add tokenizer

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}

tokenizer_config.json

@@ -0,0 +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"}

vocab.json

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