Gladys-Ann-Varughese
commited on
Commit
•
f2530ea
1
Parent(s):
def87b5
Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- Arabic-model/Arabic_model.joblib +3 -0
- Arabic-model/config.json +17 -0
- Arabic-vectorizer/Arabic_vectorizer.joblib +3 -0
- Arabic-vectorizer/config.json +17 -0
- Bengali-model/Bengali_model.joblib +3 -0
- Bengali-model/config.json +17 -0
- Bengali-vectorizer/Bengali_vectorizer.joblib +3 -0
- Bengali-vectorizer/config.json +17 -0
- Cyrillic-model/Cyrillic_model.joblib +3 -0
- Cyrillic-model/config.json +17 -0
- Cyrillic-vectorizer/Cyrillic_vectorizer.joblib +3 -0
- Cyrillic-vectorizer/config.json +17 -0
- Devanagari-model/Devanagari_model.joblib +3 -0
- Devanagari-model/config.json +17 -0
- Devanagari-vectorizer/Devanagari_vectorizer.joblib +3 -0
- Devanagari-vectorizer/config.json +17 -0
- Ethiopic-model/Ethiopic_model.joblib +3 -0
- Ethiopic-model/config.json +17 -0
- Ethiopic-vectorizer/Ethiopic_vectorizer.joblib +3 -0
- Ethiopic-vectorizer/config.json +17 -0
- Gujarati-model/Gujarati_model.joblib +3 -0
- Gujarati-model/config.json +17 -0
- Gujarati-vectorizer/Gujarati_vectorizer.joblib +3 -0
- Gujarati-vectorizer/config.json +17 -0
- Gurmukhi-model/Gurmukhi_model.joblib +3 -0
- Gurmukhi-model/config.json +17 -0
- Gurmukhi-vectorizer/Gurmukhi_vectorizer.joblib +3 -0
- Gurmukhi-vectorizer/config.json +17 -0
- Hebrew-model/Hebrew_model.joblib +3 -0
- Hebrew-model/config.json +17 -0
- Hebrew-vectorizer/Hebrew_vectorizer.joblib +3 -0
- Hebrew-vectorizer/config.json +17 -0
- Latin-model/Latin_model.joblib +3 -0
- Latin-model/config.json +17 -0
- Latin-vectorizer/Latin_vectorizer.joblib +3 -0
- Latin-vectorizer/config.json +17 -0
- Malayalam-model/Malayalam_model.joblib +3 -0
- Malayalam-model/config.json +17 -0
- Malayalam-vectorizer/Malayalam_vectorizer.joblib +3 -0
- Malayalam-vectorizer/config.json +17 -0
- Myanmar-model/Myanmar_model.joblib +3 -0
- Myanmar-model/config.json +17 -0
- Myanmar-vectorizer/Myanmar_vectorizer.joblib +3 -0
- Myanmar-vectorizer/config.json +17 -0
- Oriya-model/Oriya_model.joblib +3 -0
- Oriya-model/config.json +17 -0
- Oriya-vectorizer/Oriya_vectorizer.joblib +3 -0
- Oriya-vectorizer/config.json +17 -0
- README.md +11 -0
- Tamil-model/Tamil_model.joblib +3 -0
Arabic-model/Arabic_model.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54f6eeda85676f11e3b1b2327e84b1bb1334477af6c72d0ffd5535f4dd499425
|
3 |
+
size 257351
|
Arabic-model/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"sklearn": {
|
3 |
+
"environment": [
|
4 |
+
"scikit-learn==1.5.2"
|
5 |
+
],
|
6 |
+
"example_input": {
|
7 |
+
"data": [
|
8 |
+
"\u0641\u064a \u0627\u0644\u0628\u062f\u0621 \u062e\u0644\u0642 \u0627\u0644\u0644\u0647 \u0627\u0644\u0633\u0645\u0627\u0648\u0627\u062a \u0648\u0627\u0644\u0623\u0631\u0636."
