diff --git a/wenet/text/char_tokenizer.py b/wenet/text/char_tokenizer.py index 5e47be41b..00b59b674 100644 --- a/wenet/text/char_tokenizer.py +++ b/wenet/text/char_tokenizer.py @@ -1,3 +1,5 @@ +import re + from os import PathLike from typing import Dict, List, Optional, Union from wenet.utils.file_utils import read_symbol_table, read_non_lang_symbols