Rich Pavlovskiy

Hi, thank you for the paper and open-sourcing code. From my understanding, the model works only on the dataset it was trained on and any audio/head pose/blink signal, so it...

Pruning and Quantization

1

Hi there! Thank you very much for open sourcing code and such a great paper, awesome results! I was wondering have you tried doing any pruning or quantization on the...

Hi there! I m using EMOCA in implementation of MemoryFace(https://memoryface.github.io/) - it's basically SOTA on the lipsync task currently. For that I need to have a control over only mouth-related...

Punctuation only works on tiny model.

1

Hi there! Thank you for your work. I have noticed that punctuation only works when I use tiny model. Is there a way to have punctuation on whisper large v3?...