Fix VAD timing log to show per-call and cumulative time#3661
Open
danielbodart wants to merge 2 commits intoggml-org:masterfrom
Open
Fix VAD timing log to show per-call and cumulative time#3661danielbodart wants to merge 2 commits intoggml-org:masterfrom
danielbodart wants to merge 2 commits intoggml-org:masterfrom
Conversation
Add whisper_decode_with_state_and_aheads() which saves alignment head cross-attention data during decode, and whisper_state_get_aheads_cross_qks() to read the resulting tensor from state. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The log previously showed cumulative time labeled as just "vad time", which was misleading when called multiple times. Now shows both the per-call time and the cumulative total. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
vad time = 1.23 ms (cumulative 4.56 ms) processing 16000 samplesMotivation
When
whisper_vad_detect_speechis called multiple times (e.g. in a streaming context), the logged time was the running total, making it look like each call was getting progressively slower. This change makes it clear which value is which.