Skip to content

Creation of a neural network than can recognize voice signals from 0-9

Notifications You must be signed in to change notification settings

LiamNiisan/vocal-neural-network

Repository files navigation

vocal-neural-network

The goal of this project is to create a neural network from scratch. No machine learning framework is used, only numpy is used to handle the parameters of the model.

The built neural network is then used to learn vocal patterns and predict spoken numbers.

Runtime

Dependencies

  • numpy
  • matplotlib
  • pyqt

Parameters

The parameters can be changed using the interface once the program is executed.

The parameters are written in the nn_config.txt file.

Execution

Run the interface.py file to start the program.

Log

At each epoch, the state of the model will be saved in data/

About

Creation of a neural network than can recognize voice signals from 0-9

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages