Spaces:
Running
Running
| import os | |
| import gradio as gr | |
| from transformers import pipeline | |
| import spacy | |
| import subprocess | |
| import nltk | |
| from nltk.corpus import wordnet | |
| # 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") | |
| # 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 [] | |
| # Updated function to replace words with synonyms while preserving verb forms and pluralization | |
| def replace_with_synonyms(text): | |
| doc = nlp(text) | |
| replaced_words = {} | |
| corrected_text = [] | |
| for token in doc: | |
| word = token.text | |
| pos = token.pos_ | |
| # Get the WordNet POS tag format | |
| if pos == "VERB": | |
| wordnet_pos = wordnet.VERB | |
| elif pos == "NOUN": | |
| wordnet_pos = wordnet.NOUN | |
| elif pos == "ADJ": | |
| wordnet_pos = wordnet.ADJ | |
| elif pos == "ADV": | |
| wordnet_pos = wordnet.ADV | |
| else: | |
| corrected_text.append(word) # No change for other POS | |
| continue | |
| # Get synonyms for the word based on POS | |
| if word in replaced_words: | |
| synonym = replaced_words[word] | |
| else: | |
| synonyms = get_synonyms_nltk(word, wordnet_pos) | |
| if synonyms: | |
| synonym = synonyms[0] # Use the first synonym | |
| # Ensure the synonym retains the same form (e.g., plural, verb form) | |
| if pos == "VERB": | |
| synonym = token.lemma_ if synonym == token.lemma_ else token._.inflect(token.tag_) | |
| if pos == "NOUN" and token.tag_ == "NNS": # If plural noun, make sure synonym is plural | |
| synonym += 's' | |
| replaced_words[word] = synonym | |
| else: | |
| synonym = word # No synonym found, keep the word as is | |
| corrected_text.append(synonym) | |
| return ' '.join(corrected_text) | |
| # 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 paraphrase and correct grammar with stronger synonym usage | |
| def paraphrase_and_correct(text): | |
| paraphrased_text = capitalize_sentences_and_nouns(text) # Capitalize first to ensure proper noun capitalization | |
| # Replace words with their synonyms | |
| paraphrased_text = replace_with_synonyms(paraphrased_text) | |
| # Apply grammatical corrections (can include other corrections from the original functions) | |
| paraphrased_text = correct_article_errors(paraphrased_text) | |
| paraphrased_text = correct_singular_plural_errors(paraphrased_text) | |
| paraphrased_text = correct_tense_errors(paraphrased_text) | |
| return paraphrased_text | |
| # 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) | |
| # 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) | |
| # Correct tense errors in verbs | |
| 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) | |
| # 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() | |