Update README.md

README.md

@@ -18,11 +18,11 @@ It achieves the following results on the evaluation set:
 - Train Sparse Categorical Accuracy: 0.9836
 - Validation Loss: 0.4073
 - Validation Sparse Categorical Accuracy: 0.9583
-- Epoch: 4
+- Epoch: 3
 
 ## Model description
 
-Base model:  'bert-base-cased' it can be used for intent classification. It trained on the [Intent-Classification-Commands](https://huggingface.co/datasets/dipesh/Intent-Classification-Commands) dataset. With following classes-
+Base model:  'bert-base-cased' can be used for intent classification. It trained on the [Intent-Classification-Commands](https://huggingface.co/datasets/dipesh/Intent-Classification-Commands) dataset. With the following classes-
 
 ```
 {
@@ -50,7 +50,7 @@ Base model:  'bert-base-cased' it can be used for intent classification. It trai
 ## Intended uses & limitations
 
 Intent Classifications for Chatbot or Virtual Assistant.
-Only supports English language. It can't work on outside classes. But you can fine-tune it for your own use.
+Only supports the English language. It can't work in outside classes. But you can fine-tune it for your own use.
 
 ## Training and evaluation data