/*
 * Opus-MT bilingual vs NLLB-600M, on THIS Mac, on sermon sentences.
 *
 * The claim under test: a 77M bilingual model matches or beats NLLB-200-
 * distilled-600M on high-resource pairs at ~1/8 the size. Published chrF says
 * yes; no published CPU latency comparison exists, and quality on preaching
 * English is not what any leaderboard measures. So: measure both here.
 */
import { pipeline, env } from '@huggingface/transformers';
import os from 'os'; import path from 'path';
env.allowLocalModels = false;
env.cacheDir = path.join(os.homedir(), 'Library/Application Support/Church Translate Models');

const SENTENCES = [
  'And I want you to understand that God has a plan for your life',
  'Turn with me to the book of Romans chapter eight',
  'He was faithful even when it cost him everything',
  'Would you stand with me as we pray',
  'The grace of God is not something you can earn',
  'Peter denied him three times before the rooster crowed',
];
const PAIRS = [
  { code: 'spa_Latn', opus: 'Xenova/opus-mt-en-es', name: 'Spanish' },
  { code: 'fra_Latn', opus: 'Xenova/opus-mt-en-fr', name: 'French'  },
  { code: 'zho_Hans', opus: 'Xenova/opus-mt-en-zh', name: 'Chinese' },
];

const t = (f) => { const s = Date.now(); return f().then((r) => [Date.now() - s, r]); };
const out = (o) => (Array.isArray(o) ? o[0] : o).translation_text.trim();

console.log('loading NLLB fp32…');
const nllb = await pipeline('translation', 'Xenova/nllb-200-distilled-600M', { dtype: 'fp32' });
await nllb(SENTENCES[0], { src_lang: 'eng_Latn', tgt_lang: 'spa_Latn' });

const results = {};
for (const p of PAIRS) {
  const ts = [], txt = [];
  for (const s of SENTENCES) {
    const [ms, o] = await t(() => nllb(s, { src_lang: 'eng_Latn', tgt_lang: p.code }));
    ts.push(ms); txt.push(out(o));
  }
  results[p.name] = { nllb: { ms: ts, txt } };
}

for (const dtype of ['fp32', 'q8']) {
  for (const p of PAIRS) {
    let pipe;
    const t0 = Date.now();
    try { pipe = await pipeline('translation', p.opus, { dtype }); }
    catch (e) { console.log(p.name + ' ' + dtype + ': LOAD FAILED — ' + String(e.message).slice(0, 90)); continue; }
    const load = Date.now() - t0;
    await pipe(SENTENCES[0]);
    const ts = [], txt = [];
    for (const s of SENTENCES) { const [ms, o] = await t(() => pipe(s)); ts.push(ms); txt.push(out(o)); }
    results[p.name]['opus_' + dtype] = { ms: ts, txt, load };
    await pipe.dispose?.();
  }
}

const mean = (a) => a.reduce((x, y) => x + y, 0) / a.length;
console.log('\n=== speed, ms per sentence (mean of ' + SENTENCES.length + ') ===');
console.log('language  |  NLLB fp32 | Opus fp32 | Opus q8 | best speedup');
for (const p of PAIRS) {
  const r = results[p.name];
  const n = mean(r.nllb.ms);
  const f = r.opus_fp32 ? mean(r.opus_fp32.ms) : NaN;
  const q = r.opus_q8 ? mean(r.opus_q8.ms) : NaN;
  const best = Math.min(f || Infinity, q || Infinity);
  console.log(p.name.padEnd(9) + ' | ' + (n.toFixed(0) + 'ms').padStart(10) + ' | ' +
    ((f ? f.toFixed(0) : '—') + 'ms').padStart(9) + ' | ' + ((q ? q.toFixed(0) : '—') + 'ms').padStart(7) +
    ' | ' + (n / best).toFixed(2) + 'x');
}

console.log('\n=== output, sentence by sentence ===');
SENTENCES.forEach((s, i) => {
  console.log('\n"' + s + '"');
  for (const p of PAIRS) {
    const r = results[p.name];
    console.log('  ' + p.name);
    console.log('    NLLB      : ' + r.nllb.txt[i]);
    if (r.opus_fp32) console.log('    Opus fp32 : ' + r.opus_fp32.txt[i]);
    if (r.opus_q8)   console.log('    Opus q8   : ' + r.opus_q8.txt[i] +
      (r.opus_fp32 && r.opus_q8.txt[i] !== r.opus_fp32.txt[i] ? '   <-- differs from fp32' : ''));
  }
});