why 16kHz ? why not 22kHz ?

bshall / hubert

HuBERT content encoders for: A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion

https://bshall.github.io/soft-vc/

MIT License

323 stars 53 forks source link

Open salisbury-espinosa opened 1 year ago

salisbury-espinosa commented 1 year ago

what is the reason? the quality should be better...

goldiusleonard commented 8 months ago

I think it is due to the dataset available is in 16kHz sample rate. @salisbury-espinosa