WavTokenizer
[ICLR 2025] SOTA discrete acoustic codec models with 40/75 tokens per second for audio language modeling
jishengpeng/WavTokenizer
View on GitHub ↗[ICLR 2025] SOTA discrete acoustic codec models with 40/75 tokens per second for audio language modeling
WavTokenizer grew +0.4% in the last 30 days, ranks 54th of 76 in Audio / Speech Models, last commit 601 days ago.
Star trajectory
114 days tracked2026-07-021.3k stars today2026-10-24
Momentum
+0.4% in 30d, above the Audio / Speech Models median of +0.2%.
Maintenance
Last commit 601 days ago, staler than the median of 276d.
How it compares in Audio / Speech Models
WavTokenizer
1.3k
stars
+0.4% 30d
commit 601 days ago
Audio / Speech Models median
1.9k
stars
+0.2% 30d
commit ~276d ago
Leader · GPT-SoVITS
63.6k
stars
+2.5% 30d
commit 4 days ago
Ranked 54th of 76 by stars.
- Language
- Python
- License
- MIT License
- Contributors
- 1
- Forks
- 116
- Watchers
- 23
- Open issues
- 67
- Releases
- 0
- Created
- 2024-08-29
- Stars this week
- +1
You've seen where WavTokenizer 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.