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!
**Describe the bug** when converting voice, gradio errors out, rvc stops running, python has also crashed. no error message in cmd. crash event data (in windows event viewer) ``` AppName...
**Is your feature request related to a problem? Please describe.** Currently, RVC models with pitch guidance seem to have an f0 range from 50 Hz to 1.1 kHz. When I...
Hello! I have a question about how cross-fade works for the realtime GUI. This is more a question that could become either a feature request or a bug. Theoretically it...
Warnings ``` torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. ``` Are being spewed out during feature extraction Fix for that should be relatively easy, just replacing `torch.nn.utils.weight_norm` to...
instead of just opening a subshell that calls the extract_f0_print.py, we use a dedicated function from the file to extract the f0 this improves security and speed quite significantly Partially...
Since hifi-gan is really old and outdated, i suggest you add something newer and more robust such as BIGvae gan. The results seem promising and can improve the overall performance...
The title might be a bit confusing, but what i'm referring to is how some python scripts are ran in a subshell, even though they could be used as regular...
This idea has been around for quite some time, the main reasoning is that `.pth` files are fundamentally unsafe, allowing for remote code execution if injected. This brings us to...
the images embedded in the README on the main branch point to RVC-Boss' repo, thus they work. On dev branch however, the images URLs point to fumiami/Retrieval-based-Voice-Conversion-WebUI , and since...
what's the rationale for duplicating the mute files during training?  Why does including it just once not work?
