Re:StyleTTS2 – open-source Eleven Labs quality Text To Speech
by stevenhuang on Monday November 20, 2023 @01:20AM
(#38343308)
I mean that I already have like 10 different torch venvs for different projects all with various pinned versions and CUDA variants.
Still worth the trade-off of not having to deal with dependency hell, but you start to wonder if there is a better way. All together this is many GBs of duplicated libs, wasted bandwidth and compute.
If it's starting to get old, then this means that an LLM like Copilot should be able to do it for you, no?