[NeurIPS 2025] PyTorch implementation of [ThinkSound], a unified framework for generating audio from any modality, guided by Chain-of-Thought (CoT) reasoning.
active 2025-07-03 → 2026-06-21 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 354 days from 2025-07-03 to 2026-06-21. Pushes: 23 total, peak 6 in a day. Pull requests: 5 total, peak 3 in a day. Issues: 35 total, peak 4 in a day. Comments: 54 total, peak 6 in a day. Stars: 747 total, peak 102 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| liuhuadai | 55 | 23 | 1 | 26 |
| Jandown | 8 | 0 | 0 | 7 |
| lkcqswb | 5 | 0 | 2 | 3 |
| gravis778 | 3 | 0 | 0 | 1 |
| mikecolu | 3 | 0 | 0 | 2 |
| YangFengshan1993 | 2 | 0 | 0 | 1 |
| onestardao | 2 | 0 | 0 | 2 |
| mimi99528 | 2 | 0 | 0 | 1 |
| shanhao | 2 | 0 | 0 | 1 |
| AIFSH | 2 | 0 | 0 | 1 |
| ybx193670 | 2 | 0 | 0 | 2 |
| Moon0316 | 2 | 0 | 0 | 1 |
| RobinChen007 | 2 | 0 | 0 | 0 |
| fordcliff75 | 2 | 0 | 0 | 1 |
| jsadjasjdjas | 1 | 0 | 0 | 0 |
| somenewaccountthen | 1 | 0 | 0 | 0 |
| openaitx-system | 1 | 0 | 1 | 0 |
| ArlenCHEN | 1 | 0 | 0 | 0 |
| fangg2000 | 1 | 0 | 0 | 1 |
| SoftologyPro | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#59lkcqswb2026-03-30 03:45
- Issue comment#58lkcqswb2026-03-30 03:41PrismAudio local inference OOM: VideoPrism JAX model attempts to allocate 95GB compute buffer on single 16GB GPU (RTX 5060 Ti)
- Issue#55MrWH1232026-03-25 13:28audio vae相关以及tokenizer选择
- Issue#54EvieMu2026-03-25 07:24prismaudio 401 Client Error
- Issue comment#36onestardao2026-01-18 13:37question about audio VAE
- Issue#52wjc28302026-01-14 03:49Cannot Reproduce the Performance on VGGSound
- Issue comment#50phazei2026-01-03 23:48Where is PrismAudio model?
- Issue comment#50liuhuadai2025-12-12 02:58Where is PrismAudio model?
- Issue#49jsadjasjdjas2025-12-09 04:02模型权重问题
- Issue#47rkspsm2025-11-08 00:01Installation issues with newer GPUs
- Issue#4613042576582025-10-22 01:57同一视频在CoT Description保持不变的情况下，seed不改变，无法抽卡？
- Issue comment#39liuhuadai2025-09-01 05:46完整的CoT数据样例
- Issue comment#44liuhuadai2025-09-01 05:45关于开源audiocot数据集
- Issue#43sertacakdogan2025-08-20 11:01Meaningless Human Sound
- Issue#42notlu2025-08-20 09:55When Audiocot can be released？
- Issue comment#41mimi995282025-08-20 05:09请问为什么我只输入文本或者输入黑屏视频都会导致输出极大声的噪音？ Why do I only input text or input black screen video, resulting in extremely loud output noise?
- Issue#41mimi995282025-08-19 17:00请问为什么我只输入文本或者输入黑屏视频都会导致输出极大声的噪音？ Why do I only input text or input black screen video, resulting in extremely loud output noise?
- Issue comment#36onestardao2025-08-19 09:28question about audio VAE
- Issue#39ArlenCHEN2025-07-29 02:12完整的CoT数据样例
- Issue#37Liyang-Chen-UCLA2025-07-23 09:09Audio Editing 实现细节
- Issue#36nzhang2582025-07-21 06:08question about audio VAE
- Issue#35musend2025-07-21 04:04Dual-channel
- Issue comment#34liuhuadai2025-07-21 02:42Always generating weird music
- Issue#31gravis7782025-07-20 19:10Issue with demo.bat
- Issue#30gravis7782025-07-19 13:19issue with new code with WSL
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 747 stars here means stars gained during the window, not the repo's star count.