[MINOR:TYPO] Fix docstrings (#1653)

* [MINOR:TYPO] Update pre_tokenizers.rs

* [MINOR:TYPO] Update __init__.pyi

Author: cakiki

bindings/python/py_src/tokenizers/pre_tokenizers/__init__.pyi

@@ -421,7 +421,7 @@ class Split(PreTokenizer):
 
     Args:
         pattern (:obj:`str` or :class:`~tokenizers.Regex`):
-            A pattern used to split the string. Usually a string or a a regex built with `tokenizers.Regex`.
+            A pattern used to split the string. Usually a string or a regex built with `tokenizers.Regex`.
             If you want to use a regex pattern, it has to be wrapped around a `tokenizer.Regex`,
             otherwise we consider is as a string pattern. For example `pattern="|"`
             means you want to split on `|` (imagine a csv file for example), while

bindings/python/src/pre_tokenizers.rs

@@ -334,7 +334,7 @@ impl PyWhitespaceSplit {
 ///
 /// Args:
 ///     pattern (:obj:`str` or :class:`~tokenizers.Regex`):
-///         A pattern used to split the string. Usually a string or a a regex built with `tokenizers.Regex`.
+///         A pattern used to split the string. Usually a string or a regex built with `tokenizers.Regex`.
 ///         If you want to use a regex pattern, it has to be wrapped around a `tokenizer.Regex`,
 ///         otherwise we consider is as a string pattern. For example `pattern="|"`
 ///         means you want to split on `|` (imagine a csv file for example), while