Translate transcripts with Opus-MT in a dedicated translation worker

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

scripts/bench-translate.ts

@@ -0,0 +1,53 @@
+/**
+ * Transcript-translation speed on onnxruntime-node (CPU), D-WS4b.
+ *
+ *   flock /tmp/whisper-heavy.lock bun scripts/bench-translate.ts [batchSizes…]
+ *
+ * Translates the reference transcripts in tests/audio_files/ with the same
+ * Opus-MT loader and translation loop the browser worker uses, once per
+ * batch size, and prints wall-clock time, pieces, and whether the output
+ * depends on the batch size (padding). Downloads ~113 MB per direction into
+ * the Transformers.js cache on first run. Not browser numbers: WASM in a
+ * tab is slower than onnxruntime-node.
+ */
+
+import { join } from "node:path";
+import { buildTranslationUnits, getTranslationModel, translateUnits } from "../src/lib/translation";
+import { loadOpusMt } from "../src/worker/opusMt";
+
+const AUDIO = join(import.meta.dir, "../tests/audio_files");
+const batchSizes = process.argv.slice(2).map(Number).filter((n) => n > 0);
+const sizes = batchSizes.length > 0 ? batchSizes : [1, 8];
+
+for (const [file, source, target] of [
+  ["en_alien.txt", "en", "da"],
+  ["da_festuge.txt", "da", "en"],
+] as const) {
+  const model = getTranslationModel(source, target)!;
+  const text = await Bun.file(join(AUDIO, file)).text();
+  const units = buildTranslationUnits({ text, chunks: [] }).map((unit) => unit.text);
+  const loadStart = performance.now();
+  const translator = await loadOpusMt(model.id);
+  const loadMs = performance.now() - loadStart;
+  console.log(`\n${file} (${text.length} chars, ${units.length} lines) ${model.label} — load ${loadMs.toFixed(0)} ms`);
+  let baseline: string[] | null = null;
+  for (const batchSize of sizes) {
+    let pieces = 0;
+    const start = performance.now();
+    const out = await translateUnits(units, {
+      batchSize,
+      countTokens: translator.countTokens,
+      translateBatch: (batch) => translator.translateBatch(batch),
+      onProgress: (_done, total) => (pieces = total),
+    });
+    const seconds = (performance.now() - start) / 1000;
+    const same = baseline === null ? "baseline" : JSON.stringify(out) === JSON.stringify(baseline) ? "identical" : "differs";
+    baseline ??= out;
+    console.log(
+      `  batch ${String(batchSize).padStart(2)}: ${seconds.toFixed(2)} s, ${pieces} pieces, ` +
+        `${(text.length / seconds).toFixed(0)} chars/s, output ${same}`,
+    );
+  }
+  console.log(`  sample: ${baseline!.slice(0, 3).join(" | ")}`);
+  await translator.dispose();
+}

scripts/build.ts

@@ -3,7 +3,8 @@
  *
  * Emits a self-contained `dist/`:
  *   1. `bun build src/index.html` → hashed app-shell assets
- *   2. inference worker bundle at the stable /inference.worker.js URL
+ *   2. inference + translate worker bundles at stable /inference.worker.js and
+ *      /translate.worker.js URLs
  *   3. manifest + icons + onnxruntime .wasm/.mjs (dist/ort/, offline inference)
  *   4. sw.js with the precache manifest + a content-hash version injected
  *
@@ -53,6 +54,15 @@ const workerBuild = await Bun.build({
 });
 const workerScript = await workerBuild.outputs[0]!.text();
 await Bun.write(join(DIST, "inference.worker.js"), workerScript);
+// Transcript-translation worker (D-WS4b), same mechanism.
+const translateWorkerBuild = await Bun.build({
+  entrypoints: [join(ROOT, "src/worker/translate.worker.ts")],
+  target: "browser",
+  format: "esm",
+  minify: true,
+});
+const translateWorkerScript = await translateWorkerBuild.outputs[0]!.text();
+await Bun.write(join(DIST, "translate.worker.js"), translateWorkerScript);
 
 // 3. Static PWA assets + onnxruntime wasm binaries (offline inference — the
 // worker loads them from /ort/ instead of the jsdelivr CDN). The manifest and
@@ -89,6 +99,7 @@ const precachePaths = precachePathsFromOutputs(
   shellBuild.outputs.map((output) => relative(DIST, output.path)),
   [
     "inference.worker.js",
+    "translate.worker.js",
     "manifest.webmanifest",
     ...ICON_SIZES.map((size) => `icons/icon-${size}.png`),
     ...fontFiles.map((name) => `fonts/${name}`),
@@ -98,7 +109,7 @@ const fontBytes = await Promise.all(
   fontFiles.map((name) => Bun.file(join(FONTS_DIR, name)).bytes()),
 );
 const version = Bun.hash(
-  JSON.stringify(precachePaths) + swSource + workerScript + fontBytes.map((b) => Bun.hash(b)).join(),
+  JSON.stringify(precachePaths) + swSource + workerScript + translateWorkerScript + fontBytes.map((b) => Bun.hash(b)).join(),
 ).toString(36);
 await Bun.write(join(DIST, "sw.js"), injectPrecacheManifest(swSource, precachePaths, version));