vits2
VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design
daniilrobnikov/vits2
View on GitHub ↗VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design
vits2 grew +0.3% in the last 30 days, ranks 73rd of 76 in Audio / Speech Models, last commit 1,139 days ago.
Star trajectory
115 days tracked2026-07-02648 stars today2026-10-25
Momentum
+0.3% in 30d, above the Audio / Speech Models median of +0.3%.
Maintenance
Last commit 1,139 days ago, staler than the median of 277d.
How it compares in Audio / Speech Models
vits2
648
stars
+0.3% 30d
commit 1,139 days ago
Audio / Speech Models median
1.9k
stars
+0.3% 30d
commit ~277d ago
Leader · GPT-SoVITS
63.6k
stars
+2.4% 30d
commit 5 days ago
Ranked 73rd of 76 by stars.
- Language
- Jupyter Notebook
- License
- MIT License
- Contributors
- 1
- Forks
- 75
- Watchers
- 12
- Open issues
- 21
- Releases
- 0
- Created
- 2023-07-29
- Stars this week
- +1
You've seen where vits2 stands today.
Get the moves before everyone else: the 5 Audio / Speech Models repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.