adelacvg / NS2VC

Unofficial implementation of NaturalSpeech2 for Voice Conversion and Text to Speech

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

48khz Samplerate

stlohrey opened this issue · comments

I have been training the v4 version and the results looked promising. Thanks for the awesome work! Now, i would like to train it on 48khz audio. Could you point me at the parameters etc i would need to change to do so?
Thank you!

First, it is essential to acquire a 48k vocoder. Second, ensure that the preprocessing for mel is aligned with the specifications of your vocoder. In the config.yaml file, adjust the in_channels parameter from 100 to match the mel dimension of your vocoder.

thanks for the tips. i found this 48k vocos model:
https://huggingface.co/kittn/vocos-mel-48khz-alpha1
i will try to make it work with that.

commented

https://huggingface.co/kittn/vocos-mel-48khz-alpha1
Could you please share the 48K VOCOS model at the following address? Thank you.
ksl103177@gmail.com