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": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

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