Training done
Browse files- added_tokens.json +152 -0
- preprocessor_config.json +26 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +55 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2260 -0
added_tokens.json
ADDED
@@ -0,0 +1,152 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"1": 57656,
|
3 |
+
"<s_iitcdip>": 57523,
|
4 |
+
"<s_synthdog>": 57524,
|
5 |
+
"<sep/>": 57522,
|
6 |
+
"²": 57588,
|
7 |
+
"³": 57569,
|
8 |
+
"¶": 57609,
|
9 |
+
"¹": 57619,
|
10 |
+
"¼": 57607,
|
11 |
+
"½": 57587,
|
12 |
+
"Ī": 57537,
|
13 |
+
"ˈ": 57552,
|
14 |
+
"Ι": 57610,
|
15 |
+
"П": 57647,
|
16 |
+
"о": 57616,
|
17 |
+
"р": 57611,
|
18 |
+
"т": 57583,
|
19 |
+
"і": 57650,
|
20 |
+
"ד": 57590,
|
21 |
+
"י": 57570,
|
22 |
+
"ا": 57652,
|
23 |
+
"د": 57582,
|
24 |
+
"ذ": 57660,
|
25 |
+
"ل": 57556,
|
26 |
+
"ं": 57669,
|
27 |
+
"उ": 57591,
|
28 |
+
"क": 57644,
|
29 |
+
"ग": 57589,
|
30 |
+
"घ": 57542,
|
31 |
+
"च": 57531,
|
32 |
+
"ज": 57555,
|
33 |
+
"ट": 57645,
|
34 |
+
"ठ": 57596,
|
35 |
+
"ड": 57599,
|
36 |
+
"त": 57606,
|
37 |
+
"थ": 57567,
|
38 |
+
"द": 57620,
|
39 |
+
"ध": 57663,
|
40 |
+
"न": 57557,
|
41 |
+
"प": 57624,
|
42 |
+
"भ": 57553,
|
43 |
+
"म": 57572,
|
44 |
+
"य": 57547,
|
45 |
+
"र": 57566,
|
46 |
+
"ल": 57597,
|
47 |
+
"व": 57581,
|
48 |
+
"ष": 57622,
|
49 |
+
"स": 57659,
|
50 |
+
"ह": 57632,
|
51 |
+
"ा": 57539,
|
52 |
+
"ि": 57534,
|
53 |
+
"ी": 57635,
|
54 |
+
"ु": 57640,
|
55 |
+
"ॅ": 57551,
|
56 |
+
"े": 57646,
|
57 |
+
"ै": 57578,
|
58 |
+
"ॉ": 57538,
|
59 |
+
"ो": 57613,
|
60 |
+
"्": 57563,
|
61 |
+
"।": 57636,
|
62 |
+
"॥": 57530,
|
63 |
+
"ਂ": 57544,
|
64 |
+
"ਅ": 57540,
|
65 |
+
"ਆ": 57558,
|
66 |
+
"ਇ": 57637,
|
67 |
+
"ਈ": 57665,
|
68 |
+
"ਉ": 57608,
|
69 |
+
"ਊ": 57550,
|
70 |
+
"ਏ": 57657,
|
71 |
+
"ਐ": 57533,
|
72 |
+
"ਓ": 57664,
|
73 |
+
"ਕ": 57612,
|
74 |
+
"ਖ": 57668,
|
75 |
+
"ਗ": 57633,
|
76 |
+
"ਘ": 57618,
|
77 |
+
"ਙ": 57638,
|
78 |
+
"ਚ": 57541,
|
79 |
+
"ਛ": 57564,
|
80 |
+
"ਜ": 57576,
|
81 |
+
"ਝ": 57654,
|
82 |
+
"ਞ": 57543,
|
83 |
+
"ਟ": 57545,
|
84 |
+
"ਠ": 57667,
|
85 |
+
"ਡ": 57565,
|
86 |
+
"ਢ": 57651,
|
87 |
+
"ਣ": 57579,
|
88 |
+
"ਤ": 57574,
|
89 |
+
"ਥ": 57525,
|
90 |
+
"ਦ": 57536,
|
91 |
+
"ਧ": 57548,
|
92 |
+
"ਨ": 57643,
|
93 |
+
"ਪ": 57585,
|
94 |
+
"ਫ": 57601,
|
95 |
+
"ਬ": 57580,
|
96 |
+
"ਭ": 57625,
|
97 |
+
"ਮ": 57602,
|
98 |
+
"ਯ": 57528,
|
99 |
+
"ਰ": 57560,
|
100 |
+
"ਲ": 57670,
|
101 |
+
"ਲ਼": 57529,
|
102 |
+
"ਵ": 57605,
|
103 |
+
"ਸ਼": 57639,
|
104 |
+
"ਸ": 57603,
|
105 |
+
"ਹ": 57658,
|
106 |
+
"਼": 57661,
|
107 |
+
"ਾ": 57614,
|
108 |
+
"ਿ": 57554,
|
109 |
+
"ੀ": 57653,
|
110 |
+
"ੁ": 57568,
|
111 |
+
"ੂ": 57634,
|
112 |
+
"ੇ": 57593,
|
113 |
+
"ੈ": 57546,
|
114 |
+
"ੋ": 57594,
|
115 |
+
"ੌ": 57662,
|
116 |
+
"੍": 57561,
|
117 |
+
"ਗ਼": 57559,
|
118 |
+
"ਜ਼": 57598,
|
119 |
+
"ੜ": 57623,
|
120 |
+
"੫": 57604,
|
121 |
+
"ੰ": 57577,
|
122 |
+
"ੱ": 57526,
|
123 |
+
"ੲ": 57571,
|
124 |
+
"ੳ": 57627,
|
125 |
+
"અ": 57535,
|
126 |
+
"આ": 57642,
|
127 |
+
"ગ": 57575,
|
128 |
+
"ઘ": 57592,
|
129 |
+
"છ": 57615,
|
130 |
+
"ઠ": 57631,
|
131 |
+
"ણ": 57649,
|
132 |
+
"ત": 57628,
|
133 |
+
"ય": 57562,
|
134 |
+
"ર": 57629,
|
135 |
+
"સ": 57617,
|
136 |
+
"ા": 57648,
|
137 |
+
"ી": 57584,
|
138 |
+
"ુ": 57666,
|
139 |
+
"ૂ": 57655,
|
140 |
+
"ો": 57549,
|
141 |
+
"્": 57527,
|
142 |
+
"ດ": 57671,
|
143 |
+
"Ḍ": 57641,
|
144 |
+
"ḍ": 57621,
|
145 |
+
"Ḥ": 57573,
|
146 |
+
"Ṇ": 57532,
|
147 |
+
"Ṉ": 57595,
|
148 |
+
"ṉ": 57600,
|
149 |
+
"Ṛ": 57626,
|
150 |
+
"Ṭ": 57630,
|
151 |
+
"…": 57586
|
152 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_align_long_axis": false,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_pad": true,
|
5 |
+
"do_rescale": true,
|
6 |
+
"do_resize": true,
|
7 |
+
"do_thumbnail": true,
|
8 |
+
"image_mean": [
|
9 |
+
0.5,
|
10 |
+
0.5,
|
11 |
+
0.5
|
12 |
+
],
|
13 |
+
"image_processor_type": "DonutImageProcessor",
|
14 |
+
"image_std": [
|
15 |
+
0.5,
|
16 |
+
0.5,
|
17 |
+
0.5
|
18 |
+
],
|
19 |
+
"processor_class": "DonutProcessor",
|
20 |
+
"resample": 2,
|
21 |
+
"rescale_factor": 0.00392156862745098,
|
22 |
+
"size": [
|
23 |
+
960,
|
24 |
+
1280
|
25 |
+
]
|
26 |
+
}
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb9e3dce4c326195d08fc3dd0f7e2eee1da8595c847bf4c1a9c78b7a82d47e2d
|
3 |
+
size 1296245
|
special_tokens_map.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s_iitcdip>",
|
4 |
+
"<s_synthdog>"
|
5 |
+
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<s>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"cls_token": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"eos_token": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"mask_token": {
|
28 |
+
"content": "<mask>",
|
29 |
+
"lstrip": true,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
},
|
34 |
+
"pad_token": {
|
35 |
+
"content": "<pad>",
|
36 |
+
"lstrip": false,
|
37 |
+
"normalized": false,
|
38 |
+
"rstrip": false,
|
39 |
+
"single_word": false
|
40 |
+
},
|
41 |
+
"sep_token": {
|
42 |
+
"content": "</s>",
|
43 |
+
"lstrip": false,
|
44 |
+
"normalized": false,
|
45 |
+
"rstrip": false,
|
46 |
+
"single_word": false
|
47 |
+
},
|
48 |
+
"unk_token": {
|
49 |
+
"content": "<unk>",
|
50 |
+
"lstrip": false,
|
51 |
+
"normalized": false,
|
52 |
+
"rstrip": false,
|
53 |
+
"single_word": false
|
54 |
+
}
|
55 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,2260 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "a",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": true,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": false
|
42 |
+
},
|
43 |
+
"486": {
|
44 |
+
"content": "8",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": true,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": false
|
50 |
+
},
|
51 |
+
"1338": {
|
52 |
+
"content": "R",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": true,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": false
|
58 |
+
},
|
59 |
+
"1476": {
|
60 |
+
"content": "ı",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": true,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": false
|
66 |
+
},
|
67 |
+
"1601": {
|
68 |
+
"content": "U",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": true,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": false
|
74 |
+
},
|
75 |
+
"1681": {
|
76 |
+
"content": "[",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": true,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": false
|
82 |
+
},
|
83 |
+
"2586": {
|
84 |
+
"content": ":",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": true,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": false
|
90 |
+
},
|
91 |
+
"2664": {
|
92 |
+
"content": "–",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": true,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": false
|
98 |
+
},
|
99 |
+
"3200": {
|
100 |
+
"content": "9",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": true,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": false
|
106 |
+
},
|
107 |
+
"3890": {
|
108 |
+
"content": "Ú",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": true,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": false
|
114 |
+
},
|
115 |
+
"4573": {
|
116 |
+
"content": "Í",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": true,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": false
|
122 |
+
},
|
123 |
+
"5051": {
|
124 |
+
"content": "e",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": true,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": false
|
130 |
+
},
|
131 |
+
"5770": {
|
132 |
+
"content": "&",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": true,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": false
|
138 |
+
},
|
139 |
+
"5798": {
|
140 |
+
