search

TensorSpeech / TensorFlowTTS

:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)
https://tensorspeech.github.io/TensorFlowTTS/
Apache License 2.0
3.84k stars 815 forks source link

The inference process in on GPU or CPU #259

Closed peter05010402 closed 4 years ago

dathudeptrai commented 4 years ago

what do you mean ?

peter05010402 commented 4 years ago

Is possible inference on CPU？

ZDisket commented 4 years ago

@peter05010402 Yes, CPU inference is possible and very fast. I have about 0.243 RTF FastSpeech2 + Multi-Band MelGAN with LJSpeech settings when doing C++ inference on an Athlon x4 860k.

peter05010402 commented 4 years ago

@ZDisket thank you for your reply. I'll try it.