import os import gradio as gr from transformers import pipeline import spacy import subprocess import nltk from nltk.corpus import wordnet from spellchecker import SpellChecker import random # Initialize the English text classification pipeline for AI detection pipeline_en = pipeline(task="text-classification", model="Hello-SimpleAI/chatgpt-detector-roberta") # Initialize the spell checker spell = SpellChecker() # Ensure necessary NLTK data is downloaded nltk.download('wordnet') nltk.download('omw-1.4') # Ensure the SpaCy model is installed 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") # 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'] # Function to get synonyms using NLTK WordNet def get_synonyms_nltk(word, pos): synsets = wordnet.synsets(word, pos=pos) if synsets: lemmas = synsets[0].lemmas() return [lemma.name() for lemma in lemmas] return [] # Function to remove redundant and meaningless words def remove_redundant_words(text): doc = nlp(text) meaningless_words = {"actually", "basically", "literally", "really", "very", "just"} filtered_text = [token.text for token in doc if token.text.lower() not in meaningless_words] return ' '.join(filtered_text) # Function to capitalize the first letter of sentences and proper nouns def capitalize_sentences_and_nouns(text): doc = nlp(text) corrected_text = [] for sent in doc.sents: sentence = [] for token in sent: if token.i == sent.start: # First word of the sentence sentence.append(token.text.capitalize()) elif token.pos_ == "PROPN": # Proper noun sentence.append(token.text.capitalize()) else: sentence.append(token.text) corrected_text.append(' '.join(sentence)) return ' '.join(corrected_text) # Function to force capitalization of the first letter of every sentence def force_first_letter_capital(text): sentences = text.split(". ") # Split by period to get each sentence capitalized_sentences = [sentence[0].capitalize() + sentence[1:] if sentence else "" for sentence in sentences] return ". ".join(capitalized_sentences) # Function to handle possessive 's and retain original meaning def handle_possessives(text): doc = nlp(text) corrected_text = [] for token in doc: # If token is a possessive form (e.g., 'Earth's'), retain its original form if token.text.endswith("'s") or token.text == "'s": corrected_text.append(token.text) # Keep it as is, even if a synonym is found else: corrected_text.append(token.text) return ' '.join(corrected_text) # Function to correct tense errors in a sentence def correct_tense_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) else: corrected_text.append(token.text) return ' '.join(corrected_text) # Function to correct singular/plural errors def correct_singular_plural_errors(text): doc = nlp(text) corrected_text = [] for token in doc: if token.pos_ == "NOUN": if token.tag_ == "NN": # Singular noun if any(child.text.lower() in ['many', 'several', 'few'] for child in token.head.children): corrected_text.append(token.lemma_ + 's') else: corrected_text.append(token.text) elif token.tag_ == "NNS": # Plural noun if any(child.text.lower() in ['a', 'one'] for child in token.head.children): corrected_text.append(token.lemma_) else: corrected_text.append(token.text) else: corrected_text.append(token.text) return ' '.join(corrected_text) # Function to check and correct article errors def correct_article_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) else: corrected_text.append(token.text) return ' '.join(corrected_text) # Function to dynamically choose synonyms with more options def dynamic_synonyms(token, pos): synonyms = get_synonyms_nltk(token.lemma_, pos) # Choose a random synonym to increase variety if synonyms: random_synonym = random.choice(synonyms) return random_synonym return token.text # Function to rephrase text and replace words with more versatile synonyms def versatile_rephrase(text): doc = nlp(text) rephrased_text = [] for token in doc: pos_tag = None if token.pos_ == "NOUN": pos_tag = wordnet.NOUN elif token.pos_ == "VERB": pos_tag = wordnet.VERB elif token.pos_ == "ADJ": pos_tag = wordnet.ADJ elif token.pos_ == "ADV": pos_tag = wordnet.ADV if pos_tag: synonym = dynamic_synonyms(token, pos_tag) if token.pos_ == "VERB": if token.tag_ == "VBG": # Present participle (e.g., running) synonym = synonym + 'ing' elif token.tag_ == "VBD" or token.tag_ == "VBN": # Past tense or past participle synonym = synonym + 'ed' elif token.tag_ == "VBZ": # Third-person singular present synonym = synonym + 's' elif token.pos_ == "NOUN" and token.tag_ == "NNS": # Plural nouns synonym += 's' if not synonym ends with 's' else "" rephrased_text.append(synonym) else: rephrased_text.append(token.text) return ' '.join(rephrased_text) # Function to retain the structure of the input text (headings, paragraphs, line breaks) def retain_structure(text): lines = text.split("\n") formatted_lines = [] for line in lines: if line.strip().isupper(): # Heading if all caps formatted_lines.append(f"# {line.strip()}") # Treat it as a heading else: formatted_lines.append(line) # Otherwise, it's a paragraph or normal text return "\n".join(formatted_lines) # Function to paraphrase and correct grammar with enhanced accuracy and retain structure def paraphrase_and_correct_with_structure(text): structured_text = retain_structure(text) # Rephrase with more versatile synonyms while maintaining grammatical forms paraphrased_text = versatile_rephrase(structured_text) # Apply grammatical corrections on the rephrased text paraphrased_text = remove_redundant_words(paraphrased_text) paraphrased_text = capitalize_sentences_and_nouns(paraphrased_text) paraphrased_text = force_first_letter_capital(paraphrased_text) paraphrased_text = handle_possessives(paraphrased_text) paraphrased_text = correct_article_errors(paraphrased_text) paraphrased_text = correct_singular_plural_errors(paraphrased_text) paraphrased_text = correct_tense_errors(paraphrased_text) paraphrased_text = correct_double_negatives(paraphrased_text) paraphrased_text = ensure_subject_verb_agreement(paraphrased_text) paraphrased_text = correct_spelling(paraphrased_text) return paraphrased_text # Gradio app setup with two tabs with gr.Blocks() as demo: 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(fn=predict_en, inputs=t1, outputs=[label1, score1]) with gr.Tab("Paraphrasing & Grammar Correction"): t2 = gr.Textbox(lines=5, label='Enter text for paraphrasing and grammar correction') button2 = gr.Button("🔄 Paraphrase and Correct") result2 = gr.Textbox(lines=5, label='Corrected Text') # Connect the paraphrasing and correction function to the button button2.click(fn=paraphrase_and_correct_with_structure, inputs=t2, outputs=result2) demo.launch(share=True)