Hugging Face's logo

hadiqa123
/
xlsr_ur_training

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
2
hadiqa123 commited on
Commit
bfb3a27
•
1 Parent(s): b139617

add tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +6 -0
  2. tokenizer_config.json +10 -0
  3. vocab.json +57 -0
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 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "pad_token": "[PAD]",
6
+ "replace_word_delimiter_char": " ",
7
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
8
+ "unk_token": "[UNK]",
9
+ "word_delimiter_token": "|"
10
+ }
vocab.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "'": 25,
3
+ "[PAD]": 54,
4
+ "[UNK]": 53,
5
+ "|": 9,
6
+ "؟": 36,
7
+ "ء": 16,
8
+ "آ": 40,
9
+ "ؤ": 46,
10
+ "ئ": 27,
11
+ "ا": 44,
12
+ "ب": 17,
13
+ "ت": 50,
14
+ "ث": 20,
15
+ "ج": 51,
16
+ "ح": 31,
17
+ "خ": 7,
18
+ "د": 33,
19
+ "ذ": 28,
20
+ "ر": 10,
21
+ "ز": 14,
22
+ "س": 2,
23
+ "ش": 18,
24
+ "ص": 13,
25
+ "ض": 19,
26
+ "ط": 34,
27
+ "ظ": 22,
28
+ "ع": 32,
29
+ "غ": 37,
30
+ "ف": 8,
31
+ "ق": 42,
32
+ "ل": 5,
33
+ "م": 29,
34
+ "ن": 4,
35
+ "و": 49,
36
+ "ي": 38,
37
+ "ُ": 21,
38
+ "ِ": 1,
39
+ "ّ": 15,
40
+ "ٔ": 11,
41
+ "ٰ": 39,
42
+ "ٹ": 47,
43
+ "پ": 30,
44
+ "چ": 43,
45
+ "ڈ": 6,
46
+ "ڑ": 23,
47
+ "ژ": 12,
48
+ "ک": 0,
49
+ "گ": 52,
50
+ "ں": 24,
51
+ "ھ": 48,
52
+ "ہ": 3,
53
+ "ۂ": 45,
54
+ "ی": 35,
55
+ "ے": 41,
56
+ "۔": 26
57
+ }