Update app.py

app.py

@@ -3,11 +3,16 @@ import gradio as gr
 from transformers import AutoTokenizer, AutoModelForSequenceClassification, T5Tokenizer, T5ForConditionalGeneration
 import torch
 import nltk
+import spacy
+from nltk.corpus import wordnet
 
 # Download NLTK data (if not already downloaded)
 nltk.download('punkt')
 nltk.download('stopwords')
 
+# Load spaCy model for English
+nlp = spacy.load("en_core_web_sm")
+
 # Check for GPU and set the device accordingly
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
@@ -19,6 +24,29 @@ model = AutoModelForSequenceClassification.from_pretrained("distilbert-base-unca
 paraphrase_tokenizer = T5Tokenizer.from_pretrained("SRDdev/Paraphrase")
 paraphrase_model = T5ForConditionalGeneration.from_pretrained("SRDdev/Paraphrase").to(device)
 
+# Function to find synonyms using WordNet via NLTK
+def get_synonyms(word):
+    synonyms = set()
+    for syn in wordnet.synsets(word):
+        for lemma in syn.lemmas():
+            synonyms.add(lemma.name())
+    return list(synonyms)
+
+# Replace words with synonyms using spaCy and WordNet
+def replace_with_synonyms(text):
+    doc = nlp(text)
+    processed_text = []
+    for token in doc:
+        synonyms = get_synonyms(token.text.lower())
+        if synonyms and token.pos_ in {"NOUN", "VERB", "ADJ", "ADV"}:  # Only replace certain types of words
+            replacement = synonyms[0]  # Replace with the first synonym
+            if token.is_title:
+                replacement = replacement.capitalize()
+            processed_text.append(replacement)
+        else:
+            processed_text.append(token.text)
+    return " ".join(processed_text)
+
 # AI detection function using DistilBERT
 def detect_ai_generated(text):
     inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512).to(device)
@@ -49,10 +77,14 @@ def humanize_text(AI_text):
 
 # Main function to handle the overall process
 def main_function(AI_text):
-    ai_probability = detect_ai_generated(AI_text)
+    # Replace words with synonyms
+    text_with_synonyms = replace_with_synonyms(AI_text)
+    
+    # Detect AI-generated content
+    ai_probability = detect_ai_generated(text_with_synonyms)
     
     # Humanize AI text
-    humanized_text = humanize_text(AI_text)
+    humanized_text = humanize_text(text_with_synonyms)
     
     return f"AI-Generated Content: {ai_probability:.2f}%\n\nHumanized Text:\n{humanized_text}"
 
@@ -61,8 +93,8 @@ interface = gr.Interface(
     fn=main_function,
     inputs="textbox",
     outputs="textbox",
-    title="AI Text Humanizer",
-    description="Enter AI-generated text and get a human-written version. This space uses models from Hugging Face directly."
+    title="AI Text Humanizer with Synonym Replacement",
+    description="Enter AI-generated text and get a human-written version, with synonyms replaced for more natural output. This space uses models from Hugging Face directly."
 )
 
 # Launch the Gradio app