Tutorial: Windows installation #647

car1ot · 2021-02-02T07:26:57Z

Hello,
I have an issues with installing to windows (10). Please, could you give a guide?

ghost · 2021-02-02T07:55:24Z

Get files for Real-Time-Voice-Cloning

Download this file to get the latest version of Real-Time-Voice-Cloning: https://github.com/CorentinJ/Real-Time-Voice-Cloning/archive/master.zip
Extract it to C:\ The files will be in a folder called Real-Time-Voice-Cloning-master

Install Python

Download Python from here: https://www.python.org/ftp/python/3.7.9/python-3.7.9-amd64.exe
- Warning: Other versions of Python may not work.
- Warning: Do not install Python from the Windows Store.
Run the installer. Click the "Install Now" button. Do not change the defaults.
Exit the installer when complete. Do not disable the path length limit.
Edit the environment variables for your account. Add these locations to PATH. First is for python.exe, second is for pip.exe. Move these to the top to take precedence over any pre-existing Python installations.

%USERPROFILE%\AppData\Local\Programs\Python\Python37
%USERPROFILE%\AppData\Roaming\Programs\Python\Python37\Scripts

Set up virtual environment and install required packages

Open Windows command prompt and run these commands to set up and activate a virtual environment. Real-Time-Voice-Cloning needs this dedicated environment as it uses obsolete packages that could cause conflicts with other Python programs.

cd C:\Real-Time-Voice-Cloning-master
python -m venv venv
venv\Scripts\activate.bat

Next, run these commands to install Python packages.

pip install --upgrade pip
pip install torch -f https://download.pytorch.org/whl/torch_stable.html
pip install -r requirements.txt

Get FFmpeg

Download FFmpeg from here: https://github.com/BtbN/FFmpeg-Builds/releases/download/autobuild-2021-10-31-12-23/ffmpeg-N-104454-gd92fdc7144-win64-lgpl.zip
Extract the zip file. Move ffmpeg.exe to C:\Real-Time-Voice-Cloning-master (the same folder as demo_toolbox.py)

Pretrained models

Download pretrained models from: https://github.com/blue-fish/Real-Time-Voice-Cloning/releases/download/v1.0/pretrained.zip
Extract pretrained.zip. Move the included files to the below locations. See here if you need more help on this step.

C:\Real-Time-Voice-Cloning-master\encoder\saved_models\pretrained.pt
C:\Real-Time-Voice-Cloning-master\synthesizer\saved_models\pretrained\pretrained.pt
C:\Real-Time-Voice-Cloning-master\vocoder\saved_models\pretrained\pretrained.pt

Launching the toolbox

Open Windows command prompt and type:

cd C:\Real-Time-Voice-Cloning-master
venv\Scripts\activate.bat
python demo_toolbox.py

bigdog3604 · 2021-02-03T18:19:04Z

I have been trying to install this program for over two days without any luck. I've followed the "Poorly Documented" guide and believe I have followed all the steps. I try to launch the CLI toolbox and get an error: ModuleNotFound: No module name 'webrtcvad'. I go to the Python 3.7 lib folder and the module is there. I would love to work with @tomodachi94 to test out his new process for Windows 10 users. The existing process sucks.

ghost · 2021-02-03T18:54:52Z

@bigdog3604
Since #376, webrtcvad is optional and the toolbox will run without it.
Make sure you have downloaded the latest version of Real-Time-Voice-Cloning from this site.
Here's a download link: master.zip

ghost · 2021-02-03T18:56:41Z

The "Poorly Documented" guide is obsolete given the recent usability improvements. It is hurting users more than it is helping now. We should stop linking to it in the README.

HeliumHead · 2021-02-03T19:02:33Z

If you'd like to use
webrtcvad, I think it requires the 64 bit version of Python 3.7, but I could be confusing that with something else...

CarvellScott · 2021-03-15T01:03:06Z

I'm attempting to install this on Windows 10 as well. I used Anaconda to install Pytorch and the rest of the requirements, but as far as downloading ffmpeg goes, I'm not sure where to place it for the executable to be found...

Nonetheless, the rest of the installation seemed to proceed without any issues. Upon running the demo however, I see this message:

C:\Users\Carvell\gitrepos\Real-Time-Voice-Cloning\encoder\audio.py:13: UserWarning: Unable to import 'webrtcvad'. This package enables noise removal and is recommended.
  warn("Unable to import 'webrtcvad'. This package enables noise removal and is recommended.")
Arguments:
    enc_model_fpath:   encoder\saved_models\pretrained.pt
    syn_model_fpath:   synthesizer\saved_models\pretrained\pretrained.pt
    voc_model_fpath:   vocoder\saved_models\pretrained\pretrained.pt
    cpu:               False
    no_sound:          False
    seed:              None
    no_mp3_support:    False

A s s e r t i o n   f a i l e d !

 P r o g r a m :   C : \ U s e r s \ C a r v e l l \ a n a c o n d a 3 \ e n v s \ v o i c e _ c l o n i n g \ p y t h o n . e x e
 F i l e :   s r c / h o s t a p i / w d m k s / p a _ w i n _ w d m k s . c ,   L i n e   1 0 6 1

 E x p r e s s i o n :   F A L S E

The s p a c e d o u t text appears there as it does in my terminal. The python version in the conda env I'm using is 3.8.8.

