-
### Describe the issue
I am trying to benchmark `vits2.onnx`. The path is correct and the file exists. However, I got the following error:
`RuntimeException: [ONNXRuntimeError] : 6 : RUNTIME_E…
-
能否问问您是怎么训练一个新的语言的,我有尝试训练另外一种语言(韩语),并且保留中英日三个symbol但是训练不起来。
不知道您是怎么训练起来的。是不是需要把某些设定一开始先拔掉,然后好好的训练韩语的声学模型等等,例如关掉DD/SLM模组的训练这样吗? 因为看您的训练似乎是使用替代symbol的方式把中文给砍掉? 但可能是因为四川话和中文较相关,但另外一个客语的似乎就直接砍到剩下只有Hakka p…
-
使用官方提供的bert vits包推理, 内存持续增长; 而本项目不会, 做了哪方面的改进?
另外,如果启动该项目时只想使用bert vits的部分而不加载其他的模块, 我应该怎么做?
感谢作者开源
-
This is a follow up to the previous discussion threads regarding stochastic duration predictor in https://github.com/p0p4k/vits2_pytorch/issues/11 and https://github.com/p0p4k/vits2_pytorch/issues/68#…
-
Greetings,
First and foremost, I'd like to extend my commendations on developing such an outstanding model; its performance surpasses anything I have personally trained thus far. It's a noteworthy …
-
Is it possible to use AlignerNet (aligner.py in pflow-tts repo) instead of MAS in VITS2?
What should be changed in the code? I am a bit confused on what the inputs should be.
-
我是直接拿gpt-sovits改的,直接加载一个bert-vits2音频地址,驱动出来的声音会有“嗒”声 (单独播放音频是没有“嗒”声的)
我在试是不是因为chunk_size的问题,但好像没有用。
请作者指点一下
-
RuntimeError: expand(torch.FloatTensor{[2, 1025, 475]}, size=[2, 1025]): the number of sizes provided (2) must be greater or equal to the number of dimensions in the tensor (3)
这个怎么处理?
然后我修正了参数 再…
-
Style-Bert-VITS2的日文發正確美麗,希望有一天可以支援!
謝謝大大的努力開發!
-
Hi, I found the implementation of ResidualCouplingLayer.forward(normalize_flow.py) is different from official VITS code, and this section is not described in the VITS2 paper. what principle your imple…