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