how about wav which haven't been trained ?

HarryVolek / PyTorch_Speaker_Verification

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 166 forks source link

how about wav which haven't been trained ? #21

Closed Aurora11111 closed 5 years ago

Aurora11111 commented 5 years ago

@HarryVolek
thanks for your project ,I have run it succesfully . but there is another problem,if there is a person's speech wav that haven't been trained ,can this verify it out? I mean we haven't trained any speech wav of the new person.