Optimize max peak memory usage and add warnings on mobile for higher models

src/lib/models.ts

@@ -93,6 +93,25 @@ export function formatModelSize(bytes: number): string {
   return `${Math.round(bytes / 1e6)} MB`;
 }
 
+/**
+ * Approximate peak transient memory a browser-engine load needs (D-027): for
+ * whichever of the encoder/decoder weight files is larger, transformers.js
+ * buffers the full download into one JS-heap `Uint8Array`, then
+ * onnxruntime-web mallocs a second full-size copy inside WASM linear memory
+ * to parse it at session-creation time — a per-file ~2x peak. The
+ * sequential-session-load patch (`patches/`) keeps the encoder and decoder
+ * from both being resident at once, so the two files' peaks don't add
+ * together; only the larger one sets the peak. Approximate — real browser/
+ * runtime overhead (page baseline, Cache Storage, other tabs) adds more.
+ */
+export function estimatePeakLoadBytes(model: WhisperModel, dtype: DtypeSpec): number {
+  const encDtype = typeof dtype === "string" ? dtype : dtype.encoder_model;
+  const decDtype = typeof dtype === "string" ? dtype : dtype.decoder_model_merged;
+  const encoderBytes = model.encoderParamsM * 1e6 * BYTES_PER_PARAM[encDtype];
+  const decoderBytes = model.decoderParamsM * 1e6 * BYTES_PER_PARAM[decDtype];
+  return Math.round(2 * Math.max(encoderBytes, decoderBytes));
+}
+
 // ---------------------------------------------------------------------------
 // dtype defaults (community-known-good; see file header)
 // ---------------------------------------------------------------------------