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