Update README.md
Browse files
README.md
CHANGED
@@ -10,4 +10,29 @@ tags:
|
|
10 |
- Sentiment-Analysis
|
11 |
- Hate-Speech
|
12 |
- Finetuning-mBERT
|
13 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
- Sentiment-Analysis
|
11 |
- Hate-Speech
|
12 |
- Finetuning-mBERT
|
13 |
+
---
|
14 |
+
|
15 |
+
|
16 |
+
|
17 |
+
**<h1>Hate-Speech-Detection-in-Amharic-Language-mBERT</h1>**
|
18 |
+
|
19 |
+
This Hugging Face model card contains a machine learning model that uses fine-tuned mBERT to detect hate speech in Amharic language.
|
20 |
+
The model was fine-tuned using the Hugging Face Trainer API.
|
21 |
+
|
22 |
+
|
23 |
+
**<h1>Fine-Tuning</h1>**
|
24 |
+
|
25 |
+
This model was created by finetuning the mBERT model for the downstream task of Hate speech detection for the Amharic language.
|
26 |
+
The initial mBERT model used for finetuning is http://Davlan/bert-base-multilingual-cased-finetuned-amharic which was provided by Davlan on Huggingface.
|
27 |
+
|
28 |
+
**<h1>Dataset</h1>**
|
29 |
+
|
30 |
+
The model was fine-tuned on an Amharic Dataset that was made available by Mendeley Data (https://data.mendeley.com/datasets/ymtmxx385m).
|
31 |
+
The dataset contains 30,000 rows of Amharic text labeled as hate speech or not hate speech.
|
32 |
+
|
33 |
+
**<h1>Usage</h1>**
|
34 |
+
|
35 |
+
You can use the model through the Hugging Face Transformers library, either by directly loading the model in your Python code
|
36 |
+
or by using the Hugging Face model hub.
|
37 |
+
|
38 |
+
|