# UniLipi: A Unified Multi-Script OCR for Historical Indic Manuscripts

arXiv: https://arxiv.org/abs/2608.28195 · HTML: https://mlsanity.com/paper/2608.28195/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 65 references that are in the map.
- First posted on arXiv 28 Aug 2026.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models](https://mlsanity.com/paper/2109.10282/) (2021)
- [What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis](https://mlsanity.com/paper/1904.01906/) (2019)
- [Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study](https://mlsanity.com/paper/2112.15093/) (2021)
- [Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation](https://mlsanity.com/paper/2401.17904/) (2024)
- [HTR-VT: Handwritten Text Recognition with Vision Transformer](https://mlsanity.com/paper/2409.08573/) (2024)
- [The LAM Dataset: A Novel Benchmark for Line-Level Handwritten Text Recognition](https://mlsanity.com/paper/2208.07682/) (2022)
- [Muharaf: Manuscripts of Handwritten Arabic Dataset for Cursive Text Recognition](https://mlsanity.com/paper/2406.09630/) (2024)
- [Zero-Shot Styled Text Image Generation, but Make It Autoregressive](https://mlsanity.com/paper/2503.17074/) (2025)
- [Few Shots Are All You Need: A Progressive Few Shot Learning Approach for Low Resource Handwritten Text Recognition](https://mlsanity.com/paper/2107.10064/) (2021)
- [On the Generalization of Handwritten Text Recognition Models](https://mlsanity.com/paper/2411.17332/) (2024)
- [Beyond Isolated Words: Diffusion Brush for Handwritten Text-Line Generation](https://mlsanity.com/paper/2508.03256/) (2025)
- [Indiscapes: Instance Segmentation Networks for Layout Parsing of Historical Indic Manuscripts](https://mlsanity.com/paper/1912.07025/) (2019)
- [MRN: Multiplexed Routing Network for Incremental Multilingual Text Recognition](https://mlsanity.com/paper/2305.14758/) (2023)
- [Hyper-Local Deformable Transformers for Text Spotting on Historical Maps](https://mlsanity.com/paper/2506.15010/) (2025)
- [Generating Synthetic Handwritten Historical Documents With OCR Constrained GANs](https://mlsanity.com/paper/2103.08236/) (2021)
- [Autoregressive Styled Text Image Generation, but Make it Reliable](https://mlsanity.com/paper/2510.23240/) (2025)
- [Historic Scripts to Modern Vision: A Novel Dataset and A VLM Framework for Transliteration of Modi Script to Devanagari](https://mlsanity.com/paper/2503.13060/) (2025)
- [HTR-ConvText: Leveraging Convolution and Textual Information for Handwritten Text Recognition](https://mlsanity.com/paper/2512.05021/) (2025)

## Abstract (arXiv)

Optical character recognition (OCR) for handwritten Indic manuscripts is essential for large-scale digitization and computational access to manuscript heritage. However, existing approaches are typically developed for one script at a time and require substantial script-specific customization. This limits scalability and practical deployment across diverse collections. We present UniLipi, a unified multi-script OCR model for handwritten Indic manuscripts trained jointly across 13 Indic scripts within a single framework. UniLipi directly handles realistic manuscript conditions, including extreme variation in line geometry, large variation in line length, and partial interruptions caused by non-textual manuscript entities such as holes, stains, or pictorial illustrations. To operate effectively under ultra low-resource conditions, the model leverages script-aware synthetic manuscript data generation, substantially reducing reliance on large volumes of real annotated data. Beyond historical manuscripts, we show that UniLipi serves as an effective foundational pretrained model. Specifically, its learned representations enable good OCR performance for contemporary Indic handwriting and extend to several non-Indic scripts, including Tibetan, Italian, Latin, and Chinese scripts. In addition to transcription, UniLipi predicts script identity and per-line native character counts, supporting practical manuscript cataloging workflows.