unrea1-sama

> I'm applying MAS to FastSpeech2 to replace MFA tool. I'm using encoder output in FastSpeech2 as the encoder output in Glow-TTS to fed into MAS method. After several iteration,...

> The `duration_target` is not None even when it is called in the validation step, which will cause the model to use the ground truth directly instead of the predicted...

I'm now using mfa version 2.0.1. I will update it and see if this still happens again. Thankyou!

1. You can change another music player to see if this problem still exists. It seems that the default music player in Windows10 will have noise at the end. But...