Upload tokenizer
Browse files- added_tokens.json +2 -2
- tokenizer_config.json +4 -5
- vocab.json +81 -89
added_tokens.json
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
{
|
2 |
-
"</s>":
|
3 |
-
"<s>":
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"</s>": 83,
|
3 |
+
"<s>": 82
|
4 |
}
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
-
"
|
4 |
"content": "[UNK]",
|
5 |
"lstrip": true,
|
6 |
"normalized": false,
|
@@ -8,7 +8,7 @@
|
|
8 |
"single_word": false,
|
9 |
"special": false
|
10 |
},
|
11 |
-
"
|
12 |
"content": "[PAD]",
|
13 |
"lstrip": true,
|
14 |
"normalized": false,
|
@@ -16,7 +16,7 @@
|
|
16 |
"single_word": false,
|
17 |
"special": false
|
18 |
},
|
19 |
-
"
|
20 |
"content": "<s>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
@@ -24,7 +24,7 @@
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
"content": "</s>",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
@@ -39,7 +39,6 @@
|
|
39 |
"eos_token": "</s>",
|
40 |
"model_max_length": 1000000000000000019884624838656,
|
41 |
"pad_token": "[PAD]",
|
42 |
-
"processor_class": "Wav2Vec2BertProcessor",
|
43 |
"replace_word_delimiter_char": " ",
|
44 |
"target_lang": null,
|
45 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
+
"80": {
|
4 |
"content": "[UNK]",
|
5 |
"lstrip": true,
|
6 |
"normalized": false,
|
|
|
8 |
"single_word": false,
|
9 |
"special": false
|
10 |
},
|
11 |
+
"81": {
|
12 |
"content": "[PAD]",
|
13 |
"lstrip": true,
|
14 |
"normalized": false,
|
|
|
16 |
"single_word": false,
|
17 |
"special": false
|
18 |
},
|
19 |
+
"82": {
|
20 |
"content": "<s>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
+
"83": {
|
28 |
"content": "</s>",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
|
|
39 |
"eos_token": "</s>",
|
40 |
"model_max_length": 1000000000000000019884624838656,
|
41 |
"pad_token": "[PAD]",
|
|
|
42 |
"replace_word_delimiter_char": " ",
|
43 |
"target_lang": null,
|
44 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
vocab.json
CHANGED
@@ -1,92 +1,84 @@
|
|
1 |
{
|
2 |
-
"[PAD]":
|
3 |
-
"[UNK]":
|
4 |
-
"
|
5 |
-
"`": 2,
|
6 |
"|": 0,
|
7 |
-
"،":
|
8 |
-
"ؐ":
|
9 |
-
"ؑ":
|
10 |
-
"ؓ":
|
11 |
-
"ؔ":
|
12 |
-
"؛":
|
13 |
-
"؟":
|
14 |
-
"ء":
|
15 |
-
"آ":
|
16 |
-
"أ":
|
17 |
-
"ؤ":
|
18 |
-
"ئ":
|
19 |
-
"ا":
|
20 |
-
"ب":
|
21 |
-
"ت":
|
22 |
-
"ث":
|
23 |
-
"ج":
|
24 |
-
"ح":
|
25 |
-
