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 @@
+{"i": 0, "b": 1, "ị": 2, "u": 3, "ễ": 4, "v": 5, "ộ": 6, "r": 7, "â": 8, "ằ": 9, "o": 10, "í": 11, "h": 12, "ầ": 13, "ứ": 14, "s": 15, "õ": 16, "ổ": 17, "ố": 18, "ù": 19, "y": 20, "ĩ": 21, "ợ": 22, "ô": 23, "ờ": 24, "t": 25, "ì": 26, "ớ": 27, "è": 28, "à": 29, "m": 31, "f": 32, "ó": 33, "ũ": 34, "ỉ": 35, "ẽ": 36, "ư": 37, "ủ": 38, "é": 39, "ừ": 40, "ồ": 41, "q": 42, "ự": 43, "ế": 44, "'": 45, "ỡ": 46, "a": 47, "ẹ": 48, "g": 49, "ở": 50, "ă": 51, "ỹ": 52, "n": 53, "á": 54, "j": 55, "ể": 56, "d": 57, "e": 58, "ẫ": 59, "ỏ": 60, "ý": 61, "đ": 62, "ò": 63, "z": 64, "l": 65, "w": 66, "ơ": 67, "ả": 68, "ê": 69, "ỳ": 70, "ạ": 71, "ẻ": 72, "ậ": 73, "ụ": 74, "ẩ": 75, "p": 76, "ữ": 77, "ỵ": 78, "ỗ": 79, "ỷ": 80, "ặ": 81, "ấ": 82, "c": 83, "ề": 84, "x": 85, "ử": 86, "k": 87, "ẵ": 88, "ọ": 89, "ẳ": 90, "ú": 91, "ệ": 92, "ắ": 93, "ã": 94, "|": 30, "[UNK]": 95, "[PAD]": 96}