Digitizing Nepal's Written Heritage: A Comprehensive HTR Pipeline for Old Nepali Manuscripts

2025/12/18 by Anjali Sarawgi, Esteban Garces Arias, Sarawgi, Anjali +3 · 1 citation
Computer Science · #Handwritten Text Recognition Techniques #Natural Language Processing Techniques #Speech Recognition and Synthesis

paper · doi:10.48550/arxiv.2512.17111

Abstract

This paper presents the first end-to-end pipeline for Handwritten Text Recognition (HTR) for Old Nepali, a historically significant but low-resource language. We adopt a line-level transcription approach and systematically explore encoder-decoder architectures and data-centric techniques to improve recognition accuracy. Our best model achieves a Character Error Rate (CER) of 4.9%. In addition, we implement and evaluate decoding strategies and analyze token-level confusions to better understand model behavior and error patterns. Although the evaluation dataset is confidential, we release our training code, model configurations, and evaluation scripts to support further research on HTR for low-resource historical scripts.

Citations

• GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generation
• Advancing Offline Handwritten Text Recognition: A Systematic Review of Data Augmentation and Generation Techniques
• Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text Generation
• Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Generation
• A tailored Handwritten-Text-Recognition System for Medieval Latin
• A Contrastive Framework for Neural Text Generation
• The Curious Case of Neural Text Degeneration
• Hierarchical Neural Story Generation
• Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates
• Synthetic Data for Text Localisation in Natural Images
• Neural Machine Translation of Rare Words with Subword Units
• An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
• A Threshold Selection Method from Gray-Level Histograms

Cited by

• Automated sign detection across the Electronic Babylonian Library: A large-scale dataset and end-to-end cuneiform OCR pipeline

Related

• GraDeT-HTR: A Resource-Efficient Bengali Handwritten Text Recognition System utilizing Grapheme-based Tokenizer and Decoder-only Transformer
• Optical Text Recognition in Nepali and Bengali: A Transformer-based Approach
• Development of Pre-Trained Transformer-based Models for the Nepali Language
• Towards Nepali-language LLMs: Efficient GPT training with a Nepali BPE tokenizer
• BN-HTRd: A Benchmark Dataset for Document Level Offline Bangla Handwritten Text Recognition (HTR) and Line Segmentation