Commit
·
fcf1fc0
1
Parent(s):
f6e14fb
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>": 35, "</s>": 36}
|
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": "/WOLOF/wav2vec2-xls-r-300m-wolof/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "/WOLOF/wav2vec2-xls-r-300m-wolof", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"e": 1, "g": 2, "à": 3, "w": 4, "l": 5, "ë": 6, "o": 7, "b": 8, "h": 9, "v": 10, "ñ": 11, "m": 12, "x": 13, "u": 14, "k": 15, "f": 16, "r": 17, "i": 18, "ã": 19, "c": 20, "j": 21, "t": 22, "s": 23, "a": 24, "ó": 25, "n": 26, "y": 27, "é": 28, "q": 29, "d": 30, "ç": 31, "p": 32, "|": 0, "[UNK]": 33, "[PAD]": 34}
|