Instructions to use yanyoeurn/voice-scam-detector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Scikit-learn
How to use yanyoeurn/voice-scam-detector with Scikit-learn:
from huggingface_hub import hf_hub_download import joblib model = joblib.load( hf_hub_download("yanyoeurn/voice-scam-detector", "sklearn_model.joblib") ) # only load pickle files from sources you trust # read more about it here https://skops.readthedocs.io/en/stable/persistence.html - Notebooks
- Google Colab
- Kaggle
Voice Call Scam Detection Model
random_forest + TfidfVectorizer
(ngram (1, 3), max_features=5000).
Metrics (held-out test set)
| Accuracy | Precision | Recall | F1 | ROC-AUC |
|---|---|---|---|---|
| 1.0000 | 1.0000 | 1.0000 | 1.0000 | 1.0000 |
- Dataset:
BothBosu/scam-dialogue - Train / test samples: 1280 / 320
- Features: 5000
- Trained: 2026-01-20T13:39:06.270933
Files
voice_classifier.pklvoice_vectorizer.pkl
⚠️ scikit-learn version
Trained with scikit-learn 1.4.0. Install the same version
to avoid InconsistentVersionWarning and possible silent breakage:
pip install scikit-learn==1.4.0 joblib huggingface_hub
Usage
import joblib
from huggingface_hub import hf_hub_download
repo = "yanyoeurn/voice-scam-detector"
clf = joblib.load(hf_hub_download(repo, "voice_classifier.pkl"))
vec = joblib.load(hf_hub_download(repo, "voice_vectorizer.pkl"))
X = vec.transform(["your text here"])
print(clf.predict(X), clf.predict_proba(X))
- Downloads last month
- -