Update app.py

app.py

@@ -1,33 +1,22 @@
-import torch
-from transformers import GPT2LMHeadModel, GPT2Tokenizer
 import gradio as gr
-import matplotlib.pyplot as plt
+from transformers import pipeline
 
-model = GPT2LMHeadModel.from_pretrained("gpt2")
-tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
+# Load the GPT-2 pipeline for text generation
+classifier = pipeline("text-classification", model="gpt2")
 
-def predict_fake_news(text):
-    input_text = text
-
-    input_ids = tokenizer.encode(input_text, return_tensors='pt', add_special_tokens=True)
-
-    input_ids = input_ids[:, :1024]  
-    
-    output = model.generate(input_ids, max_length=50, num_return_sequences=1, pad_token_id=tokenizer.eos_token_id, attention_mask=input_ids)
-    generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
+def analyze_text(text):
+    # Use the GPT-2 classifier to predict if the text is fake or true
+    result = classifier(text)[0]
     
-    fake_confidence = 1 if "fake" in generated_text.lower() else 0
-    real_confidence = 1 - fake_confidence
+    # Extract the label and confidence score
+    label = result['label']
+    score = result['score']
     
-    fig, ax = plt.subplots()
-    ax.bar(["Real", "Fake"], [real_confidence, fake_confidence], color=['blue', 'red'])
-    plt.ylim(0, 1)
-    plt.xticks(rotation=45)
-    plt.title("Prediction Confidence")
-    
-    return fig
-
-input_text = gr.Textbox(lines=7, label="Paste the news article here", placeholder="Example: Scientists have discovered a new cure for cancer.")
-output_graph = gr.Image(label="Prediction Confidence")
+    return {"Result": label, "Confidence (%)": score * 100}
 
-gr.Interface(predict_fake_news, inputs=input_text, outputs=output_graph, title="Real/Fake News Detector", theme="soft").launch()
+# Gradio interface with soft theme
+gr.Interface(analyze_text, 
+             "text",
+             "text",
+             theme="soft"
+             ).launch()