support batch processing #57
Merged
Conversation
This file contains 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
|
epic thank you tengda |
|
Hi @TengdaHan, can you clarify how we should specify an optimal batch size please? It seems that a batch_size of 16 would divide the audio in 16 equally sized chunks. But does that mean that these 16 chunks will be processed in parallel? |
|
@Barabazs The audio file is chunked in the other direction: a batch_size of 16 divides the audio into X batches where each has 16 audio segments. Then each batch is transcribed together: https://github.com/m-bain/whisperX/blob/main/whisperx/transcribe.py#L415 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
What it is: Parallalize the
transcribefunction. It gives at least 2X speedup on transcribing.TODO: supporting temperature sweeping under batch processing.