What's the current best OCR?

[ChillyBop]

There are so many untranslated works in chinese/japanese/korean and OCR is the only way to read them.
Currently I've been using VNTranslator Neo with varying degrees of success.
The best by far is google translator but... The way that i've been using it is by taking a picture of my computer's screen with my phone, and that kinda sucks. If I could just get google translate to work on my computer that would be perfect, not sure if there's a practical way to do that.

 

[Entai2965]

I'm not too sure about front end apps, but the backend ocr technology that is the best is a mix between PaddleOCR (horizontal text only), MangaOCR (especially for vertical text), various LLMs that have vision capabilities.

There are a lot of front end apps in active development. As an example, those specific technologies listed above are implemented in SLR Translator's SEP add-on which internally uses ocr_tools. There are also several older apps that use MangaOCR internally, including Sugoi Toolkit.

It looks like VNTranslator supports a lot of backends for OCR, so you are probably already using the best user-friendly method if you are using that program. If you can get the Google Cloud Vision backend working in your program, then you can skip the taking a picture with your phone step, but it is also a paid service.

That is what the ocr scene looks like right now.

 

[Arisara]

I like use Luna translator or MORT especially for vns

 

[huze]

If anyone's looking for alternatives, the Sugoi Toolkit dev recently made a manga translator tool too. Might be worth checking out

 

[failedwebsite]

Not sure about non-Latin scripts, but I'm happy with the Copyfish browser add-on for scraping text from manga.

 

[lst]

From Version 14 onward, Sugoi Toolkit supports Visual Novel OCR in Chinese, Korean, and English. More info here: https://blog.sugoitoolkit.com/sug/
For scans, this is my favorite free online OCR tool: https://imagetotextfree.com/