Upload app.py

static/app.py

@@ -0,0 +1,97 @@
+import os
+import pickle
+import joblib
+import numpy as np
+import uvicorn
+from fastapi import FastAPI, UploadFile, File
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.staticfiles import StaticFiles
+from fastapi.responses import FileResponse
+from extract import extract_features  # Import feature extractor
+
+# Initialize FastAPI app
+app = FastAPI()
+
+# Enable CORS
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# Set up static files directory for frontend
+app.mount("/static", StaticFiles(directory="static"), name="static")
+
+# Load trained model, scaler, and feature list
+model_path = "models/gender_model_lr.pkl"
+scaler_path = "models/scaler_gender_model_lr.pkl"
+feature_list_path = "models/feature_list.pkl"
+
+model = joblib.load(model_path)
+scaler = joblib.load(scaler_path)
+with open(feature_list_path, "rb") as f:
+    feature_list = pickle.load(f)
+
+print("✅ Model, Scaler, and Feature List Loaded Successfully!")
+
+
+# Route to serve UI (index.html)
+@app.get("/")
+async def serve_ui():
+    return FileResponse("static/index.html")
+
+
+# Prediction API
+@app.post("/predict")
+async def predict(audio: UploadFile = File(...)):
+    try:
+        # Save uploaded file
+        UPLOAD_FOLDER = "uploads"
+        os.makedirs(UPLOAD_FOLDER, exist_ok=True)
+        filepath = os.path.join(UPLOAD_FOLDER, audio.filename)
+        
+        with open(filepath, "wb") as f:
+            f.write(await audio.read())
+
+        print(f"🟢 Processing file: {audio.filename}")
+
+        # Extract features
+        features = extract_features(filepath)
+        if features is None:
+            return {"error": "Feature extraction failed"}
+        
+        print(f"🟢 Extracted {len(features)} features.")
+
+        # Scale features
+        features_scaled = scaler.transform([features])
+        print("🟢 Features scaled successfully.")
+
+        # Predict gender
+        prediction = model.predict(features_scaled)[0]
+        confidence = model.predict_proba(features_scaled)[0]
+        print("🟢 Prediction completed.")
+
+        # Format response
+        result = {
+            "gender": "Female" if prediction == 1 else "Male",
+            "confidence": float(max(confidence)),
+            "age_group": "Unknown"
+        }
+
+        print(f"✅ Result: {result}")
+
+        # Delete temp file
+        os.remove(filepath)
+
+        return result
+
+    except Exception as e:
+        print(f"❌ Error: {e}")
+        return {"error": str(e)}
+
+
+# Run FastAPI with Uvicorn
+if __name__ == "__main__":
+    uvicorn.run("app:app", host="0.0.0.0", port=7860, reload=True)