Audio / Speech discussion: setup advice

[amberkite]

This keeps coming up in conversation so I figured I'd start a thread.

One thing I keep noticing is that people underestimate batch size until they actually try to run this stuff for more than one afternoon.

Maybe obvious to some of you, but it clicked for me this week.

[vramport]

This keeps coming up in conversation so I figured I'd start a thread.

A couple things I'd check first. On A6000, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[fastscope]

This keeps coming up in conversation so I figured I'd start a thread.

My first guess would be this: If you're on TensorRT-LLM, 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.

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

[vectorfield]

I don't think that's the whole story. I've seen people blame embeddings when the real issue was much more mundane. Could be a workload difference, but I wouldn't generalize too fast from one setup. The logs were somehow calmer than I was.

[signalcraft14]

I'd approach it in a boring order. On mini PC, 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. Turns out 'just one more test' was a lie.

[flintriver50]

Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal.

[vectorfield]

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.

[kernelhouse70]

Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quality.

[sparrowgrid]

Good point. That matches what I saw on 5090. The biggest change for me was simplifying the stack instead of adding one more optimization layer.