New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Slow inference on apple silicone #190

Open

SaKiEQ opened this issue Jan 23, 2025 · 0 comments

SaKiEQ commented Jan 23, 2025

Howdy,

this is more of question to validate what I have been doing as a error. The setup I am using runs just fine.

Apple Silicone M3 - macBook - OS X Sequoia latest 15.3 (24D60) version - 18GB ram

Using "parler-tts/parler-tiny-v1-jenny" voice for testing.
torch_device = "mps"

Yet my inference times on a 100 char sentence is around 90seconds.
It averages to about 10x per second of audio generated.

Is this the expected speed, or is something totally wrong at my end ?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment