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