Hugging Face's logo

ad019el
/
Tamasheq-XLSR-53-mixed-Kabyle

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
3
ad019el commited on
Commit
81d75b1
•
1 Parent(s): fc0d46e

add tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +6 -0
  2. tokenizer_config.json +10 -0
  3. vocab.json +48 -0
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "pad_token": "[PAD]",
6
+ "replace_word_delimiter_char": " ",
7
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
8
+ "unk_token": "[UNK]",
9
+ "word_delimiter_token": "|"
10
+ }
vocab.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 45,
3
+ "[UNK]": 44,
4
+ "|": 27,
5
+ "ĉ": 28,
6
+ "̣": 8,
7
+ "ء": 37,
8
+ "آ": 18,
9
+ "أ": 5,
10
+ "ؤ": 34,
11
+ "إ": 0,
12
+ "ئ": 4,
13
+ "ا": 3,
14
+ "ب": 2,
15
+ "ة": 33,
16
+ "ت": 1,
17
+ "ث": 12,
18
+ "ج": 9,
19
+ "ح": 32,
20
+ "خ": 26,
21
+ "د": 25,
22
+ "ذ": 20,
23
+ "ر": 13,
24
+ "ز": 24,
25
+ "س": 30,
26
+ "ش": 38,
27
+ "ص": 19,
28
+ "ض": 17,
29
+ "ط": 41,
30
+ "ظ": 29,
31
+ "ع": 15,
32
+ "غ": 23,
33
+ "ف": 10,
34
+ "ق": 16,
35
+ "ك": 31,
36
+ "ل": 22,
37
+ "م": 11,
38
+ "ن": 6,
39
+ "ه": 39,
40
+ "و": 35,
41
+ "ى": 21,
42
+ "ي": 36,
43
+ "ٱ": 40,
44
+ "چ": 14,
45
+ "ڤ": 43,
46
+ "ک": 7,
47
+ "ی": 42
48
+ }