Update app.py

app.py

@@ -1,40 +1,48 @@
 import streamlit as st
-from transformers import pipeline, BartForConditionalGeneration, BartTokenizer
-
-# Load pre-trained BART model and tokenizer
-model_name = "facebook/bart-large-cnn"  # BART large model for summarization
-model = BartForConditionalGeneration.from_pretrained(model_name)
-tokenizer = BartTokenizer.from_pretrained(model_name)
-
-# Define function to generate summary
-def generate_summary(text):
-    inputs = tokenizer([text], max_length=1024, return_tensors='pt')
-
-    # Generate summary
-    summary_ids = model.generate(
-        inputs['input_ids'],
-        max_length=150,
-        num_beams=4,
-        length_penalty=2.0,
-        early_stopping=True
-    )
-    
-    # Decode and return summary
-    generated_summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
-    return generated_summary
-
-# Streamlit app
-def main():
-    st.title("Summarization App")
-    
-    # Sidebar input for text
-    text = st.sidebar.text_area("Enter text to summarize", "Enter your text here...")
-
-    # Generate button
-    if st.sidebar.button("Generate Summary"):
-        summary = generate_summary(text)
-        st.subheader("Generated Summary:")
-        st.write(summary)
-
-if __name__ == "__main__":
-    main()
+import torch
+from transformers import pipeline
+from transformers import BartTokenizer, BartForConditionalGeneration
+
+# Replace with your Hugging Face model repository path
+model_repo_path = 'ASaboor/Bart_samsum'
+
+# Load the model and tokenizer
+model = BartForConditionalGeneration.from_pretrained(model_repo_path)
+tokenizer = BartTokenizer.from_pretrained(model_repo_path)
+
+# Initialize the summarization pipeline
+summarizer = pipeline('summarization', model=model, tokenizer=tokenizer)
+
+# Streamlit app layout
+st.set_page_config(page_title="Text Summarization App", page_icon=":memo:", layout="wide")
+
+st.title("Text Summarization App")
+st.write("""
+    This app uses a fine-tuned BART model to generate summaries of your input text.
+    Enter the text you want to summarize in the box below and click "Summarize" to see the result.
+""")
+
+# User input
+text_input = st.text_area("Enter text to summarize", height=300, placeholder="Paste your text here...")
+
+# Summarize the text
+if st.button("Summarize"):
+    if text_input:
+        with st.spinner("Generating summary..."):
+            try:
+                # Generate summary
+                summary = summarizer(text_input, max_length=150, min_length=30, do_sample=False)
+                
+                # Display summary
+                st.subheader("Summary")
+                st.write(summary[0]['summary_text'])
+            except Exception as e:
+                st.error(f"An error occurred during summarization: {e}")
+    else:
+        st.warning("Please enter some text to summarize.")
+
+# Optional: Add a footer or additional information
+st.markdown("""
+    ---
+    Made with ❤️ using [Streamlit](https://streamlit.io) and [Hugging Face Transformers](https://huggingface.co/transformers/).
+""")