humairawan/AnimeSpeech

AniSpeech数据集是一个持续扩展的带有字幕的动漫语音集合，由ShoukanLabs提供。它包含高质量的动漫语音表演，涵盖多种语调、音色和音高变化，适合训练通用的文本到语音模型。数据集支持英语，包含音频文件、字幕、音标字幕和语音特征。虽然数据集适合训练基础模型，但不建议用于单一声音的精细调优。数据集采用MIT许可证。

The AniSpeech dataset is a continually expanding collection of captioned anime voices brought to you by ShoukanLabs. It features high-quality vocal performances with variations in intonation, timbre, and pitch, ideal for training generalized text-to-speech models. The dataset supports English and includes audio files, captions, phonetic captions, and voice features. While it excels in training foundation models, it is not recommended for fine-tuning on a single voice. The dataset is released under the MIT License.