issues
search
yl4579
/
StarGANv2-VC
StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion
MIT License
466
stars
110
forks
source link
Training questions: samples and resuming
#31
Closed
skol101
closed
2 years ago
skol101
commented
2 years ago
I've started training and have questions:
I can see train/eval phases, but no wav samples in the log_dir
Can training be resumed from ? I assume it can if I put "epoch_xxx.pth" in the config file ?
yl4579
commented
2 years ago
There is no waveform generated in the training and evaluation process, so you will need to do it yourself with a vocoder.
Yes, just edit the
pretrained_model
field in the config file.
I've started training and have questions: