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