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