sleeping-ai/FakeProfile600

这是一个包含600个真实人物假声音档案的数据集，旨在用于训练健壮和多样化的文本到语音和文本到音乐模型。数据集档案包括演讲者的全名、语言代码、区域设置、性别、头像URL、语音风格、演讲者类型、额外标志和创建及更新时间戳等信息。

This dataset consists of 600 state-of-the-art fake voice profiles of real people, intended for training robust and diverse text-to-speech and text-to-music models. The profiles include the speakers full name, language code, regional locale, gender, image URL, voice style, speaker type, additional flags, and creation and update timestamps.