Update app.py

app.py

@@ -1,7 +1,6 @@
 import os
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
-import torch
+from transformers import pipeline
 import spacy
 import subprocess
 import nltk
@@ -22,31 +21,20 @@ except OSError:
 # Load a smaller Word2Vec model from Gensim's pre-trained models
 word_vectors = api.load("glove-wiki-gigaword-50")
 
-# Check for GPU and set the device accordingly
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+# Load the English AI detection pipeline using the Hello-SimpleAI model
+pipeline_en = pipeline(task="text-classification", model="Hello-SimpleAI/chatgpt-detector-roberta")
 
-# Load AI Detector model and tokenizer from Hugging Face (roberta-base-openai-detector)
-tokenizer_ai = AutoTokenizer.from_pretrained("roberta-base-openai-detector")
-model_ai = AutoModelForSequenceClassification.from_pretrained("roberta-base-openai-detector").to(device)
-
-# AI detection function using the RoBERTa-based model
+# AI detection function using the Hello-SimpleAI/chatgpt-detector-roberta model
 def detect_ai_generated(text):
-    inputs = tokenizer_ai(text, return_tensors="pt", truncation=True, max_length=512).to(device)
-    with torch.no_grad():
-        outputs = model_ai(**inputs)
-        probabilities = torch.softmax(outputs.logits, dim=1)
-    ai_probability = probabilities[0][1].item() * 100  # Probability of being AI-generated
-    human_probability = 100 - ai_probability  # Probability of being Human-written
+    res = pipeline_en(text)[0]
+    label = res['label']  # "LABEL_0" or "LABEL_1"
+    score = res['score'] * 100  # Convert probability to percentage
     
-    # Determine the label based on the higher probability
-    if ai_probability > human_probability:
-        label = "AI"
-        probability = ai_probability
-    else:
-        label = "Human"
-        probability = human_probability
+    # Map the model's label to human-readable label
+    human_readable_label = "AI" if label == "LABEL_1" else "Human"
     
-    return f"The content is {probability:.2f}% {label} Written", probability
+    # Return formatted string with label and percentage score
+    return f"The content is {score:.2f}% {human_readable_label} Written", score
 
 # Function to get synonyms using NLTK WordNet
 def get_synonyms_nltk(word, pos):
@@ -118,18 +106,18 @@ def paraphrase_and_correct(text):
     return final_text
 
 # Gradio interface definition
-with gr.Blocks() as demo:
+with gr.Blocks() as interface:
     with gr.Row():
         with gr.Column():
-            t1 = gr.Textbox(
-                lines=5, 
-                label='Text',
-                value="There are a few things that can help protect your credit card information from being misused when you give it to a restaurant or any other business:\n\nEncryption: Many businesses use encryption to protect your credit card information when it is being transmitted or stored. This means that the information is transformed into a code that is difficult for anyone to read without the right key."
-            )
-            button1 = gr.Button("🤖 Predict!")
-            label1 = gr.Textbox(lines=1, label='Predicted Label 🎃')
-            score1 = gr.Textbox(lines=1, label='Probability (%)')
+            text_input = gr.Textbox(lines=5, label="Input Text")
+            detect_button = gr.Button("AI Detection")
+            paraphrase_button = gr.Button("Paraphrase & Correct")
+        with gr.Column():
+            output_label = gr.Textbox(label="Predicted Label 🎃")
+            output_prob = gr.Textbox(label="Probability (%)")
 
-    button1.click(detect_ai_generated, inputs=[t1], outputs=[label1, score1])
+    detect_button.click(detect_ai_generated, inputs=text_input, outputs=[output_label, output_prob])
+    paraphrase_button.click(paraphrase_and_correct, inputs=text_input, outputs=output_label)
 
-demo.launch()
+# Launch the Gradio app
+interface.launch(debug=False)