tesseract-ocr/tessdata_best

Stars
1,137
Rank 39,399 (Top 0.8 %)
Language
License
Apache License 2.0
Created over 6 years ago
Updated about 2 months ago

tesseract-ocr/tessdata_best

tesseract-ocr

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Best (most accurate) trained LSTM models.

tessdata_best – Best (most accurate) trained models

This repository contains the best trained models for the Tesseract Open Source OCR Engine.

These models only work with the LSTM OCR engine of Tesseract 4.

See the Tesseract docs for additional information.

All data in the repository are licensed under the Apache-2.0 License, see file LICENSE.

tesseract

Tesseract Open Source OCR Engine (main repository)

tessdata

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

tessdoc

Tesseract documentation

langdata

Source training data for Tesseract for lots of languages

tesstrain

Train Tesseract LSTM with make

tessdata_fast

Fast integer versions of trained LSTM models

docs

Various documents related to Tesseract OCR

langdata_lstm

Data used for LSTM model training

tesseract-ocr.github.io

Tesseract documentation

test

Repository for tesseract testing

tessconfigs

Tesseract Config files

tessdata_contrib

User contributed (non Google) OCR models for Tesseract

tessapi

Tesseract source code and API documentation