"content": "ę",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": true,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": false
|
146 |
+
},
|
147 |
+
"6522": {
|
148 |
+
"content": "h",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": true,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": false
|
154 |
+
},
|
155 |
+
"6967": {
|
156 |
+
"content": "·",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": true,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": false
|
162 |
+
},
|
163 |
+
"7456": {
|
164 |
+
"content": "i",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": true,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": false
|
170 |
+
},
|
171 |
+
"7690": {
|
172 |
+
"content": "(",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": true,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": false
|
178 |
+
},
|
179 |
+
"8053": {
|
180 |
+
"content": "+",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": true,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": false
|
186 |
+
},
|
187 |
+
"9026": {
|
188 |
+
"content": "=",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": true,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": false
|
194 |
+
},
|
195 |
+
"9170": {
|
196 |
+
"content": "J",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": true,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": false
|
202 |
+
},
|
203 |
+
"9745": {
|
204 |
+
"content": "l",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": true,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": false
|
210 |
+
},
|
211 |
+
"10719": {
|
212 |
+
"content": "α",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": true,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": false
|
218 |
+
},
|
219 |
+
"10960": {
|
220 |
+
"content": "W",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": true,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": false
|
226 |
+
},
|
227 |
+
"11317": {
|
228 |
+
"content": "ι",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": true,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": false
|
234 |
+
},
|
235 |
+
"11938": {
|
236 |
+
"content": ")",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": true,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": false
|
242 |
+
},
|
243 |
+
"12162": {
|
244 |
+
"content": "Z",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": true,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": false
|
250 |
+
},
|
251 |
+
"12816": {
|
252 |
+
"content": "X",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": true,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": false
|
258 |
+
},
|
259 |
+
"14022": {
|
260 |
+
"content": "ν",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": true,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": false
|
266 |
+
},
|
267 |
+
"14301": {
|
268 |
+
"content": "<",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": true,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": false
|
274 |
+
},
|
275 |
+
"14898": {
|
276 |
+
"content": "*",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": true,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": false
|
282 |
+
},
|
283 |
+
"15811": {
|
284 |
+
"content": "z",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": true,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": false
|
290 |
+
},
|
291 |
+
"15994": {
|
292 |
+
"content": "j",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": true,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": false
|
298 |
+
},
|
299 |
+
"16191": {
|
300 |
+
"content": "t",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": true,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": false
|
306 |
+
},
|
307 |
+
"16648": {
|
308 |
+
"content": "Y",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": true,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": false
|
314 |
+
},
|
315 |
+
"17367": {
|
316 |
+
"content": "g",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": true,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": false
|
322 |
+
},
|
323 |
+
"17521": {
|
324 |
+
"content": "×",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": true,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": false
|
330 |
+
},
|
331 |
+
"17725": {
|
332 |
+
"content": "•",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": true,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": false
|
338 |
+
},
|
339 |
+
"18215": {
|
340 |
+
"content": "n",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": true,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": false
|
346 |
+
},
|
347 |
+
"19064": {
|
348 |
+
"content": "ɔ",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": true,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": false
|
354 |
+
},
|
355 |
+
"20642": {
|
356 |
+
"content": "・",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": true,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": false
|
362 |
+
},
|
363 |
+
"20825": {
|
364 |
+
"content": "è",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": true,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": false
|
370 |
+
},
|
371 |
+
"27134": {
|
372 |
+
"content": "~",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": true,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": false
|
378 |
+
},
|
379 |
+
"28019": {
|
380 |
+
"content": "c",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": true,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": false
|
386 |
+
},
|
387 |
+
"28268": {
|
388 |
+
"content": "0",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": true,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": false
|
394 |
+
},
|
395 |
+
"28431": {
|
396 |
+
"content": "'",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": true,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": false
|
402 |
+
},
|
403 |
+
"30252": {
|
404 |
+
"content": "—",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": true,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": false
|
410 |
+
},
|
411 |
+
"30424": {
|
412 |
+
"content": "✓",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": true,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": false
|
418 |
+
},
|
419 |
+
"30955": {
|
420 |
+
"content": "ਔ",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": true,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": false
|
426 |
+
},
|
427 |
+
"31285": {
|
428 |
+
"content": "ˌ",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": true,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": false
|
434 |
+
},
|
435 |
+
"32650": {
|
436 |
+
"content": "{",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": true,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": false
|
442 |
+
},
|
443 |
+
"33855": {
|
444 |
+
"content": "’",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": true,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": false
|
450 |
+
},
|
451 |
+
"33917": {
|
452 |
+
"content": "Ā",
|
453 |
+
"lstrip": false,
|
454 |
+
"normalized": true,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": false
|
458 |
+
},
|
459 |
+
"33968": {
|
460 |
+
"content": "p",
|
461 |
+
"lstrip": false,
|
462 |
+
"normalized": true,
|
463 |
+
"rstrip": false,
|
464 |
+
"single_word": false,
|
465 |
+
"special": false
|
466 |
+
},
|
467 |
+
"34490": {
|
468 |
+
"content": "]",
|
469 |
+
"lstrip": false,
|
470 |
+
"normalized": true,
|
471 |
+
"rstrip": false,
|
472 |
+
"single_word": false,
|
473 |
+
"special": false
|
474 |
+
},
|
475 |
+
"34779": {
|
476 |
+
"content": "Q",
|
477 |
+
"lstrip": false,
|
478 |
+
"normalized": true,
|
479 |
+
"rstrip": false,
|
480 |
+
"single_word": false,
