Replies: 3 comments 9 replies
-
Nemo is supposed to support multiple gpus, I think you should discuss this on their repo since the user base will be more experienced with it |
Beta Was this translation helpful? Give feedback.
1 reply
-
just got to know, we can set the device in the config file, I was using this diar_infer_meeting.yaml, so we can easily update the config file and set the device to "cuda:1" to resolve any issue. config.device="cuda:1" in helpers file will resolve this issue. |
Beta Was this translation helpful? Give feedback.
0 replies
-
facing a similar issue. Only have one GPU, still t stops the diarization at VAD. What could be the reason? |
Beta Was this translation helpful? Give feedback.
8 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hi, I am trying to load Nemo model on cuda:1, but the issue is it loads the model but when I call the diarize function it stops the diarization at VAD, what could be the possible reason for this, here is how I am loading the model, thanks.
msdd_model = ClusteringDiarizer(cfg=create_config(file_path)).to("cuda:1")
for reference, here is the attached picture,
![image](https://user-images.githubusercontent.com/83069712/235760945-9e25f26d-a3c5-45de-ad2f-d0f673cd4da7.png)
Beta Was this translation helpful? Give feedback.
All reactions