|
9 |
+
]
|
10 |
+
},
|
11 |
+
"model": {
|
12 |
+
"file": "Arabic_model.joblib"
|
13 |
+
},
|
14 |
+
"model_format": "pickle",
|
15 |
+
"task": "text-classification"
|
16 |
+
}
|
17 |
+
}
|
Arabic-vectorizer/Arabic_vectorizer.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5815f934a2b1ecf903a3f678fb5d1dc866a5577757215684241c64de23707b33
|
3 |
+
size 55565
|
Arabic-vectorizer/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"sklearn": {
|
3 |
+
"environment": [
|
4 |
+
"scikit-learn==1.5.2"
|
5 |
+
],
|
6 |
+
"example_input": {
|
7 |
+
"data": [
|
8 |
+
"\u0641\u064a \u0627\u0644\u0628\u062f\u0621 \u062e\u0644\u0642 \u0627\u0644\u0644\u0647 \u0627\u0644\u0633\u0645\u0627\u0648\u0627\u062a \u0648\u0627\u0644\u0623\u0631\u0636."
|
9 |
+
]
|
10 |
+
},
|
11 |
+
"model": {
|
12 |
+
"file": "Arabic_vectorizer.joblib"
|
13 |
+
},
|
14 |
+
"model_format": "pickle",
|
15 |
+
"task": "text-classification"
|
16 |
+
}
|
17 |
+
}
|
Bengali-model/Bengali_model.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84221aa6d1758ddda6bab53a66eb40c4bd4e9e37a58810d72296037893e09e57
|
3 |
+
size 96879
|
Bengali-model/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"sklearn": {
|
3 |
+
"environment": [
|
4 |
+
"scikit-learn==1.5.2"
|
5 |
+
],
|
6 |
+
"example_input": {
|
7 |
+
"data": [
|
8 |
+
"\u0986\u09a6\u09bf\u09a4\u09c7 \u0988\u09b6\u09cd\u09ac\u09f0\u09c7 \u0986\u0995\u09be\u09b6-\u09ae\u09a3\u09cd\u09a1\u09b2 \u0986\u09f0\u09c1 \u09aa\u09c3\u09a5\u09bf\u09f1\u09c0 \u09b8\u09c3\u09b7\u09cd\u099f\u09bf \u0995\u09f0\u09bf\u09b2\u09c7"
|
9 |
+
]
|
10 |
+
},
|
11 |
+
"model": {
|
12 |
+
"file": "Bengali_model.joblib"
|
13 |
+
},
|
14 |
+
"model_format": "pickle",
|
15 |
+
"task": "text-classification"
|
16 |
+
}
|
17 |
+
}
|
Bengali-vectorizer/Bengali_vectorizer.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:885dd5682bb07b0da245fff76118b9f1374eef1430333e24cd4e317777f7ca5f
|
3 |
+
size 60725
|
Bengali-vectorizer/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"sklearn": {
|
3 |
+
"environment": [
|
4 |
+
"scikit-learn==1.5.2"
|
5 |
+
],
|
6 |
+
"example_input": {
|
7 |
+
"data": [
|
8 |
+
"\u0986\u09a6\u09bf\u09a4\u09c7 \u0988\u09b6\u09cd\u09ac\u09f0\u09c7 \u0986\u0995\u09be\u09b6-\u09ae\u09a3\u09cd\u09a1\u09b2 \u0986\u09f0\u09c1 \u09aa\u09c3\u09a5\u09bf\u09f1\u09c0 \u09b8\u09c3\u09b7\u09cd\u099f\u09bf \u0995\u09f0\u09bf\u09b2\u09c7"
|
9 |
+
]
|
10 |
+
},
|
11 |
+
"model": {
|
12 |
+
"file": "Bengali_vectorizer.joblib"
|
13 |
+
},
|
14 |
+
"model_format": "pickle",
|
15 |
+
"task": "text-classification"
|
16 |
+
}
|
17 |
+
}
|
