Article
The SOTA Text-to-speech and Zero Shot Voice cloning model that no one knows about...
By
•
•
62Delf Shkrimm
Delfshkrimm
AI & ML interests
None yet
Recent Activity
new activity
11 days ago
HKUSTAudio/Llasa-3B:Training a specific voice
new activity
18 days ago
MultiLlasa/Llasa-1B-Multilingual-German:Specific speaker example not working
new activity
21 days ago
HKUSTAudio/Llasa-1B:streaming generate
Organizations
None yet
Delfshkrimm's activity
Training a specific voice
2
#24 opened 20 days ago
by
Delfshkrimm
Specific speaker example not working
3
#1 opened 18 days ago
by
Delfshkrimm
streaming generate
2
#2 opened about 1 month ago
by
weege007
Training Llasa-3B for French
2
#21 opened 23 days ago
by
Delfshkrimm
Typo in the example
#1 opened 21 days ago
by
Delfshkrimm
upvoted
an
article
23 days ago
commented on
The SOTA Text-to-speech and Zero Shot Voice cloning model that no one knows about...
23 days ago
Hi! Thanks for the discovery :) How hard would it be to train this model for French TTS ? Would it only require 100k hours of audio dataset? or some other (maybe complete) code? I'm wondering since Llama3.2 is multilingual how does this relate to this model?
liked
a
dataset
about 1 year ago