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

Mistral OCR 4.1

docs.mistral.ai

Post reply on HN
Print view View original

31–40 of 182 posts

Re: Mistral OCR 4.1

#31

Post by merb »

aliljet wrote: post #29
piterrro wrote: post #24

For anyone interested, I have an ocr pipeline running on rented GPUs, doing around 1000pages for 0.05-01 usd with around 0.8 seconds per page with full bounding boxes support for grounding. If you’re interested you can find contact to me via this profile. 3.5 usd/1000 pages is just too expensive…

Accuracy is truly what people die for in the OCR game. Price isn't the primary function here.. it's an equation of price, accuracy, speed, and in mayn cases regulation.

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 too much optimization (you can probably even run multiple processes on a single node)

Google documentai costs 1.5$ per 1000 which is probably better in quality and speed.

Re: Mistral OCR 4.1

#32

Post by piterrro »

aliljet wrote: post #29
piterrro wrote: post #24

For anyone interested, I have an ocr pipeline running on rented GPUs, doing around 1000pages for 0.05-01 usd with around 0.8 seconds per page with full bounding boxes support for grounding. If you’re interested you can find contact to me via this profile. 3.5 usd/1000 pages is just too expensive…

Accuracy is truly what people die for in the OCR game. Price isn't the primary function here.. it's an equation of price, accuracy, speed, and in mayn cases regulation.

Most use cases dont need that kind of accuracy, just doesnt justify the 3-4usd range. I build for that exact case (tender documents, we’re processing north of 100k pages per day), it doesnt need to recognize scanned written text from 1930s, its usually pdf/docs/scanned printed pages. The accuracy is great, bounding boxes are must have for proper grounding for building answers by LLMs. Tesseract was too slow and not enough in some cases (for example tables or images which we also recognize and describe)

Re: Mistral OCR 4.1

#34

Post by BenzeneDream »

kubb wrote: post #6
king_crimson wrote: post #3

At 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.

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.

Re: Mistral OCR 4.1

#35

Post by ux266478 »

BenzeneDream wrote: post #34
kubb wrote: post #6

Earlier 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.

> What prize do you win? Imagine a world where only one country has AGI/ASI.

"Winning the race" doesn't give you that in any meaningful capacity. It gives you, at the absolute most, a temporary window where that's the case. See: nuclear weapons.

Re: Mistral OCR 4.1

#36

Post by maelito »

mainecoder wrote: post #2

The chinese did it better, mistral is alive thanks to regulations.

No it's the other way round : the Chinese do better thanks to regulations : massive amounts of money from Big tech and public money.

Re: Mistral OCR 4.1

#37

Post by pogue »

piterrro wrote: post #32
aliljet wrote: post #29

Earlier quoted context omitted.

Accuracy is truly what people die for in the OCR game. Price isn't the primary function here.. it's an equation of price, accuracy, speed, and in mayn cases regulation.

Most use cases dont need that kind of accuracy, just doesnt justify the 3-4usd range. I build for that exact case (tender documents, we’re processing north of 100k pages per day), it doesnt need to recognize scanned written text from 1930s, its usually pdf/docs/scanned printed pages. The accuracy is great, bounding boxes are must have for proper grounding for building answers by LLMs. Tesseract was too slow and not e…

If you're getting inaccurate results from OCR what's the purpose of even doing it? Inaccuracy of text of any kind seems like a completely obvious failure of the entire purpose of scanning text into a computer.

Re: Mistral OCR 4.1

#38

Post by jr3592 »

ux266478 wrote: post #35
BenzeneDream wrote: post #34

Earlier quoted context omitted.

? 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.

> What prize do you win? Imagine a world where only one country has AGI/ASI. "Winning the race" doesn't give you that in any meaningful capacity. It gives you, at the absolute most, a temporary window where that's the case. See: nuclear weapons.

As if time isn't money? Everything is temporary... Getting somewhere first has immense value.

Re: Mistral OCR 4.1

#40

Post by tedggh »

kubb wrote: post #6
king_crimson wrote: post #3

At 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.

It's not a race. You don't get anything for winning.

A race to the bottom.
Post reply on HN