translate-es-tw

Part of the Windstorm Labs open model catalogue. Scores, licence and attribution for every model: https://windytranslate.com/models/translate-es-tw

Machine translation model, es to tw, published by Windstorm Labs.

Attribution

Derived from Helsinki-NLP/opus-mt-es-tw, licensed apache-2.0. Windstorm Labs did not train the original model. This notice provides the attribution the licence requires.

What was changed

The weights in this repository have been modified from the original. A LoRA fine-tune trained on parallel corpus data and merged into the base weights.

Method	windy-hallmark
Tensors modified	36 of 254
Max absolute weight delta	8.155e-05
Verified	tensor-by-tensor against the upstream original, 2026-07-26

The comparison is tensor-level rather than file-level: safetensors and PyTorch .bin containers hash differently even when the tensors inside are identical, so a file-hash mismatch would prove nothing.

Contents

A single transformers build in safetensors format, loadable directly:

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tok = AutoTokenizer.from_pretrained("WindyTranslate/translate-es-tw")
model = AutoModelForSeq2SeqLM.from_pretrained("WindyTranslate/translate-es-tw")

batch = tok(["<your text here>"], return_tensors="pt", padding=True)
print(tok.batch_decode(model.generate(**batch), skip_special_tokens=True))

Other builds of this pair, including CTranslate2 INT8, are not included in this repository.

Evaluation

Benchmark	chrF++	BLEU	Band
FLORES-200 dev, 48 sentences (Spanish → Twi)	30.89	7.04	Usable

Measured 2026-08-04; screening score, not a publication result. Bands: Excellent ≥60, Good 45–60, Usable 30–45, Limited 15–30, Not recommended <15 (chrF++).

Limitations

• A single language direction: es to tw.
• The evaluation above is a 48-sentence screening score, not a publication result. The weights are verified to differ from the original; that is a statement about provenance.
• Quality is not monotonic with model size or with the amount of fine-tuning applied.