GER-HSR-1K
收藏arXiv2025-09-30 收录
下载链接：
https://www.cs.technik.fhnw.ch/i4ds-datasets
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含了1000个标注样本，旨在比较标准德语的参考句子及其对应假设之间的语法、标点、大小写和语义相似性。样本来源于瑞士议会语料库和SDS-200，并使用专为瑞士德语调优的语音转文本系统进行了转录。该数据集的规模为1000个样本，其任务在于衡量语音翻译质量指标的效果。
This dataset contains 1,000 annotated samples, which aims to compare the grammatical, punctuation, capitalization, and semantic similarity between Standard German reference sentences and their corresponding hypotheses. The samples are sourced from the Swiss Parliament Corpus and SDS-200, and transcribed using a speech-to-text system fine-tuned specifically for Swiss German. With a total of 1,000 samples, this dataset is designed to evaluate the effectiveness of speech translation quality metrics.
提供机构：
Authors of the paper
