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, "v": 1, "y": 2, "q": 3, "x": 4, "j": 5, "g": 6, "s": 7, "l": 8, "'": 9, "d": 10, "w": 11, "t": 12, "c": 13, "m": 14, "p": 15, "u": 16, "h": 17, "r": 19, "b": 20, "f": 21, "e": 22, "n": 23, "a": 24, "o": 25, "i": 26, "z": 27, "|": 18, "[UNK]": 28, "[PAD]": 29}