Spaces:
Running
Running
| import os | |
| import gradio as gr | |
| from transformers import pipeline | |
| import spacy | |
| import subprocess | |
| 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") | |
| # 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 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 [] | |
| # Paraphrasing function using SpaCy and NLTK (Humanifier) | |
| def paraphrase_with_spacy_nltk(text): | |
| doc = nlp(text) | |
| paraphrased_words = [] | |
| for token in doc: | |
| # Map SpaCy POS tags to WordNet POS tags | |
| pos = None | |
| if token.pos_ in {"NOUN"}: | |
| pos = wordnet.NOUN | |
| elif token.pos_ in {"VERB"}: | |
| pos = wordnet.VERB | |
| elif token.pos_ in {"ADJ"}: | |
| pos = wordnet.ADJ | |
| elif token.pos_ in {"ADV"}: | |
| pos = wordnet.ADV | |
| synonyms = get_synonyms_nltk(token.text.lower(), pos) if pos else [] | |
| # Replace with a synonym only if it makes sense | |
| if synonyms and token.pos_ in {"NOUN", "VERB", "ADJ", "ADV"} and synonyms[0] != token.text.lower(): | |
| paraphrased_words.append(synonyms[0]) | |
| else: | |
| paraphrased_words.append(token.text) | |
| # Join the words back into a sentence | |
| paraphrased_sentence = ' '.join(paraphrased_words) | |
| return paraphrased_sentence | |
| # Combined function: Paraphrase -> Grammar Correction -> Capitalization (Humanifier) | |
| def paraphrase_and_correct(text): | |
| # Step 1: Paraphrase the text | |
| paraphrased_text = paraphrase_with_spacy_nltk(text) | |
| # Additional steps (grammar correction, capitalization) can go here... | |
| # For now, we'll return the paraphrased text as an example. | |
| 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() | |