add tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +1 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 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
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"ó": 0, "ọ": 1, "à": 2, "ặ": 4, "ĩ": 5, "ể": 6, "d": 7, "ấ": 8, "ò": 9, "ù": 10, "è": 11, "c": 12, "đ": 13, "ỹ": 14, "w": 15, "ủ": 16, "j": 17, "o": 18, "ệ": 19, "ế": 20, "b": 21, "ừ": 22, "ư": 23, "ờ": 24, "e": 25, "ẹ": 26, "ì": 27, "k": 28, "ẵ": 29, "ứ": 30, "p": 31, "ổ": 32, "é": 33, "ẽ": 34, "ề": 35, "h": 36, "ẳ": 37, "ự": 38, "ữ": 39, "v": 40, "ã": 41, "ở": 42, "x": 43, "s": 44, "ý": 45, "ễ": 46, "ạ": 47, "g": 48, "ậ": 49, "m": 50, "r": 51, "ă": 52, "t": 53, "ằ": 54, "i": 55, "ẻ": 56, "ố": 57, "ả": 58, "ỵ": 59, "l": 60, "ơ": 61, "ỏ": 62, "ẫ": 63, "ô": 64, "ẩ": 65, "ợ": 66, "ị": 67, "ử": 68, "q": 69, "ê": 70, "ỷ": 71, "á": 72, "f": 73, "í": 74, "y": 75, "ộ": 76, "ỗ": 77, "a": 78, "ồ": 79, "ỡ": 80, "â": 81, "ỉ": 82, "ú": 83, "ầ": 84, "u": 85, "õ": 86, "ụ": 87, "ỳ": 88, "n": 89, "ắ": 90, "ũ": 91, "z": 92, "ớ": 93, "|": 3, "[UNK]": 94, "[PAD]": 95}
|