[oezi]

Isn't xcodec2 also lossy? I thought it is also just another neural codec (50 tok/s, single codebook).

What are people using to upsampling back to 44,1 or 48 khz? Anything fancy?

[woodson]

They’re both lossy. They use a VAE-VQ type architecture trained with a combination of losses/discriminators. The differences are mainly the encoder/decoder architecture, the type of bottleneck quantization (RVQ, FSQ, etc.) and of course the training data.