This project trains a computer program to identify the voice of the speaker. It was a part of the master's degree (Electronic Systems Engineering) at Heilbronn University of Applied Sciences.
- Grade: 1,0 (Very good)
- Download or clone the project
- Open the cmd and run the following line of code:
$ python my_awesome_program.py
- Select some models for the training
- Select a reference
- Click the button "predict". Then you will see in the result field the prediction of the application
- Python 3.5 / 3.6 Packages:
- numpy (pip install numpy)
- Andreas Schneider
- Lisa-Franziska Schäfer
The MIT License (MIT)
Copyright (c) 2018 Andreas Schneider, Gustav Willig, Lisa-Franziska Schäfer