About 3 years after the previous major release 4.0.0 there is now a new stable release 5.0.0 for Tesseract #OCR: github.com/tesseract-ocr/…. #TesseractOCR is widely used by #Archives, #Libraries, the
@InternetArchive, many companies and individuals to get text from images.
The new #TesseractOCR 5.0.0 includes many bug fixes, is faster, supports much faster training of new OCR models, has modernized code and an improved build process and many more changes.
About 70 contributors provided code changes for #TesseractOCR 5.0.0, and many others wrote issues to report problems or suggest improvements. Thank you to all who helped getting this new release.
The latest #TesseractOCR 5.0.0 is now also available for Windows. Get it from github.com/UB-Mannheim/te….
Since Friday (2022-01-07) #TesseractOCR 5.0.1 is released and also available for Windows from
@UBMannheim(github.com/UB-Mannheim/te…). Did you know that Tesseract can run #OCR directly for images on the Web, now also for URLs with redirects?