AyseEe501 · 2021-05-21T22:23:07Z

this can help #758 (comment)

Tomcattwo · 2021-09-26T02:50:27Z

@CarvellScott You can install ffmpeg via sourceforge in Anaconda using this command:
conda install -c conda-forge ffmpeg-python
See here for details: https://anaconda.org/conda-forge/ffmpeg-python
Regards, Tomcattwo

Tornakin · 2021-09-26T19:08:42Z

I've been able to install every thing else so far but can't figure out what I'm supposed to do with (pip install -r requirements.txt)

LukeCronquist · 2021-10-20T00:39:25Z

Error: Model files not found. even though they are there D;

Also UserWarning: PySoundFile failed. also No such file or directory: 'samples/1320_00000.mp3' when run the test config

EDIT: my bad, skimmed over the 3.6/.7 only

ghost · 2021-10-20T05:01:41Z

Error: Model files not found. even though they are there D;

Most of the time, can be solved with #758 (comment) or #642 (comment)

MuhammadWaqar621 · 2023-04-10T07:55:57Z

i want to train for other language, can you able to help me?

Tomcattwo · 2023-04-10T10:25:25Z

Muhammad, No, I can't. That is a much bigger project than what I have done. Sorry.

…

________________________________ From: Muhammad Waqar ***@***.***> Sent: Monday, April 10, 2023 3:56:08 AM To: CorentinJ/Real-Time-Voice-Cloning ***@***.***> Cc: Tomcattwo ***@***.***>; Comment ***@***.***> Subject: Re: [CorentinJ/Real-Time-Voice-Cloning] Tutorial: Windows installation (#647) i want to train for other language, can you able to help me? — Reply to this email directly, view it on GitHub<#647 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/ALF47JAQOPUWGMT6C5XGJ5DXAO4JRANCNFSM4W6EC57Q>. You are receiving this because you commented.Message ID: ***@***.***>

PixelcrafterEXE · 2023-05-12T20:52:57Z

Get FFmpeg

Download FFmpeg from here: https://github.com/BtbN/FFmpeg-Builds/releases/download/autobuild-2021-10-31-12-23/ffmpeg-N-104454-gd92fdc7144-win64-lgpl.zip

Extract the zip file. Move ffmpeg.exe to C:\Real-Time-Voice-Cloning-master (the same folder as demo_toolbox.py)

Alternatively winget install FFmpeg would be more elegant.

HeliumHead mentioned this issue Mar 23, 2021

Improved Install Instructions #642

Closed

ghost pinned this issue Sep 8, 2021

ghost closed this as completed Nov 16, 2021

LeWuDISE mentioned this issue Mar 21, 2022

Download for pretrained models doesn't work anymore #1042

Open

This issue was closed.

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Tutorial: Windows installation #647

Tutorial: Windows installation #647

car1ot commented Feb 2, 2021 •

edited

ghost commented Feb 2, 2021 •

edited by ghost

bigdog3604 commented Feb 3, 2021

ghost commented Feb 3, 2021

ghost commented Feb 3, 2021

HeliumHead commented Feb 3, 2021 •

edited

CarvellScott commented Mar 15, 2021

AyseEe501 commented May 21, 2021

Tomcattwo commented Sep 26, 2021 •

edited by ghost

Tornakin commented Sep 26, 2021

LukeCronquist commented Oct 20, 2021 •

edited

ghost commented Oct 20, 2021

MuhammadWaqar621 commented Apr 10, 2023

Tomcattwo commented Apr 10, 2023 via email

PixelcrafterEXE commented May 12, 2023

Get FFmpeg

Tutorial: Windows installation #647

Tutorial: Windows installation #647

Comments

car1ot commented Feb 2, 2021 • edited

ghost commented Feb 2, 2021 • edited by ghost

Get files for Real-Time-Voice-Cloning

Install Python

Set up virtual environment and install required packages

Get FFmpeg

Pretrained models

Launching the toolbox

bigdog3604 commented Feb 3, 2021

ghost commented Feb 3, 2021

ghost commented Feb 3, 2021

HeliumHead commented Feb 3, 2021 • edited

CarvellScott commented Mar 15, 2021

AyseEe501 commented May 21, 2021

Tomcattwo commented Sep 26, 2021 • edited by ghost

Tornakin commented Sep 26, 2021

LukeCronquist commented Oct 20, 2021 • edited

ghost commented Oct 20, 2021

MuhammadWaqar621 commented Apr 10, 2023

Tomcattwo commented Apr 10, 2023 via email

PixelcrafterEXE commented May 12, 2023

Get FFmpeg

car1ot commented Feb 2, 2021 •

edited

ghost commented Feb 2, 2021 •

edited by ghost

HeliumHead commented Feb 3, 2021 •

edited

Tomcattwo commented Sep 26, 2021 •

edited by ghost

LukeCronquist commented Oct 20, 2021 •

edited