Commit
Β·
1ed2958
1
Parent(s):
1a5b35c
add azb, bho, kan, kin, lug, luo, nya, srd and edit brh
Browse files- languages/azb_Arab.json +29 -0
- languages/bho_Deva.json +38 -0
- languages/brh_Arab.json +1 -1
- languages/kan_Knda.json +20 -0
- languages/kin_Latn.json +30 -0
- languages/lug_Latn.json +29 -0
- languages/luo_Latn.json +20 -0
- languages/nya_Latn.json +29 -0
- languages/srd_Latn.json +38 -0
languages/azb_Arab.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"Language Name": "South-Azerbaijani",
|
3 |
+
"Family": "Turkic",
|
4 |
+
"Subgrouping": "Oghuz",
|
5 |
+
"Number of Speakers": "14_000_000",
|
6 |
+
"Supported by allenai/MADLAD-400": 0,
|
7 |
+
"Supported by facebook/flores": 1,
|
8 |
+
"Supported by cis-lmu/Glot500": 1,
|
9 |
+
"Sites": [
|
10 |
+
{
|
11 |
+
"Site Name": "trt.net.tr",
|
12 |
+
"Site URL": "https://www.trt.net.tr/turki/",
|
13 |
+
"Category": "news",
|
14 |
+
"Confidence": "π©",
|
15 |
+
"Info": "native speaker confirmation",
|
16 |
+
"Possible Parallel Languages": "many",
|
17 |
+
"Links": []
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"Site Name": "azb.wikipedia.org",
|
21 |
+
"Site URL": "https://azb.wikipedia.org/wiki/",
|
22 |
+
"Category": "articles",
|
23 |
+
"Confidence": "π©",
|
24 |
+
"Info": "confirmed by webpage metadata",
|
25 |
+
"Possible Parallel Languages": "many",
|
26 |
+
"Links": []
|
27 |
+
}
|
28 |
+
]
|
29 |
+
}
|
languages/bho_Deva.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"Language Name": "Bhojpuri",
|
3 |
+
"Family": "Indo-European",
|
4 |
+
"Subgrouping": "Eastern Indo-Aryan",
|
5 |
+
"Number of Speakers": "51_000_000",
|
6 |
+
"Supported by allenai/MADLAD-400": 1,
|
7 |
+
"Supported by facebook/flores": 1,
|
8 |
+
"Supported by cis-lmu/Glot500": 0,
|
9 |
+
"Sites": [
|
10 |
+
{
|
11 |
+
"Site Name": "anjoria.com",
|
12 |
+
"Site URL": "https://www.anjoria.com/news_in_bhojpuri",
|
13 |
+
"Category": "news",
|
14 |
+
"Confidence": "π©",
|
15 |
+
"Info": "confirmed by webpage metadata",
|
16 |
+
"Possible Parallel Languages": "",
|
17 |
+
"Links": []
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"Site Name": "bhojpuri.blogspot.com",
|
21 |
+
"Site URL": "https://bhojpuri.blogspot.com",
|
22 |
+
"Category": "blog",
|
23 |
+
"Confidence": "π©",
|
24 |
+
"Info": "confirmed by webpage metadata",
|
25 |
+
"Possible Parallel Languages": "",
|
26 |
+
"Links": []
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"Site Name": "jogira.com",
|
30 |
+
"Site URL": "https://jogira.com/",
|
31 |
+
"Category": "news",
|
32 |
+
"Confidence": "π©",
|
33 |
+
"Info": "confirmed by webpage metadata",
|
34 |
+
"Possible Parallel Languages": "",
|
35 |
+
"Links": []
|
36 |
+
}
|
37 |
+
]
|
38 |
+
}
|
languages/brh_Arab.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"Language Name": "Brahui",
|
3 |
"Family": "Dravidian",
|
4 |
-
"Subgrouping": "",
|
5 |
"Number of Speakers": "2_800_000",
|
6 |
"Supported by allenai/MADLAD-400": 0,
|
7 |
"Supported by facebook/flores": 0,
|
|
|
1 |
{
|
2 |
