Nian-Ci

Results 5 comments of Nian-Ci

靠耳朵听,声学模型不要依赖loss,何况是微调

这个压力主要在GPU上哈,只有预处理阶段比较吃CPU,而且让CPU分担也不起多大作用,CPU干不过GPU的,有什么问题可以去B站视频下方找花佬的QQ交流群

Yes, RVC is inspired by the well-known So-VITS-SVC, which in turn is inspired by Soft-VC (repository: https://github.com/bshall/soft-vc, paper: https://arxiv.org/abs/2111.02392). The author replaced the acoustic model and vocoder in Soft-VC with...

You can certainly create your own pretrained model, which requires you to train a model with a large amount of data and then delete the emb.g_weight layer from it. However,...

Setting devices selection in the config may work