Downloads · 30 days
10
4% of all-time downloads
zomi-crf-syllabifier
zomi-language-corpora/zomi-crf-syllabifier
zomi-crf-syllabifier is a machine learning model from zomi-language-corpora. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
250
Public
Repo size
570 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.joblib197 KB · 99%
At a glance
- Model type
- CRF
- Access
- Public
- Created
- Jun 14, 2026
- Updated
- Jun 21, 2026
- SHA
- 07b0bbe6
Model card
From the Hugging Face model README
Zomi CRF Syllabifier
A CRF-based syllabifier for Zomi.
📦 Model Overview
- Model type: CRF
- Task: Syllabification
- Version: cad781dd4d43dd3768f2c6f96a6787c38f5807d4
- Trained: Sun Jun 21 22:14:02 UTC 2026
- Framework: sklearn-crfsuite
- License: MIT
📊 Evaluation Metrics
| Metric | Value |
|---|---|
| Accuracy | 0.9979683055668428 |
| Precision | 0.9976499229235597 |
| Recall | 0.9977904992143529 |
| F1 Score | 0.9977201604146757 |
Metrics computed on:
data/zomi_only.tsv
📚 Training Data
- Dataset:
data/zomi_only.tsv - Total rows:
- Avg syllables per word: 2.43
- Avg characters per word:
🔍 How It Works
Hyphen-aware, syllable-level CRF segmentation.
🚀 Usage Example
from predict import predict_syllables
print(predict_syllables("thungetna-ah"))
- Type
- CRF
- Created
- Jun 14, 2026
- Updated
- Jun 21, 2026