from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

# Load model and tokenizer
model_name = "Ibracadabra13/arabic-bert-hate-speech-detection"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

# Function to predict hate speech
def predict_hate_speech(text):
    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=128)
    
    with torch.no_grad():
        outputs = model(**inputs)
        predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
        predicted_class = torch.argmax(predictions, dim=-1).item()
        confidence = predictions[0][predicted_class].item()
    
    label_map = {0: 'Normal', 1: 'Hate Speech'}
    return {
        'prediction': label_map[predicted_class],
        'confidence': confidence,
        'is_hate_speech': predicted_class == 1
    }

# Example usage
result = predict_hate_speech("أنت حيوان حقير")
print(result)  # {'prediction': 'Hate Speech', 'confidence': 0.97, 'is_hate_speech': True}

Training Details

Training Data: Arabic Levantine Hate Speech Detection Dataset
Training Method: Fine-tuning with manual training loop
Epochs: 2
Batch Size: 4
Learning Rate: 2e-5
Optimizer: AdamW

Performance

Accuracy: 84.5%
Normal Text: 83% precision, 96% recall
Hate Speech: 90% precision, 65% recall

Limitations

This model is trained on a specific dataset and may not generalize well to all Arabic dialects or contexts. Use with caution in production environments.