"Language Name": "Brahui",
|
3 |
"Family": "Dravidian",
|
4 |
+
"Subgrouping": "Northern Dravidian",
|
5 |
"Number of Speakers": "2_800_000",
|
6 |
"Supported by allenai/MADLAD-400": 0,
|
7 |
"Supported by facebook/flores": 0,
|
languages/kan_Knda.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"Language Name": "Kannada",
|
3 |
+
"Family": "Dravidian",
|
4 |
+
"Subgrouping": "Southern Dravidian",
|
5 |
+
"Number of Speakers": "44_000_000",
|
6 |
+
"Supported by allenai/MADLAD-400": 1,
|
7 |
+
"Supported by facebook/flores": 1,
|
8 |
+
"Supported by cis-lmu/Glot500": 1,
|
9 |
+
"Sites": [
|
10 |
+
{
|
11 |
+
"Site Name": "vijaykarnataka.com",
|
12 |
+
"Site URL": "https://vijaykarnataka.com",
|
13 |
+
"Category": "news",
|
14 |
+
"Confidence": "π©",
|
15 |
+
"Info": "confirmed by webpage metadata and glotlid",
|
16 |
+
"Possible Parallel Languages": "",
|
17 |
+
"Links": []
|
18 |
+
}
|
19 |
+
]
|
20 |
+
}
|
languages/kin_Latn.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"Language Name": "Kinyarwanda",
|
3 |
+
"Family": "Niger-Congo",
|
4 |
+
"Subgrouping": "Bantu",
|
5 |
+
"Number of Speakers": "15_000_000",
|
6 |
+
"Supported by allenai/MADLAD-400": 1,
|
7 |
+
"Supported by facebook/flores": 1,
|
8 |
+
"Supported by cis-lmu/Glot500": 1,
|
9 |
+
"Sites": [
|
10 |
+
{
|
11 |
+
"Site Name": "kigalitoday.com",
|
12 |
+
"Site URL": "https://www.kigalitoday.com/",
|
13 |
+
"Category": "news",
|
14 |
+
"Confidence": "π©",
|
15 |
+
"Info": "confirmed by webpage metadata and glotlid",
|
16 |
+
"Possible Parallel Languages": "",
|
17 |
+
"Links": []
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"Site Name": "igihe.com",
|
21 |
+
"Site URL": "https://igihe.com/index.php",
|
22 |
+
"Category": "news",
|
23 |
+
"Confidence": "π©",
|
24 |
+
"Info": "confirmed by webpage metadata and glotlid",
|
25 |
+
"Possible Parallel Languages": "eng_Latn, fra_Latn",
|
26 |
+
"Links": []
|
27 |
+
}
|
28 |
+
|
29 |
+
]
|
30 |
+
}
|
languages/lug_Latn.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"Language Name": "Ganda",
|
3 |
+
"Family": "Niger-Congo",
|
4 |
+
"Subgrouping": "Bantu",
|
5 |
+
"Number of Speakers": "5_600_000",
|
6 |
+
"Supported by allenai/MADLAD-400": 1,
|
7 |
+
"Supported by facebook/flores": 1,
|
8 |
+
"Supported by cis-lmu/Glot500": 1,
|
9 |
+
"Sites": [
|
10 |
+
{
|
11 |
+
"Site Name": "bukedde.co.ug",
|
12 |
+
"Site URL": "https://www.bukedde.co.ug/category/amawulire",
|
13 |
+
"Category": "news",
|
14 |
+
"Confidence": "π©",
|
15 |
+
"Info": "confirmed by webpage metadata and glotlid",
|
16 |
+
"Possible Parallel Languages": "",
|
17 |
+
"Links": []
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"Site Name": "gambuuze.ug",
|
21 |
+
"Site URL": "https://gambuuze.ug/",
|
22 |
+
"Category": "news",
|
23 |
+
"Confidence": "π©",
|
24 |
+
"Info": "confirmed by webpage metadata and glotlid",
|
25 |
+
"Possible Parallel Languages": "",
|
26 |
+
"Links": []
|
27 |
+
}
|
28 |
+
]
|
29 |
+
}
|
languages/luo_Latn.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"Language Name": "Luo (Kenya and Tanzania)",
