How to use RVC WebUI with Intel Iris Xe Graphics?

douari dedi:

Very helpful. I am sorry but ı would like to train in RVC with Intel Iris Xe Graphics. Please help me.

非常に役立ちます。申し訳ありませんが、Intel iris xe グラフィックスを使用した RVC でトレーニングしたいと考えています。私を助けてください。

Genişletmek için tıkla...

Currently IPEX doesn't support iGPUs.

理解した。何らかの方法を使用して intel iris xe グラフィックスでトレーニングする方法はありますか? 音声変換には成功しましたが、トレーニングでは成功せず、まだ CPU しか使用できません。

douari dedi:

インテル アイリス XE CPUを使用することはできません。

Genişletmek için tıkla...

@ディスティ
理解した。
すべて試しましたが、Intel iris xe グラフィックスで GPU を使用してトレーニングする方法はありますか? CPU でのみトレーニングできます。音声変換には directml を使用して GPU を使用できますが、トレーニングには使用できません。

Understood.
I have tried everything, but is there any way to train using GPU with intel iris xe graphics?　I can only train on cpu I can use GPU using directml for voice conversion but not for training.

@Disty
Understood.
I have tried everything, but is there any way to train using GPU with intel iris xe graphics?　I can only train on cpu I can use GPU using directml for voice conversion but not for training.

@Disty
If you do it this way, the GPU itself seems to recognize it, but no actual conversion or training can be done!
INFO | configs. Config | Found GPU Intel(R) Graphics [0x9a49].
2023-10-02 23:05:48 | INFO | configs. Config | Use xpu: 0 instead
2023-10-02 23:05:48 | INFO | __main__ | Use Language: En_US

@douari you can try compiling IPEX from the soruce for your iGPU:
xpu-master build for IGPU error · Issue #390 · intel/intel-extension-for-pytorch

We apologize. I am not very knowledgeable about this. I would appreciate it if you could write down the procedure for me.

@Disty We apologize. I am not very knowledgeable about this. I would appreciate it if you could write down the procedure for me.

This is the Intel's guide:

This is another guide:

@Disty

@Disty I tried this (Installation Guide (Linux/WSL2) — intel_extension_for_pytorch 2.0.110+xpu documentation), but I was able to build up to step 6, but an error occurred if the necessary requirements were not installed. I tried to install what I needed, but I couldn't do anything because I had no idea what to install or what command to run using only the links in steps 1 and 3. Help me. I've been experimenting with this for about 2 weeks and haven't gotten any results.

@Disty I made a mistake in the link. I tried various things according to this procedure, but I couldn't figure out what to do with only the links in steps 1 and 3.

@Disty
Yup, thanks, adding to render was it. I had added myself to video instead for some reason.

Closing this as the problems were just a result of misconfiguration, but here's a summary for future readers of what I did.

1. Install client IGPU packages
2. Add user to the render group. In my case this group already existed so sudo usermod -aG render $USER & reboot.
3. Install oneapi base toolkit
4. Create a fresh python environment and activate it.
5. Optionally source /opt/intel/oneapi/setvars.sh and run the collect_env.py script check installation
6. Clone intel-extension-for-pytorch, checkout xpu-master, and build with bash scripts/compile_bundle.sh /opt/intel/oneapi/compiler/2023.2.0/ /opt/intel/oneapi/mkl/2023.2.0/ Gen12LP, replacing Gen12LP for the desired IGPU configuration

And then remember to source /oipt/intel/oneapi/setvars.sh before using torch.

@Disty I think I'll give up on training on GPU.
By the way, I downloaded the version introduced on this site, and although I was able to start the webui, I was unable to convert the audio. Is it okay to just download this?

@Disty Release updated1006v2 · RVC-Project/Retrieval-based-Voice-Conversion-WebUI

iGPUs are not officially supported on IPEX and i don't have any iGPU to test with. Can't really help with iGPUs :/