do not remove columns when building vocab

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=datasets["train"].column_names,
     )
 
     # take union of all unique characters in each dataset

vocab.json

@@ -1 +0,0 @@
-{"a": 1, "b": 2, "c": 3, "d": 4, "e": 5, "f": 6, "g": 7, "h": 8, "i": 9, "j": 10, "k": 11, "l": 12, "m": 13, "n": 14, "o": 15, "p": 16, "q": 17, "r": 18, "s": 19, "t": 20, "u": 21, "v": 22, "w": 23, "x": 24, "y": 25, "z": 26, "ä": 27, "å": 28, "é": 29, "ô": 30, "ö": 31, "ü": 32, "|": 0, "[UNK]": 33, "[PAD]": 34}