Translation
Text-to-text neural machine translation (NMT) — i.e., translate text between different languages.
Overview
Translation uses your choice of either nmt.cpp or Bergamot as inference engine. Load any supported model using modelType: "nmt", and modelConfig.engine: "Bergamot" for Bergamot.
Translation input is defined by:
from: string: source language id (e.g., "en")to: string: target language idtext: string | string[]: text to be translated
translate() returns an object containing text and when streaming is enabled, a tokenStream for real-time output.
For a list of supported languages and their ids (string abbreviations), see qvac-sdk/schemas/translation-config.ts.
Functions
Use the following sequence of function calls:
For how to use each function, see SDK — API reference.
Models
You should load a model compatible with your chosen inference engine:
nmt.cpp(default): Bergamot or IndicTrans2. Bergamot uses intgemm*.bin+*.spmvocab files; IndicTrans2 uses GGML*.bin.- Bergamot: Bergamot model bundle. Required files: model
*.bin+vocab*.spm.
For models available as constants, see SDK — Models.
Example
The following script shows an example of translation:
import { loadModel, translate, unloadModel, MARIAN_OPUS_EN_IT_Q4_0, } from "@qvac/sdk";
try {
const modelId = await loadModel({
modelSrc: MARIAN_OPUS_EN_IT_Q4_0,
modelType: "nmt",
modelConfig: {
engine: "Opus",
from: "en",
to: "it",
},
});
console.log(`✅ Model loaded: ${modelId}`);
const text = "Hello, how are you today? I hope you are having a wonderful day!";
console.log("\n--- Streaming Translation ---");
const streamResult = translate({
modelId,
text,
modelType: "nmt",
stream: true,
});
process.stdout.write("Translated text EN -> IT: ");
for await (const token of streamResult.tokenStream) {
process.stdout.write(token);
}
console.log();
const stats = await streamResult.stats;
if (stats) {
console.log(`Processing stats:`, stats);
}
await unloadModel({ modelId, clearStorage: false });
}
catch (error) {
console.error("❌ Error:", error);
process.exit(1);
}Tip: all examples throughout this documentation are self-contained and runnable. For instructions on how to run them, see SDK quickstart.