Hugging Face's logo

hiba2
/
wav2vec2-large-mms-1b-arabic-colab

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Model card Files Metrics Community
hiba2 commited on
Commit
8fad86d
·
1 Parent(s): ff9260c

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 +107 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 104,
3
+ "<s>": 103
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
+ "101": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "102": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "103": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "104": {
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": "ar_eg",
44
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
45
+ "unk_token": "[UNK]",
46
+ "word_delimiter_token": "|"
47
+ }
vocab.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "ar_eg": {
3
+ "+": 1,
4
+ "/": 2,
5
+ "0": 3,
6
+ "1": 4,
7
+ "2": 5,
8
+ "3": 6,
9
+ "4": 7,
10
+ "5": 8,
11
+ "6": 9,
12
+ "7": 10,
13
+ "8": 11,
14
+ "9": 12,
15
+ "[PAD]": 102,
16
+ "[UNK]": 101,
17
+ "a": 13,
18
+ "b": 14,
19
+ "c": 15,
20
+ "d": 16,
21
+ "e": 17,
22
+ "f": 18,
23
+ "g": 19,
24
+ "h": 20,
25
+ "i": 21,
26
+ "j": 22,
27
+ "k": 23,
28
+ "l": 24,
29
+ "m": 25,
30
+ "n": 26,
31
+ "o": 27,
32
+ "p": 28,
33
+ "r": 29,
34
+ "s": 30,
35
+ "t": 31,
36
+ "u": 32,
37
+ "v": 33,
38
+ "w": 34,
39
+ "x": 35,
40
+ "y": 36,
41
+ "z": 37,
42
+ "|": 0,
43
+ "½": 38,
44
+ "¾": 39,
45
+ "×": 40,
46
+ "õ": 41,
47
+ "،": 42,
48
+ "؛": 43,
49
+ "ء": 44,
50
+ "آ": 45,
51
+ "أ": 46,
52
+ "ؤ": 47,
53
+ "إ": 48,
54
+ "ئ": 49,
55
+ "ا": 50,
56
+ "ب": 51,
57
+ "ة": 52,
58
+ "ت": 53,
59
+ "ث": 54,
60
+ "ج": 55,
61
+ "ح": 56,
62
+ "خ": 57,
63
+ "د": 58,
64
+ "ذ": 59,
65
+ "ر": 60,
66
+ "ز": 61,
67
+ "س": 62,
68
+ "ش": 63,
69
+ "ص": 64,
70
+ "ض": 65,
71
+ "ط": 66,
72
+ "ظ": 67,
73
+ "ع": 68,
74
+ "غ": 69,
75
+ "ـ": 70,
76
+ "ف": 71,
77
+ "ق": 72,
78
+ "ك": 73,
79
+ "ل": 74,
80
+ "م": 75,
81
+ "ن": 76,
82
+ "ه": 77,
83
+ "و": 78,
84
+ "ى": 79,
85
+ "ي": 80,
86
+ "ً": 81,
87
+ "ٌ": 82,
88
+ "ٍ": 83,
89
+ "َ": 84,
90
+ "ُ": 85,
91
+ "ِ": 86,
92
+ "ّ": 87,
93
+ "ْ": 88,
94
+ "٠": 89,
95
+ "١": 90,
96
+ "٢": 91,
97
+ "٣": 92,
98
+ "٥": 93,
99
+ "٦": 94,
100
+ "٧": 95,
101
+ "٨": 96,
102
+ "٩": 97,
103
+ "٪": 98,
104
+ "چ": 99,
105
+ "—": 100
106
+ }
107
+ }