Text Classifier
Runs entirely in your browser — no data leaves your device
SVM Spam Detector
Loading models...
A Support Vector Machine (SVM) trained on an SMS spam dataset to classify messages as spam or ham. The model is converted to ONNX and served entirely in the browser via Transformers.js — no server required. The longer-term goal is to adapt this approach to detect AI-generated content on X.com.
Model performance
| Class | Precision | Recall | F1 | Support |
|---|---|---|---|---|
| Ham | 0.99 | 0.99 | 0.99 | 954 |
| Spam | 0.96 | 0.97 | 0.97 | 161 |
| Accuracy | 0.99 | 1115 | ||
| Macro avg | 0.98 | 0.98 | 0.98 | 1115 |
| Weighted avg | 0.99 | 0.99 | 0.99 | 1115 |