tesseract-ocr/tessdata
Repository hosting trained LSTM-based OCR models for Tesseract text recognition.
Not currently ranked — collecting fresh signals.
star history
Provides pre-trained language data files for the Tesseract OCR engine. Includes integerized LSTM neural network models that balance speed and accuracy for text extraction from images. Supports the modern neural net engine (–oem 1) as well as legacy models for backward compatibility.
Frequently asked
- What is tesseract-ocr/tessdata?
- Repository hosting trained LSTM-based OCR models for Tesseract text recognition.
- Is tessdata open source?
- Yes — tesseract-ocr/tessdata is open source, released under the Apache-2.0 license.
- How popular is tessdata?
- tesseract-ocr/tessdata has 7.6k stars on GitHub.
- Where can I find tessdata?
- tesseract-ocr/tessdata is on GitHub at https://github.com/tesseract-ocr/tessdata.