Reihaneh commited on
Commit
9b966f6
·
verified ·
1 Parent(s): fa999b0

Upload tokenizer

Browse files
Files changed (1) hide show
  1. vocab.json +88 -88
vocab.json CHANGED
@@ -1,95 +1,95 @@
1
  {
2
- "&": 6,
3
- "'": 58,
4
- "(": 25,
5
- ")": 50,
6
- "-": 33,
7
- "D": 16,
8
- "E": 84,
9
- "F": 18,
10
- "L": 73,
11
- "N": 83,
12
- "Y": 31,
13
- "[": 4,
14
  "[DE]": 90,
15
  "[FY-NL]": 92,
16
  "[NL]": 91,
17
  "[PAD]": 89,
18
  "[UNK]": 88,
19
- "]": 53,
20
- "a": 56,
21
- "b": 21,
22
- "c": 12,
23
- "d": 30,
24
- "e": 61,
25
- "f": 54,
26
- "g": 29,
27
- "h": 36,
28
- "i": 41,
29
- "j": 17,
30
- "k": 82,
31
- "l": 10,
32
- "m": 35,
33
- "n": 71,
34
- "o": 47,
35
- "p": 14,
36
- "q": 11,
37
- "r": 86,
38
- "s": 38,
39
- "t": 67,
40
- "u": 75,
41
- "v": 78,
42
- "w": 27,
43
- "x": 32,
44
- "y": 74,
45
- "z": 26,
46
- "|": 40,
47
- "«": 3,
48
- "´": 28,
49
- "»": 81,
50
- "ß": 39,
51
- "à": 34,
52
- "á": 1,
53
- "â": 13,
54
- "ä": 80,
55
- "å": 52,
56
- "è": 57,
57
- "é": 24,
58
- "ê": 64,
59
- "ë": 72,
60
- "í": 46,
61
- "ï": 51,
62
- "ñ": 87,
63
- "ò": 22,
64
- "ó": 70,
65
- "ô": 8,
66
- "ö": 15,
67
- "ú": 69,
68
- "û": 20,
69
- "ü": 44,
70
- "ý": 19,
71
- "ā": 77,
72
- "ă": 76,
73
- "đ": 43,
74
- "ı": 0,
75
- "ň": 55,
76
- "ő": 65,
77
- "ş": 60,
78
- "š": 63,
79
- "ž": 68,
80
- "ș": 48,
81
- "ț": 85,
82
- "ʿ": 66,
83
- "ả": 45,
84
- "ọ": 79,
85
- "ứ": 5,
86
- "–": 37,
87
- "’": 42,
88
- "“": 59,
89
- "”": 2,
90
- "„": 9,
91
- "…": 7,
92
- "→": 23,
93
- "乡": 49,
94
- "幺": 62
95
  }
 
1
  {
2
+ "&": 43,
3
+ "'": 23,
4
+ "(": 76,
5
+ ")": 69,
6
+ "-": 46,
7
+ "D": 63,
8
+ "E": 49,
9
+ "F": 55,
10
+ "L": 41,
11
+ "N": 84,
12
+ "Y": 80,
13
+ "[": 1,
14
  "[DE]": 90,
15
  "[FY-NL]": 92,
16
  "[NL]": 91,
17
  "[PAD]": 89,
18
  "[UNK]": 88,
19
+ "]": 14,
20
+ "a": 27,
21
+ "b": 33,
22
+ "c": 72,
23
+ "d": 70,
24
+ "e": 20,
25
+ "f": 81,
26
+ "g": 44,
27
+ "h": 38,
28
+ "i": 67,
29
+ "j": 28,
30
+ "k": 64,
31
+ "l": 83,
32
+ "m": 30,
33
+ "n": 12,
34
+ "o": 48,
35
+ "p": 16,
36
+ "q": 7,
37
+ "r": 79,
38
+ "s": 42,
39
+ "t": 62,
40
+ "u": 87,
41
+ "v": 34,
42
+ "w": 52,
43
+ "x": 78,
44
+ "y": 5,
45
+ "z": 56,
46
+ "|": 21,
47
+ "«": 50,
48
+ "´": 11,
49
+ "»": 53,
50
+ "ß": 22,
51
+ "à": 31,
52
+ "á": 66,
53
+ "â": 61,
54
+ "ä": 9,
55
+ "å": 59,
56
+ "è": 45,
57
+ "é": 71,
58
+ "ê": 6,
59
+ "ë": 25,
60
+ "í": 75,
61
+ "ï": 10,
62
+ "ñ": 4,
63
+ "ò": 65,
64
+ "ó": 40,
65
+ "ô": 39,
66
+ "ö": 17,
67
+ "ú": 36,
68
+ "û": 85,
69
+ "ü": 82,
70
+ "ý": 26,
71
+ "ā": 29,
72
+ "ă": 58,
73
+ "đ": 60,
74
+ "ı": 18,
75
+ "ň": 13,
76
+ "ő": 74,
77
+ "ş": 2,
78
+ "š": 19,
79
+ "ž": 57,
80
+ "ș": 0,
81
+ "ț": 51,
82
+ "ʿ": 73,
83
+ "ả": 24,
84
+ "ọ": 54,
85
+ "ứ": 8,
86
+ "–": 32,
87
+ "’": 77,
88
+ "“": 35,
89
+ "”": 47,
90
+ "„": 86,
91
+ "…": 15,
92
+ "→": 3,
93
+ "乡": 37,
94
+ "幺": 68
95
  }