|
481 |
+
"special": false
|
482 |
+
},
|
483 |
+
"34796": {
|
484 |
+
"content": "b",
|
485 |
+
"lstrip": false,
|
486 |
+
"normalized": true,
|
487 |
+
"rstrip": false,
|
488 |
+
"single_word": false,
|
489 |
+
"special": false
|
490 |
+
},
|
491 |
+
"35059": {
|
492 |
+
"content": "א",
|
493 |
+
"lstrip": false,
|
494 |
+
"normalized": true,
|
495 |
+
"rstrip": false,
|
496 |
+
"single_word": false,
|
497 |
+
"special": false
|
498 |
+
},
|
499 |
+
"35161": {
|
500 |
+
"content": "A",
|
501 |
+
"lstrip": false,
|
502 |
+
"normalized": true,
|
503 |
+
"rstrip": false,
|
504 |
+
"single_word": false,
|
505 |
+
"special": false
|
506 |
+
},
|
507 |
+
"35354": {
|
508 |
+
"content": "π",
|
509 |
+
"lstrip": false,
|
510 |
+
"normalized": true,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false,
|
513 |
+
"special": false
|
514 |
+
},
|
515 |
+
"35544": {
|
516 |
+
"content": "S",
|
517 |
+
"lstrip": false,
|
518 |
+
"normalized": true,
|
519 |
+
"rstrip": false,
|
520 |
+
"single_word": false,
|
521 |
+
"special": false
|
522 |
+
},
|
523 |
+
"35815": {
|
524 |
+
"content": ",",
|
525 |
+
"lstrip": false,
|
526 |
+
"normalized": true,
|
527 |
+
"rstrip": false,
|
528 |
+
"single_word": false,
|
529 |
+
"special": false
|
530 |
+
},
|
531 |
+
"35816": {
|
532 |
+
"content": "o",
|
533 |
+
"lstrip": false,
|
534 |
+
"normalized": true,
|
535 |
+
"rstrip": false,
|
536 |
+
"single_word": false,
|
537 |
+
"special": false
|
538 |
+
},
|
539 |
+
"35934": {
|
540 |
+
"content": "2",
|
541 |
+
"lstrip": false,
|
542 |
+
"normalized": true,
|
543 |
+
"rstrip": false,
|
544 |
+
"single_word": false,
|
545 |
+
"special": false
|
546 |
+
},
|
547 |
+
"36209": {
|
548 |
+
"content": "?",
|
549 |
+
"lstrip": false,
|
550 |
+
"normalized": true,
|
551 |
+
"rstrip": false,
|
552 |
+
"single_word": false,
|
553 |
+
"special": false
|
554 |
+
},
|
555 |
+
"36967": {
|
556 |
+
"content": "u",
|
557 |
+
"lstrip": false,
|
558 |
+
"normalized": true,
|
559 |
+
"rstrip": false,
|
560 |
+
"single_word": false,
|
561 |
+
"special": false
|
562 |
+
},
|
563 |
+
"37093": {
|
564 |
+
"content": "v",
|
565 |
+
"lstrip": false,
|
566 |
+
"normalized": true,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false,
|
569 |
+
"special": false
|
570 |
+
},
|
571 |
+
"38167": {
|
572 |
+
"content": "3",
|
573 |
+
"lstrip": false,
|
574 |
+
"normalized": true,
|
575 |
+
"rstrip": false,
|
576 |
+
"single_word": false,
|
577 |
+
"special": false
|
578 |
+
},
|
579 |
+
"38459": {
|
580 |
+
"content": "!",
|
581 |
+
"lstrip": false,
|
582 |
+
"normalized": true,
|
583 |
+
"rstrip": false,
|
584 |
+
"single_word": false,
|
585 |
+
"special": false
|
586 |
+
},
|
587 |
+
"38460": {
|
588 |
+
"content": "‘",
|
589 |
+
"lstrip": false,
|
590 |
+
"normalized": true,
|
591 |
+
"rstrip": false,
|
592 |
+
"single_word": false,
|
593 |
+
"special": false
|
594 |
+
},
|
595 |
+
"38844": {
|
596 |
+
"content": "m",
|
597 |
+
"lstrip": false,
|
598 |
+
"normalized": true,
|
599 |
+
"rstrip": false,
|
600 |
+
"single_word": false,
|
601 |
+
"special": false
|
602 |
+
},
|
603 |
+
"39379": {
|
604 |
+
"content": "%",
|
605 |
+
"lstrip": false,
|
606 |
+
"normalized": true,
|
607 |
+
"rstrip": false,
|
608 |
+
"single_word": false,
|
609 |
+
"special": false
|
610 |
+
},
|
611 |
+
"39415": {
|
612 |
+
"content": "D",
|
613 |
+
"lstrip": false,
|
614 |
+
"normalized": true,
|
615 |
+
"rstrip": false,
|
616 |
+
"single_word": false,
|
617 |
+
"special": false
|
618 |
+
},
|
619 |
+
"39539": {
|
620 |
+
"content": ".",
|
621 |
+
"lstrip": false,
|
622 |
+
"normalized": true,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false,
|
625 |
+
"special": false
|
626 |
+
},
|
627 |
+
"39563": {
|
628 |
+
"content": "τ",
|
629 |
+
"lstrip": false,
|
630 |
+
"normalized": true,
|
631 |
+
"rstrip": false,
|
632 |
+
"single_word": false,
|
633 |
+
"special": false
|
634 |
+
},
|
635 |
+
"39905": {
|
636 |
+
"content": "r",
|
637 |
+
"lstrip": false,
|
638 |
+
"normalized": true,
|
639 |
+
"rstrip": false,
|
640 |
+
"single_word": false,
|
641 |
+
"special": false
|
642 |
+
},
|
643 |
+
"40217": {
|
644 |
+
"content": "\\",
|
645 |
+
"lstrip": false,
|
646 |
+
"normalized": true,
|
647 |
+
"rstrip": false,
|
648 |
+
"single_word": false,
|
649 |
+
"special": false
|
650 |
+
},
|
651 |
+
"40227": {
|
652 |
+
"content": "f",
|
653 |
+
"lstrip": false,
|
654 |
+
"normalized": true,
|
655 |
+
"rstrip": false,
|
656 |
+
"single_word": false,
|
657 |
+
"special": false
|
658 |
+
},
|
659 |
+
"40392": {
|
660 |
+
"content": "x",
|
661 |
+
"lstrip": false,
|
662 |
+
"normalized": true,
|
663 |
+
"rstrip": false,
|
664 |
+
"single_word": false,
|
665 |
+
"special": false
|
666 |
+
},
|
667 |
+
"40582": {
|
668 |
+
"content": "í",
|
669 |
+
"lstrip": false,
|
670 |
+
"normalized": true,
|
671 |
+
"rstrip": false,
|
672 |
+
"single_word": false,
|
673 |
+
"special": false
|
674 |
+
},
|
675 |
+
"40705": {
|
676 |
+
"content": "w",
|
677 |
+
"lstrip": false,
|
678 |
+
"normalized": true,
|
679 |
+
"rstrip": false,
|
680 |
+
"single_word": false,
|
681 |
+
"special": false
|
682 |
+
},
|
683 |
+
"40831": {
|
684 |
+
"content": "$",
|
685 |
+
"lstrip": false,
|
686 |
+
"normalized": true,
|
687 |
+
"rstrip": false,
|
688 |
+
"single_word": false,
|
689 |
+
"special": false
|
690 |
+
},
|
691 |
+
"40956": {
|
692 |
+
"content": "C",
|
693 |
+
"lstrip": false,
|
694 |
+
"normalized": true,
|
695 |
+
"rstrip": false,
|
696 |
+
"single_word": false,
|
697 |
+
"special": false
|
698 |
+
},
|
699 |
+
"41403": {
|
700 |
+
"content": "_",
|
701 |
+
"lstrip": false,
|
702 |
+
"normalized": true,
|
703 |
+
"rstrip": false,
|
704 |
+
"single_word": false,
|
705 |
+
"special": false
|
706 |
+
},
|
707 |
+
"42309": {
|
708 |
+
"content": "γ",
|
709 |
+
"lstrip": false,
|
710 |
+
"normalized": true,
|
711 |
+
"rstrip": false,
|
712 |
+
"single_word": false,
|
713 |
+
"special": false
|
714 |
+
},
|
715 |
+
"43154": {
|
716 |
+
"content": "ה",
|
717 |
+
"lstrip": false,
|
718 |
+
"normalized": true,
|
719 |
+
"rstrip": false,
|
720 |
+
"single_word": false,
|
721 |
+
"special": false
|
722 |
+
},
|
723 |
+
"43634": {
|
724 |
+
"content": "y",
|
725 |
+
"lstrip": false,
|
726 |
+
"normalized": true,
|
727 |
+
"rstrip": false,
|
728 |
+
"single_word": false,
|
729 |
+
"special": false
|
730 |
+
},
|
731 |
+
"45105": {
|
732 |
+
"content": "I",
|
733 |
+
"lstrip": false,
|
734 |
+
"normalized": true,
|
735 |
+
"rstrip": false,
|
736 |
+
"single_word": false,
|
737 |
+
"special": false
|
738 |
+
},
|
739 |
+
"45201": {
|
740 |
+
"content": "\"",
|
741 |
+
"lstrip": false,
|
742 |
+
"normalized": true,
|
743 |
+
"rstrip": false,
|
744 |
+
"single_word": false,
|
745 |
+
"special": false
|
746 |
+
},
|
747 |
+
"45202": {
|
748 |
+
"content": "B",
|
749 |
+
"lstrip": false,
|
750 |
+
"normalized": true,
|
751 |
+
"rstrip": false,
|
752 |
+
"single_word": false,
|
753 |
+
"special": false
|
754 |
+
},
|
755 |
+
"45785": {
|
756 |
+
"content": "|",
|
757 |
+
"lstrip": false,
|
758 |
+
"normalized": true,
|
759 |
+
"rstrip": false,
|
760 |
+
"single_word": false,
|
761 |
+
"special": false
|
762 |
+
},
|
763 |
+
"45964": {
|
764 |
+
"content": "M",
|
765 |
+
"lstrip": false,
|
766 |
+
"normalized": true,
|
767 |
+
"rstrip": false,
|
768 |
+
"single_word": false,
|
769 |
+
"special": false
|
770 |
+
},
|
771 |
+
"46192": {
|
772 |
+
"content": "s",
|
773 |
+
"lstrip": false,
|
774 |
+
"normalized": true,
|
775 |
+
"rstrip": false,
|
776 |
+
"single_word": false,
|
777 |
+
"special": false
|
778 |
+
},
|
779 |
+
"46318": {
|
780 |
+
"content": "K",
|
781 |
+
"lstrip": false,
|
782 |
+
"normalized": true,
|
783 |
+
"rstrip": false,
|
784 |
+
"single_word": false,
|
785 |
+
"special": false
|
786 |
+
},
|
787 |
