Fixed for decoder dl speed and mobile warnings on low memory devices.

src/worker/inference.worker.ts

@@ -13,6 +13,7 @@ import {
   pipeline,
   WhisperTextStreamer,
   type AutomaticSpeechRecognitionPipeline,
+  type PretrainedModelOptions,
   type ProgressInfo,
 } from "@huggingface/transformers";
 import { resolveDefaultDtype } from "../lib/models";
@@ -256,7 +257,7 @@ async function createPipeline(
     configureWasmThreads(device);
     const dtype = message.dtype ?? resolveDefaultDtype(message.modelId, device);
     try {
-      const asr = await pipeline("automatic-speech-recognition", message.modelId, {
+      const pipelineOptions: PretrainedModelOptions & { sequentialSessionLoad?: boolean } = {
         device,
         dtype,
         // WASM sessions cap graph optimization at "basic" (D-014): the level-2
@@ -268,7 +269,12 @@ async function createPipeline(
           session_options: { graphOptimizationLevel: "basic" as const },
         }),
         progress_callback: forwardProgress,
-      });
+        // D-027/D-029: sequential sub-model session loading trades load speed
+        // for a lower peak-memory footprint — only worth it where the UI
+        // determined this load risks crashing a mobile tab.
+        sequentialSessionLoad: message.sequentialSessionLoad ?? false,
+      };
+      const asr = await pipeline("automatic-speech-recognition", message.modelId, pipelineOptions);
       // What ort actually ended up with (it clamps to 1 without isolation) —
       // surfaced to the UI so degraded threading is visible in the field.
       const threads = env.backends.onnx.wasm?.numThreads ?? 1;