Real-time-voice-cloning: AMD / CPU-only support?

[zankai2]

Can't run it...

[daslicht]

you managed to get it wiorking with amd / cpu ?

[Traincraft101]

I have it working on amd ryzen 5 2600x

[Titaniumtown]

I had to manually edit the code to get it working

[genewitch]

I had to manually edit the code to get it working

Can you do a PR / fork?

[ghost]

@Traincraft101 push the edited code

[ByPort]

I got rid of all CUDA references in code and was able to run it on CPU
Try my repo or take a look at this commit
@genewitch @deepseek

[GtOkAi]

I got rid of all CUDA references in code and was able to run it on CPU
Try my repo or take a look at this commit
@genewitch @deepseek

I tried your repo, but returned same error. Need some special action?

[Traincraft101]

@deepsek I didn't edit the code, it just worked for me.

[seriiix]

@ByPort @GtOkAi Same.

[ByPort]

@GtOkAi @seriiix I used demo_toolbox.py. Just altered demo_cli.py so pull and try again

[GtOkAi]

@ByPort @seriiix Worked with pip3 install tensorflow==1.13.1

[gabrielmontagne]

@ByPort , awesome. thanks so much.

[Sba-Stuff]

I got rid of all CUDA references in code and was able to run it on CPU
Try my repo or take a look at this commit
@genewitch @deepseek

Tried Running This Code, Got An Issue Now , nvcuda.dll not found.

Traceback (most recent call last):
File "RTVC/demo_cli.py", line 3, in
from synthesizer.inference import Synthesizer
File "C:\Python\36\RTVC\synthesizerinference.py", line 1, in
from synthesizer.tacotron2 import Tacotron2
File "C:\Python\36\RTVC\synthesizer\tacotron2.py", line 3, in
from synthesizer.models import create_model
File "C:\Python\36\RTVC\synthesizer\models__init__.py", line 1, in
from .tacotron import Tacotron
File "C:\Python\36\RTVC\synthesizer\models\tacotron.py", line 1, in
import tensorflow as tf
File "C:\Python\36\lib\site-packages\tensorflow__init__.py", line 28, in
from tensorflow.python import pywrap_tensorflow # pylint: disable=unused-import
File "C:\Python\36\lib\site-packages\tensorflow\python__init__.py", line 49, in
from tensorflow.python import pywrap_tensorflow
File "C:\Python\36\lib\site-packages\tensorflow\python\pywrap_tensorflow.py", line 30, in
self_check.preload_check()
File "C:\Python\36\lib\site-packages\tensorflow\python\platform\self_check.py", line 70, in preload_check
% build_info.nvcuda_dll_name)

ImportError: "Could not find 'nvcuda.dll'. TensorFlow requires that this DLL be installed in a directory that is named in your %PATH% environment variable. Typically it is installed in 'C:\Windows\System32'. If it is not present, ensure that you have a CUDA-capable GPU with the correct driver installed."

[DonaldTsang]

https://mc.ai/clone-your-voice-in-5-minutes/

[Sba-Stuff]

Thank You. I Did It.
https://www.youtube.com/watch?v=Ob44qT1c4TY

[blue-fish]

Thank you for pioneering CPU support on this project @ByPort .

@pusalieth has implemented an elegant solution in #366 which provides CPU support as a fallback if necessary. Training works on CPU too! It is implemented in the main repo so I would like to suggest that everyone use that instead so we can continue developing it together.