Cyrillic-model/Cyrillic_model.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1a7726f70372f8e0f2e7409105e5426a39b302b7493cb6d95153b2d7ab857de
|
3 |
+
size 193079
|
Cyrillic-model/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"sklearn": {
|
3 |
+
"environment": [
|
4 |
+
"scikit-learn==1.5.2"
|
5 |
+
],
|
6 |
+
"example_input": {
|
7 |
+
"data": [
|
8 |
+
"\u041d\u0430 \u043f\u0430\u0447\u0430\u0442\u043a\u0443 \u0441\u0442\u0432\u0430\u0440\u044b\u045e \u0411\u043e\u0433 \u043d\u0435\u0431\u0430 \u0456 \u0437\u044f\u043c\u043b\u044e"
|
9 |
+
]
|
10 |
+
},
|
11 |
+
"model": {
|
12 |
+
"file": "Cyrillic_model.joblib"
|
13 |
+
},
|
14 |
+
"model_format": "pickle",
|
15 |
+
"task": "text-classification"
|
16 |
+
}
|
17 |
+
}
|
Cyrillic-vectorizer/Cyrillic_vectorizer.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98b916213f9aa6839429b2ffa63b6710407625ffc639ad720a39bbe0dfeb12e9
|
3 |
+
size 55594
|
Cyrillic-vectorizer/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"sklearn": {
|
3 |
+
"environment": [
|
4 |
+
"scikit-learn==1.5.2"
|
5 |
+
],
|
6 |
+
"example_input": {
|
7 |
+
"data": [
|
8 |
+
"\u041d\u0430 \u043f\u0430\u0447\u0430\u0442\u043a\u0443 \u0441\u0442\u0432\u0430\u0440\u044b\u045e \u0411\u043e\u0433 \u043d\u0435\u0431\u0430 \u0456 \u0437\u044f\u043c\u043b\u044e"
|
9 |
+
]
|
10 |
+
},
|
11 |
+
"model": {
|
12 |
+
"file": "Cyrillic_vectorizer.joblib"
|
13 |
+
},
|
14 |
+
"model_format": "pickle",
|
15 |
+
"task": "text-classification"
|
16 |
+
}
|
17 |
+
}
|
Devanagari-model/Devanagari_model.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94fe2ec68c7b43adaf2a69c4f4c1aa32dd4ab30f52d63edb1d40ce786ee29cad
|
3 |
+
size 643303
|
Devanagari-model/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"sklearn": {
|
3 |
+
"environment": [
|
4 |
+
"scikit-learn==1.5.2"
|
5 |
+
],
|
6 |
+
"example_input": {
|
7 |
+
"data": [
|
8 |
+
"\u0906\u0926\u093f \u092e\u0947\u0902 \u092a\u0930\u092e\u0947\u0936\u094d\u0935\u0930 \u0928\u0947 \u0906\u0915\u093e\u0936 \u0914\u0930 \u092a\u0943\u0925\u094d\u0935\u0940 \u0915\u0940 \u0930\u091a\u0928\u093e \u0915\u0940"
|
9 |
+
]
|
10 |
+
},
|
11 |
+
"model": {
|
12 |
+
"file": "Devanagari_model.joblib"
|
13 |
+
},
|
14 |
+
"model_format": "pickle",
|
15 |
+
"task": "text-classification"
|
16 |
+
}
|
17 |
+
}
|
Devanagari-vectorizer/Devanagari_vectorizer.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf43cfa168e7ad26e2736da3176ac15f30e52be4ede00271c1da24534901b603
|
3 |
+
size 60483
|
Devanagari-vectorizer/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"sklearn": {
|
3 |
+
"environment": [
|
4 |
+
"scikit-learn==1.5.2"
|
5 |
+
],
|
6 |
+
