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