kargaranamir
commited on
Commit
β’
0582f98
1
Parent(s):
703f596
add aii, tly.
Browse files- app.py +1 -1
- languages/aii_Syrc.json +42 -0
- languages/tly_Latn.json +24 -0
app.py
CHANGED
@@ -104,6 +104,6 @@ def main():
|
|
104 |
render_metadata()
|
105 |
st.markdown("**GlotWeb** is an indexing service for low-resource languages. It indexes **non-religous** sites or links written in each language. This list can be used to create raw text or parallel corpora and to study low-resource languages on the web.\n")
|
106 |
render_home_table()
|
107 |
-
st.markdown("\n\n<font color='gray'>We compare the level of support for these languages in the three big datasets ([
|
108 |
|
109 |
main()
|
|
|
104 |
render_metadata()
|
105 |
st.markdown("**GlotWeb** is an indexing service for low-resource languages. It indexes **non-religous** sites or links written in each language. This list can be used to create raw text or parallel corpora and to study low-resource languages on the web.\n")
|
106 |
render_home_table()
|
107 |
+
st.markdown("\n\n<font color='gray'>We compare the level of support for these languages in the three big datasets ([MADLAD400](https://huggingface.co/datasets/allenai/MADLAD-400), [FLORES200](https://huggingface.co/datasets/facebook/flores), [GLOT500](https://huggingface.co/datasets/cis-lmu/Glot500)) of low-resource languages (π₯ 0/3 < π§ 1/3 < π¨ 2/3 < π© 3/3). Although the support in these datasets for some of these languages could be just the religious texts.</font>", unsafe_allow_html=True)
|
108 |
|
109 |
main()
|
languages/aii_Syrc.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"Language Name": "Assyrian Neo-Aramaic",
|
3 |
+
"Family": "Afro-Asiatic",
|
4 |
+
"Subgrouping": "Semitic",
|
5 |
+
"Number of Speakers": "800_000",
|
6 |
+
"Supported by allenai/MADLAD-400": 1,
|
7 |
+
"Supported by facebook/flores": 0,
|
8 |
+
"Supported by cis-lmu/Glot500": 0,
|
9 |
+
"Sites": [
|
10 |
+
{
|
11 |
+
"Site Name": "reimagine.today",
|
12 |
+
"Site URL": "https://reimagine.today/?lang=as",
|
13 |
+
"Category": "insurance, government ",
|
14 |
+
"Confidence": "π©",
|
15 |
+
"Info": "confirmed by webpage metadata and glotlid",
|
16 |
+
"Possible Parallel Languages": "",
|
17 |
+
"Links": []
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"Site Name": "mesopotamiaheritage.org",
|
21 |
+
"Site URL": "https://www.mesopotamiaheritage.org/sy/",
|
22 |
+
"Category": "heritage guide",
|
23 |
+
"Confidence": "π©",
|
24 |
+
"Info": "confirmed by webpage metadata and glotlid",
|
25 |
+
"Possible Parallel Languages": "arb_Arab, eng_Latn, fra_Latn",
|
26 |
+
"Links": []
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"Site Name": "parstoday.ir",
|
30 |
+
"Site URL": "https://parstoday.ir/assyrian",
|
31 |
+
"Category": "news",
|
32 |
+
"Confidence": "π©",
|
33 |
+
"Info": "confirmed by webpage metadata and glotlid",
|
34 |
+
"Possible Parallel Languages": "many",
|
35 |
+
"Links": []
|
36 |
+
}
|
37 |
+
]
|
38 |
+
}
|
39 |
+
|
40 |
+
|
41 |
+
|
42 |
+
|
languages/tly_Latn.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"Language Name": "Talysh",
|
3 |
+
"Family": "Indo-European",
|
4 |
+
"Subgrouping": "Iranian",
|
5 |
+
"Number of Speakers": "230_000",
|
6 |
+
"Supported by allenai/MADLAD-400": 0,
|
7 |
+
"Supported by facebook/flores": 0,
|
8 |
+
"Supported by cis-lmu/Glot500": 0,
|
9 |
+
"Sites": [
|
10 |
+
{
|
11 |
+
"Site Name": "parstoday.ir",
|
12 |
+
"Site URL": "https://parstoday.ir/tly",
|
13 |
+
"Category": "news",
|
14 |
+
"Confidence": "π©",
|
15 |
+
"Info": "confirmed by webpage metadata and glotlid",
|
16 |
+
"Possible Parallel Languages": "many",
|
17 |
+
"Links": []
|
18 |
+
}
|
19 |
+
]
|
20 |
+
}
|
21 |
+
|
22 |
+
|
23 |
+
|
24 |
+
|