IndoBERT Plagiarisme Detector

Model IndoBERT-base-p1 fine-tuned untuk deteksi plagiarisme teks bahasa Indonesia (3 kelas):

  • LABEL_0 โ†’ ๐ŸŸข Tidak Mirip
  • LABEL_1 โ†’ ๐ŸŸก Paraphrase
  • LABEL_2 โ†’ ๐Ÿ”ด Plagiarisme (literal/copy-paste)

Input model: Masukkan dua teks/kalimat (question1 dan question2), model akan prediksi kemiripannya.

Performa

  • Accuracy: 78.33% (test set 300 data)
  • Dataset: 3000 data balanced + augmentasi sintetik

Cara Pakai di Python

from transformers import pipeline

detector = pipeline("text-classification", model="putraharifin/tubes_deep_learning")
result = detector("Apa pengganti y?", "Apa pengganti y dong")
print(result)  # {'label': 'LABEL_2', 'score': 0.99}
Downloads last month
13
Safetensors
Model size
0.1B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support