Hugging Face's logo

batoula187
/
wav2vec2-large-xls-r-300m-arabic-colab

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
batoula187 commited on
Commit
d38f052
•
1 Parent(s): 21ba9c3

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -4
  3. vocab.json +65 -88
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 90,
3
- "<s>": 89
4
  }
 
1
  {
2
+ "</s>": 67,
3
+ "<s>": 66
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "87": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "88": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "89": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "90": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
 
1
  {
2
  "added_tokens_decoder": {
3
+ "64": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "65": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "66": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "67": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
vocab.json CHANGED
@@ -1,91 +1,68 @@
1
  {
2
- "(": 1,
3
- ")": 2,
4
- "[PAD]": 88,
5
- "[UNK]": 87,
6
- "a": 3,
7
- "b": 4,
8
- "c": 5,
9
- "d": 6,
10
- "e": 7,
11
- "g": 8,
12
- "h": 9,
13
- "i": 10,
14
- "j": 11,
15
- "k": 12,
16
- "l": 13,
17
- "m": 14,
18
- "n": 15,
19
- "o": 16,
20
- "p": 17,
21
- "q": 18,
22
- "r": 19,
23
- "s": 20,
24
- "t": 21,
25
- "u": 22,
26
- "v": 23,
27
- "x": 24,
28
- "y": 25,
29
  "|": 0,
30
- "«": 26,
31
- "»": 27,
32
- "،": 28,
33
- "؛": 29,
34
- "؟": 30,
35
- "ء": 31,
36
- "آ": 32,
37
- "أ": 33,
38
- "ؤ": 34,
39
- "إ": 35,
40
- "ئ": 36,
41
- "ا": 37,
42
- "ب": 38,
43
- "ة": 39,
44
- "ت": 40,
45
- "ث": 41,
46
- "ج": 42,
47
- "ح": 43,
48
- "خ": 44,
49
- "د": 45,
50
- "ذ": 46,
51
- "ر": 47,
52
- "ز": 48,
53
- "س": 49,
54
- "ش": 50,
55
- "ص": 51,
56
- "ض": 52,
57
- "ط": 53,
58
- "ظ": 54,
59
- "ع": 55,
60
- "غ": 56,
61
- "ـ": 57,
62
- "ف": 58,
63
- "ق": 59,
64
- "ك": 60,
65
- "ل": 61,
66
- "م": 62,
67
- "ن": 63,
68
- "ه": 64,
69
- "و": 65,
70
- "ى": 66,
71
- "ي": 67,
72
- "ً": 68,
73
- "ٌ": 69,
74
- "ٍ": 70,
75
- "َ": 71,
76
- "ُ": 72,
77
- "ِ": 73,
78
- "ّ": 74,
79
- "ْ": 75,
80
- "ٰ": 76,
81
- "چ": 77,
82
- "ک": 78,
83
- "ھ": 79,
84
- "ی": 80,
85
- "ۖ": 81,
86
- "ۗ": 82,
87
- "ۚ": 83,
88
- "—": 84,
89
- "ﺃ": 85,
90
- "ﻻ": 86
91
  }
 
1
  {
2
+ "[PAD]": 65,
3
+ "[UNK]": 64,
4
+ "a": 1,
5
+ "b": 2,
6
+ "d": 3,
7
+ "e": 4,
8
+ "i": 5,
9
+ "n": 6,
10
+ "r": 7,
11
+ "t": 8,
12
+ "v": 9,
13
+ "y": 10,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  "|": 0,
15
+ "،": 11,
16
+ "؛": 12,
17
+ "؟": 13,
18
+ "ء": 14,
19
+ "آ": 15,
20
+ "أ": 16,
21
+ "ؤ": 17,
22
+ "إ": 18,
23
+ "ئ": 19,
24
+ "ا": 20,
25
+ "ب": 21,
26
+ "ة": 22,
27
+ "ت": 23,
28
+ "ث": 24,
29
+ "ج": 25,
30
+ "ح": 26,
31
+ "خ": 27,
32
+ "د": 28,
33
+ "ذ": 29,
34
+ "ر": 30,
35
+ "ز": 31,
36
+ "س": 32,
37
+ "ش": 33,
38
+ "ص": 34,
39
+ "ض": 35,
40
+ "ط": 36,
41
+ "ظ": 37,
42
+ "ع": 38,
43
+ "غ": 39,
44
+ "ـ": 40,
45
+ "ف": 41,
46
+ "ق": 42,
47
+ "ك": 43,
48
+ "ل": 44,
49
+ "م": 45,
50
+ "ن": 46,
51
+ "ه": 47,
52
+ "و": 48,
53
+ "ى": 49,
54
+ "ي": 50,
55
+ "ً": 51,
56
+ "ٌ": 52,
57
+ "ٍ": 53,
58
+ "َ": 54,
59
+ "ُ": 55,
60
+ "ِ": 56,
61
+ "ّ": 57,
62
+ "ْ": 58,
63
+ "ٰ": 59,
64
+ "چ": 60,
65
+ "ک": 61,
66
+ "ی": 62,
67
+ "ۖ": 63
 
 
 
 
 
 
 
 
68
  }