fix typo readme

README.md

@@ -20,7 +20,7 @@ For the moment, only the tokenizer is available. The tokenizer is based on [Sent
 
 Taking into account certain characteristics of the language, we chose that:
 
--   the tokenizer passes in lower case all the texts because The Bengali language being a monocameral scrip (no difference between capital and lower case);
+-   the tokenizer passes in lower case all the texts because the Bengali language is a monocameral scrip (no difference between capital and lower case);
 -   the sentence pieces can't go beyond the boundary of a word because the words are spaced by white spaces in the Bengali language.
 
 ## Intended uses & limitations