---
language:
- en
- ckb
tags:
- translation
- marian
- opus-mt
- en-ckb
- sorani-kurdish
library_name: transformers
pipeline_tag: translation
---

# en-ckb Marian model

This repository contains a Marian NMT model for **English (`en`) -> Sorani Kurdish (`ckb`)** trained from the local `en-ckb` directory of the OPUS-MT training workspace.

## Model summary

- Direction: `en -> ckb`
- Architecture: Marian transformer
- Subword setup: SentencePiece `spm4k-spm4k`
- Primary uploaded checkpoint: `best-chrf`
- Training dataset selection: `InterdialectCorpus Tatoeba wikimedia tico-19 navinaananthan_kurdish_sorani_parallel_corpus`
- Validation set: `openlanguagedata_flores_plus`
- Test set recipe: `openlanguagedata_flores_plus`

## Best validation metrics seen in training logs

- BLEU: 14.2475 at epoch 42 / update 55000
- chrF: 45.1146 at epoch 44 / update 58000
- Perplexity: 8.6557 at epoch 31 / update 40000

## Files

- `config.json`: Hugging Face Transformers model config
- `generation_config.json`: default generation settings
- `model.safetensors`: converted Marian weights
- `source.spm`: source SentencePiece model
- `target.spm`: target SentencePiece model
- `vocab.json`: shared Marian vocabulary
- `tokenizer_config.json`: tokenizer metadata
- `special_tokens_map.json`: tokenizer special token mapping

## Usage

This repository uses the standard **Transformers Marian** layout, so you can load it directly:

```python
from transformers import MarianMTModel, MarianTokenizer

tokenizer = MarianTokenizer.from_pretrained("your-user/en-ckb-marian")
model = MarianMTModel.from_pretrained("your-user/en-ckb-marian")

inputs = tokenizer("Hello world", return_tensors="pt")
generated = model.generate(**inputs)
print(tokenizer.decode(generated[0], skip_special_tokens=True))
```

## Notes

- The weights were converted from the local Marian checkpoint into the Hugging Face `MarianMTModel` format.
- Review dataset and license compatibility before redistributing the model publicly.