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