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