"خ":
|
26 |
-
"د":
|
27 |
-
"ذ":
|
28 |
-
"ر":
|
29 |
-
"ز":
|
30 |
-
"س":
|
31 |
-
"ش":
|
32 |
-
"ص":
|
33 |
-
"ض":
|
34 |
-
"ط":
|
35 |
-
"ظ":
|
36 |
-
"ع":
|
37 |
-
"غ":
|
38 |
-
"ف":
|
39 |
-
"ق":
|
40 |
-
"
|
41 |
-
"
|
42 |
-
"
|
43 |
-
"
|
44 |
-
"
|
45 |
-
"
|
46 |
-
"
|
47 |
-
"
|
48 |
-
"
|
49 |
-
"
|
50 |
-
"
|
51 |
-
"
|
52 |
-
"
|
53 |
-
"
|
54 |
-
"
|
55 |
-
"
|
56 |
-
"
|
57 |
-
"
|
58 |
-
"
|
59 |
-
"
|
60 |
-
"
|
61 |
-
"
|
62 |
-
"
|
63 |
-
"
|
64 |
-
"
|
65 |
-
"
|
66 |
-
"
|
67 |
-
"
|
68 |
-
"
|
69 |
-
"
|
70 |
-
"
|
71 |
-
"
|
72 |
-
"
|
73 |
-
"
|
74 |
-
"
|
75 |
-
"
|
76 |
-
"
|
77 |
-
"
|
78 |
-
"
|
79 |
-
"
|
80 |
-
"
|
81 |
-
"
|
82 |
-
"
|
83 |
-
"
|
84 |
-
"
|
85 |
-
"ﺗ": 81,
|
86 |
-
"ﺘ": 82,
|
87 |
-
"ﺩ": 83,
|
88 |
-
"ﺲ": 84,
|
89 |
-
"ﻧ": 85,
|
90 |
-
"ﻮ": 86,
|
91 |
-
"!": 87
|
92 |
}
|
|
|
1 |
{
|
2 |
+
"[PAD]": 81,
|
3 |
+
"[UNK]": 80,
|
4 |
+
"`": 1,
|
|
|
5 |
"|": 0,
|
6 |
+
"،": 2,
|
7 |
+
"ؐ": 3,
|
8 |
+
"ؑ": 4,
|
9 |
+
"ؓ": 5,
|
10 |
+
"ؔ": 6,
|
11 |
+
"؛": 7,
|
12 |
+
"؟": 8,
|
13 |
+
"ء": 9,
|
14 |
+
"آ": 10,
|
15 |
+
"أ": 11,
|
16 |
+
"ؤ": 12,
|
17 |
+
"ئ": 13,
|
18 |
+
"ا": 14,
|
19 |
+
"ب": 15,
|
20 |
+
"ت": 16,
|
21 |
+
"ث": 17,
|
22 |
+
"ج": 18,
|
23 |
+
"ح": 19,
|
24 |
+
"خ": 20,
|
25 |
+
"د": 21,
|
26 |
+
"ذ": 22,
|
27 |
+
"ر": 23,
|
28 |
+
"ز": 24,
|
29 |
+
"س": 25,
|
30 |
+
"ش": 26,
|
31 |
+
"ص": 27,
|
32 |
+
"ض": 28,
|
33 |
+
"ط": 29,
|
34 |
+
"ظ": 30,
|
35 |
+
"ع": 31,
|
36 |
+
"غ": 32,
|
37 |
+
"ف": 33,
|
38 |
+
"ق": 34,
|
39 |
+
"ل": 35,
|
40 |
+
"م": 36,
|
41 |
+
"ن": 37,
|
42 |
+
"ه": 38,
|
43 |
+
"و": 39,
|
44 |
+
"ي": 40,
|
45 |
+
"ً": 41,
|
46 |
+
"َ": 42,
|
47 |
+
"ُ": 43,
|
48 |
+
"ِ": 44,
|
49 |
+
"ّ": 45,
|
50 |
+
"ٓ": 46,
|
51 |
+
"ٔ": 47,
|
52 |
+
"ٰ": 48,
|
53 |
+
"ٴ": 49,
|
54 |
+
"ٹ": 50,
|
55 |
+
"پ": 51,
|
56 |
+
"چ": 52,
|
57 |
+
"ڈ": 53,
|
58 |
+
"ڑ": 54,
|
59 |
+
"ژ": 55,
|
60 |
+
"ک": 56,
|
61 |
+
"گ": 57,
|
62 |
+
"ں": 58,
|
63 |
+
"ھ": 59,
|
64 |
+
"ہ": 60,
|
65 |
+
"ۂ": 61,
|
66 |
+
"ۃ": 62,
|
67 |
+
"ی": 63,
|
68 |
+
"ے": 64,
|
69 |
+
"ۓ": 65,
|
70 |
+
"۔": 66,
|
71 |
+
"’": 67,
|
72 |
+
"ﭨ": 68,
|
73 |
+
"ﮭ": 69,
|
74 |
+
"ﮯ": 70,
|
75 |
+
"ﯾ": 71,
|
76 |
+
"ﷲ": 72,
|
77 |
+
"ﷺ": 73,
|
78 |
+
"ﺗ": 74,
|
79 |
+
"ﺘ": 75,
|
80 |
+
"ﺩ": 76,
|
81 |
+
"ﺲ": 77,
|
82 |
+
"ﻧ": 78,
|
83 |
+
"ﻮ": 79
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
84 |
}
|