PyTorch implementation of "Generalized End-to-End Loss for Speaker Verification" by Wan, Li et al.
BSD 3-Clause "New" or "Revised" License
575
stars
165
forks
source link
# this works fine for timit but if you get array of shape 0 for any o… #58
Closed
pranshurastogi29 closed 4 years ago
…ther audio change value of top_db # for vctk dataset use top_db=100
this works fine for timit but if you get array of shape 0 for any other audio change value of top_db
for vctk dataset use top_db=100