Instructions to use WindyWord/translate-ar-tr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use WindyWord/translate-ar-tr 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-ar-tr")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("WindyWord/translate-ar-tr", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download README.md from WindyWord/translate-ar-tr: direct link, hf CLI and curl.
- Browser
- Download file 1.85 kB
-
https://huggingface.co/WindyWord/translate-ar-tr/resolve/main/README.md
- Command line
-
hf download hf://WindyWord/translate-ar-tr/README.md
-
curl -L -o README.md https://huggingface.co/WindyWord/translate-ar-tr/resolve/main/README.md
license: apache-2.0
tags:
- translation
- marian
- windyword
- arabic
- turkish
language:
- ar
- tr
library_name: transformers
pipeline_tag: translation
base_model: Helsinki-NLP/opus-mt-ar-tr
WindyWord.ai Translation โ Arabic โ Turkish
Part of the Windstorm Labs open model catalogue. Scores, licence and attribution for every model: https://windytranslate.com/models/translate-ar-tr
Canonical copy: https://huggingface.co/WindyTranslate/translate-ar-tr
Translates Arabic โ Turkish.
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 |
|---|---|
herm0/ |
WindyEnhanced โ further fine-tuned on the OPUS-100, Tatoeba and WikiMatrix parallel corpora. |
herm0-ct2-int8/ |
WindyEnhanced ยท CPU INT8 โ CTranslate2 INT8 quantization of WindyEnhanced. |
Quick usage
Transformers (PyTorch):
from transformers import MarianMTModel, MarianTokenizer
tokenizer = MarianTokenizer.from_pretrained("WindyWord/translate-ar-tr", subfolder="herm0")
model = MarianMTModel.from_pretrained("WindyWord/translate-ar-tr", subfolder="herm0")
CTranslate2 (fast CPU inference):
import ctranslate2
translator = ctranslate2.Translator("path/to/translate-ar-tr/herm0-ct2-int8")
Apps
The Windy Word apps are built on this model family.
Provenance & License
Weights derived from Helsinki-NLP/opus-mt-ar-tr (OPUS-MT, Helsinki-NLP, University of Helsinki), licensed Apache-2.0. Windy variants are released under the same licence.