Downloads · 30 days
0
openpecha/tibetan-outline-boundary-crf-unbiased
tibetan-outline-boundary-crf-unbiased is a token classification model from openpecha. Use it when you need labels on individual words, such as names. It is set up for sklearn-crfsuite. The card lists the license as apache-2.0.
CRF model trained on the full corpus minus all unique-benchmark snippet strings (~50,880 snippets). No benchmark leakage — use this model when reporting scores on the unique split.
Downloads · 30 days
0
Access
Public
Updated Jun 5, 2026
Repo size
919 KB
Likes
0
Public
Click a slice to open those files.
.pkl919 KB · 100%
From the Hugging Face model README
CRF model trained on the full corpus minus all unique-benchmark snippet strings (~50,880 snippets). No benchmark leakage — use this model when reporting scores on the unique split.
| Precision | Recall | F1 |
|---|---|---|
| 0.752 | 0.440 | 0.555 |
pip install "outline-detection[crf]"
hf download ganga4364/tibetan-outline-boundary-crf-unbiased boundary_crf.pkl --local-dir ./models
outline-detect crf predict input.txt --model ./models/boundary_crf.pkl -o output.txt
from outline_detection.crf import CRFBoundaryDetector
det = CRFBoundaryDetector()
det.load("boundary_crf.pkl")
positions = det.predict_positions(clean_tibetan_text)
Pickle files load executable objects. Only use models from this trusted repository.