🇭🇹KreyòlAI
English → Haitian Creole · Domain-aware translation for humanitarian and healthcare work
Healthcare — 250-sentence held-out human-translated medical test set (CMU NESPOLE corpus), English → Haitian Creole:
| Model | BLEU | chrF | TER (lower is better) |
|---|---|---|---|
| Google Translate | 30.87 | 58.44 | 47.90 |
| Base NLLB-200 | 30.03 | 56.46 | 50.56 |
| KreyolAI Healthcare v3 | 29.87 | 56.94 | 49.44 |
Education — results differ by test set:
| Test set | Model | BLEU | chrF | TER (lower is better) |
|---|---|---|---|---|
| MIT-Haiti (human-translated) | Base NLLB-200 | 25.87 | 48.28 | — |
| MIT-Haiti (human-translated) | KreyolAI Education v1 | 28.63 | 50.90 | — |
Humanitarian — mined test set, preliminary result:
| Model | BLEU | chrF | TER (lower is better) |
|---|---|---|---|
| Base NLLB-200 | 28.26 | 54.54 | 55.53 |
| KreyolAI Humanitarian v1 | 29.23 | 55.87 | 54.05 |
Honest interpretation: These models range from roughly tied to modestly ahead of the base model. The real value isn't a higher score, it's a free, offline, domain-specialized translator for a language most providers treat as an afterthought.
Full details: huggingface.co/dondodoai
If the translation is wrong, submit the correct version below. Every correction helps improve the model! 🙏
| Domain |
|---|
Built on NLLB-200 1.3B with domain-specific LoRA adapters · Healthcare · Humanitarian · Education · General
dondodoai · Purpose-built for humanitarian AI in 🇭🇹 Haiti