Update app.py

app.py

@@ -1,57 +1,83 @@
 import os
-import subprocess
 import gradio as gr
 from transformers import pipeline
 import spacy
+import subprocess
 import nltk
 from nltk.corpus import wordnet
 
-# Ensure necessary NLTK data is downloaded
+# Initialize the English text classification pipeline for AI detection
+pipeline_en = pipeline(task="text-classification", model="Hello-SimpleAI/chatgpt-detector-roberta")
+
+# Function to predict the label and score for English text (AI Detection)
+def predict_en(text):
+    res = pipeline_en(text)[0]
+    return res['label'], res['score']
+
+# Ensure necessary NLTK data is downloaded for Humanifier
 nltk.download('wordnet')
 nltk.download('omw-1.4')
 
-# Ensure the SpaCy model is installed
+# Ensure the SpaCy model is installed for Humanifier
 try:
     nlp = spacy.load("en_core_web_sm")
 except OSError:
     subprocess.run(["python", "-m", "spacy", "download", "en_core_web_sm"])
     nlp = spacy.load("en_core_web_sm")
 
-# Initialize the English text classification pipeline for AI detection
-pipeline_en = pipeline(task="text-classification", model="Hello-SimpleAI/chatgpt-detector-roberta")
-
-def predict_en(text):
-    """Function to predict the label and score for English text (AI Detection)"""
-    res = pipeline_en(text)[0]
-    return res['label'], res['score']
-
+# Function to get synonyms using NLTK WordNet (Humanifier)
 def get_synonyms_nltk(word, pos):
-    """Function to get synonyms using NLTK WordNet"""
     synsets = wordnet.synsets(word, pos=pos)
     if synsets:
         lemmas = synsets[0].lemmas()
         return [lemma.name() for lemma in lemmas]
     return []
 
-def rephrase_text(text):
-    """Function to rephrase text by replacing words with synonyms"""
+# Updated function to replace words with synonyms while preserving verb forms and pluralization
+def replace_with_synonyms(text):
     doc = nlp(text)
-    rephrased_text = []
+    replaced_words = {}
+    corrected_text = []
 
     for token in doc:
-        if token.pos_ in ["NOUN", "VERB", "ADJ"]:
-            synonyms = get_synonyms_nltk(token.text, pos=token.pos_.lower())
+        word = token.text
+        pos = token.pos_
+
+        # Get the WordNet POS tag format
+        if pos == "VERB":
+            wordnet_pos = wordnet.VERB
+        elif pos == "NOUN":
+            wordnet_pos = wordnet.NOUN
+        elif pos == "ADJ":
+            wordnet_pos = wordnet.ADJ
+        elif pos == "ADV":
+            wordnet_pos = wordnet.ADV
+        else:
+            corrected_text.append(word)  # No change for other POS
+            continue
+
+        # Get synonyms for the word based on POS
+        if word in replaced_words:
+            synonym = replaced_words[word]
+        else:
+            synonyms = get_synonyms_nltk(word, wordnet_pos)
             if synonyms:
-                rephrased_text.append(synonyms[0])  # Replace with first synonym found
+                synonym = synonyms[0]  # Use the first synonym
+                # Ensure the synonym retains the same form (e.g., plural, verb form)
+                if pos == "VERB":
+                    synonym = token.lemma_ if synonym == token.lemma_ else token._.inflect(token.tag_)
+                if pos == "NOUN" and token.tag_ == "NNS":  # If plural noun, make sure synonym is plural
+                    synonym += 's'
+                replaced_words[word] = synonym
             else:
-                rephrased_text.append(token.text)
-        else:
-            rephrased_text.append(token.text)
-    
-    return ' '.join(rephrased_text)
+                synonym = word  # No synonym found, keep the word as is
+
+        corrected_text.append(synonym)
 
+    return ' '.join(corrected_text)
+
+# Function to capitalize the first letter of sentences and proper nouns (Humanifier)
 def capitalize_sentences_and_nouns(text):
-    """Function to capitalize the first letter of sentences and proper nouns"""
     doc = nlp(text)
     corrected_text = []
 
@@ -68,22 +94,42 @@ def capitalize_sentences_and_nouns(text):
 
     return ' '.join(corrected_text)
 
