translate-windy-hplt-en-kn โ€” en to kn

CTranslate2 INT8 bilingual translation model, derived from HPLT/translate-en-kn-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 Helsinki-NLP/opus-100 en-kn (hub), 2000 sentence pairs
Tensors modified 36
Max absolute weight delta 4.643e-05

Provenance

base   model.bin sha256  f8280b7629da81c6ade0d85ac3675e21ebde83db3375d526a97c277d9cea4273
this   model.bin sha256  fa400d8cba01bb4fc6bfd90261c013cdaa66b17ba7c2abfc7e9d8e9b50cce711

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 34.68 55.45
upstream, pre-fog 32.13 โ€”

Limitations

  • One language pair only (en to kn).
  • FLORES-200 is news and encyclopedic prose; it says little about conversational register.
  • No human evaluation was performed.
Downloads last month
8
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for WindyWord/translate-windy-hplt-en-kn

Finetuned
(2)
this model