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": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

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