search

nii-yamagishilab / multi-speaker-tacotron

VCTK multi-speaker tacotron for ICASSP 2020
BSD 3-Clause "New" or "Revised" License
265 stars 41 forks source link

Generating LDE embeddings. #4

Closed YoavRamon closed 4 years ago

YoavRamon commented 4 years ago

Is there a way to generate the LDE embeddings for new samples that I have?

ecooper7 commented 4 years ago

yes, the code is here in a separate repository: https://github.com/jefflai108/pytorch-kaldi-neural-speaker-embeddings I have updated the readme as well.