tencent/WildSpeech-Bench
收藏官方服务：
资源简介：
WildSpeech-Bench是一个用于评估音频到音频语音对话模型能力的端到端、系统性基准。该数据集具有三个主要特点：现实和多样化的数据策展、模拟特定于音频的挑战以及细粒度的性能评估。
WildSpeech-Bench is an end-to-end, systematic benchmark for evaluating the capabilities of audio-to-audio speech dialogue models. The dataset is characterized by three key features: realistic and diverse data curation, simulation of audio-specific challenges, and fine-grained performance evaluation.
提供机构：
tencent
