YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
Khmer N-gram Language Models
This repository contains KenLM n-gram language models for Khmer language.
Files
khmer_bigrams.binary: Bigram language modelkhmer_trigrams.binary: Trigram language model
Usage
import kenlm
# Load models
bigram_model = kenlm.LanguageModel("khmer_bigrams.binary")
trigram_model = kenlm.LanguageModel("khmer_trigrams.binary")
# Score a sentence
sentence = "αααα»α αααααΆαα ααΆααΆ ααααα α"
bigram_score = bigram_model.score(sentence)
trigram_score = trigram_model.score(sentence)
print(f"Bigram score: {bigram_score}")
print(f"Trigram score: {trigram_score}")
Installation
pip install kenlm
Download Models
from huggingface_hub import hf_hub_download
# Download bigram model
bigram_path = hf_hub_download(
repo_id="YOUR_USERNAME/khmer-ngram-models",
filename="khmer_bigrams.binary"
)
# Download trigram model
trigram_path = hf_hub_download(
repo_id="YOUR_USERNAME/khmer-ngram-models",
filename="khmer_trigrams.binary"
)
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
π
Ask for provider support