+
"46500": {
|
788 |
+
"content": "み",
|
789 |
+
"lstrip": false,
|
790 |
+
"normalized": true,
|
791 |
+
"rstrip": false,
|
792 |
+
"single_word": false,
|
793 |
+
"special": false
|
794 |
+
},
|
795 |
+
"46502": {
|
796 |
+
"content": "ṇ",
|
797 |
+
"lstrip": false,
|
798 |
+
"normalized": true,
|
799 |
+
"rstrip": false,
|
800 |
+
"single_word": false,
|
801 |
+
"special": false
|
802 |
+
},
|
803 |
+
"46579": {
|
804 |
+
"content": "ṭ",
|
805 |
+
"lstrip": false,
|
806 |
+
"normalized": true,
|
807 |
+
"rstrip": false,
|
808 |
+
"single_word": false,
|
809 |
+
"special": false
|
810 |
+
},
|
811 |
+
"46702": {
|
812 |
+
"content": "4",
|
813 |
+
"lstrip": false,
|
814 |
+
"normalized": true,
|
815 |
+
"rstrip": false,
|
816 |
+
"single_word": false,
|
817 |
+
"special": false
|
818 |
+
},
|
819 |
+
"46735": {
|
820 |
+
"content": "T",
|
821 |
+
"lstrip": false,
|
822 |
+
"normalized": true,
|
823 |
+
"rstrip": false,
|
824 |
+
"single_word": false,
|
825 |
+
"special": false
|
826 |
+
},
|
827 |
+
"47106": {
|
828 |
+
"content": "/",
|
829 |
+
"lstrip": false,
|
830 |
+
"normalized": true,
|
831 |
+
"rstrip": false,
|
832 |
+
"single_word": false,
|
833 |
+
"special": false
|
834 |
+
},
|
835 |
+
"47597": {
|
836 |
+
"content": "E",
|
837 |
+
"lstrip": false,
|
838 |
+
"normalized": true,
|
839 |
+
"rstrip": false,
|
840 |
+
"single_word": false,
|
841 |
+
"special": false
|
842 |
+
},
|
843 |
+
"47992": {
|
844 |
+
"content": "Á",
|
845 |
+
"lstrip": false,
|
846 |
+
"normalized": true,
|
847 |
+
"rstrip": false,
|
848 |
+
"single_word": false,
|
849 |
+
"special": false
|
850 |
+
},
|
851 |
+
"48318": {
|
852 |
+
"content": "O",
|
853 |
+
"lstrip": false,
|
854 |
+
"normalized": true,
|
855 |
+
"rstrip": false,
|
856 |
+
"single_word": false,
|
857 |
+
"special": false
|
858 |
+
},
|
859 |
+
"48693": {
|
860 |
+
"content": "P",
|
861 |
+
"lstrip": false,
|
862 |
+
"normalized": true,
|
863 |
+
"rstrip": false,
|
864 |
+
"single_word": false,
|
865 |
+
"special": false
|
866 |
+
},
|
867 |
+
"49224": {
|
868 |
+
"content": "d",
|
869 |
+
"lstrip": false,
|
870 |
+
"normalized": true,
|
871 |
+
"rstrip": false,
|
872 |
+
"single_word": false,
|
873 |
+
"special": false
|
874 |
+
},
|
875 |
+
"49458": {
|
876 |
+
"content": "á",
|
877 |
+
"lstrip": false,
|
878 |
+
"normalized": true,
|
879 |
+
"rstrip": false,
|
880 |
+
"single_word": false,
|
881 |
+
"special": false
|
882 |
+
},
|
883 |
+
"49933": {
|
884 |
+
"content": "G",
|
885 |
+
"lstrip": false,
|
886 |
+
"normalized": true,
|
887 |
+
"rstrip": false,
|
888 |
+
"single_word": false,
|
889 |
+
"special": false
|
890 |
+
},
|
891 |
+
"49945": {
|
892 |
+
"content": "°",
|
893 |
+
"lstrip": false,
|
894 |
+
"normalized": true,
|
895 |
+
"rstrip": false,
|
896 |
+
"single_word": false,
|
897 |
+
"special": false
|
898 |
+
},
|
899 |
+
"50155": {
|
900 |
+
"content": ";",
|
901 |
+
"lstrip": false,
|
902 |
+
"normalized": true,
|
903 |
+
"rstrip": false,
|
904 |
+
"single_word": false,
|
905 |
+
"special": false
|
906 |
+
},
|
907 |
+
"50934": {
|
908 |
+
"content": "5",
|
909 |
+
"lstrip": false,
|
910 |
+
"normalized": true,
|
911 |
+
"rstrip": false,
|
912 |
+
"single_word": false,
|
913 |
+
"special": false
|
914 |
+
},
|
915 |
+
"52165": {
|
916 |
+
"content": "-",
|
917 |
+
"lstrip": false,
|
918 |
+
"normalized": true,
|
919 |
+
"rstrip": false,
|
920 |
+
"single_word": false,
|
921 |
+
"special": false
|
922 |
+
},
|
923 |
+
"52613": {
|
924 |
+
"content": "}",
|
925 |
+
"lstrip": false,
|
926 |
+
"normalized": true,
|
927 |
+
"rstrip": false,
|
928 |
+
"single_word": false,
|
929 |
+
"special": false
|
930 |
+
},
|
931 |
+
"53031": {
|
932 |
+
"content": "÷",
|
933 |
+
"lstrip": false,
|
934 |
+
"normalized": true,
|
935 |
+
"rstrip": false,
|
936 |
+
"single_word": false,
|
937 |
+
"special": false
|
938 |
+
},
|
939 |
+
"53233": {
|
940 |
+
"content": "N",
|
941 |
+
"lstrip": false,
|
942 |
+
"normalized": true,
|
943 |
+
"rstrip": false,
|
944 |
+
"single_word": false,
|
945 |
+
"special": false
|
946 |
+
},
|
947 |
+
"53278": {
|
948 |
+
"content": "H",
|
949 |
+
"lstrip": false,
|
950 |
+
"normalized": true,
|
951 |
+
"rstrip": false,
|
952 |
+
"single_word": false,
|
953 |
+
"special": false
|
954 |
+
},
|
955 |
+
"53504": {
|
956 |
+
"content": "ṛ",
|
957 |
+
"lstrip": false,
|
958 |
+
"normalized": true,
|
959 |
+
"rstrip": false,
|
960 |
+
"single_word": false,
|
961 |
+
"special": false
|
962 |
+
},
|
963 |
+
"53669": {
|
964 |
+
"content": "V",
|
965 |
+
"lstrip": false,
|
966 |
+
"normalized": true,
|
967 |
+
"rstrip": false,
|
968 |
+
"single_word": false,
|
969 |
+
"special": false
|
970 |
+
},
|
971 |
+
"53904": {
|
972 |
+
"content": "q",
|
973 |
+
"lstrip": false,
|
974 |
+
"normalized": true,
|
975 |
+
"rstrip": false,
|
976 |
+
"single_word": false,
|
977 |
+
"special": false
|
978 |
+
},
|
979 |
+
"53958": {
|
980 |
+
"content": "L",
|
981 |
+
"lstrip": false,
|
982 |
+
"normalized": true,
|
983 |
+
"rstrip": false,
|
984 |
+
"single_word": false,
|
985 |
+
"special": false
|
986 |
+
},
|
987 |
+
"54359": {
|
988 |
+
"content": "и",
|
989 |
+
"lstrip": false,
|
990 |
+
"normalized": true,
|
991 |
+
"rstrip": false,
|
992 |
+
"single_word": false,
|
993 |
+
"special": false
|
994 |
+
},
|
995 |
+
"55144": {
|
996 |
+
"content": "6",
|
997 |
+
"lstrip": false,
|
998 |
+
"normalized": true,
|
999 |
+
"rstrip": false,
|
1000 |
+
"single_word": false,
|
1001 |
+
"special": false
|
1002 |
+
},
|
1003 |
+
"55175": {
|
1004 |
+
"content": "k",
|
1005 |
+
"lstrip": false,
|
1006 |
+
"normalized": true,
|
1007 |
+
"rstrip": false,
|
1008 |
+
"single_word": false,
|
1009 |
+
"special": false
|
1010 |
+
},
|
1011 |
+
"55410": {
|
1012 |
+
"content": "F",
|
1013 |
+
"lstrip": false,
|
1014 |
+
"normalized": true,
|
1015 |
+
"rstrip": false,
|
1016 |
+
"single_word": false,
|
1017 |
+
"special": false
|
1018 |
+
},
|
1019 |
+
"56620": {
|
1020 |
+
"content": "7",
|
1021 |
+
"lstrip": false,
|
1022 |
+
"normalized": true,
|
1023 |
+
"rstrip": false,
|
1024 |
+
"single_word": false,
|
1025 |
+
"special": false
|
1026 |
+
},
|
1027 |
+
"56739": {
|
1028 |
+
"content": "ú",
|
1029 |
+
"lstrip": false,
|
1030 |
+
"normalized": true,
|
1031 |
+
"rstrip": false,
|
1032 |
+
"single_word": false,
|
1033 |
+
"special": false
|
1034 |
+
},
|
1035 |
+
"57521": {
|
1036 |
+
"content": "<mask>",
|
1037 |
+
"lstrip": true,
|
1038 |
+
"normalized": true,
|
1039 |
+
"rstrip": false,
|
1040 |
+
"single_word": false,
|
1041 |
+
"special": true
|
1042 |
+
},
|
1043 |
+
"57522": {
|
1044 |
+
"content": "<sep/>",
|
1045 |
+
"lstrip": false,
|
1046 |
+
"normalized": true,
|
1047 |
+
"rstrip": false,
|
1048 |
+
"single_word": false,
|
1049 |
+
"special": false
|
1050 |
+
},
|
1051 |
+
"57523": {
|
1052 |
+
"content": "<s_iitcdip>",
|
1053 |
+
"lstrip": false,
|
1054 |
+
"normalized": false,
|
1055 |
+
"rstrip": false,
|
1056 |
+
"single_word": false,
|
1057 |
+
"special": true
|
1058 |
+
},
|
1059 |
+
"57524": {
|
1060 |
+
"content": "<s_synthdog>",
|
1061 |
+
"lstrip": false,
|
1062 |
+
"normalized": false,
|
1063 |
+
"rstrip": false,
|
1064 |
+
"single_word": false,
|
1065 |
+
"special": true
|
1066 |
+
},
|
1067 |
+
"57525": {
|
1068 |
+
"content": "ਥ",
|
1069 |
+
"lstrip": false,
|
1070 |
+
"normalized": true,
|
1071 |
+
"rstrip": false,
|
1072 |
+
"single_word": false,
|
1073 |
+
"special": false
|
1074 |
+
},
|
1075 |
+
"57526": {
|
1076 |
+
"content": "ੱ",
|
1077 |
+
"lstrip": false,
|
1078 |
+
"normalized": true,
|
1079 |
+
"rstrip": false,
|
1080 |
+
"single_word": false,
|
1081 |
+
"special": false
|
1082 |
+
},
|
1083 |
+
"57527": {
|
1084 |
+
"content": "્",
|
1085 |
+
"lstrip": false,
|
1086 |
+
"normalized": true,
|
1087 |
+
"rstrip": false,
|
1088 |
+
