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