Add Hugging Face Spaces deployment configuration

Dockerfile

@@ -0,0 +1,22 @@
+FROM python:3.11-slim
+
+WORKDIR /app
+
+# Install system dependencies for audio processing
+RUN apt-get update && apt-get install -y \
+    ffmpeg \
+    libsndfile1 \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements first for caching
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy application code
+COPY . .
+
+# Expose port 7860 (HuggingFace Spaces default)
+EXPOSE 7860
+
+# Run the application
+CMD ["python", "run.py", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -1,112 +1,27 @@
-# AI Voice Detection API
+---
+title: AI Voice Detection API
+emoji: 🎤
+colorFrom: blue
+colorTo: purple
+sdk: docker
+pinned: false
+license: mit
+---
 
-Detect AI-generated voices across multiple languages with NVIDIA PersonaPlex detection.
+# AI Voice Detection API
 
-## Features
+Detect AI-generated voices using advanced acoustic analysis and neural network patterns.
 
-- 🎯 **Multi-Model Detection**: Ensemble of Wav2Vec2, CNN, and signature analysis
-- 🌐 **Multi-Language Support**: Tamil, English, Hindi, Malayalam, Telugu
-- 🔍 **AI Tool Detection**: Identifies NVIDIA PersonaPlex, ElevenLabs, Azure TTS, Google WaveNet
-- 📊 **Detailed Explanations**: Technical analysis with confidence scores
+## API Endpoints
 
-## Quick Start
+- `POST /api/v1/detect` - Detect if audio is AI-generated
+- `GET /api/v1/health` - Health check
+- `GET /docs` - API documentation
 
-### 1. Install Dependencies
+## Usage
 
 ```bash
-pip install -r requirements.txt
-```
-
-### 2. Run the Server
-
-```bash
-# Development mode with auto-reload
-python run.py --reload
-
-# Or directly with uvicorn
-uvicorn app.main:app --reload --port 8000
-```
-
-### 3. Test the API
-
-Open http://localhost:8000/docs for the interactive Swagger UI.
-
-## API Usage
-
-### Detect AI Voice
-
-**Endpoint:** `POST /api/v1/detect`
-
-**Request:**
-```json
-{
-  "audio_base64": "<Base64-encoded MP3 audio>",
-  "language_hint": "en"
-}
-```
-
-**Response:**
-```json
-{
-  "classification": "ai_generated",
-  "confidence": 0.92,
-  "ai_probability": 0.92,
-  "human_probability": 0.08,
-  "ai_tool_detected": "NVIDIA PersonaPlex/Riva",
-  "explanation": {
-    "summary": "Strong evidence of AI-generated voice detected",
-    "confidence_level": "high",
-    "technical_details": {
-      "spectral_artifacts": ["Vocoder artifacts in 6-8kHz"],
-      "temporal_patterns": ["Low temporal variation"],
-      "synthesis_markers": ["HiFi-GAN fingerprint"]
-    },
-    "key_indicators": [
-      "Signature matches NVIDIA PersonaPlex/Riva",
-      "Phase coherence matches HiFi-GAN pattern"
-    ]
-  }
-}
+curl -X POST "https://YOUR-SPACE.hf.space/api/v1/detect" \
+  -H "Content-Type: application/json" \
+  -d '{"audioUrl": "https://example.com/audio.mp3"}'
 ```
-
-## Detection Methods
-
-| Method | Weight | Description |
-|--------|--------|-------------|
-| IndicWav2Vec | 45% | Deep acoustic patterns using Indian language models |
-| Spectrogram CNN | 35% | Visual artifact detection in mel spectrograms |
-| PersonaPlex Detector | 20% | AI tool signature matching |
-
-## Supported Languages
-
-| Code | Language |
-|------|----------|
-| ta | Tamil |
-| en | English |
-| hi | Hindi |
-| ml | Malayalam |
-| te | Telugu |
-
-## Project Structure
-
-```
-hackathon1/
-├── app/
-│   ├── main.py              # FastAPI application
-│   ├── config.py            # Configuration
-│   ├── api/
-│   │   ├── routes.py        # API endpoints
-│   │   └── schemas.py       # Pydantic models
-│   └── models/
-│       ├── wav2vec_detector.py      # IndicWav2Vec detector
-│       ├── spectrogram_cnn.py       # CNN classifier
-│       ├── personaplex_detector.py  # AI tool detection
-│       └── ensemble_detector.py     # Ensemble fusion
-├── requirements.txt
-├── run.py                   # Server entry point
-└── README.md
-```
-
-## License
-
-MIT License