Wav2Lip
Wav2Lip copied to clipboard
The amplitude of the mouth shape becomes smaller with custom dataset
Guys, I found the amplitude of the mouth shape becomes smaller while use custom dataset,but the pronunciation is correct. My dataset has hundreds of characters ID,and the sync expert loss is down to 0.25. How to solve this problem? @prajwalkr
The same problem!
same problem
How did you solve this problem?
How did you solve this problem?
not yet. Sad.
How did you solve this problem?
not yet. Sad.
训练响度太大,推理响度低导致的。可以调整响度,或者调整 mel
How did you solve this problem?
not yet. Sad.
训练响度太大,推理响度低导致的。可以调整响度,或者调整 mel
How did you solve this problem?
not yet. Sad.
训练响度太大,推理响度低导致的。可以调整响度,或者调整 mel
我试试看,先感谢!
How did you solve this problem?
not yet. Sad.
训练响度太大,推理响度低导致的。可以调整响度,或者调整 mel
How did you solve this problem?
not yet. Sad.
训练响度太大,推理响度低导致的。可以调整响度,或者调整 mel
我试试看,先感谢!
您好,请问有效果吗?问题解决了吗?