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 +1,37 @@
+/* The whole chain as engine.js runs it: split -> liturgy-or-NLLB -> guard. */
+import { pipeline, env } from '@huggingface/transformers';
+import { createRequire } from 'module';
+import os from 'os'; import path from 'path'; import fs from 'fs'; import vm from 'vm';
+const require = createRequire(import.meta.url);
+const Liturgy = require('./liturgy.js');
+const Guard = require('./mt-guard.js');
+
+const src = fs.readFileSync('engine.js','utf8');
+const sb={console}; vm.createContext(sb);
+vm.runInContext(src.match(/^const ABBREV_TAIL = .*$/m)[0], sb);
+const grab=(n)=>{const i=src.indexOf('function '+n+'(');let d=0;for(let k=src.indexOf('{',i);k<src.length;k++){if(src[k]==='{')d++;else if(src[k]==='}'&&--d===0)return src.slice(i,k+1);}};
+vm.runInContext(grab('splitSentences'), sb);
+
+env.allowLocalModels=false;
+env.cacheDir=path.join(os.homedir(),'Library/Application Support/Church Translate Models');
+const pipe=await pipeline('translation','Xenova/nllb-200-distilled-600M',{dtype:'fp32'});
+
+const CASES=['God is good. Amen.','Amen.','Hallelujah.','Donald Trump.',
+             'Can I get an amen?','Jesus wept. Amen.','Dr. Luke wrote this. Amen.'];
+const LANGS=['spa_Latn','fra_Latn','deu_Latn','zho_Hans'];
+
+for (const text of CASES) {
+  console.log('\n"'+text+'"   -> '+JSON.stringify(sb.splitSentences(text)));
+  for (const lang of LANGS) {
+    const parts=[];
+    for (const s of sb.splitSentences(text)) {
+      const set=Liturgy.lookup(s,lang);
+      if (set) { parts.push(set+'  [liturgy]'); continue; }
+      const o=await pipe(s,{src_lang:'eng_Latn',tgt_lang:lang});
+      const raw=(Array.isArray(o)?o[0]:o).translation_text.trim();
+      const g=Guard.clean(s,raw);
+      parts.push(g.text + (g.trimmed?'  [guard: '+g.reason.slice(0,40)+']':''));
+    }
+    console.log('   '+lang+'  '+parts.join('  |  '));
+  }
+}