Hugging Face's logo

A7oad
/
qaf-tasmi-v4

Automatic Speech Recognition
Transformers
Safetensors
ExecuTorch
wav2vec2
Model card Files
xet
 Community
A7oad commited on
Commit
4285183
·
verified ·
1 Parent(s): 8378eaf

Upload processor

Browse files
Files changed (4) hide show
  1. added_tokens.json +5 -0
  2. processor_config.json +12 -0
  3. tokenizer_config.json +56 -0
  4. vocab.json +82 -0
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "</s>": 81,
3
+ "<s>": 80,
4
+ "[UNK]": 82
5
+ }
processor_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feature_extractor": {
3
+ "do_normalize": true,
4
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
5
+ "feature_size": 1,
6
+ "padding_side": "right",
7
+ "padding_value": 0.0,
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ },
11
+ "processor_class": "Wav2Vec2Processor"
12
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "|",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "80": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "81": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "82": {
36
+ "content": "[UNK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "backend": "custom",
45
+ "bos_token": "<s>",
46
+ "do_lower_case": false,
47
+ "eos_token": "</s>",
48
+ "model_max_length": 1000000000000000019884624838656,
49
+ "pad_token": "<pad>",
50
+ "processor_class": "Wav2Vec2Processor",
51
+ "replace_word_delimiter_char": " ",
52
+ "target_lang": null,
53
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
54
+ "unk_token": "[UNK]",
55
+ "word_delimiter_token": "|"
56
+ }
vocab.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<pad>": 0,
3
+ "|": 1,
4
+ "ء": 2,
5
+ "أ": 3,
6
+ "ؤ": 4,
7
+ "إ": 5,
8
+ "ئ": 6,
9
+ "ا": 7,
10
+ "ب": 8,
11
+ "ة": 9,
12
+ "ت": 10,
13
+ "ث": 11,
14
+ "ج": 12,
15
+ "ح": 13,
16
+ "خ": 14,
17
+ "د": 15,
18
+ "ذ": 16,
19
+ "ر": 17,
20
+ "ز": 18,
21
+ "س": 19,
22
+ "ش": 20,
23
+ "ص": 21,
24
+ "ض": 22,
25
+ "ط": 23,
26
+ "ظ": 24,
27
+ "ع": 25,
28
+ "غ": 26,
29
+ "ـ": 27,
30
+ "ف": 28,
31
+ "ق": 29,
32
+ "ك": 30,
33
+ "ل": 31,
34
+ "م": 32,
35
+ "ن": 33,
36
+ "ه": 34,
37
+ "و": 35,
38
+ "ى": 36,
39
+ "ي": 37,
40
+ "ً": 38,
41
+ "ٌ": 39,
42
+ "ٍ": 40,
43
+ "َ": 41,
44
+ "ُ": 42,
45
+ "ِ": 43,
46
+ "ّ": 44,
47
+ "ْ": 45,
48
+ "ٓ": 46,
49
+ "ٔ": 47,
50
+ "ٕ": 48,
51
+ "ٮ": 49,
52
+ "ٰ": 50,
53
+ "ٱ": 51,
54
+ "ٲ": 52,
55
+ "ۖ": 53,
56
+ "ۚ": 54,
57
+ "ۜ": 55,
58
+ "۞": 56,
59
+ "۟": 57,
60
+ "ۢ": 58,
61
+ "ۥ": 59,
62
+ "ۦ": 60,
63
+ "۩": 61,
64
+ "ۭ": 62,
65
+ "‌": 63,
66
+ "": 64,
67
+ "": 65,
68
+ "": 66,
69
+ "": 67,
70
+ "": 68,
71
+ "": 69,
72
+ "": 70,
73
+ "": 71,
74
+ "": 72,
75
+ "": 73,
76
+ "": 74,
77
+ "": 75,
78
+ "": 76,
79
+ "": 77,
80
+ "": 78,
81
+ "": 79
82
+ }