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