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