Lingo

What it does

Translate text without a server.

• Marian NMT students distilled from a larger teacher, run through the Bergamot WASM runtime (int8 GEMM, single worker, no COOP/COEP headers needed).
• base-memory when available (≈37 MB, on par with cloud translators within ~5% COMET), tiny for the rest (≈22 MB). PAIRS lists every pair with size and COMET score.
• Pairs without a direct model pivot through English: es → fr loads es-en and en-fr.
• Pass html: true to translate markup while keeping the tags in place.
• Codes are BCP 47: zh is Simplified Chinese, zh-Hant Traditional. One Translator can serve many pairs; new pairs download on demand.
• Prefer one model for 100 languages? Pass model: "Xenova/m2m100_418M" (MIT, ~630 MB, Transformers.js, slower).

Specifications

Package

runonweb/translate

Base model

Firefox Translations (Marian NMT) · Mozilla

License

MPL-2.0

Weights

runonweb/firefox-translations

Download

~22 MB (tiny)~37 MB (base-memory)~49 MB (ja, ko, zh)

Quantization

int8 on WASM (Bergamot)

Backend

WASM only

Input

Text

Get started with runonweb/translate

pnpm add runonweb

npm install runonweb

bun add runonweb

yarn add runonweb

import { Translator, PAIRS } from 'runonweb/translate'

// en → es: base-memory, ~37 MB
const translator = new Translator({ from: 'en', to: 'es' })
await translator.load()

const { text } = await translator.translate('Hello world')
// "Hola mundo"

// same instance, another pair (downloaded on demand)
await translator.translate('Bonjour', { from: 'fr', to: 'en' })

// keep the markup, translate the text nodes
await translator.translate('<b>Hello</b> world', { html: true })

translator.dispose()

PAIRS['en-ja'] // { architecture: 'base-memory', bytes: 43849787, comet: 0.90, … }

Same shape everywhere: construct, load(), run, dispose(). Pass onProgressto show download progress on first use.

Questions about Lingo