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