Retrieval-based-Voice-Conversion-WebUI
Retrieval-based-Voice-Conversion-WebUI copied to clipboard
fumiama
Easily train a good VC model with voice data <= 10 mins!
is this totally will function fully well using only CPU ?
## Describe the bug: When I go to train, set my parameters, and start the train, when it finishes it says it is completed successfully but my model does not...
**Describe the bug** The PyTorch version checking code does not correctly handle versions built from source; I am one of those affected. For example, pip shows an installation of the...
**Describe the bug** Training can't begin because of an error. **To Reproduce** Steps to reproduce the behavior: 1. Go to Train 2. Click on train model 3. See error **Expected...
Thank you for this amazing project! I'm training a voice model but encountered an issue where several loss values suddenly become NaN during training. During training, I observe the following...
It seems like FairSeq is only used for HuBERT, and it is no longer work with newer versions of python. It seems like now you can use HuggingFace to use...
File "E:\Retrieval-based-Voice-Conversion-WebUI\infer\modules\train\train.py", line 256, in run net_g.module.load_state_dict( File "E:\Retrieval-based-Voice-Conversion-WebUI\venv\Lib\site-packages\torch\nn\modules\module.py", line 2593, in load_state_dict raise RuntimeError( RuntimeError: Error(s) in loading state_dict for SynthesizerTrnMs768NSFsid: Missing key(s) in state_dict: "enc_p.emb_pitch.weight", "dec.m_source.l_linear.weight", "dec.m_source.l_linear.bias", "dec.noise_convs.0.weight",...
Hi, I have been using this tool for some time, but never mastered it. I have questions to help me get more understanding. - Is there any explanation/guide about the...
As the title says, I want to know if it works with the RTX 5090. And if not, what advice can you give me to run this model on my...
Hello, can you please add an auto pitch as in sovits svc? https://github.com/svc-develop-team/so-vits-svc Autopitch would be great for beginners and professionals because manually changing the pitch to make the Voice...
