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 | |
| from inflect import engine # For pluralization | |
| # 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 and inflect engine | |
| spell = SpellChecker() | |
| inflect_engine = engine() | |
| # 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 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 if lemma.name() != word] # Avoid original word | |
| return [] | |
| # Function to remove redundant words | |
| def remove_redundant_words(text): | |
| meaningless_words = {"actually", "basically", "literally", "really", "very", "just"} | |
| return ' '.join(word for word in text.split() if word.lower() not in meaningless_words) | |
| # Function to correct spelling errors | |
| def correct_spelling(text): | |
| words = text.split() | |
| corrected_words = [spell.correction(word) for word in words] | |
| return ' '.join(corrected_words) | |
| # Function to rephrase text with synonyms | |
| def rephrase_with_synonyms(text): | |
| doc = nlp(text) | |
| rephrased_text = [] | |
| for token in doc: | |
| pos_tag = { | |
| "NOUN": wordnet.NOUN, | |
| "VERB": wordnet.VERB, | |
| "ADJ": wordnet.ADJ, | |
| "ADV": wordnet.ADV | |
| }.get(token.pos_, None) | |
| if pos_tag: | |
| synonyms = get_synonyms_nltk(token.lemma_, pos_tag) | |
| synonym = synonyms[0] if synonyms else token.text | |
| rephrased_text.append(synonym) | |
| else: | |
| rephrased_text.append(token.text) | |
| return ' '.join(rephrased_text) | |
| # Function to paraphrase and correct grammar | |
| def paraphrase_and_correct(text): | |
| cleaned_text = remove_redundant_words(text) | |
| cleaned_text = correct_spelling(cleaned_text) | |
| return rephrase_with_synonyms(cleaned_text) | |
| # Function to handle user input | |
| def process_text(input_text): | |
| ai_label, ai_score = predict_en(input_text) | |
| if ai_label == "HUMAN": | |
| corrected_text = paraphrase_and_correct(input_text) | |
| return corrected_text | |
| else: | |
| return "The text seems to be AI-generated; no correction applied." | |
| # Gradio interface | |
| iface = gr.Interface( | |
| fn=process_text, | |
| inputs=gr.Textbox(lines=10, placeholder="Enter your text here..."), | |
| outputs=gr.Textbox(label="Corrected Text"), | |
| title="Text Correction and Rephrasing", | |
| description="This app corrects and rephrases text while detecting AI-generated content." | |
| ) | |
| # Launch the interface | |
| iface.launch() | |