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") | |
| # 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 check subject-verb agreement | |
| def check_subject_verb_agreement(doc): | |
| corrected_text = [] | |
| for token in doc: | |
| if token.dep_ == "nsubj": # Check if the token is a subject | |
| subject = token | |
| verb = token.head # Find the associated verb | |
| if verb.tag_ in {"VBZ", "VBP"}: # Singular/plural verb forms | |
| if subject.tag_ == "NNS" and verb.tag_ == "VBZ": # Plural subject with singular verb | |
| corrected_text.append(verb.lemma_) # Convert verb to plural form | |
| elif subject.tag_ == "NN" and verb.tag_ == "VBP": # Singular subject with plural verb | |
| corrected_text.append(verb.lemma_ + 's') # Convert verb to singular form | |
| else: | |
| corrected_text.append(verb.text) # No correction needed | |
| else: | |
| corrected_text.append(verb.text) | |
| corrected_text.append(token.text) | |
| return ' '.join(corrected_text) | |
| # Function to correct singular/plural errors using dependency parsing | |
| def correct_singular_plural_errors(doc): | |
| corrected_text = [] | |
| for token in doc: | |
| if token.pos_ == "NOUN": | |
| if token.tag_ == "NN" and token.head.pos_ == "VERB" and token.head.tag_ == "VBP": | |
| corrected_text.append(token.lemma_ + 's') # Singular noun, plural verb | |
| elif token.tag_ == "NNS" and token.head.pos_ == "VERB" and token.head.tag_ == "VBZ": | |
| corrected_text.append(token.lemma_) # Plural noun, singular verb | |
| else: | |
| corrected_text.append(token.text) | |
| else: | |
| corrected_text.append(token.text) | |
| return ' '.join(corrected_text) | |
| # 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) | |
| return ' '.join(paraphrased_words) | |
| # Combined function: Paraphrase -> Grammar Correction -> Capitalization (Humanifier) | |
| def paraphrase_and_correct(text): | |
| # Step 1: Paraphrase the text | |
| paraphrased_text = paraphrase_with_spacy_nltk(text) | |
| # Step 2: Parse the text with spaCy | |
| doc = nlp(paraphrased_text) | |
| # Step 3: Apply grammatical corrections on the paraphrased text | |
| corrected_text = correct_article_errors(doc) | |
| corrected_text = capitalize_sentences_and_nouns(corrected_text) | |
| corrected_text = check_subject_verb_agreement(nlp(corrected_text)) | |
| corrected_text = correct_singular_plural_errors(nlp(corrected_text)) | |
| # Step 4: Capitalize sentences and proper nouns (final correction step) | |
| final_text = correct_tense_errors(nlp(corrected_text)) | |
| return final_text | |
| def predict_en(text): | |
| prediction = pipeline_en(text) | |
| label = prediction[0]['label'] | |
| score = prediction[0]['score'] | |
| return label, round(score, 4) | |
| # 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() |