Update README.md
Browse files
README.md
CHANGED
|
@@ -4,4 +4,16 @@ language:
|
|
| 4 |
- bn
|
| 5 |
- hi
|
| 6 |
pipeline_tag: text-classification
|
| 7 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
- bn
|
| 5 |
- hi
|
| 6 |
pipeline_tag: text-classification
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
This model is a finetuned version of ```google-bert/bert-base-multilingual-uncased``` model in the **Bengali** and **Hindi** languages.
|
| 10 |
+
|
| 11 |
+
The dataset used is a Kaggle Dataset - [Modified-hate-speech-bengali-hindi](https://www.kaggle.com/datasets/abirmondal/modified-hate-speech-bengali-hindi)
|
| 12 |
+
|
| 13 |
+
This model can classify Bengali and Hindi texts into the following 5 classes:
|
| 14 |
+
- text
|
| 15 |
+
- defamation
|
| 16 |
+
- hate
|
| 17 |
+
- non-hate
|
| 18 |
+
- violence
|
| 19 |
+
- vulgar
|