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 @@
+{"ay": 1, "p": 2, "aw": 3, "t": 4, "dx": 5, "ae": 6, "uh": 7, "hh": 8, "f": 9, "m": 10, "s": 11, "eh": 12, "k": 13, "g": 14, "zh": 15, "ey": 16, "ah": 17, "y": 18, "v": 19, "n": 20, "iy": 21, "z": 22, "ih": 23, "ch": 24, "er": 25, "aa": 26, "b": 27, "th": 28, "r": 29, "l": 30, "sh": 31, "jh": 32, "dh": 33, "uw": 34, "ng": 35, "ow": 36, "oy": 37, "d": 38, "w": 39, "|": 0, "[UNK]": 40, "[PAD]": 41}