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 @@
+{"r": 0, "x": 1, "w": 2, "f": 3, "3": 4, "9": 5, "h": 6, "2": 7, "y": 8, "'": 9, "a": 10, "1": 11, "b": 12, "z": 13, "4": 15, "5": 16, "n": 17, "0": 18, "k": 19, "8": 20, "c": 21, "6": 22, "u": 23, "d": 24, "i": 25, "p": 26, "q": 27, "v": 28, "e": 29, "g": 30, "t": 31, "l": 32, "j": 33, "s": 34, "m": 35, "o": 36, "|": 14, "[UNK]": 37, "[PAD]": 38}