Upload 6 files

Dockerfile

@@ -0,0 +1,23 @@
+FROM python:3.9-slim
+
+# Install system dependencies for audio processing
+RUN apt-get update && apt-get install -y \
+    ffmpeg \
+    && rm -rf /var/lib/apt/lists/*
+
+# Set working directory
+WORKDIR /app
+
+# Copy requirements and install Python dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy application code
+COPY . .
+
+# Expose port (Hugging Face Spaces uses port 7860)
+EXPOSE 7860
+
+# Run the FastAPI app
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
+

README.md

@@ -1,10 +1,74 @@
 ---
-title: Gunashree Hackathon
-emoji: 👁
-colorFrom: purple
-colorTo: indigo
+title: AI Voice Detection API
+emoji: 🎤
+colorFrom: blue
+colorTo: purple
 sdk: docker
+sdk_version: 4.38.0
+app_port: 7860
 pinned: false
+license: mit
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# AI Voice Detection API
+
+Detects whether a voice sample is AI-generated or human across multiple languages.
+
+## Supported Languages
+- Tamil
+- English
+- Hindi
+- Malayalam
+- Telugu
+
+## Features
+- FastAPI-based REST API
+- Wav2Vec2 embeddings + signal feature extraction
+- Pre-trained classifier for AI/Human voice detection
+- Base64 MP3 audio input
+- API key protected endpoints
+
+## API Endpoints
+
+### Health Check
+```
+GET /health
+```
+
+### Voice Detection
+```
+POST /api/voice-detection
+Headers:
+  x-api-key: <your-api-key>
+
+Body:
+{
+  "language": "English",
+  "audioFormat": "mp3",
+  "audioBase64": "<base64-encoded-audio>"
+}
+```
+
+## Response Format
+```json
+{
+  "status": "success",
+  "language": "English",
+  "classification": "HUMAN" | "AI_GENERATED",
+  "confidenceScore": 0.95,
+  "explanation": "Natural prosody, breathing patterns..."
+}
+```
+
+## Environment Variables
+- `API_KEY`: API key for authentication (default: "hackathon-secret")
+
+## Model Architecture
+- Uses Facebook's Wav2Vec2-base for audio embeddings
+- Extracts signal features (pitch variance, spectral centroid, zero-crossing rate)
+- Logistic regression classifier for final prediction
+
+## Team
+- ML: Gunashree
+- Backend: Tanu
+- DevOps/QA: Pavithra

app.py

@@ -0,0 +1,9 @@
+"""
+Hugging Face Spaces entry point for AI Voice Detection API
+This file imports the FastAPI app from app/main.py
+"""
+from app.main import app
+
+# Hugging Face Spaces will automatically detect and serve this app
+__all__ = ["app"]
+

requirements.txt

@@ -0,0 +1,12 @@
+fastapi
+uvicorn[standard]
+pydantic
+pydub
+librosa
+numpy
+torch
+transformers
+scikit-learn
+joblib
+soundfile
+ffmpeg-python

runtime.txt

@@ -0,0 +1 @@
+python-3.9.13