Voice Identifier ML Model

A simple Machine Learning project to recognize a speaker's voice from a set of recorded samples.

Features

• Accepts 4 speaker samples.
• Predicts speaker identity based on input voice.
• Implemented basic data preprocessing and feature extraction.
• Handles overfitting issues (in progress).

Tech Stack

• Python
• TensorFlow
• Scikit-learn
• Librosa (for audio feature extraction)

How to Run

1. Clone this repository.
2. Install dependencies:

pip install -r requirements.txt

3. Open and run:

VoiceIdentifier.py

4. Train the model with sample audio inputs.

Future Improvements

• Expand dataset for better generalization.
• Implement model regularization techniques.
• Build a simple web-based user interface.