Minor changes

data/preprocessing.py

@@ -64,8 +64,7 @@ def get_prepared_data(source_data_path: str,
 def count_words(string: str) -> int:
     return len(string.split())
 
-get_prepared_data("data/tokenizer-data/news-commentary-v11.de", "data/tokenizer-data/news-commentary-v11.en", seperator_symbol=None)
-
+# get_prepared_data("data/tokenizer-data/news-commentary-v11.de", "data/tokenizer-data/news-commentary-v11.en")
 
 def create_tokenizers(source_data_path: str, target_data_path: str, source_language: str, target_language: str):
     # setting the unknown token (e.g. for emojis)