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 language_tool_python | |
| # 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() | |
| # Initialize the LanguageTool for grammar correction | |
| tool = language_tool_python.LanguageTool('en-US') | |
| # 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 apply grammatical corrections using LanguageTool | |
| def correct_grammar(text): | |
| corrected_text = tool.correct(text) | |
| return 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) # Keep original word if no correction | |
| return ' '.join(corrected_words) | |
| # Function to capitalize the first letter of each sentence 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 rephrase with contextually appropriate synonyms | |
| 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 = wordnet.synsets(token.text, pos=pos_tag) | |
| if synonyms: | |
| synonym = synonyms[0].lemmas()[0].name() # Choose the first synonym | |
| rephrased_text.append(synonym) | |
| else: | |
| rephrased_text.append(token.text) | |
| else: | |
| rephrased_text.append(token.text) | |
| return ' '.join(rephrased_text) | |
| # Comprehensive function for paraphrasing and grammar correction | |
| def paraphrase_and_correct(text): | |
| # Step 1: Remove meaningless or redundant words | |
| cleaned_text = remove_redundant_words(text) | |
| # Step 2: Capitalize sentences and proper nouns | |
| paraphrased_text = capitalize_sentences_and_nouns(cleaned_text) | |
| # Step 3: Correct grammar using LanguageTool | |
| paraphrased_text = correct_grammar(paraphrased_text) | |
| # Step 4: Rephrase with contextually appropriate synonyms | |
| paraphrased_text = rephrase_with_synonyms(paraphrased_text) | |
| # Step 5: Correct spelling errors | |
| paraphrased_text = correct_spelling(paraphrased_text) | |
| # Step 6: Correct any remaining grammar issues after rephrasing | |
| paraphrased_text = correct_grammar(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, inputs=t2, outputs=result2) | |
| demo.launch(share=True) | |