Instructions to use Singaraj/morisien-embed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Singaraj/morisien-embed with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Singaraj/morisien-embed") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Try it in your browser: interactive demo for morisien-embed
I built an in-browser demo so you can try this model without any setup:
https://huggingface.co/spaces/Singaraj/morisien-embed-demo
It runs entirely on your device (via transformers.js) — your text is never sent anywhere. Two things to try:
- Meaning similarity — enter any two sentences (Creole, English, French, or a mix) and see how close they are in meaning.
- Cross-lingual search — type a Creole sentence and it finds the closest match among candidate sentences.
morisien-embed is, to my knowledge, the first dedicated embedding model for Mauritian Creole (Kreol Morisien). It beats LaBSE on held-out bitext retrieval in all three measured directions, and the full training pipeline, benchmark and audits are public.
If you speak Kreol Morisien, I would genuinely value your feedback — especially where it gets things wrong (slang, everyday phrases, idioms). That is exactly the signal the next version needs. Mersi.