kalomaze

Hubert doesnt even handle anything to do with spec to audio. I mean in general when processing audio. It only handles spec to text speech recognition right? Your answer seems...

> I found similar exponential slowdown as mentioned by @shroominic for my use case, which is to generate code in [a language](https://hazel.org/) similar to OCaml. The speed of generation was...

I'm doing some investigation. I think the easiest way to do this without refactors to the grammar itself is by running a check to the existing grammar function with only...

> There have been a few reports where the grammar sampling can significantly degrade the performance. It would be nice to profile and optimize the implementation - there should be...

The idea is that dividing the input microphone streams into pieces without silence on a more precise level will help minimize and get rid of the artifacts that are present...

The delay could increase if there is long, uninterrupted speaking with an adaptive chunk size. Which is why a 'maximum size' as a fallback could be beneficial as a backup...

My understanding of the code may be very incorrect and based on ancedotes. I currenty assume chunk size as 'the length of the audio that is sent to RVC for...

This can be closed.

> To me, the repetition penalty is the single most important sampling parameter. Sampling from the original distribution avoids looping in almost all cases (1.0 Temperature with nothing else), but...

> BTW, has anyone ever tried to find an optimal set of sampling parameters by minimizing perplexity over a given text or something? Don't think anyone has, but I've considered...