Speedup buffered transducer inference: remove double decoding#15301
Merged
Speedup buffered transducer inference: remove double decoding#15301
Conversation
Signed-off-by: Vladimir Bataev <vbataev@nvidia.com>
Contributor
|
[🤖]: Hi @artbataev 👋, We wanted to let you know that a CICD pipeline for this PR just finished successfully. So it might be time to merge this PR or get some approvals. |
naymaraq
requested changes
Jan 15, 2026
Collaborator
naymaraq
left a comment
There was a problem hiding this comment.
LGTM. I’d suggest adding a one-line comment for shift_indices, since the index manipulation is a bit hard to follow.
Signed-off-by: Vladimir Bataev <vbataev@nvidia.com>
naymaraq
approved these changes
Jan 24, 2026
Collaborator
naymaraq
left a comment
There was a problem hiding this comment.
Great work! Thanks @artbataev
Contributor
|
[🤖]: Hi @artbataev 👋, We wanted to let you know that a CICD pipeline for this PR just finished successfully. So it might be time to merge this PR or get some approvals. |
nune-tadevosyan
pushed a commit
to nune-tadevosyan/NeMo
that referenced
this pull request
Mar 13, 2026
…-NeMo#15301) * Remove double decoding in RNN-T buffered inference Signed-off-by: Vladimir Bataev <vbataev@nvidia.com> --------- Signed-off-by: Vladimir Bataev <vbataev@nvidia.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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Important
The
Update branchbutton must only be pressed in very rare occassions.An outdated branch is never blocking the merge of a PR.
Please reach out to the automation team before pressing that button.
What does this PR do ?
Speedup buffered RNN-T/TDT decoding in
asr/inferenceby removing double-decoding of the chunk.Results on LibriSpeech test-other with batch size 128,
nvidia/stt_en_fastconformer_transducer_largemodel, default context sizes (1.6-4.8-1.6):*measured with warmup
RTFx without warmup: 1471 (previous) -> 1619 (here)
Collection: [ASR]
Changelog
Usage
GitHub Actions CI
The Jenkins CI system has been replaced by GitHub Actions self-hosted runners.
The GitHub Actions CI will run automatically when the "Run CICD" label is added to the PR.
To re-run CI remove and add the label again.
To run CI on an untrusted fork, a NeMo user with write access must first click "Approve and run".
Before your PR is "Ready for review"
Pre checks:
PR Type:
If you haven't finished some of the above items you can still open "Draft" PR.
Who can review?
Anyone in the community is free to review the PR once the checks have passed.
Contributor guidelines contains specific people who can review PRs to various areas.
Additional Information