jefflai108 / pytorch-kaldi-neural-speaker-embeddings

A light weight neural speaker embeddings extraction based on Kaldi and PyTorch.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Input vector shape

saswat0 opened this issue · comments

How is the input vector shape (800,30)? Shouldn't it be (800,64) owing to the fact that we're extracting 64 dim fbank?