Spaces:
Running
Running
File size: 2,663 Bytes
29edf23 84669bc 59f9d5b 29edf23 30196dc 59f9d5b 936bfca 30196dc 936bfca 59f9d5b c93f011 29edf23 c93f011 936bfca 59f9d5b 10dc1f6 30196dc b3aee5e 4d1390a ea28e08 84669bc 59f9d5b 4d1390a 59f9d5b 776fa07 84669bc 4d1390a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 |
# Import dependencies
import gradio as gr
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
import nltk
from nltk.corpus import wordnet
from gensim.models import KeyedVectors
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 Word2Vec model from Gensim
word_vectors = KeyedVectors.load_word2vec_format('path/to/GoogleNews-vectors-negative300.bin.gz', binary=True, limit=100000) # Adjust path as needed
# 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)
# 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_text(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)
# 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}%"
# 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_button = gr.Button("Paraphrase Text")
with gr.Column():
output_text = gr.Textbox(label="Output")
detect_button.click(detect_ai_generated, inputs=text_input, outputs=output_text)
paraphrase_button.click(paraphrase_text, inputs=text_input, outputs=output_text)
# Launch the Gradio app
interface.launch(debug=False)
|