Multilingual Toxicity Classifier for 15 Languages (2025)
This is an instance of Glot500 that was fine-tuned on binary toxicity classification task based on our updated (2025) dataset textdetox/multilingual_toxicity_dataset.
Now, the models covers 15 languages from various language families:
| Language | Code | F1 Score |
|---|---|---|
| English | en | 0.9071 |
| Russian | ru | 0.9022 |
| Ukrainian | uk | 0.9075 |
| German | de | 0.6528 |
| Spanish | es | 0.7430 |
| Arabic | ar | 0.6207 |
| Amharic | am | 0.6676 |
| Hindi | hi | 0.7171 |
| Chinese | zh | 0.6483 |
| Italian | it | 0.5975 |
| French | fr | 0.9125 |
| Hinglish | hin | 0.7051 |
| Hebrew | he | 0.8911 |
| Japanese | ja | 0.9058 |
| Tatar | tt | 0.5834 |
How to use
import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained('textdetox/glot500-toxicity-classifier')
model = AutoModelForSequenceClassification.from_pretrained('textdetox/glot500-toxicity-classifier')
batch = tokenizer.encode("You are amazing!", return_tensors="pt")
output = model(batch)
# idx 0 for neutral, idx 1 for toxic
Citation
The model is prepared for TextDetox 2025 Shared Task evaluation.
Citation TBD soon.