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