README.md

---
title: Voice Similarity Checker
emoji: 🎙️
colorFrom: purple
colorTo: pink
sdk: gradio
sdk_version: 6.0.2
app_file: app.py
pinned: false
license: mit
---

# 🎙️ Voice Similarity Checker

Compare two voice samples using advanced speaker recognition AI powered by SpeechBrain's ECAPA-TDNN model.

## 🚀 Quick Start

### Run Locally
```bash
# Install dependencies
pip install -r requirements.txt

# Launch the Gradio interface
python app.py
```

### Run Original Script
```bash
python speech_brain_text.py
```

## ✨ Features

- 🎤 **Compare Any Audio Files**: Upload two voice samples in any format (WAV, MP3, FLAC, etc.)
- 📊 **Similarity Score**: Get a precise similarity score and speaker verification
- ⚡ **Performance Metrics**: View detailed metrics including:
  - Elapsed processing time
  - Memory usage statistics
  - CPU utilization
- 🎨 **Modern UI**: Beautiful, responsive Gradio interface with gradient themes

## 📖 How to Use

1. Upload your first audio file in the "Voice Sample 1" section
2. Upload your second audio file in the "Voice Sample 2" section
3. Click the "Compare Voices" button
4. View the similarity results and performance metrics

## 🤖 Model Information

This application uses the **SpeechBrain ECAPA-TDNN** model:
- Model: `speechbrain/spkrec-ecapa-voxceleb`
- Architecture: ECAPA-TDNN
- Training Data: VoxCeleb corpus

## 📦 Project Structure

- `app.py` - Modern Gradio web interface
- `speech_brain_text.py` - Original CLI script
- `requirements.txt` - Python dependencies
- `README.md` - This file

## 🌐 Deploy to Hugging Face Spaces

This app is ready to deploy to Hugging Face Spaces. Simply:
1. Create a new Space on Hugging Face
2. Upload all files from this repository
3. The app will automatically launch!

## 📄 License

MIT License