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": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"đ": 0, "y": 1, "ờ": 3, "ê": 4, "ủ": 5, "q": 6, "l": 7, "u": 8, "p": 9, "ổ": 10, "ữ": 11, "o": 12, "x": 13, "ẽ": 14, "ỵ": 15, "ị": 16, "ậ": 17, "ơ": 18, "ý": 19, "ử": 20, "â": 21, "ợ": 22, "ô": 23, "ẫ": 24, "4": 25, "c": 26, "ễ": 27, "ẻ": 28, "ú": 29, "ệ": 30, "s": 31, "á": 32, "ụ": 33, "ũ": 34, "ò": 35, "ỗ": 36, "v": 37, "à": 38, "ạ": 39, "ã": 40, "ỷ": 41, "m": 42, "ẹ": 43, "ả": 44, "e": 45, "a": 46, "ự": 47, "ố": 48, "ẳ": 49, "ọ": 50, "ỉ": 51, "ặ": 52, "ứ": 53, "i": 54, "k": 55, "é": 56, "ỡ": 57, "ể": 58, "ầ": 59, "h": 60, "ấ": 61, "n": 62, "ắ": 63, "g": 64, "ằ": 65, "r": 66, "ư": 67, "ỏ": 68, "ẩ": 69, "t": 70, "ă": 71, "ở": 72, "ớ": 73, "ộ": 74, "ế": 75, "ó": 76, "ồ": 77, "è": 78, "ì": 79, "ỳ": 80, "õ": 81, "ừ": 82, "ề": 83, "b": 84, "ù": 85, "ỹ": 86, "d": 87, "ĩ": 88, "ẵ": 89, "í": 90, "|": 2, "[UNK]": 91, "[PAD]": 92}
|