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