Open pustar opened 2 months ago
Thank you for sharing such nice repo! CUDA and CPU now generate different audio (tone) when given same text. How to make CUDA and CPU generate the same speech (tone) when given same text?
The random algorithms of CPU and GPU are different so we will get different result. At torch, maybe we can use a custom Generator. See https://pytorch.org/docs/stable/generated/torch.Generator.html#torch.Generator
Generator
Thank you for sharing such nice repo! CUDA and CPU now generate different audio (tone) when given same text. How to make CUDA and CPU generate the same speech (tone) when given same text?