[robertknight]

Other than EasyOCR and Tesseract, PaddleOCR (https://github.com/PaddlePaddle/PaddleOCR) is probably the most well known open-source OCR solution.

What are you planning to do with the text after detecting / recognizing it? How fast does the detection / recognition need to be in order to be useful?

[sinnse]

Giving it to an llm. Check out our website: Onistep.com

For the time: Less than 5 second or it lose all purposes.