Hugging Face's logo

monaf3
/
wav2vec2-large-xlsr-arabic-demo-colab

Model card Files Community
monaf3 commited on
Commit
2cadec1
•
1 Parent(s): 3aaf2af

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 +63 -0
  4. vocab.json +53 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "[PAD]": 52,
3
+ "[UNK]": 51
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 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "51": {
36
+ "content": "[UNK]",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "52": {
44
+ "content": "[PAD]",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "bos_token": "<s>",
53
+ "clean_up_tokenization_spaces": true,
54
+ "do_lower_case": false,
55
+ "eos_token": "</s>",
56
+ "model_max_length": 1000000000000000019884624838656,
57
+ "pad_token": "[PAD]",
58
+ "replace_word_delimiter_char": " ",
59
+ "target_lang": null,
60
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
61
+ "unk_token": "[UNK]",
62
+ "word_delimiter_token": "|"
63
+ }
vocab.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "-": 5,
3
+ "</s>": 2,
4
+ "<pad>": 0,
5
+ "<s>": 1,
6
+ "<unk>": 3,
7
+ "|": 4,
8
+ "ء": 6,
9
+ "آ": 7,
10
+ "أ": 8,
11
+ "ؤ": 9,
12
+ "إ": 10,
13
+ "ئ": 11,
14
+ "ا": 12,
15
+ "ب": 13,
16
+ "ة": 14,
17
+ "ت": 15,
18
+ "ث": 16,
19
+ "ج": 17,
20
+ "ح": 18,
21
+ "خ": 19,
22
+ "د": 20,
23
+ "ذ": 21,
24
+ "ر": 22,
25
+ "ز": 23,
26
+ "س": 24,
27
+ "ش": 25,
28
+ "ص": 26,
29
+ "ض": 27,
30
+ "ط": 28,
31
+ "ظ": 29,
32
+ "ع": 30,
33
+ "غ": 31,
34
+ "ـ": 32,
35
+ "ف": 33,
36
+ "ق": 34,
37
+ "ك": 35,
38
+ "ل": 36,
39
+ "م": 37,
40
+ "ن": 38,
41
+ "ه": 39,
42
+ "و": 40,
43
+ "ى": 41,
44
+ "ي": 42,
45
+ "ً": 43,
46
+ "ٌ": 44,
47
+ "ٍ": 45,
48
+ "َ": 46,
49
+ "ُ": 47,
50
+ "ِ": 48,
51
+ "ّ": 49,
52
+ "ْ": 50
53
+ }