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 re # 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 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 fix spacing before punctuation def fix_punctuation_spacing(text): # Split the text into words and punctuation words = text.split(' ') cleaned_words = [] punctuation_marks = {',', '.', "'", '!', '?', ':'} for word in words: if cleaned_words and word and word[0] in punctuation_marks: cleaned_words[-1] += word else: cleaned_words.append(word) return ' '.join(cleaned_words).replace(' ,', ',').replace(' .', '.').replace(" '", "'") \ .replace(' !', '!').replace(' ?', '?').replace(' :', ':') # Function to fix possessives like "Earth's" def fix_possessives(text): text = re.sub(r'(\w)\s\'\s?s', r"\1's", text) return 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: sentence.append(token.text.capitalize()) elif token.pos_ == "PROPN": 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 and ensure full stops def force_first_letter_capital(text): sentences = re.split(r'(?<=\w[.!?])\s+', text) capitalized_sentences = [] for sentence in sentences: if sentence: capitalized_sentence = sentence[0].capitalize() + sentence[1:] if not re.search(r'[.!?]$', capitalized_sentence): capitalized_sentence += '.' capitalized_sentences.append(capitalized_sentence) return " ".join(capitalized_sentences) # 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 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 ensure subject-verb agreement def ensure_subject_verb_agreement(text): doc = nlp(text) corrected_text = [] for token in doc: if token.dep_ == "nsubj" and token.head.pos_ == "VERB": if token.tag_ == "NN" and token.head.tag_ != "VBZ": corrected_text.append(token.head.lemma_ + "s") elif token.tag_ == "NNS" and token.head.tag_ == "VBZ": corrected_text.append(token.head.lemma_) corrected_text.append(token.text) return ' '.join(corrected_text) # Function to correct spelling errors def correct_spelling(text): words = text.split() corrected_words = [] for word in words: corrected_word = spell.correction(word) if corrected_word is not None: corrected_words.append(corrected_word) else: corrected_words.append(word) return ' '.join(corrected_words) # Function to replace a word with its synonym def replace_with_synonyms(text): words = text.split() replaced_words = [] for word in words: synonyms = wordnet.synsets(word) if synonyms: # Take the first synonym if available synonym = synonyms[0].lemmas()[0].name() # Replace the word with its synonym if it's different if synonym.lower() != word.lower(): replaced_words.append(synonym.replace('_', ' ')) else: replaced_words.append(word) else: replaced_words.append(word) return ' '.join(replaced_words) # Main function for paraphrasing and grammar correction def paraphrase_and_correct(text): cleaned_text = remove_redundant_words(text) paraphrased_text = capitalize_sentences_and_nouns(cleaned_text) paraphrased_text = force_first_letter_capital(paraphrased_text) paraphrased_text = correct_article_errors(paraphrased_text) paraphrased_text = correct_tense_errors(paraphrased_text) paraphrased_text = ensure_subject_verb_agreement(paraphrased_text) paraphrased_text = fix_possessives(paraphrased_text) paraphrased_text = correct_spelling(paraphrased_text) paraphrased_text = fix_punctuation_spacing(paraphrased_text) paraphrased_text = replace_with_synonyms(paraphrased_text) # Add synonym replacement here return paraphrased_text # Gradio app setup 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') 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') button2.click(fn=paraphrase_and_correct, inputs=t2, outputs=result2) demo.launch(share=True)