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