Prevent infinite loop for out-of-bound timestamps in clip_timestamps #2005
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Outdated suggestions cannot be applied.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.
I'm using the output of
get_speech_timestamps
in Silero VAD to produce values forclip_timestamps
.The VAD produces an end timestamp that is one-sample beyond the last found voice sample. I was converting these timestamps into seconds and passing them directly into
clip_timestamps
.The problem is sometimes the end timestamp would be one sample past the end of the file. In this case, whisper would go into an infinite loop, trying to run inference on segment_size of 0.