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