pytorch-kaldi-neural-speaker-embeddings

pytorch-kaldi-neural-speaker-embeddings copied to clipboard

Hi. I am exploring about speed of training and inference different multi speaker TTS models on single CPU or on singe GPU. Thanks for any explanation in this case for...

Adibian

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?

saswat0

I run the decode.py, but got an error is out of memory in GPU, can you fix it? thanks!

haha010508

Trained Models

1

can u send the Pre-Trained Models to the mail [email protected], thanks!

sicilyliulc

Hi, first of all, I really appreciate for your work based on KALDI platform for "Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition System". but,...

zeek-han