MoonInTheRiver / DiffSinger

DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code
MIT License
4.3k stars 714 forks source link

数据集标注 #95

Closed hsk-yjk closed 1 year ago

hsk-yjk commented 1 year ago

您好,我想用自己得音频数据集训练一下,但是不知道如何适配textgrid文件内容,只能通过手工标注嘛?

MoonInTheRiver commented 1 year ago

For TTS tasks, you can use alignment tools (such as MFA) to annotate, and some related instructions could be found in our repository "NATSpeech";

For SVS tasks, refer to the paper "Opencpop", and you can use alignment tools to generate some coarse annotations before manually annotating.

hsk-yjk commented 1 year ago

Thanks for your reply.