Downloads · 30 days
55
7% of all-time downloads
EA-HS
KSvendsen/EA-HS
EA-HS is a text classification model from KSvendsen. Use it when you need a label for a piece of text. The card lists the license as apache-2.0.
Multilingual hate speech classifier for East African languages, built for conflict monitoring and peacebuilding applications.
All-time downloads
778
Public
Parameters
278M
17.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt2.2 GB · 66%
At a glance
- Task
- Text Classification
- License
- apache-2.0
- Model type
- xlm-roberta
- Access
- Public
- Created
- Feb 13, 2026
- Updated
- Feb 20, 2026
- SHA
- 2c911ac8
Datasets
Model card
From the Hugging Face model README
EA-HS: East Africa Hate Speech Classifier v3
Multilingual hate speech classifier for East African languages, built for conflict monitoring and peacebuilding applications.
Model Details
- Base model: Davlan/afro-xlmr-base (Africa-focused XLM-RoBERTa)
- Fine-tuned on: AfriHate (7 African languages) + HatEval (Arabic) + HateXplain (English)
- Labels: 0 (not hate), 1 (hate), 2 (offensive)
- Languages: Swahili, Somali, Amharic, Oromo, Tigrinya, Kinyarwanda, Nigerian Pidgin, Arabic, English
Performance
| Version | Base Model | Accuracy | F1 |
|---|---|---|---|
| v3 (current) | afro-xlmr-base | 77.10% | 76.87% |
| v2 | xlm-roberta-base | 76.18% | 75.99% |
Usage
from transformers import pipeline
classifier = pipeline('text-classification', model='KSvendsen/EA-HS')
result = classifier('This is a test sentence')
Training
- 5 epochs, batch size 16, learning rate 2e-5
- Class-weighted loss + minority upsampling
- ~95k training samples across 9 languages
Developed by
MERLx / RIKO - AI-augmented conflict monitoring
- Task
- Text Classification
- Type
- xlm-roberta
- License
- apache-2.0
- Languages
- sw, so, am, om, ti, rw
- Created
- Feb 13, 2026
- Updated
- Feb 20, 2026