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