Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Conformer-based spectrogram estimator #12002

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

anteju
Copy link
Collaborator

@anteju anteju commented Jan 31, 2025

What does this PR do ?

This PR adds a spectrogram estimator based on the Conformer architecture.

Collection: audio

Changelog

  • Added a new submodule SpectrogramConformer
  • Added example config for offline and streaming configuration

Usage

N/A

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The Jenkins CI system has been replaced by GitHub Actions self-hosted runners.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

Comment on lines +129 to +131
def forward(
self, input, input_length=None, cache_last_channel=None, cache_last_time=None, cache_last_channel_len=None
):

Check notice

Code scanning / CodeQL

Returning tuples with varying lengths Note

SpectrogramConformer.forward returns
tuple of size 2
and
tuple of size 5
.
@anteju anteju added Run CICD and removed Run CICD labels Jan 31, 2025
@anteju anteju added Run CICD and removed Run CICD labels Feb 1, 2025
@anteju anteju marked this pull request as ready for review February 1, 2025 04:37
@anteju anteju requested a review from nasretdinovr February 1, 2025 04:38
real and imaginary components of the output channels.
"""

# Stack real and imaginary components
Copy link
Collaborator

@nasretdinovr nasretdinovr Feb 4, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Maybe move this comment before the line 144

@nasretdinovr
Copy link
Collaborator

Tested it locally. Looks good to me

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants