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 @@
+{"z": 0, "m": 1, "v": 2, "w": 3, "u": 4, "c": 5, "j": 6, "g": 7, "q": 8, "t": 9, "o": 10, "b": 11, "i": 12, "d": 13, "l": 14, "k": 15, "p": 16, "x": 17, "s": 18, "y": 19, "e": 20, "a": 21, "r": 22, "f": 23, "h": 24, "n": 26, "|": 25, "[UNK]": 27, "[PAD]": 28}