Instructions to use WindyWord/translate-en-cel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use WindyWord/translate-en-cel with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="WindyWord/translate-en-cel")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("WindyWord/translate-en-cel", device_map="auto") - Notebooks
- Google Colab
- Kaggle
WindyWord.ai Translation β English β Celtic
Part of the Windstorm Labs open model catalogue. Scores, licence and attribution for every model: https://windytranslate.com/models/translate-en-cel
Canonical copy: https://huggingface.co/WindyTranslate/translate-en-cel
Translates English β Celtic (Irish, Welsh, Scottish Gaelic, Breton).
Quality
No quality score is published in this repository. Current screening scores, where measured, are on the catalogue page linked above.
Available Variants
Deployment formats in this repository (subfolders):
| Variant | Description |
|---|---|
lora/ |
WindyStandard β production baseline. Transformers format for GPU inference. |
lora-ct2-int8/ |
WindyStandard Β· CPU INT8 β CTranslate2 INT8 quantization of WindyStandard for CPU inference. |
herm0/ |
WindyEnhanced β further fine-tuned on the OPUS-100, Tatoeba and WikiMatrix parallel corpora. |
herm0-ct2-int8/ |
WindyEnhanced Β· CPU INT8 β CTranslate2 INT8 quantization of WindyEnhanced. |
Quick usage
Transformers (PyTorch):
from transformers import MarianMTModel, MarianTokenizer
tokenizer = MarianTokenizer.from_pretrained("WindyWord/translate-en-cel", subfolder="lora")
model = MarianMTModel.from_pretrained("WindyWord/translate-en-cel", subfolder="lora")
CTranslate2 (fast CPU inference):
import ctranslate2
translator = ctranslate2.Translator("path/to/translate-en-cel/lora-ct2-int8")
Apps
The Windy Word apps are built on this model family.
Provenance & License
Weights derived from Helsinki-NLP/opus-mt-en-cel (OPUS-MT, Helsinki-NLP, University of Helsinki), licensed Apache-2.0. Windy variants are released under the same licence.
Model tree for WindyWord/translate-en-cel
Base model
Helsinki-NLP/opus-mt-en-cel