Downloads · 30 days
9
23% of all-time downloads
translate-windy-hplt-en-sl
WindyWord/translate-windy-hplt-en-sl
translate-windy-hplt-en-sl is a translation model from WindyWord. Use it when you need text moved from one language to another. It is set up for ctranslate2. The card lists the license as cc-by-4.0.
Part of the Windstorm Labs open model catalogue. Scores, licence and attribution for every model: https://windytranslate.com/models/translate-windy-hplt-en-sl Canonical copy: https://huggingface.co/WindyTranslate/tran…
All-time downloads
39
Public
Repo size
80.5 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin79 MB · 93%
At a glance
- Task
- Translation
- Library
- ctranslate2
- License
- cc-by-4.0
- Access
- Public
- Created
- Aug 4, 2026
- Updated
- Oct 1, 2026
- SHA
- 79f7d670
Try a prompt
Base models
Model card
From the Hugging Face model README
translate-windy-hplt-en-sl — en to sl
Part of the Windstorm Labs open model catalogue. Scores, licence and attribution for every model: https://windytranslate.com/models/translate-windy-hplt-en-sl
Canonical copy: https://huggingface.co/WindyTranslate/translate-windy-hplt-en-sl
CTranslate2 INT8 bilingual translation model, derived from
HPLT/translate-en-sl-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-sl (hub), 2000 sentence pairs |
| Tensors modified | 36 |
| Max absolute weight delta | 5.479e-05 |
Provenance
base model.bin sha256 5a32994c59202bb3909486042e365dea977025bc7c2433f55ee9755b4038079d
this model.bin sha256 19487d5f3d68cf9dfff0ef6d02eed76c10842bf762e87a7a5483bfcd53c66ecc
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 | 32.86 | 54.61 |
| upstream, pre-fog | 31.66 | — |
Limitations
- One language pair only (en to sl).
- FLORES-200 is news and encyclopedic prose; it says little about conversational register.
- No human evaluation was performed.
- Task
- Translation
- Library
- ctranslate2
- License
- cc-by-4.0
- Created
- Aug 4, 2026
- Updated
- Oct 1, 2026