Instructions to use OptimaMT/es-ar with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use OptimaMT/es-ar with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('translation', 'OptimaMT/es-ar');
Download README.md from OptimaMT/es-ar: direct link, hf CLI and curl.
- Browser
- Download file 2.92 kB
-
https://huggingface.co/OptimaMT/es-ar/resolve/main/README.md
- Command line
-
hf download hf://OptimaMT/es-ar/README.md
-
curl -L -o README.md https://huggingface.co/OptimaMT/es-ar/resolve/main/README.md
license: cc-by-4.0
language:
- es
- ar
pipeline_tag: translation
library_name: transformers.js
base_model: Helsinki-NLP/opus-mt-es-ar
tags:
- translation
- marian
- opus-mt
- onnx
OptimaMT es → ar (Spanish to Arabic)
Drop-in copy of an ONNX export of Helsinki-NLP/opus-mt-es-ar at revision 76efb7da47ad (same layout as the Xenova exports) 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: all 51 pairs, named OptimaMT/<src>-<tgt>.
Used in production:
- OpenCircle, a desktop screen translator for Windows and Linux, ships these models since v0.1.4.
| Memory after load | Linux | Windows | Identical tokens |
|---|---|---|---|
disable_quant_qdq = 1 |
526 → 282 MiB (-46 %) | 502 → 260 MiB (-48 %) | yes |
| ONNX Runtime defaults | 281 → 220 MiB (-22 %) | 197 → 166 MiB (-16 %) | yes |
FLORES-200 devtest (1,012 sentences): the same translations as the original, BLEU 10.52, chrF 43.09 (greedy).
ONNX Runtime 1.31.1, CPU, 4 threads (Linux; Windows in a VM). Interactive results: OptimaMT/results · method: REPORT.md.
Use
import { pipeline } from "@huggingface/transformers";
const translator = await pipeline("translation", "OptimaMT/es-ar", {
dtype: "q8",
session_options: { extra: { session: { disable_quant_qdq: "1" } } },
});
const [out] = await translator(">>ara<< El faro está en la costa.");
console.log(out.translation_text);
Python (translate.py: onnxruntime, sentencepiece, numpy):
python translate.py OptimaMT/es-ar "El faro está en la costa." --lang ">>ara<<"
Start every input with >>ara<< (the target variant). Use transformers.js 3.x: 4.3.2 splits this token, with the original export too.
Files
onnx/decoder_model_merged_quantized.onnx is rebuilt; tokenizer.json, special_tokens_map.json and tokenizer_config.json were written in the Xenova layout; every other file is the original, byte for byte.
Vocabulary: 62,518 tokens.
Licence and credits
- Weights: OPUS-MT by the University of Helsinki, CC BY 4.0.
- ONNX export: an ONNX export of Helsinki-NLP/opus-mt-es-ar at revision
76efb7da47ad(same layout as the Xenova exports). - Modified: the decoder's output projection was moved out of its two branches (graph change only). CC BY 4.0.