Skip to content

Report ASR LAAL (transcription commit latency)#15817

Open
naymaraq wants to merge 2 commits into
mainfrom
dkaramyan/asr-laal
Open

Report ASR LAAL (transcription commit latency)#15817
naymaraq wants to merge 2 commits into
mainfrom
dkaramyan/asr-laal

Conversation

@naymaraq

Copy link
Copy Markdown
Collaborator

Important

The Update branch button 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An outdated branch is never blocking the merge of a PR.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 ?

Add a one line overview of what this PR aims to accomplish.

Collection: [ASR]

Changelog

Adds ASR LAAL (Length-Adaptive Average Lagging) reporting — a proxy for end-of-utterance
latency that measures how far behind the audio each transcription chunk is committed.

Usage

  • You can potentially add a usage example below
# Add a code snippet demonstrating how to use this 

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The Jenkins CI system has been replaced by GitHub Actions self-hosted runners.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:

  • Make sure you read and followed Contributor guidelines
  • Did you write any new necessary tests?
  • Did you add or update any necessary documentation?
  • Does the PR affect components that are optional to install? (Ex: Numba, Pynini, Apex etc)
    • Reviewer: Does the PR have correct import guards for all optional libraries?

PR Type:

  • New Feature
  • Bugfix
  • Documentation

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

  • Related to # (issue)

Mirror the translation LAAL path for ASR: per stream, accumulate `asr_segments` =
list of (step_text, delay) where delay = request_generator.get_elapsed_duration is
the audio elapsed at the step that finalized the text. Factor the shared LAAL core
into `_compute_pipeline_laal`, rename `calculate_pipeline_laal` ->
`calculate_translation_laal`, and add `calculate_asr_laal` (skipped with a warning
when end-of-utterance detection is disabled). asr_streaming_infer logs ASR LAAL and
ST LAAL. Restores the pipeline_eval unit test.

Split out of the EoU cache-aware work into its own PR.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Signed-off-by: naymaraq <dkaramyan@nvidia.com>
@copy-pr-bot

copy-pr-bot Bot commented Jun 21, 2026

Copy link
Copy Markdown

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

@github-actions github-actions Bot added the ASR label Jun 21, 2026
@naymaraq naymaraq marked this pull request as ready for review June 21, 2026 15:19
@naymaraq

Copy link
Copy Markdown
Collaborator Author

/ok to test ca8a7e5

@github-actions

Copy link
Copy Markdown
Contributor

[🤖]: Hi @naymaraq 👋,

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.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant