[EMNLP 2025 System Demonstrations] GraDeT-HTR: A Resource-Efficient Bengali Handwritten Text Recognition System utilizing Grapheme-based Tokenizer and Decoder-only Transformer
-
Updated
Dec 12, 2025 - Python
[EMNLP 2025 System Demonstrations] GraDeT-HTR: A Resource-Efficient Bengali Handwritten Text Recognition System utilizing Grapheme-based Tokenizer and Decoder-only Transformer
This is a Bengali OCR (Optical Character Recognition) web application that can extract digital text from images containing Bengali characters. The project uses HTML, CSS, and JavaScript, leveraging modern web technologies for creating a lightweight and easy-to-use text extraction tool.
Add a description, image, and links to the bengali-ocr topic page so that developers can more easily learn about it.
To associate your repository with the bengali-ocr topic, visit your repo's landing page and select "manage topics."