Create app.py

app.py

@@ -0,0 +1,31 @@
+import streamlit as st
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+import torch
+import nltk
+
+# Download punkt for sentence tokenization
+nltk.download('punkt')
+
+# Load tokenizer and model from the Hugging Face Hub
+tokenizer = AutoTokenizer.from_pretrained("your-huggingface-username/your-model-repo-name")
+model = AutoModelForSeq2SeqLM.from_pretrained("your-huggingface-username/your-model-repo-name")
+
+st.title("Dialogue Summarization with BART")
+
+# Input dialogue
+dialogue = st.text_area("Enter dialogue:", height=200)
+
+if st.button("Summarize"):
+    # Tokenize input
+    inputs = tokenizer(dialogue, max_length=512, truncation=True, return_tensors="pt")
+
+    # Generate summary
+    summary_ids = model.generate(inputs["input_ids"], max_length=128, num_beams=4, early_stopping=True)
+    summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
+
+    # Display summary
+    st.subheader("Summary:")
+    st.write(summary)
+
+st.markdown("---")
+st.markdown("This app uses a fine-tuned BART model to summarize dialogues. The model was trained on the SAMSum dataset.")