You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
How would you explain the difference between teacher forcing and knowledge distillation ? i noticed that fastspeech2 in your implementationuses knowledge ditillation by predicting durations from AR model, however in their paper, they state that they no longer use it in fastspeech2.
The text was updated successfully, but these errors were encountered:
How would you explain the difference between teacher forcing and knowledge distillation ? i noticed that fastspeech2 in your implementationuses knowledge ditillation by predicting durations from AR model, however in their paper, they state that they no longer use it in fastspeech2.
The text was updated successfully, but these errors were encountered: