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

avoid data clipping after convolution with rir samples #4806

Merged
merged 2 commits into from
Aug 25, 2022

Conversation

nithinraok
Copy link
Collaborator

Signed-off-by: nithinraok nithinrao.koluguri@gmail.com

What does this PR do ?

Fix nan issue with precision=16

Collection: ASR

Changelog

  • Clip max value of data samples after convolution with rir impulses to 1

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

Copy link
Collaborator

@jbalam-nv jbalam-nv left a comment

Choose a reason for hiding this comment

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

LGTM

@@ -332,6 +332,7 @@ def perturb(self, data):
if not self._shift_impulse:
impulse_norm = (impulse.samples - min(impulse.samples)) / (max(impulse.samples) - min(impulse.samples))
data._samples = signal.fftconvolve(data._samples, impulse_norm, "same")
data._samples = data._samples / max(abs(data._samples))
Copy link
Collaborator

Choose a reason for hiding this comment

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

Please add a comment here about why we are doing this.

jbalam-nv
jbalam-nv previously approved these changes Aug 25, 2022
Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com>
Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com>
@nithinraok nithinraok merged commit 747989a into main Aug 25, 2022
@nithinraok nithinraok deleted the fix_fp16_issue_with_augmentation branch August 25, 2022 18:51
piraka9011 pushed a commit to piraka9011/NeMo that referenced this pull request Aug 25, 2022
* avoid data clipping after convolution with rir samples

Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com>

* add comments

Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com>

Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com>
Signed-off-by: Anas Abou Allaban <aabouallaban@pm.me>
jubick1337 pushed a commit to jubick1337/NeMo that referenced this pull request Oct 3, 2022
* avoid data clipping after convolution with rir samples

Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com>

* add comments

Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com>

Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com>
Signed-off-by: Matvei Novikov <mattyson.so@gmail.com>
hainan-xv pushed a commit to hainan-xv/NeMo that referenced this pull request Nov 29, 2022
* avoid data clipping after convolution with rir samples

Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com>

* add comments

Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com>

Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com>
Signed-off-by: Hainan Xu <hainanx@nvidia.com>
hainan-xv pushed a commit to hainan-xv/NeMo that referenced this pull request Nov 29, 2022
* avoid data clipping after convolution with rir samples

Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com>

* add comments

Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com>

Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com>
Signed-off-by: Hainan Xu <hainanx@nvidia.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants