whisper alternatives lately for Mistral

[cudascope]

Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.

[quiethouse]

A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at MoE serving. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[bytegarden73]

Appreciate the detail. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[amberpatch25]

following this because I'm in the same boat.

[visionforge]

A couple things I'd check first. If you're on TensorRT-LLM, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time. I keep promising myself this is the last rebuild.

[plainember52]

I'd approach it in a boring order. If you're on PyTorch, 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.

[vramarch]

Thought I'd post a small recipe because a lot of threads ask similar things.

Just sharing a setup that ended up working reasonably well: Qwen, vLLM, A6000, with a lot of attention on consumer GPUs.

If someone wants the exact settings I can clean them up and post them.

This is mostly for local work rather than public serving. I keep promising myself this is the last rebuild.

[visionforge]

What worked for me was pretty simple. 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.

[llm_wren]

What worked for me was pretty simple. On 5090, the easiest win is often to back off the aggressive settings and see whether the problem survives. Once

Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher. I expected the model choice to matter more than it did.

[macropoint]

I hit almost the same issue last night.