antoineedy/vidore_v3_finance_en_mteb_format

这是一个多语言图像到文本检索任务的数据集，包含多种语言的图像、文本和评分信息。数据集来源于vidore/vidore_v3_finance_en，任务类别包括视觉文档检索、图像到文本和文本到图像。数据集支持多种语言，包括德语、英语、法语、意大利语、葡萄牙语和西班牙语。

This is a multilingual image-to-text retrieval task dataset, containing image, text and score information in multiple languages. The dataset is sourced from vidore/vidore_v3_finance_en, and the task categories include visual document retrieval, image-to-text, and text-to-image. The dataset supports multiple languages, including German, English, French, Italian, Portuguese and Spanish.