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 @@
+{"5": 0, "v": 1, "s": 2, "a": 3, "o": 4, "0": 5, "b": 6, "y": 7, "e": 8, "n": 9, "d": 10, "k": 11, "x": 12, "f": 13, "t": 14, "h": 15, "j": 16, "2": 17, "l": 18, "r": 20, "1": 21, "=": 22, "w": 23, "u": 24, "c": 25, "m": 26, "g": 27, "p": 28, "i": 29, "|": 19, "[UNK]": 30, "[PAD]": 31}