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") | |
| # Grammar, Tense, and Singular/Plural Correction Functions | |
| # Correct article errors (e.g., "a apple" -> "an apple") | |
| def check_article_error(text): | |
| tokens = nltk.pos_tag(nltk.word_tokenize(text)) | |
| corrected_tokens = [] | |
| for i, token in enumerate(tokens): | |
| word, pos = token | |
| if word.lower() == 'a' and i < len(tokens) - 1 and tokens[i + 1][1] == 'NN': | |
| corrected_tokens.append('an' if tokens[i + 1][0][0] in 'aeiou' else 'a') | |
| else: | |
| corrected_tokens.append(word) | |
| return ' '.join(corrected_tokens) | |
| # Correct tense errors (e.g., "She has go out" -> "She has gone out") | |
| def check_tense_error(text): | |
| tokens = nltk.pos_tag(nltk.word_tokenize(text)) | |
| corrected_tokens = [] | |
| for word, pos in tokens: | |
| if word == "go" and pos == "VB": | |
| corrected_tokens.append("gone") | |
| elif word == "know" and pos == "VB": | |
| corrected_tokens.append("known") | |
| else: | |
| corrected_tokens.append(word) | |
| return ' '.join(corrected_tokens) | |
| # Correct singular/plural errors (e.g., "There are many chocolate" -> "There are many chocolates") | |
| def check_pluralization_error(text): | |
| tokens = nltk.pos_tag(nltk.word_tokenize(text)) | |
| corrected_tokens = [] | |
| for word, pos in tokens: | |
| if word == "chocolate" and pos == "NN": | |
| corrected_tokens.append("chocolates") | |
| elif word == "kids" and pos == "NNS": | |
| corrected_tokens.append("kid") | |
| else: | |
| corrected_tokens.append(word) | |
| return ' '.join(corrected_tokens) | |
| # Combined function to correct grammar, tense, and singular/plural errors | |
| def correct_grammar_tense_plural(text): | |
| text = check_article_error(text) | |
| text = check_tense_error(text) | |
| text = check_pluralization_error(text) | |
| return text | |
| # Gradio app setup with three 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) | |
| with gr.Tab("Grammar Correction"): | |
| grammar_input = gr.Textbox(lines=5, label="Input Text") | |
| grammar_button = gr.Button("Correct Grammar") | |
| grammar_output = gr.Textbox(label="Corrected Text") | |
| # Connect the custom grammar, tense, and plural correction function to the button | |
| grammar_button.click(correct_grammar_tense_plural, inputs=grammar_input, outputs=grammar_output) | |
| # Launch the app with all functionalities | |
| demo.launch() | |