完全基于字幕来做的吗？ #20

Open

opened

on Sep 18, 2025

看了下代码，好像基本是基于字幕来做的；没有参考图像的理解或者语音asr？

Metadata

Assignees

No one assigned

Labels

No labels

No labels

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests