Hugging Face's logo

Pak-Speech-Processing
/
w2v-bert-2.0-ur

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2-bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
mwz commited on
Commit
130b300
•
1 Parent(s): 6549bc8

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 +92 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 91,
3
+ "<s>": 90
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
+ "88": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "89": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "90": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "91": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
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 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 89,
3
+ "[UNK]": 88,
4
+ "_": 1,
5
+ "`": 2,
6
+ "|": 0,
7
+ "،": 3,
8
+ "ؐ": 4,
9
+ "ؑ": 5,
10
+ "ؓ": 6,
11
+ "ؔ": 7,
12
+ "؛": 8,
13
+ "؟": 9,
14
+ "ء": 10,
15
+ "آ": 11,
16
+ "أ": 12,
17
+ "ؤ": 13,
18
+ "ئ": 14,
19
+ "ا": 15,
20
+ "ب": 16,
21
+ "ت": 17,
22
+ "ث": 18,
23
+ "ج": 19,
24
+ "ح": 20,
25
+ "خ": 21,
26
+ "د": 22,
27
+ "ذ": 23,
28
+ "ر": 24,
29
+ "ز": 25,
30
+ "س": 26,
31
+ "ش": 27,
32
+ "ص": 28,
33
+ "ض": 29,
34
+ "ط": 30,
35
+ "ظ": 31,
36
+ "ع": 32,
37
+ "غ": 33,
38
+ "ف": 34,
39
+ "ق": 35,
40
+ "ك": 36,
41
+ "ل": 37,
42
+ "م": 38,
43
+ "ن": 39,
44
+ "ه": 40,
45
+ "و": 41,
46
+ "ى": 42,
47
+ "ي": 43,
48
+ "ً": 44,
49
+ "َ": 45,
50
+ "ُ": 46,
51
+ "ِ": 47,
52
+ "ّ": 48,
53
+ "ْ": 49,
54
+ "ٓ": 50,
55
+ "ٔ": 51,
56
+ "ٗ": 52,
57
+ "ٰ": 53,
58
+ "ٴ": 54,
59
+ "ٹ": 55,
60
+ "پ": 56,
61
+ "چ": 57,
62
+ "ڈ": 58,
63
+ "ڑ": 59,
64
+ "ژ": 60,
65
+ "ک": 61,
66
+ "گ": 62,
67
+ "ں": 63,
68
+ "ھ": 64,
69
+ "ہ": 65,
70
+ "ۂ": 66,
71
+ "ۃ": 67,
72
+ "ی": 68,
73
+ "ے": 69,
74
+ "ۓ": 70,
75
+ "۔": 71,
76
+ "’": 72,
77
+ "…": 73,
78
+ "ﭨ": 74,
79
+ "ﮭ": 75,
80
+ "ﮯ": 76,
81
+ "ﯾ": 77,
82
+ "ﷲ": 78,
83
+ "ﷺ": 79,
84
+ "ﺅ": 80,
85
+ "ﺗ": 81,
86
+ "ﺘ": 82,
87
+ "ﺩ": 83,
88
+ "ﺲ": 84,
89
+ "ﻧ": 85,
90
+ "ﻮ": 86,
91
+ "！": 87
92
+ }