Hugging Face's logo

Hunzla
/
wav2vec2-large-xls-r-300m-urdu-colab

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
Hunzla commited on
Commit
4a8adab
•
1 Parent(s): 0986cca

Upload tokenizer

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