Home / Models / translate-windy-core

Multilingual translation model translate-windy-core

One CTranslate2 INT8 model for many language directions, fine-tuned by Windstorm Labs from facebook/m2m100_1.2B.

Task: Translation (multilingual)
Lineage: M2M-100
Format: CTranslate2 (INT8)
Hugging Face: WindyWord/translate-windy-core
Last updated on HF: 2026-07-27

Quality (as published in the model card)

FLORES-200 devtest, 1012 sentences per pair, beam 4. These numbers come from the Hugging Face model card; this site has not re-measured them, and they use a different setup from our pair screening (devtest, 1,012 sentences, spBLEU and chrF), so do not compare them directly with pair scores.

Pair	spBLEU	chrF
English → Spanish	29.37	53.61
English → French	49.56	67.72
English → German	41.30	62.54
English → Italian	31.93	56.29
English → Portuguese	50.19	68.54
English → Russian	36.05	55.85
English → Chinese	27.36	29.68
English → Japanese	23.11	35.10
English → Korean	19.01	32.57
English → Arabic	20.57	42.28
English → Hindi	29.24	51.42
English → Swahili	28.19	55.32
Spanish → English	30.46	56.90
French → English	44.93	66.08
Chinese → English	27.52	54.56
Japanese → English	26.19	53.38
Mean	32.19	52.62

Covers 74 of the 76 languages in the Windy translation set. Telugu and Basque are not covered.

How to run

Shell

pip install ctranslate2 transformers sentencepiece huggingface_hub

Python

import ctranslate2
from huggingface_hub import snapshot_download
from transformers import AutoTokenizer

path = snapshot_download("WindyWord/translate-windy-core")
tok = AutoTokenizer.from_pretrained(path)   # the tokenizer ships in the repo
translator = ctranslate2.Translator(path, device="cpu", compute_type="int8")

tok.src_lang = "en"
source = tok.convert_ids_to_tokens(tok.encode("Where is the train station?"))
target_prefix = [tok.convert_ids_to_tokens(tok.get_lang_id("es"))]
result = translator.translate_batch([source], target_prefix=[target_prefix], beam_size=4)
print(tok.decode(tok.convert_tokens_to_ids(result[0].hypotheses[0][1:])))

Tested: Pattern run on 2026-10-01 against WindyWord/translate-windy-nano with ctranslate2 4.8.2 and transformers 5.18.0 on CPU. Same code path as translate-windy-core. Not run on every model individually.

Licence and attribution

Licence: MIT
Upstream: facebook/m2m100_1.2B
Upstream licence: MIT
Attribution: Based on facebook/m2m100_1.2B (M2M-100) by Meta Platforms, Inc. Licensed MIT.

Copy this into your NOTICE file (or equivalent) when you ship the model:

NOTICE

This product uses the model WindyWord/translate-windy-core
(https://huggingface.co/WindyWord/translate-windy-core), published by Windstorm Labs (https://windstormlabs.com).
Based on facebook/m2m100_1.2B (M2M-100) by Meta Platforms, Inc. Licensed MIT.
Windstorm Labs modified the upstream weights; the model card describes what was changed.
Licensed under the MIT License: https://opensource.org/license/mit

This is a convenience, not legal advice. See Licensing.