如何选择预训练的手写识别模型用于单作者微调（英文版）

英文标题：How to Choose Pretrained Handwriting Recognition Models for Single Writer Fine-Tuning中文摘要：通过对大型基准数据集和通过手写文本生成模型产生的合成数据集的研究，本文提出在大数据集上预训练手写文本识别模型，并在少量带有个人特点手写的小规模数据集上进行微调，以有效转录手稿。英文摘要：Recent advancements in Deep Learning-based Handwritten Text Recognition (HTR)have led to models with remarkable performance on both modern and historicalmanuscripts in large benchmark datasets. Nonetheless, those models struggle toobtain the same performance when applied to manuscripts with peculiarcharacteris