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

Mistral OCR

mistral.ai

Post reply on HN
Print view View original

41–50 of 450 posts

Re: Mistral OCR

#41

Post by nicodjimenez »

jcuenod wrote: post #15

Just tested with a multilingual (bidi) English/Hebrew document. The Hebrew output had no correspondence to the text whatsoever (in context, there was an English translation, and the Hebrew produced was a back-translation of that). Their benchmark results are impressive, don't get me wrong. But I'm a little disappointed. I often read multilingual document scans in the humanities. Multilingual (and esp. bidi) OCR is ch…

You can get bounding boxes from our pdf api at Mathpix.com

Disclaimer, I’m the founder

Re: Mistral OCR

#42

Post by dannyobrien »

z2 wrote: post #35

Is there a reliable handwriting OCR benchmark out there (updated, not a blog post)? Despite the gains claimed for printed text, I found (anecdotally) that trying to use Mistral OCR on my messy cursive handwriting to be much less accurate than GPT-4o, in the ballpark of 30% wrong vs closer to 5% wrong for GPT-4o. Edit: answered in another post: https://huggingface.co/spaces/echo840/ocrbench-leaderboard

Simon Willison linked to an impressive demo of Qwen2-VL in this area: I haven't found a version of it that I could run locally yet to corroborate. https://simonwillison.net/2024/Sep/4/qwen2-vl/

Re: Mistral OCR

#43

Post by dewey »

andoando wrote: post #18

Bit unrelated but is there anything that can help with really low resolution text? My neighbor got hit and run the other day for example, and I've been trying every tool I can to make out some of the letters/numbers on the plate https://ibb.co/mr8QSYnj

To even get started on this you'd also need to share some contextual information like continent, country etc. I'd say.

Re: Mistral OCR

#44

Post by alberth »

Curious to see how this performance against more real world usage of someone taking a photo of text (which the text then becomes slightly blurred) and performing OCR on it.

I can't exactly tell if the "Mistral 7B" image is an example of this exact scenario.

Re: Mistral OCR

#45

Post by roboben »

Le chat doesn’t seem to know about this change despite the blog post stating it. Can anyone explain how to use it in Le Chat?

Re: Mistral OCR

#47

Post by unboxingelf »

cxie wrote: post #40

The new Mistral OCR release looks impressive - 94.89% overall accuracy and significantly better multilingual support than competitors. As someone who's built document processing systems at scale, I'm curious about the real-world implications. Has anyone tried this on specialized domains like medical or legal documents? The benchmarks are promising, but OCR has always faced challenges with domain-specific terminology…

We’ll just stick LLM Gateway LLM in front of all the specialized LLMs. MicroLLMs Architecture.

Re: Mistral OCR

#48

Post by jacooper »

Pretty cool, would love to use this with paperless, but I just can't bring myself to send a photo of all my documents to a third party, especially legal and sensitive documents, which is what I use Paperless for.

Because of that I'm stuck with crappy vision on Ollama (Thanks to AMDs crappy ROCm support for Vllm)

Re: Mistral OCR

#50

Post by WhitneyLand »

1. There’s no simple page / sandbox to upload images and try it. Fine, I’ll code it up.

2. “Explore the Mistral AI APIs” (https://docs.mistral.ai) links to all apis except OCR.

3. The docs on the api params refer to document chunking and image chunking but no details on how their chunking works?

So much unnecessary friction smh.

Post reply on HN