kenpath/indic_tts-zero-shot-cloning
收藏Hugging Face2025-12-17 更新2025-12-20 收录
下载链接：
https://hf-mirror.com/datasets/kenpath/indic_tts-zero-shot-cloning
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含多个印度语言（如阿萨姆语、孟加拉语、古吉拉特语、印地语、卡纳达语、马拉地语、泰米尔语和泰卢固语）的文本到语音（TTS）数据，以及一些测试配置。每个配置包含参考音频、TTS文本、TTS音频和说话者信息等特征，部分测试配置还包括持续时间、文本长度和样本数量等额外特征。数据集详细列出了每个分割的大小和示例数量。
This dataset includes text-to-speech (TTS) data for multiple Indian languages (such as Assamese, Bengali, Gujarati, Hindi, Kannada, Marathi, Tamil, and Telugu) along with some test configurations. Each configuration features reference audio, TTS text, TTS audio, and speaker information, with some test configurations additionally including features like duration, text length, and number of samples. The dataset provides detailed sizes and number of examples for each split.
提供机构：
kenpath
