OPENGIT/Retrieval-based-Voice-Conversion-WebUI
1
0
Fork 0
mirror of https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git synced 2025-01-04 14:05:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

Updated 常见问题解答 (markdown)

RVC-Boss 2023-08-31 16:54:46 +08:00
parent caed3b9083
commit 7decbaf4d0
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
常见问题解答.md

@ -123,6 +123,10 @@ FileNotFoundError: Could not find module lib\site-packages\llvmlite\binding\llvm
win平台会报这个错，装上https://aka.ms/vs/17/release/vc_redist.x64.exe这个再重启WebUI就好了。
## Q17：RuntimeError: The expanded size of the tensor (17280) must match the existing size (0) at non-singleton dimension 1. Target sizes: [1, 17280]. Tensor sizes: [0]
## Q17: RuntimeError: The expanded size of the tensor (17280) must match the existing size (0) at non-singleton dimension 1. Target sizes: [1, 17280]. Tensor sizes: [0]
wavs16k文件夹下，找到文件大小显著比其他都小的一些音频文件，删掉，点击训练模型，就不会报错了，不过由于一键流程中断了你训练完模型还要点训练索引。
## Q18: RuntimeError: The size of tensor a (24) must match the size of tensor b (16) at non-singleton dimension 2
不要中途变更采样率继续训练。如果一定要变更，应更换实验名从头训练。当然你也可以把上次提取的音高和特征（0/1/2/2b folders）拷贝过去加速训练流程。