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