Retrieval-based-Voice-Conversion-WebUI

Retrieval-based-Voice-Conversion-WebUI copied to clipboard

[Feature request] Segmentation of audio based on parts to improve vocal output of long songs

3

There could be an advanced setting that detects where silence happens based on a threshold, and does each inference of long vocal pieces separately, then properly combines it into one...

kalomaze

Inferencing voice dropdown is empty

10

I've updated the project as per the instructions, but the 'Inferencing voice:' dropdown in the WebUI is still empty. I've also downloaded and loaded the pre-trained models as instructed. Could...

RodgerE1

Getting this issue under macOS, and resolved by installing bumpy version 1.23.5: https://stackoverflow.com/a/74982146 Also, as MPS training is now working, we should have `requirements-mac.txt` just like `requirements-win-for-realtime_vc_gui.txt`, as python behave...

Naozumi520

ERROR: Could not build wheels for fairseq, which is required to install pyproject.toml-based projects (while install requirements)

6

creating build\lib.win-amd64-cpython-310\fairseq\examples\textless_nlp\gslm\metrics\abx_metrics copying fairseq\examples\textless_nlp\gslm\metrics\abx_metrics\dump_abx_feats.py -> build\lib.win-amd64-cpython-310\fairseq\examples\textless_nlp\gslm\metrics\abx_metrics copying fairseq\examples\textless_nlp\gslm\metrics\abx_metrics\README.md -> build\lib.win-amd64-cpython-310\fairseq\examples\textless_nlp\gslm\metrics\abx_metrics creating build\lib.win-amd64-cpython-310\fairseq\examples\textless_nlp\gslm\metrics\asr_metrics copying fairseq\examples\textless_nlp\gslm\metrics\asr_metrics\continuation_eval.py -> build\lib.win-amd64-cpython-310\fairseq\examples\textless_nlp\gslm\metrics\asr_metrics copying fairseq\examples\textless_nlp\gslm\metrics\asr_metrics\ppx.py -> build\lib.win-amd64-cpython-310\fairseq\examples\textless_nlp\gslm\metrics\asr_metrics copying fairseq\examples\textless_nlp\gslm\metrics\asr_metrics\README.md -> build\lib.win-amd64-cpython-310\fairseq\examples\textless_nlp\gslm\metrics\asr_metrics copying fairseq\examples\textless_nlp\gslm\metrics\asr_metrics\self_auto_bleu.py -> build\lib.win-amd64-cpython-310\fairseq\examples\textless_nlp\gslm\metrics\asr_metrics creating build\lib.win-amd64-cpython-310\fairseq\examples\textless_nlp\gslm\metrics\asr_metrics\misc...

ZarBoy68

C:\Users\(myusername)\Downloads\(RVC)>python.exe infer-web.py --pycmd python.exe --port 7897 Use Language: en_US 没有发现支持的N卡, 使用CPU进行推理 Running on local URL: http://0.0.0.0:7897 loading weights/Dio_Brando_9800.pth gin_channels: 256 self.spk_embed_dim: 109 Traceback (most recent call last): File "C:\Users\username\Downloads\RVCWebui\infer-web.py", line...

HaloScripter

update poetry dependency

1

ricecakey06

Wrong naming for HP3 model output files. 使用HP3模型分离人声伴奏时，输出的文件命名错误。

1

When using HP3 model to split instrument and vocal, the _vocal_ audio is the instument, while the _instrument_ file is the vocal. 使用HP3模型分离人声伴奏时，opt/下的instrument音频实际上是人声，vocal是伴奏。其他模型则不会有这个问题。

XiangyiZhang

Error on m1 Mac mini with macOS Ventura 13.4

1

Release [updated0528v2](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/releases/tag/updated0528v2) when install dependency use pip install -r requirements.txt or manually install onnxruntime-gpu(I think this pack do not support Mac) will give error: ERROR: Could not find a version...

iamqk

I get an error when I try to open infer-web.py

1

Hi all! I already installed all required libraries but when I try to open infer-web.py, I get an error. Please help me solve the problem. I use OSX 11.7.6 (Big...

finnlogin

Question about sample rates

1

Considering 40khz sounds better than 48khz, is this because upsampling introduces duplicate data in the file that, algorithimically, makes the output voice result sound 'more robotic' despite being trained at...

kalomaze