Hugging Face's logo

ad019el
/
tamasheq-98-2

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
7
ad019el commited on
Commit
813926d
•
1 Parent(s): d7d5797

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 +66 -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 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "/": 28,
3
+ "0": 12,
4
+ "1": 26,
5
+ "2": 39,
6
+ "7": 6,
7
+ "9": 34,
8
+ "[PAD]": 63,
9
+ "[UNK]": 62,
10
+ "_": 52,
11
+ "a": 36,
12
+ "c": 20,
13
+ "e": 8,
14
+ "f": 56,
15
+ "j": 45,
16
+ "l": 42,
17
+ "m": 48,
18
+ "o": 23,
19
+ "q": 49,
20
+ "r": 1,
21
+ "t": 47,
22
+ "u": 33,
23
+ "w": 54,
24
+ "|": 10,
25
+ "ء": 38,
26
+ "آ": 29,
27
+ "أ": 22,
28
+ "ؤ": 44,
29
+ "إ": 24,
30
+ "ئ": 9,
31
+ "ا": 7,
32
+ "ب": 30,
33
+ "ة": 27,
34
+ "ت": 37,
35
+ "ث": 50,
36
+ "ج": 35,
37
+ "ح": 46,
38
+ "خ": 19,
39
+ "د": 5,
40
+ "ذ": 14,
41
+ "ر": 41,
42
+ "ز": 15,
43
+ "س": 13,
44
+ "ش": 0,
45
+ "ص": 55,
46
+ "ض": 16,
47
+ "ط": 11,
48
+ "ظ": 53,
49
+ "ع": 58,
50
+ "غ": 59,
51
+ "ف": 21,
52
+ "ق": 25,
53
+ "ك": 60,
54
+ "ل": 4,
55
+ "م": 51,
56
+ "ن": 32,
57
+ "ه": 31,
58
+ "و": 61,
59
+ "ى": 3,
60
+ "ي": 43,
61
+ "ٱ": 18,
62
+ "چ": 40,
63
+ "ڤ": 2,
64
+ "ک": 57,
65
+ "ی": 17
66
+ }