|
3 |
+
"Family": "Nilo-Saharan",
|
4 |
+
"Subgrouping": "Nilotic",
|
5 |
+
"Number of Speakers": "4_200_000",
|
6 |
+
"Supported by allenai/MADLAD-400": 1,
|
7 |
+
"Supported by facebook/flores": 1,
|
8 |
+
"Supported by cis-lmu/Glot500": 1,
|
9 |
+
"Sites": [
|
10 |
+
{
|
11 |
+
"Site Name": "rmsradio.co.ke",
|
12 |
+
"Site URL": "https://rmsradio.co.ke/brands/ramogi-fm/",
|
13 |
+
"Category": "radio station, news",
|
14 |
+
"Confidence": "π©",
|
15 |
+
"Info": "confirmed by webpage metadata and glotlid",
|
16 |
+
"Possible Parallel Languages": "",
|
17 |
+
"Links": []
|
18 |
+
}
|
19 |
+
]
|
20 |
+
}
|
languages/nya_Latn.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"Language Name": "Nyanja",
|
3 |
+
"Family": "Niger-Congo",
|
4 |
+
"Subgrouping": "Bantu",
|
5 |
+
"Number of Speakers": "7_000_000",
|
6 |
+
"Supported by allenai/MADLAD-400": 1,
|
7 |
+
"Supported by facebook/flores": 1,
|
8 |
+
"Supported by cis-lmu/Glot500": 1,
|
9 |
+
"Sites": [
|
10 |
+
{
|
11 |
+
"Site Name": "mwnation.com",
|
12 |
+
"Site URL": "https://mwnation.com/section/chichewa/",
|
13 |
+
"Category": "news",
|
14 |
+
"Confidence": "π©",
|
15 |
+
"Info": "confirmed by webpage metadata and glotlid",
|
16 |
+
"Possible Parallel Languages": "",
|
17 |
+
"Links": []
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"Site Name": "radiomaria.mw",
|
21 |
+
"Site URL": "https://www.radiomaria.mw/",
|
22 |
+
"Category": "radio station, news",
|
23 |
+
"Confidence": "π©",
|
24 |
+
"Info": "confirmed by webpage metadata and glotlid",
|
25 |
+
"Possible Parallel Languages": "",
|
26 |
+
"Links": []
|
27 |
+
}
|
28 |
+
]
|
29 |
+
}
|
languages/srd_Latn.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"Language Name": "Sardinian",
|
3 |
+
"Family": "Indo-European",
|
4 |
+
"Subgrouping": "Italic",
|
5 |
+
"Number of Speakers": "1_000_000",
|
6 |
+
"Supported by allenai/MADLAD-400": 1,
|
7 |
+
"Supported by facebook/flores": 1,
|
8 |
+
"Supported by cis-lmu/Glot500": 1,
|
9 |
+
"Sites": [
|
10 |
+
{
|
11 |
+
"Site Name": "salimbasarda.net",
|
12 |
+
"Site URL": "https://salimbasarda.net/",
|
13 |
+
"Category": "culture",
|
14 |
+
"Confidence": "π©",
|
15 |
+
"Info": "confirmed by webpage metadata and glotlid",
|
16 |
+
"Possible Parallel Languages": "",
|
17 |
+
"Links": []
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"Site Name": "ilminuto.info",
|
21 |
+
"Site URL": "https://www.ilminuto.info/sc/",
|
22 |
+
"Category": "news",
|
23 |
+
"Confidence": "π©",
|
24 |
+
"Info": "confirmed by webpage metadata and glotlid",
|
25 |
+
"Possible Parallel Languages": "ita_Latn",
|
26 |
+
"Links": []
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"Site Name": "sc.wikipedia.org",
|
30 |
+
"Site URL": "https://sc.wikipedia.org/wiki/",
|
31 |
+
"Category": "articles",
|
32 |
+
"Confidence": "π©",
|
33 |
+
"Info": "confirmed by webpage metadata",
|
34 |
+
"Possible Parallel Languages": "many",
|
35 |
+
"Links": []
|
36 |
+
}
|
37 |
+
]
|
38 |
+
}
|