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