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