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