scenic sequoia
Model Info :
- Architecture : RVC Arch.
- Vocoder : NSF-HiFiGAN
- Sample Rate : 32kHz
- F0 Extraction : RMVPE
- Embedder : ContentVec
- Pretrain : Legacy Core 1.6
- Precision : FP32
Training Details :
- Epochs : 155
- Dataset Length : 10m 56s
- Batch Size : 4
feel free to give feedback if you find any issues with this model, so i can improve it in the next training
