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": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

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