Create app.py

app.py

@@ -0,0 +1,26 @@
+import gradio as gr
+from transformers import pipeline
+
+# Initialize the summarization pipeline
+summarizer = pipeline("summarization", model="facebook/bart-large-cnn")  # You can choose other models
+
+def summarize_text(text):
+    """Summarizes the given text using the pre-trained model."""
+    try:
+        summary = summarizer(text, max_length=150, min_length=30, do_sample=False)[0]['summary_text'] # Adjust max and min length as needed
+        return summary
+    except Exception as e:
+        return f"Error during summarization: {str(e)}"
+
+# Create the Gradio interface
+iface = gr.Interface(
+    fn=summarize_text,
+    inputs=gr.Textbox(lines=5, label="Nepali Text to Summarize"),
+    outputs=gr.Textbox(lines=5, label="Summary"),
+    title="Nepali Text Summarizer",
+    description="Enter Nepali text and get a concise summary using a pre-trained NLP model.",
+    allow_flagging=False
+)
+
+if __name__ == "__main__":
+    iface.launch()