"single_word": false,
|
1089 |
+
"special": false
|
1090 |
+
},
|
1091 |
+
"57528": {
|
1092 |
+
"content": "ਯ",
|
1093 |
+
"lstrip": false,
|
1094 |
+
"normalized": true,
|
1095 |
+
"rstrip": false,
|
1096 |
+
"single_word": false,
|
1097 |
+
"special": false
|
1098 |
+
},
|
1099 |
+
"57529": {
|
1100 |
+
"content": "ਲ਼",
|
1101 |
+
"lstrip": false,
|
1102 |
+
"normalized": true,
|
1103 |
+
"rstrip": false,
|
1104 |
+
"single_word": false,
|
1105 |
+
"special": false
|
1106 |
+
},
|
1107 |
+
"57530": {
|
1108 |
+
"content": "॥",
|
1109 |
+
"lstrip": false,
|
1110 |
+
"normalized": true,
|
1111 |
+
"rstrip": false,
|
1112 |
+
"single_word": false,
|
1113 |
+
"special": false
|
1114 |
+
},
|
1115 |
+
"57531": {
|
1116 |
+
"content": "च",
|
1117 |
+
"lstrip": false,
|
1118 |
+
"normalized": true,
|
1119 |
+
"rstrip": false,
|
1120 |
+
"single_word": false,
|
1121 |
+
"special": false
|
1122 |
+
},
|
1123 |
+
"57532": {
|
1124 |
+
"content": "Ṇ",
|
1125 |
+
"lstrip": false,
|
1126 |
+
"normalized": true,
|
1127 |
+
"rstrip": false,
|
1128 |
+
"single_word": false,
|
1129 |
+
"special": false
|
1130 |
+
},
|
1131 |
+
"57533": {
|
1132 |
+
"content": "ਐ",
|
1133 |
+
"lstrip": false,
|
1134 |
+
"normalized": true,
|
1135 |
+
"rstrip": false,
|
1136 |
+
"single_word": false,
|
1137 |
+
"special": false
|
1138 |
+
},
|
1139 |
+
"57534": {
|
1140 |
+
"content": "ि",
|
1141 |
+
"lstrip": false,
|
1142 |
+
"normalized": true,
|
1143 |
+
"rstrip": false,
|
1144 |
+
"single_word": false,
|
1145 |
+
"special": false
|
1146 |
+
},
|
1147 |
+
"57535": {
|
1148 |
+
"content": "અ",
|
1149 |
+
"lstrip": false,
|
1150 |
+
"normalized": true,
|
1151 |
+
"rstrip": false,
|
1152 |
+
"single_word": false,
|
1153 |
+
"special": false
|
1154 |
+
},
|
1155 |
+
"57536": {
|
1156 |
+
"content": "ਦ",
|
1157 |
+
"lstrip": false,
|
1158 |
+
"normalized": true,
|
1159 |
+
"rstrip": false,
|
1160 |
+
"single_word": false,
|
1161 |
+
"special": false
|
1162 |
+
},
|
1163 |
+
"57537": {
|
1164 |
+
"content": "Ī",
|
1165 |
+
"lstrip": false,
|
1166 |
+
"normalized": true,
|
1167 |
+
"rstrip": false,
|
1168 |
+
"single_word": false,
|
1169 |
+
"special": false
|
1170 |
+
},
|
1171 |
+
"57538": {
|
1172 |
+
"content": "ॉ",
|
1173 |
+
"lstrip": false,
|
1174 |
+
"normalized": true,
|
1175 |
+
"rstrip": false,
|
1176 |
+
"single_word": false,
|
1177 |
+
"special": false
|
1178 |
+
},
|
1179 |
+
"57539": {
|
1180 |
+
"content": "ा",
|
1181 |
+
"lstrip": false,
|
1182 |
+
"normalized": true,
|
1183 |
+
"rstrip": false,
|
1184 |
+
"single_word": false,
|
1185 |
+
"special": false
|
1186 |
+
},
|
1187 |
+
"57540": {
|
1188 |
+
"content": "ਅ",
|
1189 |
+
"lstrip": false,
|
1190 |
+
"normalized": true,
|
1191 |
+
"rstrip": false,
|
1192 |
+
"single_word": false,
|
1193 |
+
"special": false
|
1194 |
+
},
|
1195 |
+
"57541": {
|
1196 |
+
"content": "ਚ",
|
1197 |
+
"lstrip": false,
|
1198 |
+
"normalized": true,
|
1199 |
+
"rstrip": false,
|
1200 |
+
"single_word": false,
|
1201 |
+
"special": false
|
1202 |
+
},
|
1203 |
+
"57542": {
|
1204 |
+
"content": "घ",
|
1205 |
+
"lstrip": false,
|
1206 |
+
"normalized": true,
|
1207 |
+
"rstrip": false,
|
1208 |
+
"single_word": false,
|
1209 |
+
"special": false
|
1210 |
+
},
|
1211 |
+
"57543": {
|
1212 |
+
"content": "ਞ",
|
1213 |
+
"lstrip": false,
|
1214 |
+
"normalized": true,
|
1215 |
+
"rstrip": false,
|
1216 |
+
"single_word": false,
|
1217 |
+
"special": false
|
1218 |
+
},
|
1219 |
+
"57544": {
|
1220 |
+
"content": "ਂ",
|
1221 |
+
"lstrip": false,
|
1222 |
+
"normalized": true,
|
1223 |
+
"rstrip": false,
|
1224 |
+
"single_word": false,
|
1225 |
+
"special": false
|
1226 |
+
},
|
1227 |
+
"57545": {
|
1228 |
+
"content": "ਟ",
|
1229 |
+
"lstrip": false,
|
1230 |
+
"normalized": true,
|
1231 |
+
"rstrip": false,
|
1232 |
+
"single_word": false,
|
1233 |
+
"special": false
|
1234 |
+
},
|
1235 |
+
"57546": {
|
1236 |
+
"content": "ੈ",
|
1237 |
+
"lstrip": false,
|
1238 |
+
"normalized": true,
|
1239 |
+
"rstrip": false,
|
1240 |
+
"single_word": false,
|
1241 |
+
"special": false
|
1242 |
+
},
|
1243 |
+
"57547": {
|
1244 |
+
"content": "य",
|
1245 |
+
"lstrip": false,
|
1246 |
+
"normalized": true,
|
1247 |
+
"rstrip": false,
|
1248 |
+
"single_word": false,
|
1249 |
+
"special": false
|
1250 |
+
},
|
1251 |
+
"57548": {
|
1252 |
+
"content": "ਧ",
|
1253 |
+
"lstrip": false,
|
1254 |
+
"normalized": true,
|
1255 |
+
"rstrip": false,
|
1256 |
+
"single_word": false,
|
1257 |
+
"special": false
|
1258 |
+
},
|
1259 |
+
"57549": {
|
1260 |
+
"content": "ો",
|
1261 |
+
"lstrip": false,
|
1262 |
+
"normalized": true,
|
1263 |
+
"rstrip": false,
|
1264 |
+
"single_word": false,
|
1265 |
+
"special": false
|
1266 |
+
},
|
1267 |
+
"57550": {
|
1268 |
+
"content": "ਊ",
|
1269 |
+
"lstrip": false,
|
1270 |
+
"normalized": true,
|
1271 |
+
"rstrip": false,
|
1272 |
+
"single_word": false,
|
1273 |
+
"special": false
|
1274 |
+
},
|
1275 |
+
"57551": {
|
1276 |
+
"content": "ॅ",
|
1277 |
+
"lstrip": false,
|
1278 |
+
"normalized": true,
|
1279 |
+
"rstrip": false,
|
1280 |
+
"single_word": false,
|
1281 |
+
"special": false
|
1282 |
+
},
|
1283 |
+
"57552": {
|
1284 |
+
"content": "ˈ",
|
1285 |
+
"lstrip": false,
|
1286 |
+
"normalized": true,
|
1287 |
+
"rstrip": false,
|
1288 |
+
"single_word": false,
|
1289 |
+
"special": false
|
1290 |
+
},
|
1291 |
+
"57553": {
|
1292 |
+
"content": "भ",
|
1293 |
+
"lstrip": false,
|
1294 |
+
"normalized": true,
|
1295 |
+
"rstrip": false,
|
1296 |
+
"single_word": false,
|
1297 |
+
"special": false
|
1298 |
+
},
|
1299 |
+
"57554": {
|
1300 |
+
"content": "ਿ",
|
1301 |
+
"lstrip": false,
|
1302 |
+
"normalized": true,
|
1303 |
+
"rstrip": false,
|
1304 |
+
"single_word": false,
|
1305 |
+
"special": false
|
1306 |
+
},
|
1307 |
+
"57555": {
|
1308 |
+
"content": "ज",
|
1309 |
+
"lstrip": false,
|
1310 |
+
"normalized": true,
|
1311 |
+
"rstrip": false,
|
1312 |
+
"single_word": false,
|
1313 |
+
"special": false
|
1314 |
+
},
|
1315 |
+
"57556": {
|
1316 |
+
"content": "ل",
|
1317 |
+
"lstrip": false,
|
1318 |
+
"normalized": true,
|
1319 |
+
"rstrip": false,
|
1320 |
+
"single_word": false,
|
1321 |
+
"special": false
|
1322 |
+
},
|
1323 |
+
"57557": {
|
1324 |
+
"content": "न",
|
1325 |
+
"lstrip": false,
|
1326 |
+
"normalized": true,
|
1327 |
+
"rstrip": false,
|
1328 |
+
"single_word": false,
|
1329 |
+
"special": false
|
1330 |
+
},
|
1331 |
+
"57558": {
|
1332 |
+
"content": "ਆ",
|
1333 |
+
"lstrip": false,
|
1334 |
+
"normalized": true,
|
1335 |
+
"rstrip": false,
|
1336 |
+
"single_word": false,
|
1337 |
+
"special": false
|
1338 |
+
},
|
1339 |
+
"57559": {
|
1340 |
+
"content": "ਗ਼",
|
1341 |
+
"lstrip": false,
|
1342 |
+
"normalized": true,
|
1343 |
+
"rstrip": false,
|
1344 |
+
"single_word": false,
|
1345 |
+
"special": false
|
1346 |
+
},
|
1347 |
+
"57560": {
|
1348 |
+
"content": "ਰ",
|
1349 |
+
"lstrip": false,
|
1350 |
+
"normalized": true,
|
1351 |
+
"rstrip": false,
|
1352 |
+
"single_word": false,
|
1353 |
+
"special": false
|
1354 |
+
},
|
1355 |
+
"57561": {
|
1356 |
+
"content": "੍",
|
1357 |
+
"lstrip": false,
|
1358 |
+
"normalized": true,
|
1359 |
+
"rstrip": false,
|
1360 |
+
"single_word": false,
|
1361 |
+
"special": false
|
1362 |
+
},
|
1363 |
+
"57562": {
|
1364 |
+
"content": "ય",
|
1365 |
+
"lstrip": false,
|
1366 |
+
"normalized": true,
|
1367 |
+
"rstrip": false,
|
1368 |
+
"single_word": false,
|
1369 |
+
"special": false
|
1370 |
+
},
|
1371 |
+
"57563": {
|
1372 |
+
"content": "्",
|
1373 |
+
"lstrip": false,
|
1374 |
+
"normalized": true,
|
1375 |
+
"rstrip": false,
|
1376 |
+
"single_word": false,
|
1377 |
+
"special": false
|
1378 |
+
},
|
1379 |
+
"57564": {
|
1380 |
+
"content": "ਛ",
|
1381 |
+
"lstrip": false,
|
1382 |
+
"normalized": true,
