Instructions to use HackitzLabs/opus-mt-tl-en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use HackitzLabs/opus-mt-tl-en with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('translation', 'HackitzLabs/opus-mt-tl-en');
opus-mt-tl-en (ONNX, quantized) β Tagalog/Filipino β English
ONNX conversion of Helsinki-NLP/opus-mt-tl-en for on-device use with transformers.js, as used by JustMail for Windows (HackitzLabs).
Changes from the original: converted to ONNX and quantized (int8) for on-device use with transformers.js (converter: transformers.js v2.17.2 scripts). Weights are otherwise unmodified. No fine-tuning.
Credit
Original model: OPUS-MT by the Language Technology Research Group at the University of Helsinki (JΓΆrg Tiedemann et al.), trained on OPUS data. Licensed under Apache 2.0.
Tiedemann, J. & Thottingal, S. (2020). OPUS-MT β Building open translation services for the World. EAMT 2020.
Note
Output is formal/textbook English. Treat it as a first draft.
- Downloads last month
- 23
Model tree for HackitzLabs/opus-mt-tl-en
Base model
Helsinki-NLP/opus-mt-tl-en