fix column removal issue

run_speech_recognition_ctc.py

@@ -331,7 +331,7 @@ def create_vocabulary_from_data(
         batched=True,
         batch_size=10000,
         keep_in_memory=False,
-        remove_columns=datasets["train"].column_names,
+        remove_columns=[col for col in datasets["train"].column_names if col in datasets["eval"].column_names],
     )
 
     # take union of all unique characters in each dataset