Update README.md

README.md

@@ -89,7 +89,6 @@ def insert_accents(text, model, tokenizer):
 
 
 text = "Nhin nhung mua thu di, em nghe sau len trong nang."
-
 tokens, predictions = insert_accents(text, model, tokenizer)
 ```
 
@@ -171,7 +170,10 @@ Obtained:
 [('Nhin', {217}), ('nhung', {388}), ('mua', {407}), ('thu', {378}), ('di,', {120, 0}), ('em', {185}), ('nghe', {185}), ('sau', {41}), ('len', {188}), ('trong', {302}), ('nang.', {0, 14})]
 ```
 
-Then our final part: 
+For each word, we now have a set of tag indexes to apply to it. 
+For ex, for the first word "Nhin" above, we'd apply the tag at index `217` in our tags set. 
+
+The following is our final part: 
 
 ```python
 def get_accented_words(merged_tokens_preds, label_list):
@@ -211,7 +213,8 @@ In this example, the model made 1 mistake with the word "sầu" (but predicted "
 More info can be found <a href="https://peterhung.org/tech/insert-vietnamese-accent-transformer-model/#vs-hmm" target="_blank">here</a>.
 
 
+
 ## Live Demo
 There is a live demo of this model available <a href="https://ai.vietnameseaccent.com/" target="_blank">here</a>. 
 
-This demo is run on CPU so the speed is quite slow.
+This demo is run on CPU so the speed is expected to be not as fast as when run on GPU.