Voice-Gender-Prediction

A simple Machine learning application of Gender Prediction using Audio file of Humans

TO SIMPLY RUN THIS MODEL

1. Clone this repository.
2. Run the gui.py file
3. Upload the audio file (.wav file onmly) you want to test.
4. Click on "Detect" button.
5. You can even listen to the audio file by clicking "Play Audio" button.
6. View the result.

TO RUN THIS MODEL YOURSELF:

1. Clone this repository.
2. Download this dataset from here
3. Extract the dataset to your repository folder.
4. The balanced-all.csv has the preprocessed audio file stored in .npy format.
5. Open the Model jupyter notebook
6. Run this notebook
7. Run the gui.py file.
8. Upload the audio file (.wav file onmly) you want to test.
9. Click on "Detect" button.
10. You can even listen to the audio file by clicking "Play Audio" button.
11. View the result.

SAMPLE OUTPUTS

Sample Output1

Sample Output2

Sample Output3

Sample Output4