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!
Seems like there is a repo that already does this: https://github.com/codename0og/codename-rvc-fork
Hi, In colab the rmvpe option doesn't appear there are only pm, harvest and dio
**To Reproduce** 1) train a new voice model using a single 3 sec silent audio file, 1 epoch. Run inference on the same 3 sec silent audio using the model...
**Is your feature request related to a problem? Please describe.** Currently, 44.1khz audio options are not present in RVC. Given that it's a common sample rate for CDs, I would...
Hello! I'm copying this from a different RVC fork as it sounds like a really useful feature to help improve realism of models! ### Description What Does RMSEnergyExtractor Do? **Calculates...
**Describe the bug** This seems to be an unintentional regression. If one stops training mid-session and resumes, it starts from the beginning instead of continuing with the saved D and...
**Describe the bug** When I try to load weights or perform inference, I get errors appearing in the UI but no corresponding information in the console. The python process still...
I don't know why this hasn't been taken care of already but it's essential.  although even when merging as 40k or 48k using 2 32k weights it still outputs...
Hi: 我正在用以下代码片段尝试将SynthesizerTrnMs768NSFsid类模型导出成ONNX： ```python import sys sys.path.append('../') from configs.config import Config from infer.modules.vc.modules import VC import torch # 加载配置和vc模型 config = Config() vc = VC(config) vc.get_vc("Youdao.pth") net_g = vc.net_g class NetGAdpater(torch.nn.Module):...
RuntimeError: cuDNN error: CUDNN_STATUS_NOT_SUPPORTED. This error may appear if you passed in a non-contiguous input. I only get this on input files longer than about 10 minutes. If I truncate...