"example_input": {
|
7 |
+
"data": [
|
8 |
+
"\u0906\u0926\u093f \u092e\u0947\u0902 \u092a\u0930\u092e\u0947\u0936\u094d\u0935\u0930 \u0928\u0947 \u0906\u0915\u093e\u0936 \u0914\u0930 \u092a\u0943\u0925\u094d\u0935\u0940 \u0915\u0940 \u0930\u091a\u0928\u093e \u0915\u0940"
|
9 |
+
]
|
10 |
+
},
|
11 |
+
"model": {
|
12 |
+
"file": "Devanagari_vectorizer.joblib"
|
13 |
+
},
|
14 |
+
"model_format": "pickle",
|
15 |
+
"task": "text-classification"
|
16 |
+
}
|
17 |
+
}
|
Ethiopic-model/Ethiopic_model.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:729a0b13600dcf93b5fed48afa180b3c8bf80538a9406cfe9bc8a86c4c906c3d
|
3 |
+
size 129047
|
Ethiopic-model/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"sklearn": {
|
3 |
+
"environment": [
|
4 |
+
"scikit-learn==1.5.2"
|
5 |
+
],
|
6 |
+
"example_input": {
|
7 |
+
"data": [
|
8 |
+
"\u12d3\u1265\u122b\u1203\u121c\u1293 \u12f3\u12cd\u1274\u1293\u12ae \u1343\u1333\u1222 \u121b\u12d4 \u12ec\u1231\u1235 \u12aa\u122a\u1235\u1276\u1234\u12ae \u123e\u12ed\u1295\u1276 \u12dc\u122d\u1343 \u1202\u12da\u12ac\u1366"
|
9 |
+
]
|
10 |
+
},
|
11 |
+
"model": {
|
12 |
+
"file": "Ethiopic_model.joblib"
|
13 |
+
},
|
14 |
+
"model_format": "pickle",
|
15 |
+
"task": "text-classification"
|
16 |
+
}
|
17 |
+
}
|
Ethiopic-vectorizer/Ethiopic_vectorizer.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc840de2ee28e445f2ff48e19396370871425ad2378620d9c28405afc6409eaf
|
3 |
+
size 57731
|
Ethiopic-vectorizer/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"sklearn": {
|
3 |
+
"environment": [
|
4 |
+
"scikit-learn==1.5.2"
|
5 |
+
],
|
6 |
+
"example_input": {
|
7 |
+
"data": [
|
8 |
+
"\u12d3\u1265\u122b\u1203\u121c\u1293 \u12f3\u12cd\u1274\u1293\u12ae \u1343\u1333\u1222 \u121b\u12d4 \u12ec\u1231\u1235 \u12aa\u122a\u1235\u1276\u1234\u12ae \u123e\u12ed\u1295\u1276 \u12dc\u122d\u1343 \u1202\u12da\u12ac\u1366"
|
9 |
+
]
|
10 |
+
},
|
11 |
+
"model": {
|
12 |
+
"file": "Ethiopic_vectorizer.joblib"
|
13 |
+
},
|
14 |
+
"model_format": "pickle",
|
15 |
+
"task": "text-classification"
|
16 |
+
}
|
17 |
+
}
|
Gujarati-model/Gujarati_model.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09e13a20f447b2b2895be2e5c6ddb86d23dbd5b406e21f2ef2fcf6c387763de1
|
3 |
+
size 64839
|
Gujarati-model/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"sklearn": {
|
3 |
+
"environment": [
|
4 |
+
"scikit-learn==1.5.2"
|
5 |
+
],
|
6 |
+
"example_input": {
|
7 |
+
"data": [
|
8 |
+
"\u0aaa\u0acd\u0ab0\u0abe\u0ab0\u0a82\u0aad\u0ac7 \u0a88\u0ab6\u0acd\u0ab5\u0ab0\u0ac7 \u0a86\u0a95\u0abe\u0ab6 \u0aa4\u0aa5\u0abe \u0aaa\u0ac3\u0aa5\u0acd\u0ab5\u0ac0 \u0a89\u0aa4\u0acd\u0aaa\u0aa8\u0acd\u0aa8 \u0a95\u0ab0\u0acd\u0aaf\u0abe\u0a82"
