Closed 313024351 closed 5 years ago
We don't have any recipe that uses both of those things.
On Sun, Dec 16, 2018 at 5:17 PM 韩佳俊 notifications@github.com wrote:
I want to decode through VTLN model and i-vecotr model. How do I achieve it? I don't see any "decode.sh" that has vtln+ivecotr. thanks.
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/kaldi-asr/kaldi/issues/2918, or mute the thread https://github.com/notifications/unsubscribe-auth/ADJVu_44veItn2sVZsaIZXW3pjngzXXCks5u5vDAgaJpZM4ZVijl .
Can I add vtln to nnet2/decode.sh?
We don't have any recipe that uses both of those things. … On Sun, Dec 16, 2018 at 5:17 PM 韩佳俊 @.***> wrote: I want to decode through VTLN model and i-vecotr model. How do I achieve it? I don't see any "decode.sh" that has vtln+ivecotr. thanks. — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#2918>, or mute the thread https://github.com/notifications/unsubscribe-auth/ADJVu_44veItn2sVZsaIZXW3pjngzXXCks5u5vDAgaJpZM4ZVijl .
Can I add vtln to nnet2/decode.sh?
I don't believe the nnet2 recipes support training on adapted features. Anyway, the short answer is that if you have to ask, you probably wouldn't be able to do it.
Hi @313024351 , Can you share decoding script if you was able to achieve any decoding with VTLN? (or any guidance, please :))
I want to decode through VTLN model and i-vecotr model. How do I achieve it? I don't see any "decode.sh" that has vtln+ivecotr. thanks.