Update app.py

app.py

@@ -104,7 +104,7 @@ st.title("📰 Fake News & Deepfake Detection Tool")
 st.write("🚀 Detect Fake News, Deepfake Images, and Videos using AI")
 
 # Load Models
-fake_news_detector = pipeline("text-classification", model="MoritzLaurer/deberta-v3-large-contrastive-fake-news")
+fake_news_detector = pipeline("text-classification", model="microsoft/deberta-v3-base")
 
 # Load Deepfake Detection Models
 base_model_image = Xception(weights="imagenet", include_top=False)
@@ -137,64 +137,41 @@ def detect_deepfake_image(image_path):
     label = "FAKE" if confidence > 0.5 else "REAL"
     return {"label": label, "score": confidence}
 
-# # ---- Fake News Detection Section ----
-# st.subheader("📝 Fake News Detection")
-# news_input = st.text_area("Enter News Text:", placeholder="Type here...")
-
-# # Manually verified facts database (you can expand this)
-# fact_check_db = {
-#     "elon musk was born in 1932": "FAKE",
-#     "earth revolves around the sun": "REAL",
-#     "the moon is made of cheese": "FAKE",
-# }
-
-# def check_manual_facts(text):
-#     text_lower = text.lower().strip()
-#     return fact_check_db.get(text_lower, None)
-
-# if st.button("Check News"):
-#     st.write("🔍 Processing...")
-
-#     # Check if the news is in the fact-check database
-#     manual_result = check_manual_facts(news_input)
-#     if manual_result:
-#         if manual_result == "FAKE":
-#             st.error(f"⚠️ Result: This news is **FAKE** (Verified by Database).")
-#         else:
-#             st.success(f"✅ Result: This news is **REAL** (Verified by Database).")
-#     else:
-#         # Use AI model if fact is not in the database
-#         prediction = fake_news_detector(news_input)
-#         label = prediction[0]['label'].lower()
-#         confidence = prediction[0]['score']
-
-#         if "fake" in label or confidence < 0.5:
-#             st.error(f"⚠️ Result: This news is **FAKE**. (Confidence: {confidence:.2f})")
-#         else:
-#             st.success(f"✅ Result: This news is **REAL**. (Confidence: {confidence:.2f})")
-from transformers import pipeline
-import streamlit as st
-
-# ✅ Load a Valid Fake News Detection Model
-fake_news_detector = pipeline("text-classification", model="MoritzLaurer/deberta-v3-large-contrastive-fake-news")
-
+# ---- Fake News Detection Section ----
 st.subheader("📝 Fake News Detection")
 news_input = st.text_area("Enter News Text:", placeholder="Type here...")
 
+# Manually verified facts database (you can expand this)
+fact_check_db = {
+    "elon musk was born in 1932": "FAKE",
+    "earth revolves around the sun": "REAL",
+    "the moon is made of cheese": "FAKE",
+}
+
+def check_manual_facts(text):
+    text_lower = text.lower().strip()
+    return fact_check_db.get(text_lower, None)
+
 if st.button("Check News"):
     st.write("🔍 Processing...")
 
-    # ✅ Get Model Prediction
-    prediction = fake_news_detector(news_input)
-    label = prediction[0]['label'].lower()
-    confidence = prediction[0]['score']
-
-    # ✅ Ensure Correct Classification
-    if "fake" in label or confidence < 0.5:
-        st.error(f"⚠️ Result: This news is **FAKE**. (Confidence: {confidence:.2f})")
+    # Check if the news is in the fact-check database
+    manual_result = check_manual_facts(news_input)
+    if manual_result:
+        if manual_result == "FAKE":
+            st.error(f"⚠️ Result: This news is **FAKE** (Verified by Database).")
+        else:
+            st.success(f"✅ Result: This news is **REAL** (Verified by Database).")
     else:
-        st.success(f"✅ Result: This news is **REAL**. (Confidence: {confidence:.2f})")
+        # Use AI model if fact is not in the database
+        prediction = fake_news_detector(news_input)
+        label = prediction[0]['label'].lower()
+        confidence = prediction[0]['score']
 
+        if "fake" in label or confidence < 0.5:
+            st.error(f"⚠️ Result: This news is **FAKE**. (Confidence: {confidence:.2f})")
+        else:
+            st.success(f"✅ Result: This news is **REAL**. (Confidence: {confidence:.2f})")
 
 # ---- Deepfake Image Detection Section ----
 st.subheader("📸 Deepfake Image Detection")