Hugging Face's logo

hadiqa123
/
xls-r_cv_ur

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
2
hadiqa123 commited on
Commit
7584cef
•
1 Parent(s): 03066fc

Upload tokenizer

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