Help with Audio / Speech: setup advice

[llmarch83]

Posting this in case it saves someone else a little time.

I'm helping a small team set up a local workflow. We don't need a giant stack, but we do care about reranking.

Simple and boring is a valid answer.

[sanescope]

A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.

[signalpeak]

A couple questions before I guess too hard. Is this local-only or are you routing anything externally?

[vramforge]

A couple questions before I guess too hard. Is this local-only or are you routing anything externally?

same here on my side.

[vectorfield]

My first guess would be this: On 5090, the easiest win is often to back off the aggressive settings and see whether the problem survives. Once you know the plain path works, then add the faster path back in piece by piece.

[signalcraft14]

Thanks, that helps. The pattern around batch size has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[cozywire]

A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Kimi and compare from there.

[prompttinker44]

My first guess would be this: If you're on Ollama, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[sparrowhall]

I tested this tonight. I couldn't reproduce the slowdown until I pushed context much higher.

[signalpeak]

A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Kimi and compare from there.

Tried to reproduce it just now. The issue went away once I changed one setting and restarted the stack cleanly. I expected the model choice to matter more than it did.

If you post your exact settings, people here can probably narrow it down pretty fast.