Replies: 1 comment
-
This model wasn't released by Nvidia, so you can only use telephonic, you can tune the parameters in the YAML file for better performance |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I think there is an error in the diarization, I don't know where but I know it is there, I have made transcription of several audios and with the domine_type: "telephonic", but if there are more than 3 speakers it doesn't take them into account. I tried to try with "meeting", but in the msdd_model is "null" (line 59 of diar_infer_meeting.yaml), I tried to try with the msdd_model "telephonic", while keeping the domine_typr: "meeting", but I get a GPU memory error asking for more than 50GB. I would like to know if you have any suggestions on how to use the domine_typer of meeting, as I would like to try with meeting transcriptions.
Sorry for my bad English and congratulations you have a very accurate program, thank you very much for your time.
Translated with DeepL.com (free version)
Beta Was this translation helpful? Give feedback.
All reactions