Update app.py

app.py

@@ -0,0 +1,49 @@
+import streamlit as st
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+# Load tokenizer and model
+model_identifier = "songhieng/khmer-mt5-summarization"
+tokenizer = AutoTokenizer.from_pretrained(model_identifier)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_identifier)
+
+# Set page configuration
+st.set_page_config(page_title="Khmer Text Summarization", layout="wide")
+
+# App title and description
+st.title("Khmer Text Summarization")
+st.write("Enter Khmer text below to generate a concise summary.")
+
+# Text input
+user_input = st.text_area("Input Text:", height=300)
+
+# Summarization parameters
+st.sidebar.header("Summarization Settings")
+max_length = st.sidebar.slider("Maximum Summary Length", min_value=50, max_value=300, value=150, step=10)
+min_length = st.sidebar.slider("Minimum Summary Length", min_value=10, max_value=100, value=30, step=5)
+num_beams = st.sidebar.slider("Number of Beams", min_value=1, max_value=10, value=4, step=1)
+
+# Summarize button
+if st.button("Summarize"):
+    if user_input.strip():
+        try:
+            # Tokenize input
+            inputs = tokenizer.encode(user_input, return_tensors="pt", truncation=True)
+
+            # Generate summary
+            summary_ids = model.generate(
+                inputs,
+                max_length=max_length,
+                min_length=min_length,
+                num_beams=num_beams,
+                length_penalty=2.0,
+                early_stopping=True
+            )
+            summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
+
+            # Display summary
+            st.subheader("Summary:")
+            st.write(summary)
+        except Exception as e:
+            st.error(f"An error occurred during summarization: {e}")
+    else:
+        st.warning("Please enter some text to summarize.")