-
Notifications
You must be signed in to change notification settings - Fork 1.8k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[REQUEST]: Update RMVPE to the latest checkpoint #930
Comments
Another thing is that the number of mel frames required to be input during the RMVPE inference process is an integer multiple of 32. If it is not an integer multiple of 32, using pad will degrade the effect (may cause frequency doubling error). In other words, considering that 1 frame is 10ms, it is recommended that the audio sampling point of rmvpe inference (under 16khz sampling rate) is 160 * (32*n - 1), where n is an integer (minus 1 because mel analysis will have one more frame). |
Thank you. I am willing to give it a try. |
done. |
close |
In a few words, describe your idea
The RVC official repository has updated the RMVPE checkpoint , which is in the author's huggingface . I am responsible for training this new RMVPE model. The performance of this checkpoint is better when I test it. You can test it and update it if there is no problem.
More information
No response
The text was updated successfully, but these errors were encountered: