[flagged]
[dead]
OCR It – pull text out of un-copyable documents for your LLM
31–40 of 41 posts
Re: OCR It – pull text out of un-copyable documents for your LLM
#32Does anyone have suggestions on how I could OCR lots of handwritten math notes with diagrams? I have tons of PDFs waiting for me to manually type them myself and can't justify dedicating weeks to do it.
Most LLMs can do a pretty good job of this out of the box.
If you have a coding agent available, ask it to try transcribing a few of the PDFs.
Re: OCR It – pull text out of un-copyable documents for your LLM
#33If you use a Linux desktop (I am on Fedora), Gradia[1][2] is definitely worth a look as well.
It has a similar workflow for taking screenshots and then immediately annotating or editing them, without having to open a separate image editor. And: it provides also an local OCR feature (which is why I comment this here), you can extract text from a screenshot with on-screen OCR using Tesseract with the small button beside the "Crop Image" one.
Combined with the syntax-highlighting feature for screenshots of code snippets, the OCR is surprisingly useful in combination if you e.g. quickly discuss some code in a chat when copy is blocked for whatever reason (e.g. somone sent you a screenshot in the first place).
[1] https://gradia.alexandervanhee.be/
[2] https://flathub.org/en/apps/be.alexandervanhee.gradia
Edit: fixed wrong link index numbers
Re: OCR It – pull text out of un-copyable documents for your LLM
#34Is Tesseract still the best choice for local OCR in 2026? I was always underwhelmed with its real-world performance.
There's EasyOCR and RapidOCR too, I guess benchmark and see what's best for your material? Oh and Multimodal LLMs :)
I did a small benchmark for RapidOCR: https://thiagotigaz.github.io/ocr-it/bench/
For the input text rendered on screen, Tesseract did better on both accuracy and speed. We got about 0.1% character error vs 1–2% for RapidOCR, and Tesseract was roughly 2.5x faster. Blur was the biggest difference: 0.4% vs 14%.
The big problem is that this is synthetic rendered text, which is basically the easy case and also the only kind of input this extension captures. I wouldn't assume the same results for scanned documents.
I haven't tested EasyOCR yet.
Re: OCR It – pull text out of un-copyable documents for your LLM
#35I added Firefox support. 0.3.0 builds for both browsers from the same source, and it's submitted for both google/chrome and mozilla/firefox, i am waiting on reviews now, which usually takes a few days.
Until it's approved you guys can download the ready to use releases:
Download ocr-it-firefox-0.3.0.zip from https://github.com/thiagotigaz/ocr-it/releases/tag/v0.3.0
If you'd rather build from source, the steps are in the README: https://github.com/thiagotigaz/ocr-it#install
Re: OCR It – pull text out of un-copyable documents for your LLM
#36I added Firefox support. 0.3.0 builds for both browsers from the same source, and it's submitted for both google/chrome and mozilla/firefox, i am waiting on reviews now, which usually takes a few days. Until it's approved you guys can download the ready to use releases: Download ocr-it-firefox-0.3.0.zip from https://github.com/thiagotigaz/ocr-it/releases/tag/v0.3.0 If you'd rather build from source, the steps are in…
Great news!
Re: OCR It – pull text out of un-copyable documents for your LLM
#37Is Tesseract still the best choice for local OCR in 2026? I was always underwhelmed with its real-world performance.
It works very well for me. It handles non-English characters and diacritics without issues.
Re: OCR It – pull text out of un-copyable documents for your LLM
#38Earlier quoted context omitted.
There's EasyOCR and RapidOCR too, I guess benchmark and see what's best for your material? Oh and Multimodal LLMs :)
I did a small benchmark for RapidOCR: https://thiagotigaz.github.io/ocr-it/bench/ For the input text rendered on screen, Tesseract did better on both accuracy and speed. We got about 0.1% character error vs 1–2% for RapidOCR, and Tesseract was roughly 2.5x faster. Blur was the biggest difference: 0.4% vs 14%. The big problem is that this is synthetic rendered text, which is basically the easy case and also the only k…
Lol, yea, not so rapid then! :)
Re: OCR It – pull text out of un-copyable documents for your LLM
#39Is Tesseract still the best choice for local OCR in 2026? I was always underwhelmed with its real-world performance.
We did some benchmarking against other libraries like RapidOCR and EasyOCR
results in https://thiagotigaz.github.io/ocr-it/bench/
Re: OCR It – pull text out of un-copyable documents for your LLM
#40Hi guys, the chrome extension was finally approved and is now available at
https://chromewebstore.google.com/detail/ocr-it/pekiamimgjbj...
We are still waiting for the firefox extension to be approved, i will post it here whenever we hear something. In the meanwhile it can be tested with the zip file here https://github.com/thiagotigaz/ocr-it/releases or by building manually.