search

triton-inference-server / server

The Triton Inference Server provides an optimized cloud and edge inferencing solution.
https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/index.html
BSD 3-Clause "New" or "Revised" License
8.2k stars 1.46k forks source link

Is there any guide to deploy QuartzNet through triton inference server? #2258

Closed zjyuan closed 3 years ago

zjyuan commented 3 years ago

I am looking for a guide to deploy QuartzNet through triton inference server. After googled, I got nothing. Hope the experts here can provide some help.

CoderHam commented 3 years ago

You can follow the instructions for deploying models here. Please also follow backend specific instructions. From my reading I understand QuartzNet is a Job Scheduler for the .NET Platform and not a backend (deep learning framework) or a model. If so Tritonserver does not cater to this usecase.

zjyuan commented 3 years ago

You can follow the instructions for deploying models here. Please also follow backend specific instructions. From my reading I understand QuartzNet is a Job Scheduler for the .NET Platform and not a backend (deep learning framework) or a model. If so Tritonserver does not cater to this usecase.

Thanks for your reply. QuartzNet is another asr model, like jasper, but smaller. FYI. https://developer.nvidia.com/blog/develop-smaller-speech-recognition-models-with-nvidias-nemo-framework/

CoderHam commented 3 years ago

Could you follow the instructions from the docs and let us know if you have any issues.

RAHUL-KAD commented 1 year ago

Here is the updated link for model repository Here