Pasha S
Pasha S
@lucidrains Thanks for the reply. so in case if i want to condition on both text and audio. i need to pass text and audio to text_embeds by token right?...
Yes I am looking forward to it ! Training code will definitely make this repo reach more audience
@Poeroz can you atleast give us some guidelines to train and finetune the model.
any updates on this ?