Difference between Encodec and Funcodec

[lbehringer]

Hi,

first of all, thank you for making this toolkit publicly available.

I have a question regarding the difference between Encodec and Funcodec in your paper:
In Table 3, you list Encodec and Funcodec as different models. Initially I thought Funcodec refers to the frequency-domain model. However, on your demo page, the models "FunCodec" and "FunCodec-2x" are time-domain models, and I was unable to find a difference to the Encodec architecture (besides the training data and the increased stride for the 2x model).

I am probably missing something and would be grateful if you could clarify this.

[lbehringer]

I found that this has already been answered here: #5
Closed.