mirror of
https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git
synced 2026-11-05 00:27:30 +00:00
[GH-ISSUE #1542] HuBERT ExtraLarge instead of HuBert base model? #1017
Labels
No labels
AMD/Intel
bug
bug
bug
colab
dependencies
documentation
duplicate
enhancement
following up
good first issue
help wanted
invalid
question
stale
stale
stale
todo list
wontfix
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
RVC-Project/Retrieval-based-Voice-Conversion-WebUI#1017
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @ghost on GitHub (Nov 14, 2023).
Original GitHub issue: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/issues/1542
Not an Issue:
Just wanted to know that Can we use HuBERT Extra Large model instead of HuBERT base model?
Will it perform better and generate better quality results?
Reference : https://github.com/facebookresearch/fairseq/tree/main/examples/hubert
@blakejrobinson commented on GitHub (Nov 15, 2023):
I did experiment with this. One obvious thing is that you won't be able to run models other people make (unless they also use hubert extra large) as inference requires the same HuBERT that was used to train.
Not sure I could hear much quality difference between trained models, but I didn't go into much detail once I'd realised the above.
@Tps-F commented on GitHub (Nov 16, 2023):
Support for other HuBerts, including ExtraLarge, is planned.
@ghost commented on GitHub (Nov 17, 2023):
@Tps-F Looking forward to it,
@Mixomo commented on GitHub (Nov 22, 2023):
Looking forward! 👀
@thepowerfuldeez commented on GitHub (Dec 2, 2023):
Hi! Adding some comment here, correct me if I'm wrong. Modern SVC systems use ContentVec instead of plain Hubert, which is special pre-training of Hubert that disentangles speaker features making it better suited for voice conversion task.
Using just larger Hubert might not make better quality out of the end-to-end system.
Instead, combination of Whisper-large-v3 and ContentVec gives better results, as described in this paper: https://arxiv.org/abs/2310.11160
@ghost commented on GitHub (Dec 8, 2023):
@thepowerfuldeez Have you tried this integration?
@hakku615 commented on GitHub (Apr 24, 2026):