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 @@
-{"p": 0, "c": 1, "k": 2, "'": 4, "e": 5, "h": 6, "w": 7, "z": 8, "o": 9, "f": 10, "b": 11, "d": 12, "m": 13, "r": 14, "a": 15, "g": 16, "x": 17, "t": 18, "v": 19, "l": 20, "y": 21, "j": 22, "u": 23, "s": 24, "i": 25, "n": 26, "q": 27, "|": 3, "[UNK]": 28, "[PAD]": 29}
+{"i": 0, "e": 1, "p": 2, "h": 3, "a": 4, "d": 5, "n": 6, "u": 7, "m": 8, "f": 9, "x": 10, "w": 11, "t": 13, "k": 14, "r": 15, "o": 16, "q": 17, "j": 18, "z": 19, "'": 20, "s": 21, "v": 22, "b": 23, "y": 24, "c": 25, "g": 26, "l": 27, "|": 12, "[UNK]": 28, "[PAD]": 29}