Amharic Hate Speech Detection Model

• free: Non-hate speech content.
• hate: Hate speech content.

Model Details

• Model Name: DawitMelka/amharic-hate-speech-detection-mBERT
• Architecture: BERT-based model for sequence classification.
• Language: Amharic
• Problem Type: Binary classification

Use Cases

• Moderation: Flagging potentially harmful or offensive content in Amharic.
• Research: Analyzing trends in hate speech within Amharic texts.
• Content Filtering: Ensuring safe online environments.

Labels

• free: Indicates the input text does not contain hate speech.
• hate: Indicates the input text contains hate speech.

Example Usage

Hugging Face Inference API

Output

Local Deployment

1. Install dependencies:
   pip install fastapi uvicorn transformers torch
2. Create a Python file main.py:
   python

   1from fastapi import FastAPI, HTTPException 2from pydantic import BaseModel 3from transformers import AutoTokenizer, AutoModelForSequenceClassification 4import torch 5 6app = FastAPI() 7 8MODEL_NAME = "DawitMelka/amharic-hate-speech-detection-mBERT" 9tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME) 10model = AutoModelForSequenceClassification.from_pretrained(MODEL_NAME) 11 12class TextRequest(BaseModel): 13 text: str 14 15@app.post("/predict/") 16async def predict(request: TextRequest): 17 text = request.text 18 if not text.strip(): 19 raise HTTPException(status_code=400, detail="Text cannot be empty.") 20 21 inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True) 22 outputs = model(**inputs) 23 logits = outputs.logits 24 prediction = torch.argmax(logits, dim=1).item() 25 labels = {0: "free", 1: "hate"} 26 return {"text": text, "prediction": labels.get(prediction, "unknown")}
3. Start the FastAPI server:
   uvicorn main:app --reload
4. Test the API:
   bash

   1curl -X POST "http://127.0.0.1:8000/predict/" \ 2-H "Content-Type: application/json" \ 3-d '{"text": "ሰላም እንድት ነው"}'

Training Details

• Dataset: The model was fine-tuned on a curated dataset of Amharic texts labeled as hate or free speech.
• Base Model: mBERT
• Framework: Hugging Face Transformers

Limitations

• Bias: The model's predictions depend on the training data and may inherit any biases present in it.
• Language Scope: Designed for Amharic only and may not perform well on other languages.
• Context Understanding: May misclassify nuanced or ambiguous content.

License

Citation

@misc{amharic-hate-speech-detection,
  author = {Dawit Melka},
  title = {Amharic Hate Speech Detection Model},
  year = {2025},
  publisher = {Hugging Face},
  url = {https://huggingface.co/DawitMelka/amharic-hate-speech-detection-mBERT}
}

Acknowledgments