-def correct_tense_errors(text):
-    """Function to correct tense errors in a sentence"""
+# Function to paraphrase and correct grammar with stronger synonym usage
+def paraphrase_and_correct(text):
+    paraphrased_text = capitalize_sentences_and_nouns(text)  # Capitalize first to ensure proper noun capitalization
+    
+    # Replace words with their synonyms
+    paraphrased_text = replace_with_synonyms(paraphrased_text)
+
+    # Apply grammatical corrections (can include other corrections from the original functions)
+    paraphrased_text = correct_article_errors(paraphrased_text)
+    paraphrased_text = correct_singular_plural_errors(paraphrased_text)
+    paraphrased_text = correct_tense_errors(paraphrased_text)
+
+    return paraphrased_text
+
+# Correct article errors
+def correct_article_errors(text):
     doc = nlp(text)
     corrected_text = []
     for token in doc:
-        if token.pos_ == "VERB" and token.dep_ in {"aux", "auxpass"}:
-            lemma = wordnet.morphy(token.text, wordnet.VERB) or token.text
-            corrected_text.append(lemma)
+        if token.text in ['a', 'an']:
+            next_token = token.nbor(1)
+            if token.text == "a" and next_token.text[0].lower() in "aeiou":
+                corrected_text.append("an")
+            elif token.text == "an" and next_token.text[0].lower() not in "aeiou":
+                corrected_text.append("a")
+            else:
+                corrected_text.append(token.text)
         else:
             corrected_text.append(token.text)
     return ' '.join(corrected_text)
 
+# Correct singular/plural errors
 def correct_singular_plural_errors(text):
-    """Function to correct singular/plural errors"""
     doc = nlp(text)
     corrected_text = []
+    
     for token in doc:
         if token.pos_ == "NOUN":
             if token.tag_ == "NN":  # Singular noun
@@ -98,48 +144,39 @@ def correct_singular_plural_errors(text):
                     corrected_text.append(token.text)
         else:
             corrected_text.append(token.text)
+    
     return ' '.join(corrected_text)
 
-def correct_article_errors(text):
-    """Function to check and correct article errors"""
+# Correct tense errors in verbs
+def correct_tense_errors(text):
     doc = nlp(text)
     corrected_text = []
     for token in doc:
-        if token.text in ['a', 'an']:
-            next_token = token.nbor(1)
-            if token.text == "a" and next_token.text[0].lower() in "aeiou":
-                corrected_text.append("an")
-            elif token.text == "an" and next_token.text[0].lower() not in "aeiou":
-                corrected_text.append("a")
-            else:
-                corrected_text.append(token.text)
+        if token.pos_ == "VERB" and token.dep_ in {"aux", "auxpass"}:
+            lemma = wordnet.morphy(token.text, wordnet.VERB) or token.text
+            corrected_text.append(lemma)
         else:
             corrected_text.append(token.text)
     return ' '.join(corrected_text)
 
-def paraphrase_and_correct(text):
-    """Function to rephrase and correct grammar"""
-    rephrased_text = rephrase_text(text)
-    rephrased_text = capitalize_sentences_and_nouns(rephrased_text)  # Capitalize first to ensure proper noun capitalization
-    rephrased_text = correct_article_errors(rephrased_text)
-    rephrased_text = correct_tense_errors(rephrased_text)
-    rephrased_text = correct_singular_plural_errors(rephrased_text)
-    return rephrased_text
-
-# Define Gradio interface
+# Gradio app setup with two tabs
 with gr.Blocks() as demo:
-    with gr.Row():
-        t1 = gr.Textbox(label="Input Text", lines=5)
-        button1 = gr.Button("Process")
-    with gr.Row():
-        output_text = gr.Textbox(label="Processed Text", lines=5)
-        label1 = gr.Label(label="AI Detection Label")
-        score1 = gr.Label(label="AI Detection Score")
+    with gr.Tab("AI Detection"):
+        t1 = gr.Textbox(lines=5, label='Text')
+        button1 = gr.Button("🤖 Predict!")
+        label1 = gr.Textbox(lines=1, label='Predicted Label 🎃')
+        score1 = gr.Textbox(lines=1, label='Prob')
+
+        # Connect the prediction function to the button
+        button1.click(predict_en, inputs=[t1], outputs=[label1, score1], api_name='predict_en')
     
-    button1.click(
-        fn=lambda text: (paraphrase_and_correct(text), *predict_en(text)),
-        inputs=[t1],
-        outputs=[output_text, label1, score1]
-    )
+    with gr.Tab("Humanifier"):
+        text_input = gr.Textbox(lines=5, label="Input Text")
+        paraphrase_button = gr.Button("Paraphrase & Correct")
+        output_text = gr.Textbox(label="Paraphrased Text")
+
+        # Connect the paraphrasing function to the button
+        paraphrase_button.click(paraphrase_and_correct, inputs=text_input, outputs=output_text)
 
+# Launch the app with the remaining functionalities
 demo.launch()