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 and keep the same grammatical form | |
| def get_synonym(word, pos_tag): | |
| synsets = wordnet.synsets(word) | |
| if not synsets: | |
| return word | |
| for synset in synsets: | |
| if synset.pos() == pos_tag: # Match the part of speech | |
| synonym = synset.lemmas()[0].name() # Get the first lemma | |
| # Check if the original word and synonym are in the same form (singular/plural, tense, etc.) | |
| if word.islower(): | |
| return synonym.lower() | |
| else: | |
| return synonym.capitalize() | |
| return word | |
| # Function to rephrase text and replace words with their synonyms while maintaining form | |
| def rephrase_with_synonyms(text): | |
| doc = nlp(text) | |
| rephrased_text = [] | |
| for token in doc: | |
| # Get the correct POS tag for WordNet | |
| 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: | |
| synonym = get_synonym(token.text, pos_tag) | |
| # Ensure that the verb/noun/plural/singular is kept intact | |
| if token.pos_ == "VERB": | |
| synonym = token.lemma_ if token.morph.get("Tense") == "Past" else synonym | |
| elif token.pos_ == "NOUN" and token.tag_ == "NNS": # Plural nouns | |
| synonym += 's' if not synonym.endswith('s') else "" | |
| 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): | |
| paraphrased_text = capitalize_sentences_and_nouns(text) # Capitalize first to ensure proper noun capitalization | |
| # 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) | |
| # Rephrase with synonyms while maintaining grammatical forms | |
| paraphrased_text = rephrase_with_synonyms(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(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() | |