Our great sponsors
-
timm-flutter-pytorch-lite-blogpost
PyTorch at the Edge: Deploying Over 964 TIMM Models on Android with TorchScript and Flutter.
-
EfficientConformer
[ASRU 2021] Efficient Conformer: Progressive Downsampling and Grouped Attention for Automatic Speech Recognition
-
WorkOS
The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.
So I tried converting an ASR model[0] to ONNX about a year or two back. It was really painful. The pain could largely be ascribed to:
(1) code that is very dynamic, making it hard for Pytorch to convert the modules to TorchScript (which it does before converting them to ONNX)
(2) ops that were simply not available in ONNX. Especially, torch.fft, also some others.
[0] https://github.com/burchim/EfficientConformer
Related posts
- how to deploy object detection and image classification model in flutter?
- PyTorch at the Edge: Deploy 964 TIMM Models on Android with TorchScript
- PyTorch at the Edge: Deploy 964 TIMM Models on Android with TorchScript
- PyTorch at the Edge: Deploy 964 TIMM Models on Android with TorchScript
- PyTorch at the Edge: Deploying Over 964 TIMM Models on Android with TorchScript and Flutter.