Juan Coria

@swm35 the warnings are not the cause of the issue. I also get them without a segmentation fault. Since you get the progress bar, `StreamingInference` is at least getting to...

@swm35 thank you for that valuable info. I suggest you separate that line into: ```python wave = wave.to(self.device) output = self.model(wave) output = output.cpu() return output ``` Then debug line...

@swm35 I suggest you open an issue on pyannote.audio. It could be a matter of model size but I wouldn't be so sure

Hi @danielrhodes, as I posted previously, I suggest you debug line by line until you arrive to the line that's causing the crash. Once we know which line causes it...

I like it, that way we can automatically set the lowest possible latency. This could be implemented as `--step auto`, but also somewhere in the python API

**Another idea:** Implement this as a `diart.profile recording.wav` that also runs a quick grid search on that file to suggest hyper-parameter values without running a costly tuning. This would be...

thanks @sorgfresser ! I think you could simplify that by using `python:3.10-bookworm`. Also, no need to use venv, right?