Create app.py

app.py

@@ -0,0 +1,38 @@
+import gradio as gr
+import pickle
+import torch
+import numpy as np
+from transformers import BertTokenizer, BertModel
+from sklearn.linear_model import LogisticRegression
+
+# Load BERT tokenizer and model
+tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
+bert_model = BertModel.from_pretrained('bert-base-uncased')
+
+# Load the trained Logistic Regression classifier
+with open('bert_cased_model.pkl', 'rb') as model_file:
+    classifier = pickle.load(model_file)
+
+# Define function to preprocess and classify text
+def classify_text(text):
+    # Preprocess text and get BERT embeddings
+    inputs = tokenizer(text, padding=True, truncation=True, return_tensors="pt")
+    with torch.no_grad():
+        outputs = bert_model(**inputs)
+        embeddings = outputs.last_hidden_state[:, 0, :].numpy()
+
+    # Predict using the classifier
+    label = classifier.predict(embeddings)
+    return label[0]
+
+# Create the Gradio interface
+iface = gr.Interface(
+    fn=classify_text,
+    inputs="text",
+    outputs="text",
+    title="Text Classification: Human or AI?",
+    description="Enter a text to classify whether it's generated by a human or AI.",
+)
+
+# Launch the Gradio interface
+iface.launch()