AlphaMind

> 在 Paddlespeech 执行安装同时执行`pip install .`依赖和 paddlespeech, 执行`python3 setup.py install`安装 paddlespeech 不安装依赖 > > 有什么没有成功安装再安装就是依赖了 可是差的有点多啊，装了好几个库了

>  "each quantizer uses a codebook of size N = 2r/Nq = 280/8 = 1024" but i find each quantizer uses a codebook is 1024x512, so N=1024x512? and 8x10x9=720bit,...

> I was able to get it working on my side, there were quite a lot of things that I tried out, so not sure which actually made it work....

> try `dim=256` it seems to be the minimum supported size. i try dim=256, but it does not work 

还有嘛

very very very same questions

> From the spectrogram on my end, extending the speech from 24kHz to 48kHz appears to be working fine. > > I’m not entirely sure if, by “the outputs are...

> Set dim = 32 > > Like so > > ``` > import torch > > from mamba_ssm.modules.mamba2 import Mamba2 > > batch, length, dim = 2, 64, 32...