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": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

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