add tokenizer

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

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