RVC-Boss
RVC-Boss
Try batch size2 first, if oom error is caused, then batch size 1.
It's because the pretrained feature encoder we used only support 16khz. In Automatic Speech Recognition (ASR) task, there is no pretrained feature encoder use audio exceeding 16khz as input. Maybe...
↑ is right. You should install vc++ first. We're planning removing the dependency of fairseq in the next versions.
What is the model of your Mac computer? Do you have an Nvidia graphics card?
File "/Users/naozumi/Downloads/RVC/Retrieval-based-Voice-Conversion-WebUI-updated0618v2/lib/infer_pack/models.py", line 418, in forward sine_merge = self.l_tanh(self.l_linear(sine_wavs)) you can also change this line to sine_merge = self.l_tanh(self.l_linear(sine_wavs.to(self.l_linear.weight.dtype))) to fix it
You can try it. I will try and test your version, if all functions are successfully tested, I can merge it to main.
你看看3_feature256文件夹下有没有东西（或者有没有这个文件夹）
step2提特征有报错要截图我看下
My Computer no space