Instructions to use OptimaMT/en-pt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use OptimaMT/en-pt with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('translation', 'OptimaMT/en-pt');
|
Download README.md from OptimaMT/en-pt: direct link, hf CLI and curl.
- Browser
- Download file 2.68 kB
-
https://huggingface.co/OptimaMT/en-pt/resolve/main/README.md
- Command line
-
hf download hf://OptimaMT/en-pt/README.md
-
curl -L -o README.md https://huggingface.co/OptimaMT/en-pt/resolve/main/README.md
2.68 kB
| license: cc-by-4.0 | |
| language: | |
| - en | |
| - pt | |
| pipeline_tag: translation | |
| library_name: transformers.js | |
| base_model: Xenova/opus-mt-en-ROMANCE | |
| tags: | |
| - translation | |
| - marian | |
| - opus-mt | |
| - onnx | |
| # OptimaMT en → pt (English to Portuguese) | |
| Drop-in copy of [Xenova/opus-mt-en-ROMANCE](https://huggingface.co/Xenova/opus-mt-en-ROMANCE) at revision `9d2ba69ac80c` with a lighter merged decoder: ONNX Runtime's fast mode (`disable_quant_qdq = 1`, 2.3–2.5× faster) at half the memory. Same weights, same tokens. | |
| Part of [OptimaMT](https://github.com/AmerAlreyahi/OptimaMT): [all 51 pairs](https://huggingface.co/collections/OptimaMT/optimamt-lighter-opus-mt-onnx-models-6af228dc9cd91f015e56e869), named `OptimaMT/<src>-<tgt>`. | |
| **Used in production:** | |
| - [OpenCircle](https://github.com/AmerAlreyahi/OpenCircle), a desktop screen translator for Windows and Linux, ships these models since v0.1.4. | |
| | Memory after load | Linux | Identical tokens | | |
| |---|---:|---| | |
| | `disable_quant_qdq = 1` | 542 → 289 MiB (-47 %) | yes | | |
| | ONNX Runtime defaults | 291 → 225 MiB (-22 %) | yes | | |
| FLORES-200 devtest (1,012 sentences): the same translations as the original, BLEU 41.73, chrF 66.59 (greedy). | |
| ONNX Runtime 1.31.1, CPU, 4 threads (Linux only, not yet measured on Windows). Interactive results: [OptimaMT/results](https://huggingface.co/spaces/OptimaMT/results) · | |
| method: [REPORT.md](https://github.com/AmerAlreyahi/OptimaMT/blob/main/REPORT.md). | |
| ## Use | |
| ```js | |
| import { pipeline } from "@huggingface/transformers"; | |
| const translator = await pipeline("translation", "OptimaMT/en-pt", { | |
| dtype: "q8", | |
| session_options: { extra: { session: { disable_quant_qdq: "1" } } }, | |
| }); | |
| const [out] = await translator(">>pt_br<< The lighthouse stands on the coast."); | |
| console.log(out.translation_text); | |
| ``` | |
| Python ([translate.py](https://github.com/AmerAlreyahi/OptimaMT/blob/main/scripts/translate.py): onnxruntime, sentencepiece, numpy): | |
| ```bash | |
| python translate.py OptimaMT/en-pt "The lighthouse stands on the coast." --lang ">>pt_br<<" | |
| ``` | |
| Start every input with `>>pt_br<<` (the target variant). Use transformers.js 3.x: 4.3.2 splits this token, with the original export too. | |
| ## Files | |
| Only `onnx/decoder_model_merged_quantized.onnx` is rebuilt; every other file is the original, byte for byte. | |
| Vocabulary: 65,001 tokens. | |
| ## Licence and credits | |
| - Weights: [OPUS-MT](https://huggingface.co/Helsinki-NLP/opus-mt-en-ROMANCE) by the University of Helsinki, CC BY 4.0. | |
| - ONNX export: [Xenova/opus-mt-en-ROMANCE](https://huggingface.co/Xenova/opus-mt-en-ROMANCE) at revision `9d2ba69ac80c`. | |
| - Modified: the decoder's output projection was moved out of its two branches (graph change only). CC BY 4.0. | |