|
9 |
+
]
|
10 |
+
},
|
11 |
+
"model": {
|
12 |
+
"file": "Gujarati_model.joblib"
|
13 |
+
},
|
14 |
+
"model_format": "pickle",
|
15 |
+
"task": "text-classification"
|
16 |
+
}
|
17 |
+
}
|
Gujarati-vectorizer/Gujarati_vectorizer.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90ff0043e86901dd16be792f992e43c617ce0fbb140a03fde8651762df9f132d
|
3 |
+
size 61031
|
Gujarati-vectorizer/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"sklearn": {
|
3 |
+
"environment": [
|
4 |
+
"scikit-learn==1.5.2"
|
5 |
+
],
|
6 |
+
"example_input": {
|
7 |
+
"data": [
|
8 |
+
"\u0aaa\u0acd\u0ab0\u0abe\u0ab0\u0a82\u0aad\u0ac7 \u0a88\u0ab6\u0acd\u0ab5\u0ab0\u0ac7 \u0a86\u0a95\u0abe\u0ab6 \u0aa4\u0aa5\u0abe \u0aaa\u0ac3\u0aa5\u0acd\u0ab5\u0ac0 \u0a89\u0aa4\u0acd\u0aaa\u0aa8\u0acd\u0aa8 \u0a95\u0ab0\u0acd\u0aaf\u0abe\u0a82"
|
9 |
+
]
|
10 |
+
},
|
11 |
+
"model": {
|
12 |
+
"file": "Gujarati_vectorizer.joblib"
|
13 |
+
},
|
14 |
+
"model_format": "pickle",
|
15 |
+
"task": "text-classification"
|
16 |
+
}
|
17 |
+
}
|
Gurmukhi-model/Gurmukhi_model.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71c5b995c7abbd240bd321fd41fad374d3744e03e5412c8f7951059de129138c
|
3 |
+
size 64839
|
Gurmukhi-model/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"sklearn": {
|
3 |
+
"environment": [
|
4 |
+
"scikit-learn==1.5.2"
|
5 |
+
],
|
6 |
+
"example_input": {
|
7 |
+
"data": [
|
8 |
+
"\u0a06\u0a26 \u0a35\u0a3f\u0a71\u0a1a \u0a2a\u0a30\u0a2e\u0a47\u0a38\u0a3c\u0a41\u0a30 \u0a28\u0a47 \u0a05\u0a15\u0a3e\u0a38\u0a3c \u0a05\u0a24\u0a47 \u0a27\u0a30\u0a24\u0a40 \u0a28\u0a42\u0a70 \u0a38\u0a3f\u0a30\u0a1c\u0a3f\u0a06"
|
9 |
+
]
|
10 |
+
},
|
11 |
+
"model": {
|
12 |
+
"file": "Gurmukhi_model.joblib"
|
13 |
+
},
|
14 |
+
"model_format": "pickle",
|
15 |
+
"task": "text-classification"
|
16 |
+
}
|
17 |
+
}
|
Gurmukhi-vectorizer/Gurmukhi_vectorizer.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:183568afc8f54fa9ce05bff6f9b10d2ab91776e1cdb4644f3c2838cf6daaf881
|
3 |
+
size 60784
|
Gurmukhi-vectorizer/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"sklearn": {
|
3 |
+
"environment": [
|
4 |
+
"scikit-learn==1.5.2"
|
5 |
+
],
|
6 |
+
"example_input": {
|
7 |
+
"data": [
|
8 |
+
"\u0a06\u0a26 \u0a35\u0a3f\u0a71\u0a1a \u0a2a\u0a30\u0a2e\u0a47\u0a38\u0a3c\u0a41\u0a30 \u0a28\u0a47 \u0a05\u0a15\u0a3e\u0a38\u0a3c \u0a05\u0a24\u0a47 \u0a27\u0a30\u0a24\u0a40 \u0a28\u0a42\u0a70 \u0a38\u0a3f\u0a30\u0a1c\u0a3f\u0a06"
|
9 |
+
]
|
10 |
+
},
|
11 |
+
"model": {
|
12 |
+
"file": "Gurmukhi_vectorizer.joblib"
|
13 |
+
},
|
14 |