|
1383 |
+
"rstrip": false,
|
1384 |
+
"single_word": false,
|
1385 |
+
"special": false
|
1386 |
+
},
|
1387 |
+
"57565": {
|
1388 |
+
"content": "ਡ",
|
1389 |
+
"lstrip": false,
|
1390 |
+
"normalized": true,
|
1391 |
+
"rstrip": false,
|
1392 |
+
"single_word": false,
|
1393 |
+
"special": false
|
1394 |
+
},
|
1395 |
+
"57566": {
|
1396 |
+
"content": "र",
|
1397 |
+
"lstrip": false,
|
1398 |
+
"normalized": true,
|
1399 |
+
"rstrip": false,
|
1400 |
+
"single_word": false,
|
1401 |
+
"special": false
|
1402 |
+
},
|
1403 |
+
"57567": {
|
1404 |
+
"content": "थ",
|
1405 |
+
"lstrip": false,
|
1406 |
+
"normalized": true,
|
1407 |
+
"rstrip": false,
|
1408 |
+
"single_word": false,
|
1409 |
+
"special": false
|
1410 |
+
},
|
1411 |
+
"57568": {
|
1412 |
+
"content": "ੁ",
|
1413 |
+
"lstrip": false,
|
1414 |
+
"normalized": true,
|
1415 |
+
"rstrip": false,
|
1416 |
+
"single_word": false,
|
1417 |
+
"special": false
|
1418 |
+
},
|
1419 |
+
"57569": {
|
1420 |
+
"content": "³",
|
1421 |
+
"lstrip": false,
|
1422 |
+
"normalized": true,
|
1423 |
+
"rstrip": false,
|
1424 |
+
"single_word": false,
|
1425 |
+
"special": false
|
1426 |
+
},
|
1427 |
+
"57570": {
|
1428 |
+
"content": "י",
|
1429 |
+
"lstrip": false,
|
1430 |
+
"normalized": true,
|
1431 |
+
"rstrip": false,
|
1432 |
+
"single_word": false,
|
1433 |
+
"special": false
|
1434 |
+
},
|
1435 |
+
"57571": {
|
1436 |
+
"content": "ੲ",
|
1437 |
+
"lstrip": false,
|
1438 |
+
"normalized": true,
|
1439 |
+
"rstrip": false,
|
1440 |
+
"single_word": false,
|
1441 |
+
"special": false
|
1442 |
+
},
|
1443 |
+
"57572": {
|
1444 |
+
"content": "म",
|
1445 |
+
"lstrip": false,
|
1446 |
+
"normalized": true,
|
1447 |
+
"rstrip": false,
|
1448 |
+
"single_word": false,
|
1449 |
+
"special": false
|
1450 |
+
},
|
1451 |
+
"57573": {
|
1452 |
+
"content": "Ḥ",
|
1453 |
+
"lstrip": false,
|
1454 |
+
"normalized": true,
|
1455 |
+
"rstrip": false,
|
1456 |
+
"single_word": false,
|
1457 |
+
"special": false
|
1458 |
+
},
|
1459 |
+
"57574": {
|
1460 |
+
"content": "ਤ",
|
1461 |
+
"lstrip": false,
|
1462 |
+
"normalized": true,
|
1463 |
+
"rstrip": false,
|
1464 |
+
"single_word": false,
|
1465 |
+
"special": false
|
1466 |
+
},
|
1467 |
+
"57575": {
|
1468 |
+
"content": "ગ",
|
1469 |
+
"lstrip": false,
|
1470 |
+
"normalized": true,
|
1471 |
+
"rstrip": false,
|
1472 |
+
"single_word": false,
|
1473 |
+
"special": false
|
1474 |
+
},
|
1475 |
+
"57576": {
|
1476 |
+
"content": "ਜ",
|
1477 |
+
"lstrip": false,
|
1478 |
+
"normalized": true,
|
1479 |
+
"rstrip": false,
|
1480 |
+
"single_word": false,
|
1481 |
+
"special": false
|
1482 |
+
},
|
1483 |
+
"57577": {
|
1484 |
+
"content": "ੰ",
|
1485 |
+
"lstrip": false,
|
1486 |
+
"normalized": true,
|
1487 |
+
"rstrip": false,
|
1488 |
+
"single_word": false,
|
1489 |
+
"special": false
|
1490 |
+
},
|
1491 |
+
"57578": {
|
1492 |
+
"content": "ै",
|
1493 |
+
"lstrip": false,
|
1494 |
+
"normalized": true,
|
1495 |
+
"rstrip": false,
|
1496 |
+
"single_word": false,
|
1497 |
+
"special": false
|
1498 |
+
},
|
1499 |
+
"57579": {
|
1500 |
+
"content": "ਣ",
|
1501 |
+
"lstrip": false,
|
1502 |
+
"normalized": true,
|
1503 |
+
"rstrip": false,
|
1504 |
+
"single_word": false,
|
1505 |
+
"special": false
|
1506 |
+
},
|
1507 |
+
"57580": {
|
1508 |
+
"content": "ਬ",
|
1509 |
+
"lstrip": false,
|
1510 |
+
"normalized": true,
|
1511 |
+
"rstrip": false,
|
1512 |
+
"single_word": false,
|
1513 |
+
"special": false
|
1514 |
+
},
|
1515 |
+
"57581": {
|
1516 |
+
"content": "व",
|
1517 |
+
"lstrip": false,
|
1518 |
+
"normalized": true,
|
1519 |
+
"rstrip": false,
|
1520 |
+
"single_word": false,
|
1521 |
+
"special": false
|
1522 |
+
},
|
1523 |
+
"57582": {
|
1524 |
+
"content": "د",
|
1525 |
+
"lstrip": false,
|
1526 |
+
"normalized": true,
|
1527 |
+
"rstrip": false,
|
1528 |
+
"single_word": false,
|
1529 |
+
"special": false
|
1530 |
+
},
|
1531 |
+
"57583": {
|
1532 |
+
"content": "т",
|
1533 |
+
"lstrip": false,
|
1534 |
+
"normalized": true,
|
1535 |
+
"rstrip": false,
|
1536 |
+
"single_word": false,
|
1537 |
+
"special": false
|
1538 |
+
},
|
1539 |
+
"57584": {
|
1540 |
+
"content": "ી",
|
1541 |
+
"lstrip": false,
|
1542 |
+
"normalized": true,
|
1543 |
+
"rstrip": false,
|
1544 |
+
"single_word": false,
|
1545 |
+
"special": false
|
1546 |
+
},
|
1547 |
+
"57585": {
|
1548 |
+
"content": "ਪ",
|
1549 |
+
"lstrip": false,
|
1550 |
+
"normalized": true,
|
1551 |
+
"rstrip": false,
|
1552 |
+
"single_word": false,
|
1553 |
+
"special": false
|
1554 |
+
},
|
1555 |
+
"57586": {
|
1556 |
+
"content": "…",
|
1557 |
+
"lstrip": false,
|
1558 |
+
"normalized": true,
|
1559 |
+
"rstrip": false,
|
1560 |
+
"single_word": false,
|
1561 |
+
"special": false
|
1562 |
+
},
|
1563 |
+
"57587": {
|
1564 |
+
"content": "½",
|
1565 |
+
"lstrip": false,
|
1566 |
+
"normalized": true,
|
1567 |
+
"rstrip": false,
|
1568 |
+
"single_word": false,
|
1569 |
+
"special": false
|
1570 |
+
},
|
1571 |
+
"57588": {
|
1572 |
+
"content": "²",
|
1573 |
+
"lstrip": false,
|
1574 |
+
"normalized": true,
|
1575 |
+
"rstrip": false,
|
1576 |
+
"single_word": false,
|
1577 |
+
"special": false
|
1578 |
+
},
|
1579 |
+
"57589": {
|
1580 |
+
"content": "ग",
|
1581 |
+
"lstrip": false,
|
1582 |
+
"normalized": true,
|
1583 |
+
"rstrip": false,
|
1584 |
+
"single_word": false,
|
1585 |
+
"special": false
|
1586 |
+
},
|
1587 |
+
"57590": {
|
1588 |
+
"content": "ד",
|
1589 |
+
"lstrip": false,
|
1590 |
+
"normalized": true,
|
1591 |
+
"rstrip": false,
|
1592 |
+
"single_word": false,
|
1593 |
+
"special": false
|
1594 |
+
},
|
1595 |
+
"57591": {
|
1596 |
+
"content": "उ",
|
1597 |
+
"lstrip": false,
|
1598 |
+
"normalized": true,
|
1599 |
+
"rstrip": false,
|
1600 |
+
"single_word": false,
|
1601 |
+
"special": false
|
1602 |
+
},
|
1603 |
+
"57592": {
|
1604 |
+
"content": "ઘ",
|
1605 |
+
"lstrip": false,
|
1606 |
+
"normalized": true,
|
1607 |
+
"rstrip": false,
|
1608 |
+
"single_word": false,
|
1609 |
+
"special": false
|
1610 |
+
},
|
1611 |
+
"57593": {
|
1612 |
+
"content": "ੇ",
|
1613 |
+
"lstrip": false,
|
1614 |
+
"normalized": true,
|
1615 |
+
"rstrip": false,
|
1616 |
+
"single_word": false,
|
1617 |
+
"special": false
|
1618 |
+
},
|
1619 |
+
"57594": {
|
1620 |
+
"content": "ੋ",
|
1621 |
+
"lstrip": false,
|
1622 |
+
"normalized": true,
|
1623 |
+
"rstrip": false,
|
1624 |
+
"single_word": false,
|
1625 |
+
"special": false
|
1626 |
+
},
|
1627 |
+
"57595": {
|
1628 |
+
"content": "Ṉ",
|
1629 |
+
"lstrip": false,
|
1630 |
+
"normalized": true,
|
1631 |
+
"rstrip": false,
|
1632 |
+
"single_word": false,
|
1633 |
+
"special": false
|
1634 |
+
},
|
1635 |
+
"57596": {
|
1636 |
+
"content": "ठ",
|
1637 |
+
"lstrip": false,
|
1638 |
+
"normalized": true,
|
1639 |
+
"rstrip": false,
|
1640 |
+
"single_word": false,
|
1641 |
+
"special": false
|
1642 |
+
},
|
1643 |
+
"57597": {
|
1644 |
+
"content": "ल",
|
1645 |
+
"lstrip": false,
|
1646 |
+
"normalized": true,
|
1647 |
+
"rstrip": false,
|
1648 |
+
"single_word": false,
|
1649 |
+
"special": false
|
1650 |
+
},
|
1651 |
+
"57598": {
|
1652 |
+
"content": "ਜ਼",
|
1653 |
+
"lstrip": false,
|
1654 |
+
"normalized": true,
|
1655 |
+
"rstrip": false,
|
1656 |
+
"single_word": false,
|
1657 |
+
"special": false
|
1658 |
+
},
|
1659 |
+
"57599": {
|
1660 |
+
"content": "ड",
|
1661 |
+
"lstrip": false,
|
1662 |
+
"normalized": true,
|
1663 |
+
"rstrip": false,
|
1664 |
+
"single_word": false,
|
1665 |
+
"special": false
|
1666 |
+
},
|
1667 |
+
"57600": {
|
1668 |
+
"content": "ṉ",
|
1669 |
+
"lstrip": false,
|
1670 |
+
"normalized": true,
|
1671 |
+
"rstrip": false,
|
1672 |
+
"single_word": false,
|
1673 |
+
"special": false
|
1674 |
+
},
|
1675 |
+
"57601": {
|
1676 |
+
"content": "ਫ",
|
1677 |
+
