#I am trying to make my voice PE work locally
1 messages · Page 1 of 1 (latest)
1 messages · Page 1 of 1 (latest)
I have a nice dedicated system for this 20 cores, 32G ram, 2TB storage, GeForce RTX 5060 GPU. My understanding is that I can install ollama and whisper (faster_whisper) on that machine and have it do the stt and llm work. Is that correct?
Yes
And Piper for TTS too if you want
What’s the latency going to be like?
I'm not sure the addons support using the GPU though.