Hugging Face's logo

Shehryar718
/
URDU-ASR

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Shehryar718 commited on
Commit
eded62c
•
1 Parent(s): c66fe2d

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +4 -0
  2. special_tokens_map.json +6 -0
  3. tokenizer_config.json +47 -0
  4. vocab.json +88 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 87,
3
+ "<s>": 86
4
+ }
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 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "84": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "85": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "86": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "87": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "[PAD]",
42
+ "replace_word_delimiter_char": " ",
43
+ "target_lang": null,
44
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
45
+ "unk_token": "[UNK]",
46
+ "word_delimiter_token": "|"
47
+ }
vocab.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "'": 50,
3
+ "[PAD]": 85,
4
+ "[UNK]": 84,
5
+ "`": 13,
6
+ "|": 66,
7
+ "،": 76,
8
+ "ؑ": 74,
9
+ "ؓ": 40,
10
+ "ؔ": 64,
11
+ "؛": 75,
12
+ "؟": 14,
13
+ "ء": 81,
14
+ "آ": 57,
15
+ "أ": 39,
16
+ "ؤ": 78,
17
+ "ئ": 26,
18
+ "ا": 51,
19
+ "ب": 77,
20
+ "ت": 80,
21
+ "ث": 69,
22
+ "ج": 59,
23
+ "ح": 58,
24
+ "خ": 24,
25
+ "د": 27,
26
+ "ذ": 49,
27
+ "ر": 20,
28
+ "ز": 41,
29
+ "س": 62,
30
+ "ش": 17,
31
+ "ص": 55,
32
+ "ض": 54,
33
+ "ط": 56,
34
+ "ظ": 42,
35
+ "ع": 9,
36
+ "غ": 32,
37
+ "ف": 2,
38
+ "ق": 43,
39
+ "ك": 47,
40
+ "ل": 36,
41
+ "م": 63,
42
+ "ن": 72,
43
+ "ه": 44,
44
+ "و": 6,
45
+ "ى": 68,
46
+ "ي": 53,
47
+ "ً": 29,
48
+ "َ": 67,
49
+ "ُ": 8,
50
+ "ِ": 83,
51
+ "ّ": 30,
52
+ "ْ": 23,
53
+ "ٓ": 0,
54
+ "ٔ": 33,
55
+ "ٗ": 15,
56
+ "ٰ": 4,
57
+ "ٹ": 21,
58
+ "پ": 19,
59
+ "چ": 35,
60
+ "ڈ": 61,
61
+ "ڑ": 38,
62
+ "ژ": 16,
63
+ "ک": 52,
64
+ "گ": 70,
65
+ "ں": 1,
66
+ "ھ": 22,
67
+ "ہ": 28,
68
+ "ۂ": 79,
69
+ "ۃ": 5,
70
+ "ی": 10,
71
+ "ے": 7,
72
+ "ۓ": 25,
73
+ "۔": 11,
74
+ "’": 71,
75
+ "…": 31,
76
+ "ﭨ": 37,
77
+ "ﮭ": 73,
78
+ "ﮯ": 46,
79
+ "ﯾ": 48,
80
+ "ﷲ": 12,
81
+ "ﷺ": 45,
82
+ "ﺗ": 3,
83
+ "ﺘ": 18,
84
+ "ﺩ": 65,
85
+ "ﺲ": 82,
86
+ "ﻧ": 60,
87
+ "ﻮ": 34
88
+ }