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 @@
+{"h": 0, "z": 1, "x": 2, "k": 3, "p": 4, "i": 5, "u": 6, "b": 7, "d": 8, "m": 9, "y": 10, "r": 11, "c": 12, "n": 13, "a": 14, "s": 15, "v": 16, "o": 17, "t": 19, "e": 20, "l": 21, "q": 22, "w": 23, "g": 24, "'": 25, "j": 26, "f": 27, "|": 18, "[UNK]": 28, "[PAD]": 29}