jonathansuru/fon_tts_speaker_13
收藏官方服务：
资源简介：
该数据集包含音频、文本、说话者和性别四个特征。音频的采样率为44100Hz。数据集包含195个训练样本，总大小为41708314.44370546字节，下载大小为51470416字节。
This dataset includes four features: audio, text, speaker, and gender. The audio has a sampling rate of 44100Hz. The dataset contains 195 training samples, with a total size of 41708314.44370546 bytes and a download size of 51470416 bytes.
提供机构：
jonathansuru