+
"model_format": "pickle",
|
15 |
+
"task": "text-classification"
|
16 |
+
}
|
17 |
+
}
|
Hebrew-model/Hebrew_model.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40bd498f557a99905438cefaf7642b64891d574af74df4dab2eb6c9deb3a9891
|
3 |
+
size 64887
|
Hebrew-model/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"sklearn": {
|
3 |
+
"environment": [
|
4 |
+
"scikit-learn==1.5.2"
|
5 |
+
],
|
6 |
+
"example_input": {
|
7 |
+
"data": [
|
8 |
+
"\u05d1\u05e8\u05d0\u05e9\u05d9\u05ea \u05d1\u05e8\u05d0 \u05d0\u05dc\u05d4\u05d9\u05dd \u05d0\u05ea \u05d4\u05e9\u05de\u05d9\u05dd \u05d5\u05d0\u05ea \u05d4\u05d0\u05e8\u05e5"
|
9 |
+
]
|
10 |
+
},
|
11 |
+
"model": {
|
12 |
+
"file": "Hebrew_model.joblib"
|
13 |
+
},
|
14 |
+
"model_format": "pickle",
|
15 |
+
"task": "text-classification"
|
16 |
+
}
|
17 |
+
}
|
Hebrew-vectorizer/Hebrew_vectorizer.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e8815b653d564a33ab755f985c287c6df0e3dc2a01ea0adc1ea082c0eab6cc8
|
3 |
+
size 55845
|
Hebrew-vectorizer/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"sklearn": {
|
3 |
+
"environment": [
|
4 |
+
"scikit-learn==1.5.2"
|
5 |
+
],
|
6 |
+
"example_input": {
|
7 |
+
"data": [
|
8 |
+
"\u05d1\u05e8\u05d0\u05e9\u05d9\u05ea \u05d1\u05e8\u05d0 \u05d0\u05dc\u05d4\u05d9\u05dd \u05d0\u05ea \u05d4\u05e9\u05de\u05d9\u05dd \u05d5\u05d0\u05ea \u05d4\u05d0\u05e8\u05e5"
|
9 |
+
]
|
10 |
+
},
|
11 |
+
"model": {
|
12 |
+
"file": "Hebrew_vectorizer.joblib"
|
13 |
+
},
|
14 |
+
"model_format": "pickle",
|
15 |
+
"task": "text-classification"
|
16 |
+
}
|
17 |
+
}
|
Latin-model/Latin_model.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c3b095d092fb3020e752e3d4a1f19d8d80f619edcd46465ed363b2022127b3e
|
3 |
+
size 25802695
|
Latin-model/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"sklearn": {
|
3 |
+
"environment": [
|
4 |
+
"scikit-learn==1.5.2"
|
5 |
+
],
|
6 |
+
"example_input": {
|
7 |
+
"data": [
|
8 |
+
"In the beginning God created the heavens and the earth."
|
9 |
+
]
|
10 |
+
},
|
11 |
+
"model": {
|
12 |
+
"file": "Latin_model.joblib"
|
13 |
+
},
|
14 |
+
"model_format": "pickle",
|
15 |
+
"task": "text-classification"
|
16 |
+
}
|
17 |
+
}
|
Latin-vectorizer/Latin_vectorizer.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78adcfbe3c5b99843fc6beaaf399767dbc190c7e0fda183c132ba3c013a4fcb1
|
3 |
+
size 50646
|
Latin-vectorizer/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"sklearn": {
|
3 |
+
"environment": [
|
4 |
+
"scikit-learn==1.5.2"
|
5 |
+
],
|
6 |
+
"example_input": {
|
7 |
+
"data": [
|
8 |
+
"In the beginning God created the heavens and the earth."
