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