YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Mongolian KenLM 5-gram Language Model
Trained for MonSub ASR post-processing.
Training Data
- Mongolian Wikipedia: 531,327 sentences
- CC-100 Mongolian: up to 5M sentences
- Common conversational phrases: 12,330
- Total: 543,675 sentences, 76.4 MB
Model
- Order: 5-gram (or 3-gram fallback)
- Format: KenLM binary (.bin)
- Size: 208.5 MB
Usage
import kenlm
model = kenlm.Model("mn_5gram.bin")
score = model.score("энэ бол тест өгүүлбэр")
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support