CHURRO：利用开放权重大型视觉语言模型实现高精度、低成本的历史文本识别，让历史变得可读
CHURRO: Making History Readable with an Open-Weight Large Vision-Language Model for High-Accuracy, Low-Cost Historical Text Recognition
AI总结：
针对现有模型难以识别历史文本的问题，提出30亿参数的开放权重VLM CHURRO，基于最大历史文本识别数据集CHURRO-DS训练，在印刷体和手写体识别上超越所有对比模型，且成本效益显著。
摘要：
历史文献的准确文本识别可以极大地推进文化遗产的研究与保护。然而，现有的视觉语言模型（VLMs）是为现代标准化文本设计的，不具备阅读历史材料中多种语言和文字、不规则版面以及频繁出现的退化现象的能力。本文提出了CHURRO，一个专门用于历史文本识别的30亿参数开放权重VLM。该模型在CHURRO-DS上训练，这是迄今为止最大的历史文本识别数据集。CHURRO-DS整合了155个历史语料库，包含99,491页，跨越22个世纪的文本遗产，涵盖46个语系，包括历史变体和死语言。我们在CHURRO-DS上评估了多个开放权重和闭源的VLM以及光学字符识别（OCR）系统，发现CHURRO优于所有其他VLM。在CHURRO-DS测试集上，CHURRO在印刷体和手写体上分别达到了82.3%和70.1%的归一化Levenshtein相似度，比第二好的模型Gemini 2.5 Pro分别高出1.4%和6.5%，同时成本效益高出15.5倍。通过发布模型和数据集，我们旨在推动社区驱动的研究，以提高历史文本的可读性并加速学术研究。
英文摘要：
Accurate text recognition for historical documents can greatly advance the study and preservation of cultural heritage. Existing vision-language models (VLMs), however, are designed for modern, standardized texts and are not equipped to read the diverse languages and scripts, irregular layouts, and frequent degradation found in historical materials. This paper presents CHURRO, a 3B-parameter open-weight VLM specialized for historical text recognition. The model is trained on CHURRO-DS, the largest historical text recognition dataset to date. CHURRO-DS unifies 155 historical corpora comprising 99,491 pages, spanning 22 centuries of textual heritage across 46 language clusters, including historical variants and dead languages. We evaluate several open-weight and closed VLMs and optical character recognition (OCR) systems on CHURRO-DS and find that CHURRO outperforms all other VLMs. On the CHURRO-DS test set, CHURRO achieves 82.3% (printed) and 70.1% (handwritten) normalized Levenshtein similarity, surpassing the second-best model, Gemini 2.5 Pro, by 1.4% and 6.5%, respectively, while being 15.5 times more cost-effective. By releasing the model and dataset, we aim to enable community-driven research to improve the readability of historical texts and accelerate scholarship.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
