Incorrect behavior in the subword tokenizer

[hunterhector]

Describe the bug
The subword tokenizer did not consider lowercasing the text (even while using uncased BERT)

Expected behavior

1. It should consider the case according to the pre-trained model
2. It should also consider doing basic tokenization following texar-pytorch.

Screenshots
If applicable, add screenshots to help explain your problem.

Environment (please complete the following information):

• OS: [e.g. iOS]
• Version [e.g. 22]
• Python and Package verions: [e.g. Python version, Pytorch version]

Additional context
Add any other context about the problem here.