How can i use sentis for facial animation?

[alexandreribard_unity]

Typically you need to find a model (most likely a transformer/time-series model) that takes input a wav file and outputs some blendshapes or skinning deformations.
There is a ongoing thread here:

Model didn't import: ljspeech-jets-onnx

Thanks for the feedback! This gives me a new push So basically I have to find a recreate or import a tokenizer like this GitHub - neuml/ttstokenizer: Tokenizer for Text to Speech (TTS) models