Update README.md

README.md

@@ -210,7 +210,8 @@ In this example, the model made 1 mistake with the word "sầu" (but predicted "
 
 ## Limitations 
 - This model will accept a maximum of 512 tokens, which is a limitation inherited from the base pretrained XLM-Roberta model.
-- It has a higher accuracy (97%) than <a href="https://vietnameseaccent.com/" target="_blank">the HMM version</a> (91%).
+- It has a higher accuracy (97%) than <a href="https://vietnameseaccent.com/" target="_blank">the HMM version</a> (91%), 
+but at the expense of a probably longer running time. 
 More info can be found <a href="https://peterhung.org/tech/insert-vietnamese-accent-transformer-model/#vs-hmm" target="_blank">here</a>.