Instructions to use Helsinki-NLP/opus-mt-en-mos with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-en-mos 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="Helsinki-NLP/opus-mt-en-mos")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-en-mos") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-en-mos", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from Helsinki-NLP/opus-mt-en-mos: direct link, hf CLI and curl.
- Browser
- Download file 824 Bytes
-
https://huggingface.co/Helsinki-NLP/opus-mt-en-mos/resolve/main/README.md
- Command line
-
hf download hf://Helsinki-NLP/opus-mt-en-mos/README.md
-
curl -L -o README.md https://huggingface.co/Helsinki-NLP/opus-mt-en-mos/resolve/main/README.md
824 Bytes
| tags: | |
| - translation | |
| license: apache-2.0 | |
| ### opus-mt-en-mos | |
| * source languages: en | |
| * target languages: mos | |
| * OPUS readme: [en-mos](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/en-mos/README.md) | |
| * dataset: opus | |
| * model: transformer-align | |
| * pre-processing: normalization + SentencePiece | |
| * download original weights: [opus-2020-01-20.zip](https://object.pouta.csc.fi/OPUS-MT-models/en-mos/opus-2020-01-20.zip) | |
| * test set translations: [opus-2020-01-20.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-mos/opus-2020-01-20.test.txt) | |
| * test set scores: [opus-2020-01-20.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-mos/opus-2020-01-20.eval.txt) | |
| ## Benchmarks | |
| | testset | BLEU | chr-F | | |
| |-----------------------|-------|-------| | |
| | JW300.en.mos | 26.9 | 0.417 | | |