ICTNLP/SpokenVisIT
收藏Hugging Face2025-06-16 更新2025-07-05 收录
下载链接：
https://hf-mirror.com/datasets/ICTNLP/SpokenVisIT
下载链接
链接失效反馈官方服务：
资源简介：
SpokenVisIT是一个基于VisIT-Bench构建的面向真实世界的视觉-语音交互基准数据集，用于评估大型多模态模型在视觉定位的语音交互能力。该数据集将文本指令转换为口语，使得研究者可以评估模型在处理口语指令时的表现。
SpokenVisIT is a real-world visual-speech interaction benchmark based on VisIT-Bench, designed to evaluate the visual-grounded speech interaction capabilities of omni large multimodal models (LMMs). It converts textual instructions into spoken language to assess the performance of models in handling spoken instructions.
提供机构：
ICTNLP
