Update README.md

README.md

@@ -20,4 +20,4 @@ tags:
 
 Whisper model finetuned using audio data from Open STT Russian Dataset (https://github.com/snakers4/open_stt). 
 
-Due to differences in tokenization of source data (in our data normalization process, we replace punctucation with `""` rather than Whisper's `" "`), there is a slight degredation on CommonVoice.
+There is a differences in tokenization of source data (in our data normalization process, we replace punctucation with "" rather than Whisper's " "). This mismatch leads to a slight degradation on CommonVoice.