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