search

NVIDIA / NeMo

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
https://docs.nvidia.com/nemo-framework/user-guide/latest/overview.html
Apache License 2.0
11.95k stars 2.49k forks source link

Export to mlmodel/mlpackage? #7603

Closed hadiidbouk closed 11 months ago

hadiidbouk commented 1 year ago

Is your feature request related to a problem? Please describe. No

Describe the solution you'd like A way to export to models like ECAPA-TDNN to an mlmodel/mlpackage so we can add it easily to our iOS applications

Provide a code snippet on how new APIs/changes would be used by others.

Describe alternatives you've considered I already traced the model and used Libtorch, it works well, but I believe having a mlpackage will reduce the size of the model and the performance will be better. Without forgetting how easy the implementation is.

titu1994 commented 1 year ago

Export of models is a best effort by our team. We only support torchscript and onnx for our models. From there, there are many further export options available - especially onnx to X

github-actions[bot] commented 12 months ago

This issue is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.

github-actions[bot] commented 11 months ago

This issue was closed because it has been inactive for 7 days since being marked as stale.