This repository has been archived by the owner on Oct 19, 2024. It is now read-only.
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
{{ message }}
-
目前还没有做实验来验证，但是从原理上可能降低模型在说话人增多时发生音色泄漏的风险，从而使单模型有能力运用更多数据（多说话人）继而增强表现。
可以预期的风险:
Beta Was this translation helpful? Give feedback.
All reactions