The Surya OCR toolkit is a suite of 4 models that do OCR in 90+ languages, line detection, layout analysis, and reading order detection. Surya has 6000+ Github Stars, is used by hundreds of organizations, and benchmarks well against cloud services.
Here's what Surya can do.
Surya handles OCR in over 90 languages. See benchmarks.
Surya does state of the art line detection in any language. See benchmarks.
Surya does state of the art layout analysis on a range of documents. See benchmarks.
Surya does state of the art reading order detection on a range of documents. See benchmarks.
