You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When I run CUDA_VISIBLE_DEVICES=0,1 python tasks/run.py --config egs/stylesinger.yaml --exp_name StyleSinger --reset to train my model based on the Chinese dataset, I got this error. I have done the work of data processing, this may be where to make config file changes. If you see this message, please help reply. Thank you very much.
The text was updated successfully, but these errors were encountered:
After seeing your question, I tried to replicate the steps you described. I was able to successfully complete the training process without encountering any errors. There are a few things you might want to check:
Data Preprocessing:
Could you double-check that your ph_set configuration during data preprocessing is correct?
Also, please verify that the F0 extraction process is working as intended.
Environment:
Are you sure you're using the correct environment? I successfully ran the StyleSinger training in a relatively older Python environment, specifically version 3.8.19. This detail might be important.
TensorBoard Import Update:
I've recently updated a tensorboard import that might have been causing the problem. Please take a look at the latest code on the repository. It could potentially resolve the issue you're facing.
When I run CUDA_VISIBLE_DEVICES=0,1 python tasks/run.py --config egs/stylesinger.yaml --exp_name StyleSinger --reset to train my model based on the Chinese dataset, I got this error. I have done the work of data processing, this may be where to make config file changes. If you see this message, please help reply. Thank you very much.
The text was updated successfully, but these errors were encountered: