Spaces:
Running
Running
| # Import dependencies | |
| import gradio as gr | |
| from transformers import AutoTokenizer, AutoModelForSequenceClassification | |
| import torch | |
| import nltk | |
| from nltk.corpus import wordnet | |
| import spacy | |
| from gensim.models import KeyedVectors | |
| from gensim import downloader as api | |
| from nltk.tokenize import word_tokenize | |
| # Download NLTK data (if not already downloaded) | |
| nltk.download('punkt') | |
| nltk.download('stopwords') | |
| nltk.download('wordnet') # Download WordNet | |
| # Load spaCy model | |
| nlp = spacy.load("en_core_web_sm") | |
| # Load a smaller Word2Vec model from Gensim's pre-trained models | |
| word_vectors = api.load("glove-wiki-gigaword-50") | |
| # Check for GPU and set the device accordingly | |
| device = torch.device("cuda" if torch.cuda.is_available() else "cpu") | |
| # Load AI Detector model and tokenizer from Hugging Face (DistilBERT) | |
| tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english") | |
| model = AutoModelForSequenceClassification.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english").to(device) | |
| # AI detection function using DistilBERT | |
| def detect_ai_generated(text): | |
| inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512).to(device) | |
| with torch.no_grad(): | |
| outputs = model(**inputs) | |
| probabilities = torch.softmax(outputs.logits, dim=1) | |
| ai_probability = probabilities[0][1].item() # Probability of being AI-generated | |
| return f"AI-Generated Content Probability: {ai_probability:.2f}%" | |
| # Function to get synonyms using Gensim Word2Vec | |
| def get_synonyms_gensim(word): | |
| try: | |
| synonyms = word_vectors.most_similar(positive=[word], topn=5) | |
| return [synonym[0] for synonym in synonyms] | |
| except KeyError: | |
| return [] | |
| # Paraphrasing function using Gensim for synonym replacement | |
| def paraphrase_with_gensim(text): | |
| words = word_tokenize(text) | |
| paraphrased_words = [] | |
| for word in words: | |
| synonyms = get_synonyms_gensim(word.lower()) | |
| if synonyms: | |
| paraphrased_words.append(synonyms[0]) | |
| else: | |
| paraphrased_words.append(word) | |
| return ' '.join(paraphrased_words) | |
| # Paraphrasing function using spaCy for synonym replacement | |
| def paraphrase_with_spacy(text): | |
| doc = nlp(text) | |
| paraphrased_words = [] | |
| for token in doc: | |
| synonyms = get_synonyms_gensim(token.text.lower()) | |
| if synonyms and token.pos_ in {"NOUN", "VERB", "ADJ", "ADV"}: # Only replace certain types of words | |
| paraphrased_words.append(synonyms[0]) | |
| else: | |
| paraphrased_words.append(token.text) | |
| return ' '.join(paraphrased_words) | |
| # Gradio interface definition | |
| with gr.Blocks() as interface: | |
| with gr.Row(): | |
| with gr.Column(): | |
| text_input = gr.Textbox(lines=5, label="Input Text") | |
| detect_button = gr.Button("AI Detection") | |
| paraphrase_gensim_button = gr.Button("Paraphrase with Gensim") | |
| paraphrase_spacy_button = gr.Button("Paraphrase with spaCy") | |
| with gr.Column(): | |
| output_text = gr.Textbox(label="Output") | |
| detect_button.click(detect_ai_generated, inputs=text_input, outputs=output_text) | |
| paraphrase_gensim_button.click(paraphrase_with_gensim, inputs=text_input, outputs=output_text) | |
| paraphrase_spacy_button.click(paraphrase_with_spacy, inputs=text_input, outputs=output_text) | |
| # Launch the Gradio app | |
| interface.launch(debug=False) | |