Create app.py

app.py

@@ -0,0 +1,29 @@
+# Import necessary libraries
+from transformers import pipeline
+import gradio as gr
+
+# Load the summarization pipeline with the BART-large-cnn model.
+# BART-large-cnn is fine-tuned for news summarization and is available on Hugging Face:contentReference[oaicite:8]{index=8}.
+summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
+
+# Define a function to perform summarization on the input text.
+def summarize_text(text):
+    # Use the summarizer pipeline to generate a summary.
+    # We set min_length and max_length to control the size of the summary:contentReference[oaicite:9]{index=9}.
+    summary = summarizer(text, max_length=130, min_length=30, do_sample=False)[0]['summary_text']
+    return summary
+
+# Create Gradio interface components for input and output.
+input_text = gr.Textbox(lines=10, label="Input Text", placeholder="Enter or paste text to summarize...")
+output_summary = gr.Textbox(label="Summary")
+
+demo = gr.Interface(
+    fn=summarize_text,
+    inputs=input_text,
+    outputs=output_summary,
+    title="📝 Text Summarization with BART",
+    description="**Description:** This app summarizes long text into a concise version. "
+                "It uses a pre-trained BART-large-cnn model to generate an abstractive summary of the input text."
+)
+
+demo.launch()