lucasw89/au_whisper_web
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix WASM (cpu)

Browse Source
This commit is contained in:
Lucas Winther
2026-07-10 04:37:01 +02:00
parent 3be6721d46
commit 5246fb6b31
3 changed files with 36 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/offline.md
+8
View File
@@ -61,6 +61,14 @@ model.decoder.embed_tokens.weight_merged_0_scale for node:
model.decoder.embed_tokens.weight_transposed_DequantizeLinear
```
**Diagnosed & fixed (2026-07-10, D-014):** a level-2 graph-optimizer bug in
the onnxruntime-web build bundled with Transformers.js 4.2, triggered by the
8-bit decoders' tied `embed_tokens` weight — not a model or cache problem.
The worker now caps WASM sessions at `graphOptimizationLevel: "basic"`
(`src/worker/inference.worker.ts`), verified against the same ort-web build
outside the browser. **Re-run this step with Backend = WASM to confirm in a
real browser.**
## 3. Go offline and transcribe
1. DevTools → Network → throttling **Offline** (or OS airplane mode — stronger,