WIP: uncommitted work at pause (session limit)

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

tests/live-real-model.test.ts

@@ -10,6 +10,9 @@ import {
   type LiveTranscribeFn,
 } from "../src/lib/live";
 import { resolveDefaultDtype } from "../src/lib/models";
+import { LONG_FORM_DEFAULTS, transcribeLongForm } from "../src/worker/longform";
+import { createWhisperDeps, loadSileroVad } from "../src/worker/longform/transformers";
+import { decodeClip } from "./clips";
 import { wordErrorRate } from "./dsp";
 
 /**
@@ -265,6 +268,9 @@ describe("live pipeline accuracy (real model, real recordings)", () => {
           normalize(reference),
           normalize((await transcribe(whole)).text),
         );
+        // File-mode accuracy gate (spec 001): the chunked file path is held
+        // to the same per-clip bar as live.
+        expect(fileWer).toBeLessThanOrEqual(MAX_WER_BY_CLIP[clip.base] ?? MAX_WER);
 
         // The live session, with the injected clock advancing with the audio
         // fed so pass scheduling behaves as in real time.
@@ -310,3 +316,61 @@ describe("live pipeline accuracy (real model, real recordings)", () => {
     );
   }
 });
+
+// ---------------------------------------------------------------------------
+// File-mode accuracy of the long-form pipeline (D-WS3a): Silero VAD chunks,
+// one decode per ≤ 30 s chunk — the path behind "Skip silence". Same
+// per-clip bars as the live and chunked file paths above.
+// ---------------------------------------------------------------------------
+
+describe("long-form file pipeline accuracy (real model, real recordings)", () => {
+  for (const clip of clips) {
+    test.skipIf(!available)(
+      `${clip.base} (${clip.language}): long-form whole-file transcript stays close to the reference`,
+      async () => {
+        const reference = await Bun.file(join(AUDIO_DIR, clip.transcriptFile)).text();
+        const audio = await decodeClip(clip.audioFile);
+        const asr = await loadAsr();
+        const vad = await loadSileroVad({ localOnly: false });
+        try {
+          const result = await transcribeLongForm(
+            audio,
+            {
+              speechProbabilities: (pcm) => vad.speechProbabilities(pcm),
+              ...createWhisperDeps(asr, { multilingual: true }),
+            },
+            { ...LONG_FORM_DEFAULTS, language: clip.language, task: "transcribe" },
+          );
+          const wer = wordErrorRate(normalize(reference), normalize(result.text));
+          expect(wer).toBeLessThanOrEqual(MAX_WER_BY_CLIP[clip.base] ?? MAX_WER);
+          expect(result.noSpeech).toBe(false);
+          const last = result.chunks.at(-1)!;
+          expect(last.timestamp[1] ?? last.timestamp[0]).toBeLessThanOrEqual(
+            audio.length / RATE + 1,
+          );
+          if (clip.language !== "en") {
+            // "Auto-detect" in the UI: the chunked path forces English here
+            // (Transformers.js 4.2 has no detection); long-form detects once
+            // on the first speech chunk and pins it (D-WS3a).
+            const auto = await transcribeLongForm(
+              audio,
+              {
+                speechProbabilities: (pcm) => vad.speechProbabilities(pcm),
+                ...createWhisperDeps(asr, { multilingual: true }),
+              },
+              { ...LONG_FORM_DEFAULTS, task: "transcribe" },
+            );
+            expect(auto.language).toBe(clip.language);
+            expect(
+              wordErrorRate(normalize(reference), normalize(auto.text)),
+            ).toBeLessThanOrEqual(MAX_WER_BY_CLIP[clip.base] ?? MAX_WER);
+          }
+        } finally {
+          await vad.dispose();
+        }
+      },
+      DOWNLOAD_BUDGET_MS +
+        probeDurationSeconds(join(AUDIO_DIR, clip.audioFile)) * MS_PER_AUDIO_SECOND,
+    );
+  }
+});

tests/offline.md

@@ -106,6 +106,25 @@ Result: Works.
 
 Result: Works
 
+## 5. "Skip silence" (long-form pipeline, D-WS3a/D-WS3b)
+
+1. Online, open **Advanced**, tick **Skip silence in uploaded files**, and
+   transcribe a file. DevTools → Network shows one request for
+   `onnx-community/silero-vad/…/onnx/model.onnx` (2.2 MB); the console logs
+   "speech-detection (VAD) model ready". The transcript arrives with progress
+   moving in jumps over pauses. Repeat on WebGPU (the owner's backend) and note
+   wall-clock against the same file with the option off.
+2. Go offline (DevTools "Offline"), reload, transcribe again: no network
+   request at all, same long-form path (console line as above).
+3. Clear only the silero-vad entries from `transformers-cache` (Application →
+   Cache Storage), stay offline, transcribe: still no network request; the
+   console says the VAD model is unavailable and the file is transcribed the
+   usual way.
+4. Transcribe a file of pure silence or music with the option on: the
+   transcript reads "No speech was found in this recording."
+
+Result: _pending (no real browser in the dev environment)_
+
 ## Recording the result
 
 When this passes in a real browser, flip the `[~]` offline-verification item