stepfun-ai/StepEval-Audio-360

StepEval Audio 360是一个全面的评估数据集，用于评估多模态大型语言模型（MLLMs）在人类-人工智能音频交互中的能力。这个音频基准数据集由专业的人类标注员提供，涵盖了各种能力：唱歌、创造力、角色扮演、逻辑推理、语音理解、语音指令遵循、游戏、语音情感控制以及语言能力。数据集包含不同语言和方言的人声录音，包括四川话、粤语、英语和日语，同时包含音频和转录数据。

StepEval Audio 360 is a comprehensive dataset that evaluates the ability of multi-modal large language models (MLLMs) in human-AI audio interaction. This audio benchmark dataset, sourced from professional human annotators, covers a full spectrum of capabilities: singing, creativity, role-playing, logical reasoning, voice understanding, voice instruction following, gaming, speech emotion control, and language ability. It comprises human voice recorded in different languages and dialects, including Chinese (Szechuan dialect and Cantonese), English, and Japanese, and contains both audio and transcription data.