We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Tesseract Open Source OCR Engine (main repository)
C++ 63.3k 9.6k
Best (most accurate) trained LSTM models.
1.3k 390
Trained models with fast variant of the "best" LSTM models + legacy models
6.5k 2.2k
Fast integer versions of trained LSTM models
501 142
Tesseract documentation
User contributed (non Google) OCR models for Tesseract
Repository for tesseract testing
Train Tesseract LSTM with make
Source training data for Tesseract for lots of languages
Data used for LSTM model training