Update app.py

app.py

@@ -3,8 +3,6 @@ import gradio as gr
 from transformers import AutoTokenizer, AutoModelForSequenceClassification, T5Tokenizer, T5ForConditionalGeneration
 import torch
 import nltk
-import random
-import string
 
 # Download NLTK data (if not already downloaded)
 nltk.download('punkt')
@@ -30,71 +28,6 @@ def detect_ai_generated(text):
     ai_probability = probabilities[0][1].item()  # Probability of being AI-generated
     return ai_probability
 
-# Random text transformations to simulate human-like errors
-def random_capitalize(word):
-    if word.isalpha() and random.random() < 0.1:
-        return word.capitalize()
-    return word
-
-def random_remove_punctuation(text):
-    if random.random() < 0.2:
-        text = list(text)
-        indices = [i for i, c in enumerate(text) if c in string.punctuation]
-        if indices:
-            remove_indices = random.sample(indices, min(3, len(indices)))
-            for idx in sorted(remove_indices, reverse=True):
-                text.pop(idx)
-        return ''.join(text)
-    return text
-
-def random_double_period(text):
-    if random.random() < 0.2:
-        text = text.replace('.', '..', 3)
-    return text
-
-def random_double_space(text):
-    if random.random() < 0.2:
-        words = text.split()
-        for _ in range(min(3, len(words) - 1)):
-            idx = random.randint(0, len(words) - 2)
-            words[idx] += '  '
-        return ' '.join(words)
-    return text
-
-def random_replace_comma_space(text, period_replace_percentage=0.33):
-    comma_occurrences = text.count(", ")
-    period_occurrences = text.count(". ")
-    replace_count_comma = max(1, comma_occurrences // 3)
-    replace_count_period = max(1, period_occurrences // 3)
-    comma_indices = [i for i in range(len(text)) if text.startswith(", ", i)]
-    period_indices = [i for i in range(len(text)) if text.startswith(". ", i)]
-    replace_indices_comma = random.sample(comma_indices, min(replace_count_comma, len(comma_indices)))
-    replace_indices_period = random.sample(period_indices, min(replace_count_period, len(period_indices)))
-    for idx in sorted(replace_indices_comma + replace_indices_period, reverse=True):
-        if text.startswith(", ", idx):
-            text = text[:idx] + " ," + text[idx + 2:]
-        if text.startswith(". ", idx):
-            text = text[:idx] + " ." + text[idx + 2:]
-    return text
-
-def transform_paragraph(paragraph):
-    words = paragraph.split()
-    if len(words) > 12:
-        words = [random_capitalize(word) for word in words]
-        transformed_paragraph = ' '.join(words)
-        transformed_paragraph = random_remove_punctuation(transformed_paragraph)
-        transformed_paragraph = random_double_period(transformed_paragraph)
-        transformed_paragraph = random_double_space(transformed_paragraph)
-        transformed_paragraph = random_replace_comma_space(transformed_paragraph)
-    else:
-        transformed_paragraph = paragraph
-    return transformed_paragraph
-
-def transform_text(text):
-    paragraphs = text.split('\n')
-    transformed_paragraphs = [transform_paragraph(paragraph) for paragraph in paragraphs]
-    return '\n'.join(transformed_paragraphs)
-
 # Humanize the AI-detected text using the SRDdev Paraphrase model
 def humanize_text(AI_text):
     paragraphs = AI_text.split("\n")
@@ -116,14 +49,12 @@ def humanize_text(AI_text):
 
 # Main function to handle the overall process
 def main_function(AI_text):
-    ai_probabilities = [detect_ai_generated(sentence) for sentence in nltk.sent_tokenize(AI_text)]
-    ai_generated_percentage = sum([1 for prob in ai_probabilities if prob > 0.5]) / len(ai_probabilities) * 100
+    ai_probability = detect_ai_generated(AI_text)
     
-    # Transform AI text to make it more human-like
+    # Humanize AI text
     humanized_text = humanize_text(AI_text)
-    humanized_text = transform_text(humanized_text)  # Add randomness to simulate human errors
     
-    return f"AI-Generated Content: {ai_generated_percentage:.2f}%\n\nHumanized Text:\n{humanized_text}"
+    return f"AI-Generated Content: {ai_probability:.2f}%\n\nHumanized Text:\n{humanized_text}"
 
 # Gradio interface definition
 interface = gr.Interface(