4.0 with LSTM
Clone this wiki locally
Tesseract 4.0 alpha source code is available in the 'master' branch of the repository. It adds a new OCR engine based on LSTM neural networks. It initially works (well) on x86/Linux. Model data for 101 languages is available in the tessdata repository.
- TrainingTesseract 4.00 - Finetuning Example - Arabic
- TrainingTesseract 4.00 - Replace Top Layer Example - Norwegian
- TrainingTesseract 4.00 - Replace Top Layer Example - Devanagari
Unofficial Ubuntu PPAs for Tesseract 4.00 & Leptonica 1.74:
Leponica 1.74.1 package for Debian:
4.0.0-alpha for Windows
Unofficial experimental binaries of tesseract-ocr 4.0.0-alpha (Jan 30, 2017) are available from the following links:
- Windows Installer made with MinGW-w64 from UB Mannheim
- zip file with cppan generated .dll and .exe files, You have to install VC2015 x86 redist from microsoft.com in order to run them.
Unofficial binaries of tesseract-ocr 4.0.0-alpha [as of commit 2f10be5] with GUI interface are available for gImageReader from
Download 4.0.0alpha traineddata to use with the above from master branch of tessdata. e.g. for Hindi download the following file:
3.05-dev for Windows
An unofficial installer for Tesseract 3.05-dev for Windows is available from Tesseract at UB Mannheim. This includes the training tools.
The 3.05 branch on GitHub can be used by those who want the bug fixes for 3.04 release.
The current official release is 3.04.1.