Skip to content

Pinned Loading

  1. tesseract Public

    Tesseract Open Source OCR Engine (main repository)

    C++ 68k 10k

  2. tessdata_best Public

    Best (most accurate) trained LSTM models.

    1.4k 402

  3. tessdata Public

    Trained models with fast variant of the "best" LSTM models + legacy models

    7k 2.4k

  4. tessdata_fast Public

    Fast integer versions of trained LSTM models

    549 153

Repositories

Showing 10 of 14 repositories
  • tesseract Public

    Tesseract Open Source OCR Engine (main repository)

    C++ 67,989 Apache-2.0 10,005 418 (7 issues need help) 26 Updated Jul 6, 2025
  • tessdoc Public

    Tesseract documentation

    HTML 2,092 398 19 5 Updated Jun 7, 2025
  • tesstrain Public

    Train Tesseract LSTM with make

    Python 686 Apache-2.0 206 63 3 Updated Apr 18, 2025
  • tessdata_contrib Public

    User contributed (non Google) OCR models for Tesseract

    27 Apache-2.0 25 0 3 Updated Apr 18, 2025
  • langdata Public

    Source training data for Tesseract for lots of languages

    857 Apache-2.0 878 46 (1 issue needs help) 9 Updated Apr 1, 2025
  • tessdata_fast Public

    Fast integer versions of trained LSTM models

    549 Apache-2.0 153 3 0 Updated Aug 2, 2024
  • test Public

    Repository for tesseract testing

    Shell 33 Apache-2.0 33 1 0 Updated Jun 9, 2024
  • tessdata_best Public

    Best (most accurate) trained LSTM models.

    1,374 Apache-2.0 402 23 1 Updated Mar 9, 2024
  • tessdata Public

    Trained models with fast variant of the "best" LSTM models + legacy models

    7,021 Apache-2.0 2,357 53 (2 issues need help) 2 Updated Mar 9, 2024
  • langdata_lstm Public

    Data used for LSTM model training

    118 Apache-2.0 156 24 (1 issue needs help) 5 Updated Mar 9, 2024