Hugging Face's logo

sqrk
/
mms-mixat-tri-transcript

Model card Files Community
sqrk commited on
Commit
e41445d
•
1 Parent(s): 9ba86b8

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 +82 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 79,
3
+ "<s>": 78
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
+ "76": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "77": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "78": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "79": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": true,
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": "ara",
44
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
45
+ "unk_token": "[UNK]",
46
+ "word_delimiter_token": "|"
47
+ }
vocab.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "ara": {
3
+ "0": 1,
4
+ "3": 2,
5
+ "4": 3,
6
+ "[": 4,
7
+ "[PAD]": 77,
8
+ "[UNK]": 76,
9
+ "]": 5,
10
+ "a": 6,
11
+ "b": 7,
12
+ "c": 8,
13
+ "d": 9,
14
+ "e": 10,
15
+ "f": 11,
16
+ "g": 12,
17
+ "h": 13,
18
+ "i": 14,
19
+ "j": 15,
20
+ "k": 16,
21
+ "l": 17,
22
+ "m": 18,
23
+ "n": 19,
24
+ "o": 20,
25
+ "p": 21,
26
+ "q": 22,
27
+ "r": 23,
28
+ "s": 24,
29
+ "t": 25,
30
+ "u": 26,
31
+ "v": 27,
32
+ "w": 28,
33
+ "x": 29,
34
+ "y": 30,
35
+ "z": 31,
36
+ "|": 0,
37
+ "؛": 32,
38
+ "ء": 33,
39
+ "آ": 34,
40
+ "أ": 35,
41
+ "ؤ": 36,
42
+ "إ": 37,
43
+ "ئ": 38,
44
+ "ا": 39,
45
+ "ب": 40,
46
+ "ة": 41,
47
+ "ت": 42,
48
+ "ث": 43,
49
+ "ج": 44,
50
+ "ح": 45,
51
+ "خ": 46,
52
+ "د": 47,
53
+ "ذ": 48,
54
+ "ر": 49,
55
+ "ز": 50,
56
+ "س": 51,
57
+ "ش": 52,
58
+ "ص": 53,
59
+ "ض": 54,
60
+ "ط": 55,
61
+ "ظ": 56,
62
+ "ع": 57,
63
+ "غ": 58,
64
+ "ف": 59,
65
+ "ق": 60,
66
+ "ك": 61,
67
+ "ل": 62,
68
+ "م": 63,
69
+ "ن": 64,
70
+ "ه": 65,
71
+ "و": 66,
72
+ "ى": 67,
73
+ "ي": 68,
74
+ "ً": 69,
75
+ "ٍ": 70,
76
+ "َ": 71,
77
+ "ُ": 72,
78
+ "ِ": 73,
79
+ "ی": 74,
80
+ "–": 75
81
+ }
82
+ }