GraDeT-HTR: A Resource-Efficient Bengali Handwritten Text Recognition System utilizing Grapheme-based Tokenizer and Decoder-only Transformer

Md. Mahmudul Hasan, Ahmed Nesar Tahsin Choudhury, Mahmudul Hasan +1

Despite Bengali being the sixth most spoken language in the world, handwritten text recognition (HTR) systems for Bengali remain severely underdeveloped. The complexity of Bengali…