|
9 |
+
]
|
10 |
+
},
|
11 |
+
"model": {
|
12 |
+
"file": "Latin_vectorizer.joblib"
|
13 |
+
},
|
14 |
+
"model_format": "pickle",
|
15 |
+
"task": "text-classification"
|
16 |
+
}
|
17 |
+
}
|
Malayalam-model/Malayalam_model.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a62b144a8eca51036e64d3e6e33fc3b6936cbcdd358822826ca11bce8bbc6f65
|
3 |
+
size 64855
|
Malayalam-model/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"sklearn": {
|
3 |
+
"environment": [
|
4 |
+
"scikit-learn==1.5.2"
|
5 |
+
],
|
6 |
+
"example_input": {
|
7 |
+
"data": [
|
8 |
+
"\u0d06\u0d26\u0d3f\u0d2f\u0d3f\u0d7d \u0d26\u0d48\u0d35\u0d02 \u0d06\u0d15\u0d3e\u0d36\u0d35\u0d41\u0d02 \u0d2d\u0d42\u0d2e\u0d3f\u0d2f\u0d41\u0d02 \u0d38\u0d43\u0d37\u0d4d\u0d1f\u0d3f\u0d1a\u0d4d\u0d1a\u0d41"
|
9 |
+
]
|
10 |
+
},
|
11 |
+
"model": {
|
12 |
+
"file": "Malayalam_model.joblib"
|
13 |
+
},
|
14 |
+
"model_format": "pickle",
|
15 |
+
"task": "text-classification"
|
16 |
+
}
|
17 |
+
}
|
Malayalam-vectorizer/Malayalam_vectorizer.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0eed565355931fe25e4fdd5227643c240101fbf5c053ef0981593fdd11c479e5
|
3 |
+
size 61231
|
Malayalam-vectorizer/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"sklearn": {
|
3 |
+
"environment": [
|
4 |
+
"scikit-learn==1.5.2"
|
5 |
+
],
|
6 |
+
"example_input": {
|
7 |
+
"data": [
|
8 |
+
"\u0d06\u0d26\u0d3f\u0d2f\u0d3f\u0d7d \u0d26\u0d48\u0d35\u0d02 \u0d06\u0d15\u0d3e\u0d36\u0d35\u0d41\u0d02 \u0d2d\u0d42\u0d2e\u0d3f\u0d2f\u0d41\u0d02 \u0d38\u0d43\u0d37\u0d4d\u0d1f\u0d3f\u0d1a\u0d4d\u0d1a\u0d41"
|
9 |
+
]
|
10 |
+
},
|
11 |
+
"model": {
|
12 |
+
"file": "Malayalam_vectorizer.joblib"
|
13 |
+
},
|
14 |
+
"model_format": "pickle",
|
15 |
+
"task": "text-classification"
|
16 |
+
}
|
17 |
+
}
|
Myanmar-model/Myanmar_model.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16066463e965d01b37f101fa8c071c106d8d3acea729843d0f86a96d35746ec8
|
3 |
+
size 64839
|
Myanmar-model/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"sklearn": {
|
3 |
+
"environment": [
|
4 |
+
"scikit-learn==1.5.2"
|
5 |
+
],
|
6 |
+
"example_input": {
|
7 |
+
"data": [
|
8 |
+
"\u1018\u102f\u200b\u101b\u102c\u1038\u200b\u101e\u200b\u1001\u1004\u103a\u200b\u101e\u100a\u103a\u200b\u1005\u200b\u1000\u103c\u200b\u101d\u200b\u1020\u102c\u200b\u1000\u102d\u102f\u200b\u1016\u1014\u103a\u200b\u1006\u1004\u103a\u1038 \u1010\u1031\u102c\u103a\u200b\u1019\u1030\u200b\u101e\u1031\u102c\u200b\u1021\u200b\u1001\u102b"
|
9 |
+
]
|
10 |
+
},
|
11 |
+
"model": {
|
12 |
+
"file": "Myanmar_model.joblib"
|
13 |
+
},
|
14 |
+
"model_format": "pickle",
|
15 |
+
"task": "text-classification"
|
16 |
+
}
|
17 |
+
}
|
Myanmar-vectorizer/Myanmar_vectorizer.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b81245e609b53030136a3489a89e7bc1f7d34903776085172597d88c9ed9c06c
|
3 |
+
size 60711
|
Myanmar-vectorizer/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"sklearn": {
|
3 |
+
"environment": [
|
4 |
+
"scikit-learn==1.5.2"
|
5 |
+
],
|
6 |
+
"example_input": {
|
