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