Modelpublic

WindyWord/translate-windy-hplt-ta-en

sourceHugging Facecc-by-4.0updated 2mo agoView on Hugging Face

0likes7downloads

Model Card

translate-windy-hplt-ta-en — ta to en

CTranslate2 INT8 bilingual translation model, derived from `HPLT/translate-ta-en-v2.0-hplt_opus` (the HPLT project, CC-BY-4.0).

CC-BY-4.0 permits commercial use and modification and requires attribution; this notice provides it. Windstorm Labs did not train the base model.

Recovery note

HPLT publishes native Marian (.npz + .spm + .vocab) and marks its repos inference: false. An earlier conversion of this model to transformers format corrupted the weights, producing untranslatable output, and the model was written off. It was recovered on 2026-07-26 by converting the original .npz with the official Marian converter. The model was always fine; the conversion was not.

What was changed

A deliberately minimal LoRA fine-tune ("windy hallmark") merged into the base weights.


Rank / alpha	8 / 16
Learning rate / steps	2.5e-06 / 50
Target modules	`q_proj`, `v_proj`
Seed	42 (reproducible)
Training data	opus100_ta-en (clinic cache), 2000 sentence pairs
Tensors modified	36
Max absolute weight delta	2.822e-05

Provenance

base   model.bin sha256  35f781d4779867b8af76611842feec8dda2768c9185104767f531fac2ae54cda
this   model.bin sha256  a42a5417b01e3a038ac21a29b32ee6d9821f3d53b66f8a9e78c2da298187190d

Verified on the quantized artifact you download, not merely internal weights.

Evaluation

FLORES-200 devtest, 200 sentences, beam 4, CTranslate2 INT8 on CPU. Metrics: spBLEU (flores200 tokenizer) + chrF (word_order=0).

	spBLEU	chrF
this model	27.74	52.91
upstream, pre-fog	26.71	—

Limitations

—One language pair only (ta to en).
—FLORES-200 is news and encyclopedic prose; it says little about conversational register.
—No human evaluation was performed.