@qvac/translation-nmtcpp

npm i @qvac/translation-nmtcpp

// IndicTrans2 — fetch from the QVAC model registry
const {
  ensureIndicTransModelFile,
  getIndicTransFileName
} = require('@qvac/translation-nmtcpp/lib/indictrans-model-fetcher')

const path = require('bare-path')

const modelPath = path.join('./model/indictrans', getIndicTransFileName())
await ensureIndicTransModelFile(modelPath) // downloads if not already present

// Bergamot — fetch from the Firefox Remote Settings CDN
const {
  ensureBergamotModelFiles,
  getBergamotFileNames
} = require('@qvac/translation-nmtcpp/lib/bergamot-model-fetcher')

const modelDir = await ensureBergamotModelFiles('en', 'it', './model/bergamot/enit')
const fileNames = getBergamotFileNames('en', 'it') // { modelName, srcVocabName, dstVocabName }

const args = {
  files: {
    model: modelPath // resolved path from Step 1
  },
  params: {
    mode: 'full',
    srcLang: 'eng_Latn',   // Source language (ISO 15924 code)
    dstLang: 'hin_Deva'    // Target language (ISO 15924 code)
  },
  config: {
    modelType: TranslationNmtcpp.ModelTypes.IndicTrans
  }
}

const path = require('bare-path')

const args = {
  files: {
    model: path.join(modelDir, fileNames.modelName),
    srcVocab: path.join(modelDir, fileNames.srcVocabName),
    dstVocab: path.join(modelDir, fileNames.dstVocabName)
  },
  params: {
    mode: 'full',
    srcLang: 'en',    // Source language (ISO 639-1 code)
    dstLang: 'it'     // Target language (ISO 639-1 code)
  },
  config: {
    modelType: TranslationNmtcpp.ModelTypes.Bergamot
  }
}

// Generation parameters for IndicTrans2
const generationParams = {
  beamsize: 4,            // Beam search width (>=1). 1 disables beam search
  lengthpenalty: 0.6,     // Length normalization strength (>=0)
  maxlength: 128,         // Maximum generated tokens (>0)
  repetitionpenalty: 1.2, // Penalize previously generated tokens (0..2)
  norepeatngramsize: 2,   // Disallow repeating n-grams of this size (0..10)
  temperature: 0.8,       // Sampling temperature [0..2]
  topk: 40,               // Keep top-K logits [0..vocab_size]
  topp: 0.9               // Nucleus sampling threshold (0 < p <= 1)
}

const TranslationNmtcpp = require('@qvac/translation-nmtcpp')

// IndicTrans - must specify modelType + generation parameters
const model = new TranslationNmtcpp({
  ...args, // files + params from Step 2
  config: {
    modelType: TranslationNmtcpp.ModelTypes.IndicTrans,
    ...generationParams,  // Spread generation params from Step 3
    maxlength: 256        // Override for longer outputs
  }
})

// Bergamot - vocab files are passed via `files` (see Step 2); limited generation params support
const model = new TranslationNmtcpp({
  ...args, // files (model + srcVocab + dstVocab) + params from Step 2
  config: {
    modelType: TranslationNmtcpp.ModelTypes.Bergamot,
    beamsize: 4 // Only beamsize supported for Bergamot
  }
})

TranslationNmtcpp.ModelTypes = {
  IndicTrans: 'IndicTrans', // Indic language models
  Bergamot: 'Bergamot'      // Firefox Translations models
}

try {
  // Basic usage
  await model.load()
} catch (error) {
  console.error('Failed to load model:', error)
}

try {
  // Execute translation on input text
  const response = await model.run('Hello world! Welcome to the internet of peers!')

  // Process streamed output using callback
  await response
    .onUpdate(outputChunk => {
      // Handle each new piece of translated text
      console.log(outputChunk)
    })
    .await() // Wait for translation to complete

  // Access performance statistics (if enabled with opts.stats)
  if (response.stats) {
    console.log('Translation completed in:', response.stats.totalTime, 'ms')
  }
} catch (error) {
  console.error('Translation failed:', error)
}

// Array of texts to translate (English)
const textsToTranslate = [
  'Hello world!',
  'How are you today?',
  'Machine translation has revolutionized communication.'
]

try {
  // Batch translation - returns array of translated strings
  const translations = await model.runBatch(textsToTranslate)

  // Output each translation
  translations.forEach((translatedText, index) => {
    console.log(`Original: ${textsToTranslate[index]}`)
    console.log(`Translated: ${translatedText}\n`)
  })
} catch (error) {
  console.error('Batch translation failed:', error)
}

// Always unload the model when finished to free memory
try {
  await model.unload()
} catch (error) {
  console.error('Failed to unload model:', error)
}

const TranslationNmtcpp = require('@qvac/translation-nmtcpp')

// Available model types
TranslationNmtcpp.ModelTypes = {
  IndicTrans: 'IndicTrans',  // For Indic language translations
  Bergamot: 'Bergamot'       // For Bergamot/Firefox translations
}

// Enable C++ logging
const logger = {
  info: (msg) => console.log('[C++ INFO]', msg),
  warn: (msg) => console.warn('[C++ WARN]', msg),
  error: (msg) => console.error('[C++ ERROR]', msg),
  debug: (msg) => console.log('[C++ DEBUG]', msg)
}

const args = {
  files: { model: modelPath, srcVocab, dstVocab }, // resolved paths (see Step 1)
  params: { mode: 'full', srcLang: 'en', dstLang: 'it' },
  config: { modelType: TranslationNmtcpp.ModelTypes.Bergamot },
  logger  // Pass logger to enable C++ logs
}

const args = {
  files: { model: modelPath, srcVocab, dstVocab }, // resolved paths (see Step 1)
  params: { mode: 'full', srcLang: 'en', dstLang: 'it' },
  config: { modelType: TranslationNmtcpp.ModelTypes.Bergamot }
  // No logger = suppress C++ logs
}

# Run with C++ logging disabled (default)
bare examples/quickstart.js

# Run with C++ logging enabled
VERBOSE=1 bare examples/quickstart.js