Create app.py

app.py

@@ -0,0 +1,33 @@
+import gradio as gr
+from transformers import BertTokenizer, BertForSequenceClassification
+from transformers import pipeline
+import torch
+
+# Load model and tokenizer
+model_name = "nlptown/bert-base-multilingual-uncased-sentiment"
+model = BertForSequenceClassification.from_pretrained(model_name)
+tokenizer = BertTokenizer.from_pretrained(model_name)
+
+# Define pipeline
+classifier = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)
+
+# Prediction function
+def predict_sentiment(text):
+    if not text.strip():
+        return "Please enter some text."
+    result = classifier(text)[0]
+    label = result['label']
+    score = round(result['score'], 4)
+    return f"Sentiment: {label} (Confidence: {score})"
+
+# Gradio UI
+interface = gr.Interface(
+    fn=predict_sentiment,
+    inputs=gr.Textbox(lines=3, placeholder="Enter movie review..."),
+    outputs="text",
+    title="IMDB Movie Review Sentiment Analysis with BERT",
+    description="This demo uses BERT to predict sentiment on IMDB-like reviews. Model: nlptown/bert-base-multilingual-uncased-sentiment"
+)
+
+if __name__ == "__main__":
+    interface.launch()