+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Generative AI (https://www.datasculpting.ai/inference/forumdisplay.php?fid=17)
+--- Forum: Audio / Speech (https://www.datasculpting.ai/inference/forumdisplay.php?fid=71)
+--- Thread: Audio / Speech discussion (/showthread.php?tid=972)
Pages:
1
2
Audio / Speech discussion - signalpeak - 10-10-2026
Did a bit of testing and thought I'd post the result here.
I tried this with Mistral using LM Studio on 7900 XTX. The headline result was better than I expected, but tokens/sec still ended up being the limiting factor.
Nothing scientific here, just practical notes from a real setup.
I expected the biggest difference to come from the model, but the stack around it mattered at least as much.
Re: Audio / Speech discussion - cudapoint - 10-12-2026
I'd approach it in a boring order. On Threadripper box, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.
Re: Audio / Speech discussion - kernelghost - 10-12-2026
Thanks, that helps. That matches what I saw on A6000. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: Audio / Speech discussion - vramforge - 10-12-2026
Need a little more detail here. Do you see the same thing with a smaller batch or shorter prompt?
Re: Audio / Speech discussion - sparrowhall - 10-12-2026
Tried to reproduce it just now. The issue went away once I changed one setting and restarted the stack cleanly.
Re: Audio / Speech discussion - nanogarden - 10-12-2026
I hit almost the same issue last night.
Re: Audio / Speech discussion - sparrowcraft - 10-14-2026
worth checking the driver first.
Re: Audio / Speech discussion - cachebench - 10-15-2026
that fixed it for me too.
Re: Audio / Speech discussion - signalpeak - 10-15-2026
Quote:that fixed it for me too.
Thanks, that helps. I ended up in about the same place using vLLM. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.
Re: Audio / Speech discussion - sparrowhall - 10-16-2026
I'd start with the simpler stack.