NLLB-200 1.3B Spanish ↔ Wayuunaiki
Neural machine translation between Spanish and Wayuunaiki, a Colombian Indigenous language (Wayuu people, La Guajira, in Colombia and Venezuela). The model is bidirectional: it translates Spanish to Wayuunaiki and Wayuunaiki to Spanish.
Fine-tune of facebook/nllb-200-1.3B from the thesis Data-Centric Strategies for Low-Resource Neural Machine Translation in Colombian Indigenous Languages (Universidad de los Andes, FLAG Lab).
Languages
| Role | Language | Tokenizer code | ISO 639-3 |
|---|---|---|---|
| Source / target | Spanish | spa_Latn | spa |
| Source / target | Wayuunaiki | way_Latn | guc |
Results
SacreBLEU and chrF2 on the held-out test partition.
| Direction | BLEU | chrF2 |
|---|---|---|
| Spanish to Wayuunaiki | 19.78 | 43.08 |
| Wayuunaiki to Spanish | 17.06 | 33.08 |
Usage
from transformers import AutoModelForSeq2SeqLM, NllbTokenizer
tok = NllbTokenizer.from_pretrained("Flaglab/nllb-1.3B-wayuunaiki-esp-backtranslation")
model = AutoModelForSeq2SeqLM.from_pretrained("Flaglab/nllb-1.3B-wayuunaiki-esp-backtranslation")
# Spanish to Wayuunaiki
tok.src_lang = "spa_Latn"
inputs = tok("Buenos días, ¿cómo estás?", return_tensors="pt")
out = model.generate(**inputs, forced_bos_token_id=tok.convert_tokens_to_ids("way_Latn"))
print(tok.batch_decode(out, skip_special_tokens=True))
Training
- Base model: facebook/nllb-200-1.3B
- Strategy: Without-dictionary corpus variant with backtranslation from monolingual Wayuunaiki.
- Tokenizer: NLLB SentencePiece extended with a custom Wayuunaiki vocabulary.
License and intended use
Released under CC-BY-NC 4.0, inherited from NLLB-200: non-commercial use only. Intended for research on machine translation for Colombian Indigenous languages. Outputs have not been validated by human speakers.