add time log and reduce processing time

app.py

@@ -11,8 +11,8 @@ logger = logging.getLogger(__name__)
 app = FastAPI()
 
 # Load model and tokenizer
-tokenizer = AutoTokenizer.from_pretrained("VietAI/vit5-base")
-model = AutoModelForSeq2SeqLM.from_pretrained("VietAI/vit5-base")
+tokenizer = AutoTokenizer.from_pretrained("VietAI/vit5-large-vietnews-summarization")
+model = AutoModelForSeq2SeqLM.from_pretrained("VietAI/vit5-large-vietnews-summarization")
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 model.to(device)