"lstrip": false,
|
1678 |
+
"normalized": true,
|
1679 |
+
"rstrip": false,
|
1680 |
+
"single_word": false,
|
1681 |
+
"special": false
|
1682 |
+
},
|
1683 |
+
"57602": {
|
1684 |
+
"content": "ਮ",
|
1685 |
+
"lstrip": false,
|
1686 |
+
"normalized": true,
|
1687 |
+
"rstrip": false,
|
1688 |
+
"single_word": false,
|
1689 |
+
"special": false
|
1690 |
+
},
|
1691 |
+
"57603": {
|
1692 |
+
"content": "ਸ",
|
1693 |
+
"lstrip": false,
|
1694 |
+
"normalized": true,
|
1695 |
+
"rstrip": false,
|
1696 |
+
"single_word": false,
|
1697 |
+
"special": false
|
1698 |
+
},
|
1699 |
+
"57604": {
|
1700 |
+
"content": "੫",
|
1701 |
+
"lstrip": false,
|
1702 |
+
"normalized": true,
|
1703 |
+
"rstrip": false,
|
1704 |
+
"single_word": false,
|
1705 |
+
"special": false
|
1706 |
+
},
|
1707 |
+
"57605": {
|
1708 |
+
"content": "ਵ",
|
1709 |
+
"lstrip": false,
|
1710 |
+
"normalized": true,
|
1711 |
+
"rstrip": false,
|
1712 |
+
"single_word": false,
|
1713 |
+
"special": false
|
1714 |
+
},
|
1715 |
+
"57606": {
|
1716 |
+
"content": "त",
|
1717 |
+
"lstrip": false,
|
1718 |
+
"normalized": true,
|
1719 |
+
"rstrip": false,
|
1720 |
+
"single_word": false,
|
1721 |
+
"special": false
|
1722 |
+
},
|
1723 |
+
"57607": {
|
1724 |
+
"content": "¼",
|
1725 |
+
"lstrip": false,
|
1726 |
+
"normalized": true,
|
1727 |
+
"rstrip": false,
|
1728 |
+
"single_word": false,
|
1729 |
+
"special": false
|
1730 |
+
},
|
1731 |
+
"57608": {
|
1732 |
+
"content": "ਉ",
|
1733 |
+
"lstrip": false,
|
1734 |
+
"normalized": true,
|
1735 |
+
"rstrip": false,
|
1736 |
+
"single_word": false,
|
1737 |
+
"special": false
|
1738 |
+
},
|
1739 |
+
"57609": {
|
1740 |
+
"content": "¶",
|
1741 |
+
"lstrip": false,
|
1742 |
+
"normalized": true,
|
1743 |
+
"rstrip": false,
|
1744 |
+
"single_word": false,
|
1745 |
+
"special": false
|
1746 |
+
},
|
1747 |
+
"57610": {
|
1748 |
+
"content": "Ι",
|
1749 |
+
"lstrip": false,
|
1750 |
+
"normalized": true,
|
1751 |
+
"rstrip": false,
|
1752 |
+
"single_word": false,
|
1753 |
+
"special": false
|
1754 |
+
},
|
1755 |
+
"57611": {
|
1756 |
+
"content": "р",
|
1757 |
+
"lstrip": false,
|
1758 |
+
"normalized": true,
|
1759 |
+
"rstrip": false,
|
1760 |
+
"single_word": false,
|
1761 |
+
"special": false
|
1762 |
+
},
|
1763 |
+
"57612": {
|
1764 |
+
"content": "ਕ",
|
1765 |
+
"lstrip": false,
|
1766 |
+
"normalized": true,
|
1767 |
+
"rstrip": false,
|
1768 |
+
"single_word": false,
|
1769 |
+
"special": false
|
1770 |
+
},
|
1771 |
+
"57613": {
|
1772 |
+
"content": "ो",
|
1773 |
+
"lstrip": false,
|
1774 |
+
"normalized": true,
|
1775 |
+
"rstrip": false,
|
1776 |
+
"single_word": false,
|
1777 |
+
"special": false
|
1778 |
+
},
|
1779 |
+
"57614": {
|
1780 |
+
"content": "ਾ",
|
1781 |
+
"lstrip": false,
|
1782 |
+
"normalized": true,
|
1783 |
+
"rstrip": false,
|
1784 |
+
"single_word": false,
|
1785 |
+
"special": false
|
1786 |
+
},
|
1787 |
+
"57615": {
|
1788 |
+
"content": "છ",
|
1789 |
+
"lstrip": false,
|
1790 |
+
"normalized": true,
|
1791 |
+
"rstrip": false,
|
1792 |
+
"single_word": false,
|
1793 |
+
"special": false
|
1794 |
+
},
|
1795 |
+
"57616": {
|
1796 |
+
"content": "о",
|
1797 |
+
"lstrip": false,
|
1798 |
+
"normalized": true,
|
1799 |
+
"rstrip": false,
|
1800 |
+
"single_word": false,
|
1801 |
+
"special": false
|
1802 |
+
},
|
1803 |
+
"57617": {
|
1804 |
+
"content": "સ",
|
1805 |
+
"lstrip": false,
|
1806 |
+
"normalized": true,
|
1807 |
+
"rstrip": false,
|
1808 |
+
"single_word": false,
|
1809 |
+
"special": false
|
1810 |
+
},
|
1811 |
+
"57618": {
|
1812 |
+
"content": "ਘ",
|
1813 |
+
"lstrip": false,
|
1814 |
+
"normalized": true,
|
1815 |
+
"rstrip": false,
|
1816 |
+
"single_word": false,
|
1817 |
+
"special": false
|
1818 |
+
},
|
1819 |
+
"57619": {
|
1820 |
+
"content": "¹",
|
1821 |
+
"lstrip": false,
|
1822 |
+
"normalized": true,
|
1823 |
+
"rstrip": false,
|
1824 |
+
"single_word": false,
|
1825 |
+
"special": false
|
1826 |
+
},
|
1827 |
+
"57620": {
|
1828 |
+
"content": "द",
|
1829 |
+
"lstrip": false,
|
1830 |
+
"normalized": true,
|
1831 |
+
"rstrip": false,
|
1832 |
+
"single_word": false,
|
1833 |
+
"special": false
|
1834 |
+
},
|
1835 |
+
"57621": {
|
1836 |
+
"content": "ḍ",
|
1837 |
+
"lstrip": false,
|
1838 |
+
"normalized": true,
|
1839 |
+
"rstrip": false,
|
1840 |
+
"single_word": false,
|
1841 |
+
"special": false
|
1842 |
+
},
|
1843 |
+
"57622": {
|
1844 |
+
"content": "ष",
|
1845 |
+
"lstrip": false,
|
1846 |
+
"normalized": true,
|
1847 |
+
"rstrip": false,
|
1848 |
+
"single_word": false,
|
1849 |
+
"special": false
|
1850 |
+
},
|
1851 |
+
"57623": {
|
1852 |
+
"content": "ੜ",
|
1853 |
+
"lstrip": false,
|
1854 |
+
"normalized": true,
|
1855 |
+
"rstrip": false,
|
1856 |
+
"single_word": false,
|
1857 |
+
"special": false
|
1858 |
+
},
|
1859 |
+
"57624": {
|
1860 |
+
"content": "प",
|
1861 |
+
"lstrip": false,
|
1862 |
+
"normalized": true,
|
1863 |
+
"rstrip": false,
|
1864 |
+
"single_word": false,
|
1865 |
+
"special": false
|
1866 |
+
},
|
1867 |
+
"57625": {
|
1868 |
+
"content": "ਭ",
|
1869 |
+
"lstrip": false,
|
1870 |
+
"normalized": true,
|
1871 |
+
"rstrip": false,
|
1872 |
+
"single_word": false,
|
1873 |
+
"special": false
|
1874 |
+
},
|
1875 |
+
"57626": {
|
1876 |
+
"content": "Ṛ",
|
1877 |
+
"lstrip": false,
|
1878 |
+
"normalized": true,
|
1879 |
+
"rstrip": false,
|
1880 |
+
"single_word": false,
|
1881 |
+
"special": false
|
1882 |
+
},
|
1883 |
+
"57627": {
|
1884 |
+
"content": "ੳ",
|
1885 |
+
"lstrip": false,
|
1886 |
+
"normalized": true,
|
1887 |
+
"rstrip": false,
|
1888 |
+
"single_word": false,
|
1889 |
+
"special": false
|
1890 |
+
},
|
1891 |
+
"57628": {
|
1892 |
+
"content": "ત",
|
1893 |
+
"lstrip": false,
|
1894 |
+
"normalized": true,
|
1895 |
+
"rstrip": false,
|
1896 |
+
"single_word": false,
|
1897 |
+
"special": false
|
1898 |
+
},
|
1899 |
+
"57629": {
|
1900 |
+
"content": "ર",
|
1901 |
+
"lstrip": false,
|
1902 |
+
"normalized": true,
|
1903 |
+
"rstrip": false,
|
1904 |
+
"single_word": false,
|
1905 |
+
"special": false
|
1906 |
+
},
|
1907 |
+
"57630": {
|
1908 |
+
"content": "Ṭ",
|
1909 |
+
"lstrip": false,
|
1910 |
+
"normalized": true,
|
1911 |
+
"rstrip": false,
|
1912 |
+
"single_word": false,
|
1913 |
+
"special": false
|
1914 |
+
},
|
1915 |
+
"57631": {
|
1916 |
+
"content": "ઠ",
|
1917 |
+
"lstrip": false,
|
1918 |
+
"normalized": true,
|
1919 |
+
"rstrip": false,
|
1920 |
+
"single_word": false,
|
1921 |
+
"special": false
|
1922 |
+
},
|
1923 |
+
"57632": {
|
1924 |
+
"content": "ह",
|
1925 |
+
"lstrip": false,
|
1926 |
+
"normalized": true,
|
1927 |
+
"rstrip": false,
|
1928 |
+
"single_word": false,
|
1929 |
+
"special": false
|
1930 |
+
},
|
1931 |
+
"57633": {
|
1932 |
+
"content": "ਗ",
|
1933 |
+
"lstrip": false,
|
1934 |
+
"normalized": true,
|
1935 |
+
"rstrip": false,
|
1936 |
+
"single_word": false,
|
1937 |
+
"special": false
|
1938 |
+
},
|
1939 |
+
"57634": {
|
1940 |
+
"content": "ੂ",
|
1941 |
+
"lstrip": false,
|
1942 |
+
"normalized": true,
|
1943 |
+
"rstrip": false,
|
1944 |
+
"single_word": false,
|
1945 |
+
"special": false
|
1946 |
+
},
|
1947 |
+
"57635": {
|
1948 |
+
"content": "ी",
|
1949 |
+
"lstrip": false,
|
1950 |
+
"normalized": true,
|
1951 |
+
"rstrip": false,
|
1952 |
+
"single_word": false,
|
1953 |
+
"special": false
|
1954 |
+
},
|
1955 |
+
"57636": {
|
1956 |
+
"content": "।",
|
1957 |
+
"lstrip": false,
|
1958 |
+
"normalized": true,
|
1959 |
+
"rstrip": false,
|
1960 |
+
"single_word": false,
|
1961 |
+
"special": false
|
1962 |
+
},
|
1963 |
+
"57637": {
|
1964 |
+
"content": "ਇ",
|
1965 |
+
"lstrip": false,
|
1966 |
+
"normalized": true,
|
1967 |
+
"rstrip": false,
|
1968 |
+
"single_word": false,
|
1969 |
+
"special": false
|
1970 |
+
},
|
1971 |
+
"57638": {
|
