singing voice change based on whisper, and lora for singing voice clone. You will feel the beauty of the code from this project. Uni-SVC main branch is for singing voice clone based on whisper with speaker encoder and speaker adapter. Uni-SVC main target is to develop lora for SVC. With lora, maybe clone a singer just need 10 stence after 10 minutes train. Each singer is a plug-in of the base model.
Features
- Singing voice conversion based on whisper, UnivNet and NSF
- Model which contains 56 singers of 50 hours singing data is training
- You can preview models
- Uni-SVC for baker
- Uni-SVC for Opencpop
- Open source singing voice conversion
- Change sample rate of waves
Categories
Voice CloningLicense
MIT LicenseFollow lora-svc
Other Useful Business Software
Custom VMs From 1 to 96 vCPUs With 99.95% Uptime
Live migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of lora-svc!