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