Can't set n_quantizers for encode()

[lonce]

It appears that DAC.encode() always uses 9 codebooks, ignoring the n_quantizer argument. The z and code index vectors returned are always the same (see screen capture below).

Thank you,

• lonce

[lonce]

I can set n_quatizers for the 16kHz model and get expected tensor sizes for codes and different z vectors, so this seems to be an issue only for the 44kHz model.

[HaiFengZeng]

you need to set model to eval state, model.eval()