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Outdated suggestions cannot be applied.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.
Demo for Android capable of streaming audio in X second sizes.
If anyone has any better ideas for handling the audio buffer on android let me know please! Currently if there is too much audio data to be transcribed I just drop the buffer. This usually happens on silence or if you speak in nonsense. I plan on implementing a VAD library to mitigate silence being processed.
In assets/models I converted distil-small to ggml and it appears to process audio 2x faster than real time. Currently running on an S24 Ultra with just the CPU.