (ARM64, which makes PyTorch a little bit trickier than usual) by running Claude Code as root in a new Docker container and having it figure it out. Notes here: https://simonwillison.net/2025/Oct/20/deepseek-ocr-claude-co... Here's a result I got https://github.com/simonw/research/blob/main/deepseek-ocr-nv... - against this image: https://static.simonwillison.n…

Looks like this did really solid, with the exception of the paragraph directly below the quote. It hallucinated some filler there and bridge it with the next column. Thanks for running the test quickly!

By my eye it just bridge. I didn't see any filler. It went from "Code is a language" - above the quote and then to "in a garden by name." which was the top of the next column but missing the chicken subject.

Re: DeepSeek OCR

#220

Post by arkmm »

simonw wrote: post #199

I figured out how to get this running on the NVIDIA Spark (ARM64, which makes PyTorch a little bit trickier than usual) by running Claude Code as root in a new Docker container and having it figure it out. Notes here: https://simonwillison.net/2025/Oct/20/deepseek-ocr-claude-co... Here's a result I got https://github.com/simonw/research/blob/main/deepseek-ocr-nv... - against this image: https://static.simonwillison.n…

Wow, this deserves its own submission.
Post reply on HN