Spaces:
Sleeping
Sleeping
| 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 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 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 get the correct synonym while maintaining verb form | |
| def replace_with_synonym(token): | |
| pos = None | |
| if token.pos_ == "VERB": | |
| pos = wordnet.VERB | |
| elif token.pos_ == "NOUN": | |
| pos = wordnet.NOUN | |
| elif token.pos_ == "ADJ": | |
| pos = wordnet.ADJ | |
| elif token.pos_ == "ADV": | |
| pos = wordnet.ADV | |
| synonyms = get_synonyms_nltk(token.lemma_, pos) | |
| if synonyms: | |
| synonym = synonyms[0] | |
| if token.tag_ == "VBG": # Present participle | |
| synonym += 'ing' | |
| elif token.tag_ == "VBD" or token.tag_ == "VBN": # Past tense or past participle | |
| synonym += 'ed' | |
| elif token.tag_ == "VBZ": # Third-person singular present | |
| synonym += 's' | |
| return synonym | |
| return token.text | |
| # Function to check for and avoid double negatives | |
| def correct_double_negatives(text): | |
| doc = nlp(text) | |
| corrected_text = [] | |
| for token in doc: | |
| if token.text.lower() == "not" and any(child.text.lower() == "never" for child in token.head.children): | |
| corrected_text.append("always") | |
| 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": # Singular noun, should use singular verb | |
| corrected_text.append(token.head.lemma_ + "s") | |
| elif token.tag_ == "NNS" and token.head.tag_ == "VBZ": # Plural noun, should not use singular verb | |
| 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) | |
| corrected_words.append(corrected_word if corrected_word else word) | |
| return ' '.join(corrected_words) | |
| # Function to correct punctuation issues | |
| def correct_punctuation(text): | |
| # Fix spacing before punctuation | |
| text = re.sub(r'\s([?.!,";:])', r'\1', text) | |
| # Add missing commas in compound sentences | |
| text = re.sub(r'(\w+)\s+and\s+(\w+)', r'\1, and \2', text) | |
| return text | |
| # Function to rephrase text and replace words with their synonyms while maintaining form | |
| def rephrase_with_synonyms(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: | |
| synonyms = get_synonyms_nltk(token.text, pos_tag) | |
| if synonyms: | |
| synonym = synonyms[0] # Just using the first synonym for simplicity | |
| if token.pos_ == "VERB": | |
| if token.tag_ == "VBG": # Present participle | |
| synonym += 'ing' | |
| elif token.tag_ == "VBD" or token.tag_ == "VBN": # Past tense or past participle | |
| synonym += 'ed' | |
| elif token.tag_ == "VBZ": # Third-person singular present | |
| synonym += 's' | |
| elif token.pos_ == "NOUN" and token.tag_ == "NNS": # Plural nouns | |
| synonym += 's' if not synonym.endswith('s') else "" | |
| rephrased_text.append(synonym) | |
| else: | |
| rephrased_text.append(token.text) | |
| else: | |
| rephrased_text.append(token.text) | |
| return ' '.join(rephrased_text) | |
| # Function to paraphrase and correct grammar with enhanced accuracy | |
| def paraphrase_and_correct(text): | |
| # Remove meaningless or redundant words first | |
| cleaned_text = remove_redundant_words(text) | |
| # Capitalize sentences and nouns | |
| paraphrased_text = capitalize_sentences_and_nouns(cleaned_text) | |
| # Correct tense and singular/plural errors | |
| paraphrased_text = correct_tense_errors(paraphrased_text) | |
| paraphrased_text = correct_singular_plural_errors(paraphrased_text) | |
| paraphrased_text = correct_article_errors(paraphrased_text) | |
| paraphrased_text = correct_double_negatives(paraphrased_text) | |
| paraphrased_text = ensure_subject_verb_agreement(paraphrased_text) | |
| # Correct spelling and punctuation | |
| paraphrased_text = correct_spelling(paraphrased_text) | |
| paraphrased_text = correct_punctuation(paraphrased_text) | |
| # Rephrase with synonyms | |
| paraphrased_text = rephrase_with_synonyms(paraphrased_text) | |
| # Force capitalization of the first letter of each sentence | |
| final_text = force_first_letter_capital(paraphrased_text) | |
| return final_text | |
| # Gradio interface | |
| iface = gr.Interface( | |
| fn=paraphrase_and_correct, | |
| inputs=gr.Textbox(label="Input Text", lines=5, placeholder="Enter text here..."), | |
| outputs=gr.Textbox(label="Output Text", lines=5), | |
| title="Text Paraphraser and Grammar Corrector", | |
| description="This tool paraphrases the input text, corrects grammar, improves punctuation, and enhances overall clarity." | |
| ) | |
| iface.launch() | |