IndexTTS 2.5 Technical Report
Researchers have released a technical report for IndexTTS 2.5, an update to their zero-shot neural text-to-speech foundation model. The system continues to utilize a two-part architecture consisting of a transformer-based Text-to-Semantic module and a non-autoregressive Semantic-to-Mel module.
Covered by 1 source
- AarXiv CS.AI↗Yunpei Li, Xun Zhou, Jinchao Wang, Lu Wang, Yong Wu, Siyi Zhou, Yiquan Zhou, Yining Wang, Yaogen Yang, Zhetao Hu, Shiyao Duan, Jiacheng Xu, Bin Xia, Jingchen ShuAug 11