Update app.py

app.py

@@ -5,7 +5,11 @@ from transformers import pipeline
 
 # 1️⃣  small, open model that needs no access-token
 MODEL_ID = "Xenova/distilbart-cnn-6-6"
-summariser = pipeline("summarization", model=MODEL_ID, device=-1)  # -1 = CPU
+# summariser = pipeline("summarization", model=MODEL_ID, device=-1)  # -1 = CPU
+tok   = AutoTokenizer.from_pretrained(MODEL_ID)
+model = ORTModelForSeq2SeqLM.from_pretrained(MODEL_ID, file_name="model.onnx")
+
+summariser = pipeline("summarization", model=model, tokenizer=tok, device=-1)
 
 # 2️⃣  rough char limit that maps to the model’s 1 024-token window
 MAX_CHUNK = 3_500