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