Church Translate, as it runs at the campuses

Live sermon translation into 100+ languages, running entirely on one Mac per campus: audio in, voice detection, Whisper on the GPU, NLLB-200 in its own process, and a built-in web server the congregation reads from on their phones. No audio leaves the building. This is the source only. What used to sit beside it — 14 GB of speech and translation models, 8 GB of voice bundles, 6 GB of natural voices, the Electron caches, and the app data holding the operator PIN and every service transcript — is machine state and downloaded assets, and stays in the NAS backup where it belongs. The vendored node, cloudflared and Windows ffmpeg binaries are out too (533 MB, re-fetched for packaging); the browser-side runtime beside them is kept, so a checkout still serves the congregation page. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-23 15:41:21 -04:00
commit c9eef0672c
118 changed files with 36031 additions and 0 deletions
@@ -0,0 +1,53 @@
+/* Measure the hallucination and what actually stops it. Runs the same model,
+   dtype and cache the app uses, in a plain node process like mt-service.js. */
+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 t0 = Date.now();
+const pipe = await pipeline('translation', 'Xenova/nllb-200-distilled-600M', { dtype: 'fp32' });
+console.log('loaded in ' + ((Date.now() - t0) / 1000).toFixed(1) + 's\n');
+
+/* The exact lines from the operator's screenshot, plus stress cases. */
+const CASES = [
+  'Donald Trump.',
+  'Hello, hello.',
+  'His name was John.',
+  'Open up to the book, Matthew.',
+  'Today we are going to talk about Peter in the Bible.',
+  'Turn with me to John chapter 3.',
+  'Amen.',
+  'Jesus wept.',
+  'Paul wrote to the church at Corinth.',
+  'How many countries in the world?',
+  'And God said, let there be light, and there was light.'
+];
+
+const CONFIGS = [
+  { name: 'current (no params)', opts: {} },
+  { name: 'cap 2x+8',            opts: null, cap: (n) => Math.ceil(n * 2) + 8 },
+  { name: 'cap 2x+8 +nrng3',     opts: { no_repeat_ngram_size: 3 }, cap: (n) => Math.ceil(n * 2) + 8 },
+  { name: 'beams2 cap2x+8',      opts: { num_beams: 2, no_repeat_ngram_size: 3 }, cap: (n) => Math.ceil(n * 2) + 8 }
+];
+
+const tok = pipe.tokenizer;
+for (const cfg of CONFIGS) {
+  console.log('=== ' + cfg.name + ' ===');
+  let total = 0;
+  for (const text of CASES) {
+    const nIn = tok(text).input_ids.dims.at(-1);
+    const opts = Object.assign({ src_lang: 'eng_Latn', tgt_lang: 'spa_Latn' }, cfg.opts || {});
+    if (cfg.cap) opts.max_new_tokens = cfg.cap(nIn);
+    const s = Date.now();
+    const out = await pipe(text, opts);
+    const ms = Date.now() - s;
+    total += ms;
+    const got = (Array.isArray(out) ? out[0] : out).translation_text.trim();
+    const flag = (!/[?？]/.test(text) && /[?？]/.test(got)) ? '  <-- INVENTED A QUESTION' : '';
+    console.log('  ' + String(ms).padStart(5) + 'ms  in' + String(nIn).padStart(3) + '  ' + got + flag);
+  }
+  console.log('  total ' + total + 'ms\n');
+}