Flaglab/nllb-600M-kamentsa-esp

NLLB-200 600M Spanish ↔ Kamëntsá

Neural machine translation between Spanish and Kamëntsá, a Colombian Indigenous language (Kamëntsá people, Sibundoy Valley, Putumayo). The model is bidirectional: it translates Spanish to Kamëntsá and Kamëntsá to Spanish.

Fine-tune of facebook/nllb-200-distilled-600M 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	Kamëntsá	kam_Latn	kbh

Results

SacreBLEU and chrF2 on the held-out test partition.

Direction	BLEU	chrF2
Spanish to Kamëntsá	6.36	27.72
Kamëntsá to Spanish	4.31	22.95

Usage

from transformers import AutoModelForSeq2SeqLM, NllbTokenizer

tok = NllbTokenizer.from_pretrained("Flaglab/nllb-600M-kamentsa-esp")
model = AutoModelForSeq2SeqLM.from_pretrained("Flaglab/nllb-600M-kamentsa-esp")

# Spanish to Kamëntsá
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("kam_Latn"))
print(tok.batch_decode(out, skip_special_tokens=True))

Training

• Base model: facebook/nllb-200-distilled-600M
• Strategy: Expanded bilingual corpus (full variant).
• Tokenizer: NLLB SentencePiece extended with a custom Kamëntsá 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.