Digitizing Nepal's Written Heritage: A Comprehensive HTR Pipeline for Old Nepali Manuscripts
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 16 of its 42 references that are in the map. First posted on arXiv 18 Dec 2025.
Builds on
16 of 42 references.
References · 16
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
- 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
- 2019The Curious Case of Neural Text Degenerationcited by 2,916
- 2018Hierarchical Neural Story Generationcited by 1,193
- 2018Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidatescited by 639
- 2015An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognitioncited by 520
- 2016Synthetic Data for Text Localisation in Natural Imagescited by 396
- 2017Beam Search Strategies for Neural Machine Translationcited by 232
- 2022A Contrastive Framework for Neural Text Generationcited by 225
- 2024Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Generationcited by 27
- 2024Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text Generationcited by 26
4 more
- 2018Handwriting Recognition of Historical Documents with few labeled datacited by 10
- 2025GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generationcited by 10
- 2023A tailored Handwritten-Text-Recognition System for Medieval Latincited by 4
- 2025Advancing Offline Handwritten Text Recognition: A Systematic Review of Data Augmentation and Generation Techniquescited by 2
Built on by
Citing papers per year: 2026: 2.
2 papers.