Disable transformersjs-whisper-wasm by default.#212
Merged
Conversation
✅ Deploy Preview for webkit-jetstream-preview ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
Contributor
Author
|
CC @eqrion |
Contributor
|
@danleh would it be possible to have a trimmed-down version of this model running instead? |
kmiller68
force-pushed
the
disable-whisper-wasm
branch
from
864a583 to
d314d91
Compare
Whisper is a much more diverse workload in comparison to Bert but has some notable downsides. In particular, the model is much bigger and its overall memory footprint is much higher. This causes memory issues on iOS and seems to be related to a relatively high jetsam rate there. Whisper also takes much longer to run than Bert. So getting rid of the longer workload speeds up the benchmark overall.
kmiller68
force-pushed
the
disable-whisper-wasm
branch
from
d314d91 to
3870ecc
Compare
Contributor
Author
|
CI / Build error seems unrelated to this PR. Per sync discussions we're going to deprecate this in favor of BERT. |
Contributor
|
I would say disable instead of deprecate (I think we should keep this in the repo and ideally still evaluate internally and work on reducing the memory consumption, if we can), but otherwise: thanks for the analysis and merging! |
Contributor
Author
Ah, yeah, fair enough, disable is definitely more accurate. |
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Whisper is a much more diverse workload in comparison to Bert but has some notable downsides. In particular, the model is much bigger and its overall memory footprint is much higher. This causes memory issues on iOS and seems to be related to a relatively high jetsam rate there.
Whisper also takes much longer to run than Bert. So getting rid of the longer workload speeds up the benchmark overall.