MERaLiON/CPQA-Evaluation-Set
收藏Hugging Face2025-05-31 更新2025-07-05 收录
下载链接：
https://hf-mirror.com/datasets/MERaLiON/CPQA-Evaluation-Set
下载链接
链接失效反馈官方服务：
资源简介：
CPQA-Eval-LLM数据集是一个评估大型语音语言模型在理解语音中的上下文和副语言线索能力的评估集。该数据集包含2647个由语言模型生成的问答对和479个相关YouTube视频链接，数据以Hugging Face数据集格式存储，包括视频链接、问题文本和答案文本。
CPQA-Eval-LLM set is an evaluation set designed to assess the capability of large speech-language models (Speech-LLMs) to understand contextual and paralinguistic cues in speech. The dataset consists of 2647 LLM-generated question–answer pairs and 479 associated YouTube video links, stored in the Hugging Face Dataset format, including video links, question text, and answer text.
提供机构：
MERaLiON
