-
Notifications
You must be signed in to change notification settings - Fork 78
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
16k和48k的二选一还是两种都要? #49
Comments
都要,现在感觉48k可能是负优化,不如16k 我现在用好一些的数据去练一下48k模型,验证一下是否真的是负优化 |
48K的大概要到练到多少才好?我到32000步感觉听上去和10000步的一样 |
确实,偷懒了,低音会出现问题。看来还是要老老实实的,正正经经的训练48K模型。 |
参数量小的模型是这样的,底模很容易被洗干净,试听差异不是很明显,可以推理一下试试看 |
用的东北切蒲英的数据集训练的模型,效果还算理想,nsf-hifigan增强的意义不大了,断音问题明显。 |
训练时不到100步,模型的大小就不变了,这属于什么问题? |
目前练出来的48K感觉和目标原音也不太像,是不是因为我的数据集不是歌声的原因 |
indeed, I had this problem when I had the wav files in sub maps, It's definitely related too the wave files not being found. |
16k和48k的二选一还是两种都要?
The text was updated successfully, but these errors were encountered: