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