How does this perform with non-Latin and non-LTR scripts? Say, Chinese, Arabic, Devangari, Adlam, etc.?
Mistral OCR 4.1
151–160 of 182 posts
Re: Mistral OCR 4.1
#152The chinese did it better, mistral is alive thanks to regulations.
It's not regulations, it's European companies being (legitimately) worried about their data sovereignty if they use US or Chinese AI providers.
Re: Mistral OCR 4.1
#153Earlier quoted context omitted.
Tbf even with tesseract you already get shit ton of accuracy and you can probably do these 1000 pages for way less than 3.5€. For 3.5€ you can spin up a cloud instance with 8vCPU+32gb on gcloud for 11 hours (or 11 instances for an hour) which can do way more than 1000 pages per hour on tesseract. It takes you around 6 second per page +-4 seconds start/stop depending on what you are doing on that instance size without…
Tesseract is not a substitute for these models, which understand complex layouts and also extract bounding boxes for things like tables and pictures. They are also much better at making sense of cursive scripts. I’ve been there, implementing a way to linearise text from a document with pages with 1, 2 or 3 columns, some of them in landscape is a nightmare. And that’s not even considering equations. In the end it’s wa…
> "I’ve been there, implementing a way to linearise text from a document with pages with 1, 2 or 3 columns, some of them in landscape is a nightmare."
I thought it's actually a fun problem! Some of the naive solutions (based on alternating horizontal/vertical recursion) are quite elegant and cool.
Re: Mistral OCR 4.1
#154Earlier quoted context omitted.
It's not a race. You don't get anything for winning.
? It absolutely is a race. Whether thats a positive thing or not is debatable but every lab is definitely in a race. What prize do you win? Imagine a world where only one country has AGI/ASI. Or a world where Europe only gets access to frontier models 6 months later. Far from ideal.
> Imagine a world where only one country has AGI/ASI
Who says the LLM race ends at an AGI/ASI finish line in the first place ?
Re: Mistral OCR 4.1
#155At this point I lost all hope for Europe playing any significant role in the AI race. If that’s a good or a bad thing I don’t know, but it seems to me like that’s the reality.
Commoditization is a beautiful thing. It seems Anthropic and OpenAI are really struggling to maintain much of a moat. Mistral might not be leading but it's not trailing by that much either. And of course the Chinese are doing their own thing quite successfully. The reality is that the US is betting its economy on data centers at great expense and is exposing its economy to great risk. Also while geographically a lot…
Nothing to worry about for europe. Open source and open weights will enable europe to pick up the slck when the party is over. Then the US markets will possibly regret the AI-bubble.
Re: Mistral OCR 4.1
#156I didn't quite understand.
Re: Mistral OCR 4.1
#157I think people misunderstand the utility of Mistral's OCR. It's not going to beat SOTA models for extraction on edge-case docs, but it's MUCH cheaper and faster and does an excellent job on simple ones. I've been working on converting PDFs to EPUBs and Mistral has been making steady improvements. On a chapter of Bleak House it was able to extract and tag the header, titles, and references at the bottom every time. Th…
> it's MUCH cheaper and faster and does an excellent job on simple ones.
OCR should be:
1. Privacy-respecting, i.e. running on your own machine without network communications. 2. Fully open-source. 3. Gratis.
The first one is a must, the second is very important for the public interest, and the third one is a nice-to-have.
Mistral does not appear to satisfy even the first-, let alone all three.
Re: Mistral OCR 4.1
#158Earlier quoted context omitted.
i.e. it's one AI company that's basically guaranteed to never fail since it has a market niche guaranteed by European companies and governments.
Which is also why their most recent model "Shieldstral" does nothing except monitor and moderate internet content. After stuff like Chat Control I think they're obviously seeing a big demand for this kind of "internet safety" technology in Europe.
I don’t think any European AI model can reach the experience and productivity of average NSA/CIA analyst.
Re: Mistral OCR 4.1
#159Earlier quoted context omitted.
Tesseract is not a substitute for these models, which understand complex layouts and also extract bounding boxes for things like tables and pictures. They are also much better at making sense of cursive scripts. I’ve been there, implementing a way to linearise text from a document with pages with 1, 2 or 3 columns, some of them in landscape is a nightmare. And that’s not even considering equations. In the end it’s wa…
> "I’ve been there, implementing a way to linearise text from a document with pages with 1, 2 or 3 columns, some of them in landscape is a nightmare." I thought it's actually a fun problem! Some of the naive solutions (based on alternating horizontal/vertical recursion) are quite elegant and cool.
It was fun!
What was not so fun was to make it work reliably. I ended up with piles of ugly code to handle edge cases, and issues kept piling up. So in the end I was happy to use someone else’s solution.
Re: Mistral OCR 4.1
#160Mistral has been very good with handwritten ocr, expecting the new models to get better with that across languages.