Audio Classification using Machine Learning This app is designed to show integration of tensorflow, flask, by developing a web app to make classification of two different sounds, per say, two persons. Steps:
- Record audio samples from two person
- Prepare mfcc for audio records
- Traing MultiLayerPersoptron using tensorflow-keras
- Save model
- Record a sample for prediction
- Make the prediction Since the purpose of this app is to demonstrate integration, model performance may not be too good (can be much better using different structures).
