fix WASM (cpu)

src/worker/inference.worker.ts

@@ -136,6 +136,14 @@ async function createPipeline(
       const asr = await pipeline("automatic-speech-recognition", message.modelId, {
         device,
         dtype,
+        // WASM sessions cap graph optimization at "basic" (D-014): the level-2
+        // QDQ transform in the bundled onnxruntime-web build rejects the 8-bit
+        // decoders' tied embed_tokens weight ("Missing required scale …
+        // DequantizeLinear"). q4 models use native MatMulNBits ops, so the
+        // lower level costs them nothing. WebGPU keeps the default level.
+        ...(device === "wasm" && {
+          session_options: { graphOptimizationLevel: "basic" as const },
+        }),
         progress_callback: forwardProgress,
       });
       post({ type: "load-progress", status: "ready", device });