7 |
+
"data": [
|
8 |
+
"\u1018\u102f\u200b\u101b\u102c\u1038\u200b\u101e\u200b\u1001\u1004\u103a\u200b\u101e\u100a\u103a\u200b\u1005\u200b\u1000\u103c\u200b\u101d\u200b\u1020\u102c\u200b\u1000\u102d\u102f\u200b\u1016\u1014\u103a\u200b\u1006\u1004\u103a\u1038 \u1010\u1031\u102c\u103a\u200b\u1019\u1030\u200b\u101e\u1031\u102c\u200b\u1021\u200b\u1001\u102b"
|
9 |
+
]
|
10 |
+
},
|
11 |
+
"model": {
|
12 |
+
"file": "Myanmar_vectorizer.joblib"
|
13 |
+
},
|
14 |
+
"model_format": "pickle",
|
15 |
+
"task": "text-classification"
|
16 |
+
}
|
17 |
+
}
|
Oriya-model/Oriya_model.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d63134c06c421cee8fce7e5f0cc7c1fe0124c55d5d2f0bbf3c876c0830e6d6f2
|
3 |
+
size 64839
|
Oriya-model/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"sklearn": {
|
3 |
+
"environment": [
|
4 |
+
"scikit-learn==1.5.2"
|
5 |
+
],
|
6 |
+
"example_input": {
|
7 |
+
"data": [
|
8 |
+
"\u0b06\u0b26\u0b4d\u0b5f\u0b30\u0b47 \u0b2a\u0b30\u0b2e\u0b47\u0b36\u0b4d\u0b71\u0b30 \u0b38\u0b4d\u0b71\u0b30\u0b4d\u0b17\u0b38\u0b2e\u0b42\u0b39 \u0b13 \u0b2a\u0b43\u0b25\u0b3f\u0b2c\u0b40\u0b15\u0b41 \u0b38\u0b43\u0b37\u0b4d\u0b1f\u0b3f \u0b15\u0b32\u0b47"
|
9 |
+
]
|
10 |
+
},
|
11 |
+
"model": {
|
12 |
+
"file": "Oriya_model.joblib"
|
13 |
+
},
|
14 |
+
"model_format": "pickle",
|
15 |
+
"task": "text-classification"
|
16 |
+
}
|
17 |
+
}
|
Oriya-vectorizer/Oriya_vectorizer.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc3e85eb93609f14ea38a88db0892f5f7db8056f60da0b6640dcc164496ef318
|
3 |
+
size 60971
|
Oriya-vectorizer/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"sklearn": {
|
3 |
+
"environment": [
|
4 |
+
"scikit-learn==1.5.2"
|
5 |
+
],
|
6 |
+
"example_input": {
|
7 |
+
"data": [
|
8 |
+
"\u0b06\u0b26\u0b4d\u0b5f\u0b30\u0b47 \u0b2a\u0b30\u0b2e\u0b47\u0b36\u0b4d\u0b71\u0b30 \u0b38\u0b4d\u0b71\u0b30\u0b4d\u0b17\u0b38\u0b2e\u0b42\u0b39 \u0b13 \u0b2a\u0b43\u0b25\u0b3f\u0b2c\u0b40\u0b15\u0b41 \u0b38\u0b43\u0b37\u0b4d\u0b1f\u0b3f \u0b15\u0b32\u0b47"
|
9 |
+
]
|
10 |
+
},
|
11 |
+
"model": {
|
12 |
+
"file": "Oriya_vectorizer.joblib"
|
13 |
+
},
|
14 |
+
"model_format": "pickle",
|
15 |
+
"task": "text-classification"
|
16 |
+
}
|
17 |
+
}
|
README.md
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Multi-Script Language Identifier
|
2 |
+
|
3 |
+
This repository contains models and vectorizers for identifying languages written in various scripts. Each script has a corresponding model (`model.joblib`) and vectorizer (`vectorizer.joblib`).
|
4 |
+
|
5 |
+
## How It Works
|
6 |
+
- The `vectorizer.joblib` preprocesses text for the model.
|
7 |
+
- The `model.joblib` predicts the language based on the preprocessed input.
|
8 |
+
|
9 |
+
## Files
|
10 |
+
- `model.joblib`: Trained model for a specific script.
|
11 |
+
- `vectorizer.joblib`: Preprocessor required for the corresponding model.
|
Tamil-model/Tamil_model.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f74261fad5500517b3ccc72185eff5f222491324f6c2c61caa05b0677da8fdf4
|
3 |
+
size 64839
|