So, why don’t you try ‘nemo2riva --onnx-opset=15’ (or 16) ?
Related topics
Topic | Replies | Views | Activity | |
---|---|---|---|---|
Failed to convert Nemo model to Riva using nemo2riva for ASR | 1 | 47 | January 24, 2025 | |
Unable to convert any nemo models. PermissionError: Cannot encrypt the artifact without encryption | 1 | 571 | March 4, 2024 | |
Riva Build fails for finetuned conformer NeMo models with batch size 1 | 2 | 748 | November 1, 2022 | |
Fine Tune the hind Nvidia Nemo | 25 | 1675 | January 25, 2023 | |
JARVIS throwing errors for offline ASR when using own model | 12 | 2845 | September 4, 2021 | |
Init. Jarvis with german model | 9 | 1466 | November 4, 2021 | |
RIVA error, when deploying official Conformer ASR network | 10 | 1944 | January 27, 2023 | |
Nvidia Nemo Intent model | 6 | 1478 | October 17, 2023 | |
Tao Finetuning | 24 | 965 | December 26, 2022 | |
[jetson-voice] ASR/NLP/TTS for Jetson | 62 | 8747 | December 10, 2023 |