# A Free Lunch? Adapting PP-OCRv6 for Historical Text Recognition

arXiv: https://arxiv.org/abs/2609.20064 · HTML: https://mlsanity.com/paper/2609.20064/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 19 of its 36 references that are in the map.
- First posted on arXiv 17 Sep 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Document understanding and multimodal RAG](https://mlsanity.com/mllm/document-understanding-and-multimodal-rag/)

## Builds on (most cited first, 19 of 19)

- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://mlsanity.com/paper/1507.05717/) (2015)
- [TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models](https://mlsanity.com/paper/2109.10282/) (2021)
- [NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition](https://mlsanity.com/paper/1806.00926/) (2018)
- [DAN: a Segmentation-free Document Attention Network for Handwritten Document Recognition](https://mlsanity.com/paper/2203.12273/) (2022)
- [OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold](https://mlsanity.com/paper/2006.07491/) (2020)
- [DTrOCR: Decoder-only Transformer for Optical Character Recognition](https://mlsanity.com/paper/2308.15996/) (2023)
- [Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural Networks](https://mlsanity.com/paper/1812.11894/) (2018)
- [HTR-VT: Handwritten Text Recognition with Vision Transformer](https://mlsanity.com/paper/2409.08573/) (2024)
- [SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition](https://mlsanity.com/paper/2411.15858/) (2024)
- [LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR](https://mlsanity.com/paper/2601.14251/) (2026)
- [Calamari - A High-Performance Tensorflow-based Deep Learning Package for Optical Character Recognition](https://mlsanity.com/paper/1807.02004/) (2018)
- [PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks](https://mlsanity.com/paper/2606.13108/) (2026)
- [Fully Convolutional Networks for Handwriting Recognition](https://mlsanity.com/paper/1907.04888/) (2019)
- [On the Generalization of Handwritten Text Recognition Models](https://mlsanity.com/paper/2411.17332/) (2024)
- [CHURRO: Making History Readable with an Open-Weight Large Vision-Language Model for High-Accuracy, Low-Cost Historical Text Recognition](https://mlsanity.com/paper/2509.19768/) (2025)
- [PP-OCRv5: A Specialized 5M-Parameter Model Rivaling Billion-Parameter Vision-Language Models on OCR Tasks](https://mlsanity.com/paper/2603.24373/) (2026)
- [Easter2.0: Improving convolutional models for handwritten text recognition](https://mlsanity.com/paper/2205.14879/) (2022)
- [Reading or Guessing? Visual Grounding Failures of Vision-Language Models for OCR in Ancient Greek Editions](https://mlsanity.com/paper/2605.27750/) (2026)

## Abstract (arXiv)

Despite impressive reported scores, large vision-language models have seen limited practical uptake in historical automatic text recognition because of their computational cost, dependence on large-scale pretraining, and hallucination. Historical ATR therefore continues to rely largely on compact CRNN line recognizers, which are visually grounded and trainable on modest data. Lightweight recurrence-free recognizers promise the accuracy of larger models with the practical advantages of CRNNs, yet have not been comprehensively evaluated on historical writing. We adapt PP-OCRv6, a recent compact text recognizer without strong language modeling, for historical line recognition and compare it with a conventional CRNN across generalized pretraining, domain-specific training, corpus-level fine-tuning, and manuscript-specific few-shot adaptation on multilingual Latin- and Arabic-script material. While PP-OCRv6 does not consistently outperform the baseline when trained from scratch, heterogeneous pretraining produces markedly better generalization. Comparisons with the Qwen3.5-based Medusa recognizer further show that fine-tuned PP-OCRv6 can outperform a large VLM tailored towards historical Latin-script HTR.