How to use from the
Use from the
Transformers.js library
// npm i @huggingface/transformers
import { pipeline } from '@huggingface/transformers';

// Allocate pipeline
const pipe = await pipeline('translation', 'OptimaMT/en-pt');

OptimaMT en β†’ pt (English to Portuguese)

Drop-in copy of Xenova/opus-mt-en-ROMANCE at revision 9d2ba69ac80c with a lighter merged decoder: ONNX Runtime's fast mode (disable_quant_qdq = 1, 2.3–2.5Γ— 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 Identical tokens
disable_quant_qdq = 1 542 β†’ 289 MiB (-47 %) yes
ONNX Runtime defaults 291 β†’ 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 Β· method: REPORT.md.

Use

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: onnxruntime, sentencepiece, numpy):

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 by the University of Helsinki, CC BY 4.0.
  • ONNX export: 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.
Downloads last month
45
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for OptimaMT/en-pt

Quantized
(1)
this model

Space using OptimaMT/en-pt 1

Collection including OptimaMT/en-pt