I can't say I've ever wanted to transcribe code from an image. That seems super niche. Perhaps the specific idea is to harvest coding textbooks as training data for LLMs?
I'm guessing to automatically scrape videos for future training rounds.
How we made our OCR code more accurate
21–30 of 50 posts
Re: How we made our OCR code more accurate
#22Anything that mentions tesseract is about 10 years out of date at this point.
I just built a pipeline with tesseract last year. What's better that is open source and runnable locally? VLLM hallucination is a blocker for my use case.
If you are stuck with open source, then your options are limited.
Otherwise I'd say just use your operating system's OCR API. Both Windows and MacOS have excellent APIs for this.
Re: How we made our OCR code more accurate
#23Anything that mentions tesseract is about 10 years out of date at this point.
Quite simply, you’re completely wrong. Modern tesseract versions include a modern LSTM AI. It can very affordably be deployed on CPU, yet its performance is competitive with much more expensive large GPU-based models. Especially if you handle a high volume of scans, chances are that tesseract will have the best bang per buck.
i remember that you could not train it your self in a font like you could in older versions, it that still the case?
Re: How we made our OCR code more accurate
#24Re: How we made our OCR code more accurate
#25Neat article, but I feel like I have no idea why they're doing this! Is transcribing code from images really such a big use case?
I guess it would be excellent to evade security monitors to take unauthorized copies of your employers codebase.
Re: How we made our OCR code more accurate
#26Re: How we made our OCR code more accurate
#27Anything that mentions tesseract is about 10 years out of date at this point.
Quite simply, you’re completely wrong. Modern tesseract versions include a modern LSTM AI. It can very affordably be deployed on CPU, yet its performance is competitive with much more expensive large GPU-based models. Especially if you handle a high volume of scans, chances are that tesseract will have the best bang per buck.
My company probably spent close to 6 figures overall creating Tesseract 5 custom models for various languages. Surya beats them all and is open source (and quite faster).
Re: How we made our OCR code more accurate
#28Neat article, but I feel like I have no idea why they're doing this! Is transcribing code from images really such a big use case?
Maybe they want to compile the Apollo Guidance Computer source code... https://www.softwareheritage.org/wp-content/uploads/2019/07/...
If it's not a joke, I think it was already digitized: https://github.com/chrislgarry/Apollo-11
Re: How we made our OCR code more accurate
#29Tesseract OCR was created by digital (DEC) in 19_8_5 (yes, 40 not four YEARs ago). Now go back and read the article and ROFL with me.
What is this argument? Much software we use today was created in the 80s.
Re: How we made our OCR code more accurate
#30I can't say I've ever wanted to transcribe code from an image. That seems super niche. Perhaps the specific idea is to harvest coding textbooks as training data for LLMs?
Eh, imagine poor documentation where people take screenshots of steps and don't write them out.
I can also imagine plenty of YouTube tutorials that type the code live... seems fairly useful