1972 |
+
"content": "ਙ",
|
1973 |
+
"lstrip": false,
|
1974 |
+
"normalized": true,
|
1975 |
+
"rstrip": false,
|
1976 |
+
"single_word": false,
|
1977 |
+
"special": false
|
1978 |
+
},
|
1979 |
+
"57639": {
|
1980 |
+
"content": "ਸ਼",
|
1981 |
+
"lstrip": false,
|
1982 |
+
"normalized": true,
|
1983 |
+
"rstrip": false,
|
1984 |
+
"single_word": false,
|
1985 |
+
"special": false
|
1986 |
+
},
|
1987 |
+
"57640": {
|
1988 |
+
"content": "ु",
|
1989 |
+
"lstrip": false,
|
1990 |
+
"normalized": true,
|
1991 |
+
"rstrip": false,
|
1992 |
+
"single_word": false,
|
1993 |
+
"special": false
|
1994 |
+
},
|
1995 |
+
"57641": {
|
1996 |
+
"content": "Ḍ",
|
1997 |
+
"lstrip": false,
|
1998 |
+
"normalized": true,
|
1999 |
+
"rstrip": false,
|
2000 |
+
"single_word": false,
|
2001 |
+
"special": false
|
2002 |
+
},
|
2003 |
+
"57642": {
|
2004 |
+
"content": "આ",
|
2005 |
+
"lstrip": false,
|
2006 |
+
"normalized": true,
|
2007 |
+
"rstrip": false,
|
2008 |
+
"single_word": false,
|
2009 |
+
"special": false
|
2010 |
+
},
|
2011 |
+
"57643": {
|
2012 |
+
"content": "ਨ",
|
2013 |
+
"lstrip": false,
|
2014 |
+
"normalized": true,
|
2015 |
+
"rstrip": false,
|
2016 |
+
"single_word": false,
|
2017 |
+
"special": false
|
2018 |
+
},
|
2019 |
+
"57644": {
|
2020 |
+
"content": "क",
|
2021 |
+
"lstrip": false,
|
2022 |
+
"normalized": true,
|
2023 |
+
"rstrip": false,
|
2024 |
+
"single_word": false,
|
2025 |
+
"special": false
|
2026 |
+
},
|
2027 |
+
"57645": {
|
2028 |
+
"content": "ट",
|
2029 |
+
"lstrip": false,
|
2030 |
+
"normalized": true,
|
2031 |
+
"rstrip": false,
|
2032 |
+
"single_word": false,
|
2033 |
+
"special": false
|
2034 |
+
},
|
2035 |
+
"57646": {
|
2036 |
+
"content": "े",
|
2037 |
+
"lstrip": false,
|
2038 |
+
"normalized": true,
|
2039 |
+
"rstrip": false,
|
2040 |
+
"single_word": false,
|
2041 |
+
"special": false
|
2042 |
+
},
|
2043 |
+
"57647": {
|
2044 |
+
"content": "П",
|
2045 |
+
"lstrip": false,
|
2046 |
+
"normalized": true,
|
2047 |
+
"rstrip": false,
|
2048 |
+
"single_word": false,
|
2049 |
+
"special": false
|
2050 |
+
},
|
2051 |
+
"57648": {
|
2052 |
+
"content": "ા",
|
2053 |
+
"lstrip": false,
|
2054 |
+
"normalized": true,
|
2055 |
+
"rstrip": false,
|
2056 |
+
"single_word": false,
|
2057 |
+
"special": false
|
2058 |
+
},
|
2059 |
+
"57649": {
|
2060 |
+
"content": "ણ",
|
2061 |
+
"lstrip": false,
|
2062 |
+
"normalized": true,
|
2063 |
+
"rstrip": false,
|
2064 |
+
"single_word": false,
|
2065 |
+
"special": false
|
2066 |
+
},
|
2067 |
+
"57650": {
|
2068 |
+
"content": "і",
|
2069 |
+
"lstrip": false,
|
2070 |
+
"normalized": true,
|
2071 |
+
"rstrip": false,
|
2072 |
+
"single_word": false,
|
2073 |
+
"special": false
|
2074 |
+
},
|
2075 |
+
"57651": {
|
2076 |
+
"content": "ਢ",
|
2077 |
+
"lstrip": false,
|
2078 |
+
"normalized": true,
|
2079 |
+
"rstrip": false,
|
2080 |
+
"single_word": false,
|
2081 |
+
"special": false
|
2082 |
+
},
|
2083 |
+
"57652": {
|
2084 |
+
"content": "ا",
|
2085 |
+
"lstrip": false,
|
2086 |
+
"normalized": true,
|
2087 |
+
"rstrip": false,
|
2088 |
+
"single_word": false,
|
2089 |
+
"special": false
|
2090 |
+
},
|
2091 |
+
"57653": {
|
2092 |
+
"content": "ੀ",
|
2093 |
+
"lstrip": false,
|
2094 |
+
"normalized": true,
|
2095 |
+
"rstrip": false,
|
2096 |
+
"single_word": false,
|
2097 |
+
"special": false
|
2098 |
+
},
|
2099 |
+
"57654": {
|
2100 |
+
"content": "ਝ",
|
2101 |
+
"lstrip": false,
|
2102 |
+
"normalized": true,
|
2103 |
+
"rstrip": false,
|
2104 |
+
"single_word": false,
|
2105 |
+
"special": false
|
2106 |
+
},
|
2107 |
+
"57655": {
|
2108 |
+
"content": "ૂ",
|
2109 |
+
"lstrip": false,
|
2110 |
+
"normalized": true,
|
2111 |
+
"rstrip": false,
|
2112 |
+
"single_word": false,
|
2113 |
+
"special": false
|
2114 |
+
},
|
2115 |
+
"57656": {
|
2116 |
+
"content": "1",
|
2117 |
+
"lstrip": false,
|
2118 |
+
"normalized": true,
|
2119 |
+
"rstrip": false,
|
2120 |
+
"single_word": false,
|
2121 |
+
"special": false
|
2122 |
+
},
|
2123 |
+
"57657": {
|
2124 |
+
"content": "ਏ",
|
2125 |
+
"lstrip": false,
|
2126 |
+
"normalized": true,
|
2127 |
+
"rstrip": false,
|
2128 |
+
"single_word": false,
|
2129 |
+
"special": false
|
2130 |
+
},
|
2131 |
+
"57658": {
|
2132 |
+
"content": "ਹ",
|
2133 |
+
"lstrip": false,
|
2134 |
+
"normalized": true,
|
2135 |
+
"rstrip": false,
|
2136 |
+
"single_word": false,
|
2137 |
+
"special": false
|
2138 |
+
},
|
2139 |
+
"57659": {
|
2140 |
+
"content": "स",
|
2141 |
+
"lstrip": false,
|
2142 |
+
"normalized": true,
|
2143 |
+
"rstrip": false,
|
2144 |
+
"single_word": false,
|
2145 |
+
"special": false
|
2146 |
+
},
|
2147 |
+
"57660": {
|
2148 |
+
"content": "ذ",
|
2149 |
+
"lstrip": false,
|
2150 |
+
"normalized": true,
|
2151 |
+
"rstrip": false,
|
2152 |
+
"single_word": false,
|
2153 |
+
"special": false
|
2154 |
+
},
|
2155 |
+
"57661": {
|
2156 |
+
"content": "਼",
|
2157 |
+
"lstrip": false,
|
2158 |
+
"normalized": true,
|
2159 |
+
"rstrip": false,
|
2160 |
+
"single_word": false,
|
2161 |
+
"special": false
|
2162 |
+
},
|
2163 |
+
"57662": {
|
2164 |
+
"content": "ੌ",
|
2165 |
+
"lstrip": false,
|
2166 |
+
"normalized": true,
|
2167 |
+
"rstrip": false,
|
2168 |
+
"single_word": false,
|
2169 |
+
"special": false
|
2170 |
+
},
|
2171 |
+
"57663": {
|
2172 |
+
"content": "ध",
|
2173 |
+
"lstrip": false,
|
2174 |
+
"normalized": true,
|
2175 |
+
"rstrip": false,
|
2176 |
+
"single_word": false,
|
2177 |
+
"special": false
|
2178 |
+
},
|
2179 |
+
"57664": {
|
2180 |
+
"content": "ਓ",
|
2181 |
+
"lstrip": false,
|
2182 |
+
"normalized": true,
|
2183 |
+
"rstrip": false,
|
2184 |
+
"single_word": false,
|
2185 |
+
"special": false
|
2186 |
+
},
|
2187 |
+
"57665": {
|
2188 |
+
"content": "ਈ",
|
2189 |
+
"lstrip": false,
|
2190 |
+
"normalized": true,
|
2191 |
+
"rstrip": false,
|
2192 |
+
"single_word": false,
|
2193 |
+
"special": false
|
2194 |
+
},
|
2195 |
+
"57666": {
|
2196 |
+
"content": "ુ",
|
2197 |
+
"lstrip": false,
|
2198 |
+
"normalized": true,
|
2199 |
+
"rstrip": false,
|
2200 |
+
"single_word": false,
|
2201 |
+
"special": false
|
2202 |
+
},
|
2203 |
+
"57667": {
|
2204 |
+
"content": "ਠ",
|
2205 |
+
"lstrip": false,
|
2206 |
+
"normalized": true,
|
2207 |
+
"rstrip": false,
|
2208 |
+
"single_word": false,
|
2209 |
+
"special": false
|
2210 |
+
},
|
2211 |
+
"57668": {
|
2212 |
+
"content": "ਖ",
|
2213 |
+
"lstrip": false,
|
2214 |
+
"normalized": true,
|
2215 |
+
"rstrip": false,
|
2216 |
+
"single_word": false,
|
2217 |
+
"special": false
|
2218 |
+
},
|
2219 |
+
"57669": {
|
2220 |
+
"content": "ं",
|
2221 |
+
"lstrip": false,
|
2222 |
+
"normalized": true,
|
2223 |
+
"rstrip": false,
|
2224 |
+
"single_word": false,
|
2225 |
+
"special": false
|
2226 |
+
},
|
2227 |
+
"57670": {
|
2228 |
+
"content": "ਲ",
|
2229 |
+
"lstrip": false,
|
2230 |
+
"normalized": true,
|
2231 |
+
"rstrip": false,
|
2232 |
+
"single_word": false,
|
2233 |
+
"special": false
|
2234 |
+
},
|
2235 |
+
"57671": {
|
2236 |
+
"content": "ດ",
|
2237 |
+
"lstrip": false,
|
2238 |
+
"normalized": true,
|
2239 |
+
"rstrip": false,
|
2240 |
+
"single_word": false,
|
2241 |
+
"special": false
|
2242 |
+
}
|
2243 |
+
},
|
2244 |
+
"additional_special_tokens": [
|
2245 |
+
"<s_iitcdip>",
|
2246 |
+
"<s_synthdog>"
|
2247 |
+
],
|
2248 |
+
"bos_token": "<s>",
|
2249 |
+
"clean_up_tokenization_spaces": false,
|
2250 |
+
"cls_token": "<s>",
|
2251 |
+
"eos_token": "</s>",
|
2252 |
+
"mask_token": "<mask>",
|
2253 |
+
"model_max_length": 1000000000000000019884624838656,
|
2254 |
+
"pad_token": "<pad>",
|
2255 |
+
"processor_class": "DonutProcessor",
|
2256 |
+
"sep_token": "</s>",
|
2257 |
+
"sp_model_kwargs": {},
|
2258 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
2259 |
+
"unk_token": "<unk>"
|
2260 |
+
}
|