-
Notifications
You must be signed in to change notification settings - Fork 792
Comments
Debug VITS for multi-speaker training#6
Conversation
models/tts/valle/valle_trainer.py
Outdated
| "trian_stage": self.args.train_stage | ||
| } | ||
| return state_dict | ||
| # def _get_state_dict(self): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
why is this impacted?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Is the commented code implemented in any base trainer (new_trainer or tts_trainer)? If so, we can just delete them.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It's the testing code before. And unuseful now. I have deleted it.
models/tts/valle/valle_trainer.py
Outdated
| "trian_stage": self.args.train_stage | ||
| } | ||
| return state_dict | ||
| # def _get_state_dict(self): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Is the commented code implemented in any base trainer (new_trainer or tts_trainer)? If so, we can just delete them.