Closed meriamOu closed 1 year ago
hey, I run the repo with the suggested audio,
python svc_inference.py --config configs/base.yaml --model ./vits_pretrain/sovits5.0.pretrain.pth --spk ./configs/singers/singer0001.npy --wave test.wav
The inference result is very noisy. I can not hear the lyrics at all. Any suggestions in this case? Thank you
you can compare with hugging face demo.
hey, I run the repo with the suggested audio,
python svc_inference.py --config configs/base.yaml --model ./vits_pretrain/sovits5.0.pretrain.pth --spk ./configs/singers/singer0001.npy --wave test.wav
The inference result is very noisy. I can not hear the lyrics at all. Any suggestions in this case? Thank you