TTS that sounds less fake

[vectorfield]

Maybe I'm missing something obvious.

My current setup is TensorRT-LLM with B200, and I keep running into prefill/decode split.

Would appreciate practical advice rather than theory.

For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.

[tensorworks]

Maybe I'm missing something obvious.

Can you fill in a bit more context? Are you testing this on 4090 or something else?

[kernelpeak]

following this because I'm in the same boat.

[amberpatch25]

I tested this tonight. The issue went away once I changed one setting and restarted the stack cleanly. The surprise was that memory pressure showed up before throughput collapsed.

[bytegarden73]

A couple things I'd check first. If you're on LM Studio, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.

[kernelpeak]

What exact setup are you running? Are you testing this on B200 or something else?

[amberpatch25]

Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it did.

[tensorkite]

Good point. The pattern around token cost has been pretty similar for me.

[cudascope]

worth checking the driver first.

[southspark]

Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher.