Skip to content

Clone a voice in 5 seconds to generate arbitrary speech in real-time

License

Notifications You must be signed in to change notification settings

sahilrajpal121/DS-Intern-Assignment

 
 

Repository files navigation

You can read the original README.md file here

After hours and hours of playing around and messing with package dependecy issues, I have finally managed to make it work in Conda environment.

Run python demo_cli.py and see if it works.

I'd suggest you to use conda virutal env. Here is a Google colab file which runs this repo and generates the audio output, as per task.

Some Instructions and Suggestions

  1. Please install all the packages
pip install -r requirements.txt
  1. Make sure you have torch installed seperately (refer to original README file for more)
  2. Make sure you have ffmpeg installed. ( not required for Google colab)
  3. (Optional) If webrtcvad spits wheels error, try running this on CLI
pip install webrtcvad-wheels

About

Clone a voice in 5 seconds to generate arbitrary speech in real-time

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Languages

  • Python 100.0%