Commit
•
33426be
1
Parent(s):
120256b
Add basic tags and description to the README
Browse files
README.md
CHANGED
|
@@ -1 +1,32 @@
|
|
| 1 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- as
|
| 4 |
+
- bn
|
| 5 |
+
- gu
|
| 6 |
+
- hi
|
| 7 |
+
- mr
|
| 8 |
+
- ne
|
| 9 |
+
- or
|
| 10 |
+
- pa
|
| 11 |
+
- si
|
| 12 |
+
license: apache-2.0
|
| 13 |
+
datasets:
|
| 14 |
+
- oscar
|
| 15 |
+
tags:
|
| 16 |
+
- multilingual
|
| 17 |
+
- albert
|
| 18 |
+
- masked-language-modeling
|
| 19 |
+
- sentence-order-prediction
|
| 20 |
+
- fill-mask
|
| 21 |
+
- nlp
|
| 22 |
+
---
|
| 23 |
+
|
| 24 |
+
# XLMIndic Base Uniscript
|
| 25 |
+
|
| 26 |
+
Pretrained ALBERT model on the OSCAR corpus on the languages Assamese, Bengali, Gujarati, Hindi, Marathi,
|
| 27 |
+
Nepali, Oriya, Panjabi and Sinhala. Like ALBERT it was pretrained using as masked language modeling (MLM)
|
| 28 |
+
and a sentence order prediction (SOP) objective. This model was pretrained after transliterating the text
|
| 29 |
+
to ISO-15919 format using the Aksharamukha library. A demo of Aksharamukha library is hosted [here](https://aksharamukha.appspot.com/converter)
|
| 30 |
+
where you can transliterate your text and use it on our model on the inference widget.
|
| 31 |
+
|
| 32 |
+
|