Upload 2 files

ai_text_detector_valid_final.py

@@ -0,0 +1,59 @@
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
+import numpy as np
+
+# Multiple AI text detection models
+MODELS = {
+    "OpenAI Detector": "roberta-base-openai-detector",    # HuggingFace OpenAI GPT-2 detector
+    "GPT Detector": "Kishanjaisoorya/AI-Text-Detector",   # Community AI detector
+    "GPTZero-Style": "Hello-SimpleAI/chatgpt-detector-roberta"  # Another HF model
+}
+
+def load_model(model_id):
+    tokenizer = AutoTokenizer.from_pretrained(model_id)
+    model = AutoModelForSequenceClassification.from_pretrained(model_id)
+    return tokenizer, model
+
+def predict(text, tokenizer, model):
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
+    with torch.no_grad():
+        outputs = model(**inputs)
+        probs = torch.nn.functional.softmax(outputs.logits, dim=-1)
+    return probs[0].numpy()  # [human_prob, ai_prob]
+
+def detect_text(text):
+    results = {}
+    ai_scores = []
+
+    for name, model_id in MODELS.items():
+        try:
+            tokenizer, model = load_model(model_id)
+            probs = predict(text, tokenizer, model)
+            human_score, ai_score = probs
+            results[name] = {
+                "Human Probability": round(float(human_score) * 100, 2),
+                "AI Probability": round(float(ai_score) * 100, 2),
+            }
+            ai_scores.append(ai_score)
+        except Exception as e:
+            results[name] = {"error": str(e)}
+
+    # Final average score across models
+    if ai_scores:
+        avg_ai = np.mean(ai_scores) * 100
+        results["Final Score"] = {
+            "AI Probability (average)": round(avg_ai, 2),
+            "Human Probability (average)": round(100 - avg_ai, 2),
+        }
+
+    return results
+
+
+if __name__ == "__main__":
+    text = input("Enter text to analyze:\n")
+    output = detect_text(text)
+    print("\n--- Detection Results ---")
+    for model, scores in output.items():
+        print(f"\n[{model}]")
+        for k, v in scores.items():
+            print(f"{k}: {v}%")

app.py

@@ -0,0 +1,18 @@
+import gradio as gr
+import ai_text_detector_valid_final as detector
+
+def run_detector(text):
+    try:
+        return detector.detect_text(text)  # change if your function is named differently
+    except Exception as e:
+        return f"Error: {e}"
+
+demo = gr.Interface(
+    fn=run_detector,
+    inputs=gr.Textbox(lines=10, placeholder="Paste your text here..."),
+    outputs="text",
+    title="AI Text Detector",
+    description="Check if text is AI-generated or human."
+)
+
+demo.launch()