UVR BVE beta model
Added 2023-08-08 05:36:31 +0000 UTC
We now have the world's first Backing Vocal Extraction model!
This model is designed to isolate only the backing vocals while keeping the lead vocal in the instrumental stem.
The model is still in the training phase, so the results will not be perfect. We expect to see an improvement in a week.
Please note that this model is very resource intensive so the maximum song
length is limited to 15 minutes.