[TTS] MagpieTTS: Implement Frechet Codec Distance metric + some minor inference bugfixes#15223
Merged
blisc merged 9 commits intoNVIDIA-NeMo:mainfrom Jan 7, 2026
Merged
Conversation
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
nemo/collections/tts/modules/magpietts_inference/evaluate_generated_audio.py
Fixed
Show fixed
Hide fixed
Signed-off-by: Fejgin, Roy <rfejgin@nvidia.com>
Instead of taking a codec instance, accept a codec name: local path or HF/NGC name. This simplifies the metric's integration in calling code. Signed-off-by: Fejgin, Roy <rfejgin@nvidia.com>
Signed-off-by: Fejgin, Roy <rfejgin@nvidia.com>
Signed-off-by: Fejgin, Roy <rfejgin@nvidia.com>
* address some CI linting issues * include a file that was missed in last commit Signed-off-by: Fejgin, Roy <rfejgin@nvidia.com>
rfejgin
force-pushed
the
magpietts_frechet_codec_distance
branch
from
8d997ac to
3fc5f37
Compare
Signed-off-by: Fejgin, Roy <rfejgin@nvidia.com>
blisc
requested changes
Dec 30, 2025
blisc
previously approved these changes
Jan 6, 2026
* Add (optional) saving of generated codes and FCD calcualtion to longform version of inference * Clean up how disabling FCD is done: make it an explicit part of EvaluationConfig Signed-off-by: Fejgin, Roy <rfejgin@nvidia.com>
Collaborator
Author
|
@subhankar-ghosh Could you please review just the latest commit in this PR? That part touches EvaluationConfig and longform inference. I mean the commit titled |
nemo/collections/tts/modules/magpietts_inference/evaluate_generated_audio.py
Show resolved
Hide resolved
nemo/collections/tts/modules/magpietts_inference/evaluate_generated_audio.py
Show resolved
Hide resolved
Collaborator
subhankar-ghosh
left a comment
subhankar-ghosh
left a comment
There was a problem hiding this comment.
Left a few comments. They are the points where I thought things might break just for you to double check. Otherwise LGTM. Make sure the tests pass.
subhankar-ghosh
approved these changes
Jan 7, 2026
AkCodes23
pushed a commit
to AkCodes23/NeMo
that referenced
this pull request
Jan 28, 2026
… inference bugfixes (NVIDIA-NeMo#15223) * Add metric: Freceht Distance in codec embedding space Signed-off-by: Fejgin, Roy <rfejgin@nvidia.com> * Frechet Codec Distance API change Instead of taking a codec instance, accept a codec name: local path or HF/NGC name. This simplifies the metric's integration in calling code. Signed-off-by: Fejgin, Roy <rfejgin@nvidia.com> * Integrate Frechet Codec Distance in inference scripts Signed-off-by: Fejgin, Roy <rfejgin@nvidia.com> * Add a __init__.py package marker to test directory Signed-off-by: Fejgin, Roy <rfejgin@nvidia.com> * Cleanup and add missing files * address some CI linting issues * include a file that was missed in last commit Signed-off-by: Fejgin, Roy <rfejgin@nvidia.com> * Comments and cleanup Signed-off-by: Fejgin, Roy <rfejgin@nvidia.com> * Integrate FCD in longform inference and rework --disable_fcd * Add (optional) saving of generated codes and FCD calcualtion to longform version of inference * Clean up how disabling FCD is done: make it an explicit part of EvaluationConfig Signed-off-by: Fejgin, Roy <rfejgin@nvidia.com> --------- Signed-off-by: Fejgin, Roy <rfejgin@nvidia.com> Signed-off-by: Akhil Varanasi <akhilvaranasi23@gmail.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
4 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.
What does this PR do ?
Adds the Frechet Codec Distance metric and integrates it in MagpieTTS inference scripts. Also fixes some minor MagpieTTS inference bugs.
Collection: TTS
Changelog
The Frechet Distance (FD) is commonly used to evaluate generative models (e.g. Frechet Inception Distance, Frechet Audio Distance). In this PR we implements FD in the embedding space of a neural codec. This is a metric that measures how closely the distributions of real and generated codec frames match, at the single frame level.
Changes:
frechet_codec_distance.py: An implementation of FD in codec embedding space. Builds on TorchMetrics' FID implementation. We provide the audio codec as a custom feature extractor.test_frechet_coec_distance.py: Unit test--disable_fcdcommand line argument tomagpietts_inference.pytitanet_smallspeaker representation model. This was present in earlier versions of the inference scripts and appears to have been accidentally lost in recent refactoringsPR Type: