search

google-research / mint

Multi-modal Content Creation Model Training Infrastructure including the FACT model (AI Choreographer) implementation.
Apache License 2.0
497 stars 85 forks source link

how can i use my own audio input? #40

Open liufangzhoubaba opened 2 years ago

liufangzhoubaba commented 2 years ago

how can i use my own audio input?

liruilong940607 commented 2 years ago

Hi We are currently not support that in the code base. But it should be that hard to modify the code.

Please to refer to the preprocessing code on how to extract audio features and create the test file:

https://github.com/google-research/mint/blob/main/tools/preprocessing.py