Spaces:
Running
Running
| 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 SpellChecker for spelling correction | |
| # Initialize the English text classification pipeline for AI detection | |
| pipeline_en = pipeline(task="text-classification", model="Hello-SimpleAI/chatgpt-detector-roberta") | |
| # 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'] | |
| # Ensure necessary NLTK data is downloaded for Humanifier | |
| nltk.download('wordnet') | |
| nltk.download('omw-1.4') | |
| # Ensure the SpaCy model is installed for Humanifier | |
| 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 SpellChecker | |
| spell = SpellChecker() | |
| # Function to get synonyms using NLTK WordNet (Humanifier) | |
| 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 capitalize the first letter of sentences and proper nouns (Humanifier) | |
| 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 correct singular/plural errors (Singular/Plural Correction) | |
| 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 correct tense errors in a sentence (Tense Correction) | |
| 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 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": | |
| synonym = synonym + 'ing' | |
| elif token.tag_ == "VBD" or token.tag_ == "VBN": | |
| synonym = synonym + 'ed' | |
| elif token.tag_ == "VBZ": | |
| synonym = 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": | |
| 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 = [spell.candidates(word) or word for word in words] | |
| return ' '.join(corrected_words) | |
| # Function to paraphrase, correct grammar, and fix spelling errors | |
| def paraphrase_and_correct(text): | |
| # Capitalize first to ensure proper noun capitalization | |
| paraphrased_text = capitalize_sentences_and_nouns(text) | |
| # Apply grammatical corrections | |
| paraphrased_text = correct_article_errors(paraphrased_text) | |
| paraphrased_text = correct_singular_plural_errors(paraphrased_text) | |
| paraphrased_text = correct_tense_errors(paraphrased_text) | |
| paraphrased_text = correct_double_negatives(paraphrased_text) | |
| paraphrased_text = ensure_subject_verb_agreement(paraphrased_text) | |
| # Replace words with synonyms while maintaining verb form | |
| doc = nlp(paraphrased_text) | |
| final_text = [] | |
| for token in doc: | |
| if token.pos_ in {"VERB", "NOUN", "ADJ", "ADV"}: | |
| final_text.append(replace_with_synonym(token)) | |
| else: | |
| final_text.append(token.text) | |
| # Correct spelling errors | |
| final_text = correct_spelling(' '.join(final_text)) | |
| return final_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(predict_en, inputs=[t1], outputs=[label1, score1], api_name='predict_en') | |
| with gr.Tab("Humanifier"): | |
| text_input = gr.Textbox(lines=5, label="Input Text") | |
| paraphrase_button = gr.Button("Paraphrase & Correct") | |
| output_text = gr.Textbox(label="Paraphrased Text") | |
| # Connect the paraphrasing function to the button | |
| paraphrase_button.click(paraphrase_and_correct, inputs=text_input, outputs=output_text) | |
| # Launch the app with the remaining functionalities | |
| demo.launch() | |