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 +1,69 @@
+/*
+ * short-questions.js — one-word questions that must never be guessed at.
+ *
+ * MEASURED: "What?" is the single most frequent invented line left after every
+ * other guard — the shipped NLLB renders it "¿Qué es eso?" (15 archive rows),
+ * "Yeah?" -> "¿Qué es eso?" (6), "Hello?" -> "¿Qué pasa?" (6), "How?" -> "¿Cómo
+ * es que lo hizo?" (3). The preacher says "What?" about three times a service.
+ * Because the SOURCE is itself a question, the hallucination guard rightly
+ * refuses to blank the output (a Spanish question is the correct shape) — so
+ * these bypass the model altogether, the way liturgy.js does for "Amen".
+ *
+ * Whole-utterance match only, one word, terminal '?' or '.' or nothing. The
+ * table holds only words whose one-word rendering is not a matter of register
+ * or denomination. Languages not listed fall through to the model unchanged.
+ */
+(function (root, factory) {
+  if (typeof module === 'object' && module.exports) module.exports = factory();
+  else root.ShortQuestions = factory();
+}(typeof self !== 'undefined' ? self : this, function () {
+  'use strict';
+
+  /* word -> { lang: rendering } — the base language stands for its variants. */
+  const TABLE = {
+    what:   { spa_Latn: '¿Qué?',        por_Latn: 'O quê?',      fra_Latn: 'Quoi ?',           deu_Latn: 'Was?',       ita_Latn: 'Cosa?' },
+    why:    { spa_Latn: '¿Por qué?',    por_Latn: 'Por quê?',    fra_Latn: 'Pourquoi ?',       deu_Latn: 'Warum?',     ita_Latn: 'Perché?' },
+    who:    { spa_Latn: '¿Quién?',      por_Latn: 'Quem?',       fra_Latn: 'Qui ?',            deu_Latn: 'Wer?',       ita_Latn: 'Chi?' },
+    how:    { spa_Latn: '¿Cómo?',       por_Latn: 'Como?',       fra_Latn: 'Comment ?',        deu_Latn: 'Wie?',       ita_Latn: 'Come?' },
+    where:  { spa_Latn: '¿Dónde?',      por_Latn: 'Onde?',       fra_Latn: 'Où ?',             deu_Latn: 'Wo?',        ita_Latn: 'Dove?' },
+    when:   { spa_Latn: '¿Cuándo?',     por_Latn: 'Quando?',     fra_Latn: 'Quand ?',          deu_Latn: 'Wann?',      ita_Latn: 'Quando?' },
+    which:  { spa_Latn: '¿Cuál?',       por_Latn: 'Qual?',       fra_Latn: 'Lequel ?',         deu_Latn: 'Welche?',    ita_Latn: 'Quale?' },
+    yeah:   { spa_Latn: '¿Sí?',         por_Latn: 'Sim?',        fra_Latn: 'Oui ?',            deu_Latn: 'Ja?',        ita_Latn: 'Sì?' },
+    yes:    { spa_Latn: '¿Sí?',         por_Latn: 'Sim?',        fra_Latn: 'Oui ?',            deu_Latn: 'Ja?',        ita_Latn: 'Sì?' },
+    hello:  { spa_Latn: '¿Hola?',       por_Latn: 'Olá?',        fra_Latn: 'Allô ?',           deu_Latn: 'Hallo?',     ita_Latn: 'Pronto?' },
+    right:  { spa_Latn: '¿Verdad?',     por_Latn: 'Certo?',      fra_Latn: "N'est-ce pas ?",   deu_Latn: 'Oder?',      ita_Latn: 'Vero?' },
+    really: { spa_Latn: '¿En serio?',   por_Latn: 'Sério?',      fra_Latn: 'Vraiment ?',       deu_Latn: 'Wirklich?',  ita_Latn: 'Davvero?' },
+    okay:   { spa_Latn: '¿Está bien?',  por_Latn: 'Está bem?',   fra_Latn: "D'accord ?",       deu_Latn: 'Okay?',      ita_Latn: 'Va bene?' },
+    ok:     { spa_Latn: '¿Está bien?',  por_Latn: 'Está bem?',   fra_Latn: "D'accord ?",       deu_Latn: 'Okay?',      ita_Latn: 'Va bene?' },
+    ready:  { spa_Latn: '¿Listos?',     por_Latn: 'Prontos?',    fra_Latn: 'Prêts ?',          deu_Latn: 'Bereit?',    ita_Latn: 'Pronti?' },
+    huh:    { spa_Latn: '¿Eh?',         por_Latn: 'Hã?',         fra_Latn: 'Hein ?',           deu_Latn: 'Hä?',        ita_Latn: 'Eh?' }
+  };
+
+  const VARIANT_OF = { spa_ES: 'spa_Latn', spa_MX: 'spa_Latn', por_PT: 'por_Latn' };
+
+  /* "What?", "what.", "WHAT", '"What?"' — one word, optionally punctuated. */
+  function key(text) {
+    const t = String(text || '').trim().replace(/^[\s"'“‘(\[]+/u, '').replace(/[\s"'”’)\]]+$/u, '');
+    const m = t.match(/^([A-Za-z]+)[?.!…]*$/);
+    return m ? m[1].toLowerCase() : null;
+  }
+
+  /*
+   * Only a source that IS a question (ends in '?') or is a bare interrogative
+   * word: "What." is Whisper dropping the mark; "What" alone is the same. A
+   * bare "yes"/"okay"/"right"/"ready" with a period is an ANSWER, not a
+   * question, and must reach the model as one — so those need the '?'.
+   */
+  const NEEDS_MARK = new Set(['yeah', 'yes', 'hello', 'right', 'really', 'okay', 'ok', 'ready', 'huh']);
+
+  function lookup(text, lang) {
+    const k = key(text);
+    if (!k || !TABLE[k]) return null;
+    const asked = /\?[?!.…]*\s*["'”’)\]]*$/.test(String(text || '').trim());
+    if (!asked && NEEDS_MARK.has(k)) return null;
+    const row = TABLE[k];
+    return row[lang] || row[VARIANT_OF[lang]] || null;
+  }
+
+  return { lookup, TABLE };
+}));