Skip to content
This repository has been archived by the owner on Jul 11, 2024. It is now read-only.

Commit

Permalink
TITAN 48k
Browse files Browse the repository at this point in the history
  • Loading branch information
LightSpark55 committed May 22, 2024
1 parent b92d46a commit 00667b9
Showing 1 changed file with 3 additions and 1 deletion.
4 changes: 3 additions & 1 deletion Get-Started/Pretrained.md
Original file line number Diff line number Diff line change
Expand Up @@ -70,10 +70,12 @@ Works well with Korean and some types of Japanese voices. Unlike typical pre-tra
### TITAN by blaise-tk

It gives cleaner results compared to the original pretrained, also handles the accent better. Like Ov2 Super, it allows models to be trained with few epochs, it only supports **32K and 40k** sample rate.
It gives cleaner results compared to the original pretrained, also handles the accent better. Like Ov2 Super, it allows models to be trained with few epochs, it only supports **all the saple rates**.

> **32K**: https://huggingface.co/blaise-tk/TITAN/tree/main/models/medium/32k/pretrained
> **40K**: https://huggingface.co/blaise-tk/TITAN/tree/main/models/medium/40k/pretrained
> **48K**: https://huggingface.co/blaise-tk/TITAN/tree/main/models/medium/48k/pretrained
Make sure to select the sample rate according to the [sample rate](https://docs.applio.org/guides/datasets/sample-rate/#what-is-sample-rate) of the custom pretraineds.

0 comments on commit 00667b9

Please sign in to comment.