Update README.md

README.md

@@ -15,7 +15,9 @@ main.h5: the model trained on the data.csv file for 2 epoches with a batch size
 
 tokenizer.pkl: contain the tokenizer for 5he pre-trained model. genorated by train.py
 
-interact.py: pulls categorizer.h5, and tokenizer.pkl together in a simple text-based assistan (voice in and out put comeing soon)
+interact.py: pulls categorizer.h5, and tokenizer.pkl together in a simple text-based assistan (voice in and out put coming soon)
+
+data.csv: the custom dataset this it is trained on
 
 ## How to actualy use this model
 1. download categorizer.h5, tokenizer.pkl, and interact.py