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