---
language:
- ckb
- kur
license: apache-2.0
library_name: sentence-transformers
pipeline_tag: sentence-similarity
base_model: haryads/kurdish-roberta
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- kurdish
- sorani
- central-kurdish
- ckb
- embeddings
- semantic-search
- retrieval
---

# Kurdish Sorani Sentence Embedding Model

A **Kurdish Sorani sentence embedding model** for Central Kurdish (`ckb`). It
maps Kurdish sentences to 512-dimensional vectors for semantic search, retrieval
(RAG), clustering and sentence similarity.

Unlike the multilingual models adapted for Kurdish by vocabulary trimming, this
model was **trained on Kurdish text**: a RoBERTa base trained from scratch on a
1-million-sentence Kurdish corpus with a custom 32k Kurdish BPE tokenizer, then
fine-tuned with contrastive learning (MultipleNegativesRankingLoss) on ~22k
Kurdish sentence pairs with hard negatives.

If you searched for a "Kurdish sentence embedding model", a "Sorani semantic
search model", or a "ckb text embedding model" — this is one, and it is trained
on Kurdish rather than repurposed from a multilingual model.

## Usage

```python
from sentence_transformers import SentenceTransformer

model = SentenceTransformer("haryads/kurdish-sentence-embeddings")

sentences = [
    "کەشوهەوای ئەمڕۆ زۆر باراناوییە",
    "ئەمڕۆ ئاسمان دەگرێت و باران دەبارێت",
    "من حەزم لە خواردنی شۆربای نیسکە",
]
emb = model.encode(sentences)
print(model.similarity(emb, emb))
```

## Evaluation

Measured on an internal Kurdish benchmark: a retrieval task (match a sentence to
its lemmatized form among 1,000 candidates) and a topic-separation task (800
triplets). Compared against `paraphrase-multilingual-MiniLM-L12-v2` on identical
data.

| Model | Retrieval R@1 | MRR | Topic accuracy |
|-------|:---:|:---:|:---:|
| **This model** | **0.978** | **0.984** | **0.931** |
| paraphrase-multilingual-MiniLM-L12-v2 | 0.960 | 0.970 | 0.786 |
| RoBERTa base, mean-pooled (no fine-tuning) | 0.930 | 0.944 | 0.635 |

The model outperforms the multilingual baseline on Kurdish for both retrieval and
topic separation.

## Details

- Output dimension: 512
- Max sequence length: 128 tokens
- Pooling: mean, with L2 normalization
- Base: from-scratch Kurdish RoBERTa + 32k Kurdish BPE tokenizer
- Fine-tuning: MultipleNegativesRankingLoss on paraphrase, lemma and topic pairs
  with hard negatives
- Language: Central Kurdish / Sorani (`ckb`), Arabic script

## Intended use and limits

Best for Kurdish semantic search, retrieval (RAG), clustering and similarity.
Sorani only for now. Trained on news-heavy text, so very domain-specific or
colloquial input may need in-domain fine-tuning. For best results, normalize
input (Arabic vs. Kurdish `ی`/`ک`, ZWNJ, digits) before encoding.

## License

Apache-2.0.