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

ONNX runtime for Nemo models (#26) #27

Merged
merged 3 commits into from
May 12, 2023
Merged

ONNX runtime for Nemo models (#26) #27

merged 3 commits into from
May 12, 2023

Conversation

github-actions[bot]
Copy link

@github-actions github-actions bot commented May 12, 2023

Description

  • Shift from pytorch to onnx runtime for nemo models (x2 faster for Rpi4)
  • Replacing resampy with soxr as x10 faster
  • Using torchscript preprocessor, waiting for onnx here
  • Dependencies list reduced to onnx, torch, sentencepiece
  • Added available_languages importable variable

Other Notes

No breaking changes

* Updated requirements

* Added model sample_rate field

* Added onnx execution

* Added trim_memory

* Use soxr resampling

* Added read_file

* Fix tensor warning

* Added available_languages property
@NeonBohdan
Copy link
Collaborator

@NeonDaniel Please release this as 0.2.0 for NeonGeckoCom/neon-stt-plugin-nemo#15 to merge

@NeonDaniel NeonDaniel marked this pull request as ready for review May 12, 2023 19:48
@NeonDaniel NeonDaniel merged commit 2f1c862 into main May 12, 2023
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.

2 participants