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