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