ubisoft-laforge-ZeroEGGS
ubisoft-laforge-ZeroEGGS copied to clipboard
a streaming pipeline
Hello guys, I wrote a streaming inference pipeline in Python for this project, including torch jit script, int8 dynamic quantization, and streaming interface for the audio encoder and decoder (style vector is pre-generated and worked as an embedding input while inference). If interested, please comment, and I will make a MR.
looking forward to it!
looking forward to it!
Reallly looking forward to it!
yes, please make a MR.
I also have a question, this means the framework support realtime generate?
looking forward to it, too!