Spaces:
Running
Running
| import os | |
| import subprocess | |
| import gradio as gr | |
| from transformers import pipeline | |
| import spacy | |
| import nltk | |
| from nltk.corpus import wordnet | |
| # 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") | |
| # Initialize the English text classification pipeline for AI detection | |
| pipeline_en = pipeline(task="text-classification", model="Hello-SimpleAI/chatgpt-detector-roberta") | |
| def predict_en(text): | |
| """Function to predict the label and score for English text (AI Detection)""" | |
| res = pipeline_en(text)[0] | |
| return res['label'], res['score'] | |
| def get_synonyms_nltk(word, pos): | |
| """Function to get synonyms using NLTK WordNet""" | |
| synsets = wordnet.synsets(word, pos=pos) | |
| if synsets: | |
| lemmas = synsets[0].lemmas() | |
| return [lemma.name() for lemma in lemmas] | |
| return [] | |
| def rephrase_text(text): | |
| """Function to rephrase text by replacing words with synonyms""" | |
| doc = nlp(text) | |
| rephrased_text = [] | |
| for token in doc: | |
| if token.pos_ in ["NOUN", "VERB", "ADJ"]: | |
| synonyms = get_synonyms_nltk(token.text, pos=token.pos_.lower()) | |
| if synonyms: | |
| rephrased_text.append(synonyms[0]) # Replace with first synonym found | |
| else: | |
| rephrased_text.append(token.text) | |
| else: | |
| rephrased_text.append(token.text) | |
| return ' '.join(rephrased_text) | |
| def capitalize_sentences_and_nouns(text): | |
| """Function to capitalize the first letter of sentences and proper nouns""" | |
| 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) | |
| def correct_tense_errors(text): | |
| """Function to correct tense errors in a sentence""" | |
| 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) | |
| def correct_singular_plural_errors(text): | |
| """Function to correct singular/plural errors""" | |
| 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) | |
| def correct_article_errors(text): | |
| """Function to check and correct article errors""" | |
| 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) | |
| def paraphrase_and_correct(text): | |
| """Function to rephrase and correct grammar""" | |
| rephrased_text = rephrase_text(text) | |
| rephrased_text = capitalize_sentences_and_nouns(rephrased_text) # Capitalize first to ensure proper noun capitalization | |
| rephrased_text = correct_article_errors(rephrased_text) | |
| rephrased_text = correct_tense_errors(rephrased_text) | |
| rephrased_text = correct_singular_plural_errors(rephrased_text) | |
| return rephrased_text | |
| # Define Gradio interface | |
| with gr.Blocks() as demo: | |
| with gr.Row(): | |
| t1 = gr.Textbox(label="Input Text", lines=5) | |
| button1 = gr.Button("Process") | |
| with gr.Row(): | |
| output_text = gr.Textbox(label="Processed Text", lines=5) | |
| label1 = gr.Label(label="AI Detection Label") | |
| score1 = gr.Label(label="AI Detection Score") | |
| button1.click( | |
| fn=lambda text: (paraphrase_and_correct(text), *predict_en(text)), | |
| inputs=[t1], | |
| outputs=[output_text, label1, score1] | |
| ) | |
| demo.launch() | |