fix(pwa): cache ML model weights so they don't re-download on refresh - #86
Merged
Conversation
transformers.js fetches Whisper weights from huggingface.co (cross-origin) and its own Cache Storage wasn't reliably persisting for users, so the model re-downloaded on every refresh. Add a service-worker CacheFirst runtimeCaching rule for the HF hosts (incl. cdn-lfs* / *.hf.co redirect CDNs) and cdn.jsdelivr (ORT wasm) — our SW now serves them from cache across refreshes. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Deploying with
|
| Status | Name | Latest Commit | Updated (UTC) |
|---|---|---|---|
| ✅ Deployment successful! View logs |
goodwebtools | 680d6f4 | Aug 01 2026, 11:51 AM |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The Whisper model re-downloaded on every refresh — transformers.js fetches it from huggingface.co (cross-origin) and its own Cache Storage wasn't persisting. Add a service-worker CacheFirst runtimeCaching rule for the HF hosts (incl.
cdn-lfs*/*.hf.coredirect CDNs) +cdn.jsdelivr.net(ORT wasm), so our SW serves them from cache across refreshes.Verified the rule is in the generated
sw.js. build green.*.huggingface.co/*.hf.co(e.g. CloudFront), that host won't match — the fully-robust fallback is self-hosting the models on our R2. Will confirm with the reporter.🤖 Generated with Claude Code