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