Questions about MMVC_Trainer
Closed this issue · 2 comments
I have some questions about MMVC_Trainer.
(1) G_180000.pth and D_180000.pth
In the fine_model, there are G_180000.pth and D_180000.pth model files.
What is G_180000.pth for?
What is D_180000.pth for?
(2) G_latest_99999999.pth and D_latest_99999999.pth
In the logs/20220306_24000, there are G_latest_99999999.pth and D_latest_99999999.pth model files.
What kind of training is done for G_latest_99999999.pth?
What kind of training is done for D_latest_99999999.pth?
I apologize for the delay.
(1)
MMVC is a VC model based on VITS.
G stands for Generator, and D stands for Discriminator.
G_180000.pth and D_180000.pth are pre-trained models.
Based on these models, fine-tuning is performed using the source speaker's voice data and the target speaker's voice.
(2)
G_latest_99999999.pth and D_latest_99999999.pth being the most recent models saved at the intervals specified in the config file.
Is the answer provided addressing the intention of your question？
The most recent models saved, OK