Retrieval-based-Voice-Conversion-WebUI issues

Training Cancel button and Model List Management

2

The training needs a cancel or stop button to stop the training process, since training can easily be resumed, I see no reason why a simple stop button is too...

jurassicjordan

Web inference fails due to insufficient memory

3

Web inference fails due to insufficient memory

c469591

Sound Module?

2

I'm trying to install and I keep getting this Traceback (most recent call last): File "C:\TCHT\Retrieval-based-Voice-Conversion-WebUI\infer-web.py", line 24, in from MDXNet import MDXNetDereverb File "C:\TCHT\Retrieval-based-Voice-Conversion-WebUI\MDXNet.py", line 1, in import soundfile...

Mal009

16khz for inference vs 22khz?

2

I notice 16khz seems to be hard programmed into the code for the downsampling phase. I think supporting more modular sample rates for inference audio would make sense. With librosa...

kalomaze

I have a problem with the interface

1

I have a problem Show me this message Traceback (most recent call last): File "C:\TCHT\Retrieval-based-Voice-Conversion-WebUI\infer-web.py", line 314, in uvr pre_fun = MDXNetDereverb(15) File "C:\TCHT\Retrieval-based-Voice-Conversion-WebUI\MDXNet.py", line 242, in __init__ self.pred =...

ayaayams

How does RVC handle reconstructing audio from the spectrogram?

7

Are you guys using librosa.griffinlim or some other technique when converting to audio from spectrogram data?

kalomaze

Stop extracting features when hubert_base.pt does not exist.

3

When there is no hubert_base.pt, the training process will not stop, and it will normally run through each epoch. However, the speed is abnormally fast, and the result is a...

JunityZhan