[Experimental] Use blob for decode result instead of base64 #1
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Outdated suggestions cannot be applied.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.
See huggingface/transformers.js#118 (comment).
In Android emulator (Apple M2), the inference time is down from 40s to 10s in Whisper tiny.en example. Since it's using record audio, this difference isn't very absolute.
getArrayBufferForBlob
from react-native-blob-jsi-helperThe better way will be help onnxruntime-react-native migrate to use JSI, I'm already planning for that.
* Just experimental, so it haven't handle with encode. Also didn't do Blob deletion after decode, so it may be necessary to restart the App frequently to avoid other problems.