kimi音频转换Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation
active 2025-04-25 → 2026-06-12 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 414 days from 2025-04-25 to 2026-06-12. Pushes: 4 total, peak 4 in a day. Pull requests: 18 total, peak 8 in a day. Issues: 81 total, peak 18 in a day. Comments: 133 total, peak 29 in a day. Stars: 1,981 total, peak 573 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 |
|---|---|---|---|---|
| AlanSwift | 24 | 1 | 5 | 15 |
| MoyanZitto | 21 | 3 | 5 | 11 |
| chaunceyliu30 | 7 | 0 | 0 | 5 |
| leo19941227 | 6 | 0 | 0 | 3 |
| xingchensong | 5 | 0 | 0 | 5 |
| SimZhou | 5 | 0 | 0 | 4 |
| SherlockHao | 5 | 0 | 0 | 1 |
| rsxdalv | 5 | 0 | 1 | 4 |
| effort-yq | 5 | 0 | 0 | 2 |
| hua2014 | 4 | 0 | 0 | 3 |
| weedge | 4 | 0 | 3 | 0 |
| sunnysouthfire | 4 | 0 | 0 | 3 |
| wwfcnu | 3 | 0 | 0 | 3 |
| Graduo | 3 | 0 | 0 | 3 |
| Kydon-ai | 3 | 0 | 0 | 2 |
| wzy3650 | 3 | 0 | 0 | 1 |
| zhnglicho | 3 | 0 | 0 | 3 |
| miovovo | 3 | 0 | 0 | 1 |
| wulaoshi | 3 | 0 | 0 | 2 |
| tianzhangwu | 3 | 0 | 0 | 2 |
Recent activity
Latest issues, pull requests and releases
- Issue#51XXGUI2026-03-09 09:30docker pull异常
- Issue comment#77SolutionArichtect2025-12-24 07:32效果不错，期待支持 vllm 部署
- Issue#159SandroChen2025-12-10 08:23请教下有比较好用的服务端代码吗？
- Issue comment#115Mukil072025-11-29 07:58Quick question regarding S2S fine-tuning
- Issue comment#133TKL-tao2025-11-26 01:50WARN StateMonitor:4e4c65886b652b0b:Rank1 : kernel begins at work 55731 may hang in polling, time 20250710-204243
- Issue comment#2kkailaasa2025-11-12 20:43finetune /train code
- Issue#154soaring06162025-11-04 04:38---
- Issue comment#145newday12552025-09-28 03:00偶尔出现asr非常慢，并且生成的文字都是重复内容
- Issue comment#153taoli-github2025-09-28 02:14微调停住
- Issue comment#45ranck6262025-09-27 17:42Some plans for Kimi-Audio.
- Issue#153FreeLo0op2025-09-23 10:18微调停住
- Issue#151taoli-github2025-09-17 03:31微调时对训练数据的时长有要求吗
- Issue#150117212062025-09-09 03:48how to use self-own tts data finetune kimi-audio
- Issue#149shnulailai2025-09-03 03:08请问支持声音标识吗，区分不同人讲的话
- Issue#147hyysam2025-08-22 05:50why "audio-text" input not use whisper feature?
- Issue comment#120woskii2025-08-21 12:20RuntimeError in Multi-turn Conversation with Long History 运行有较长历史的多轮对话时报错
- Issue comment#101zhaodp2025-08-19 06:07模型重复输出
- Issue#144Amber09132025-08-18 08:22加载超大数据集内存会爆炸
- Issue#140xxr33762025-08-13 06:17这就是用openAI的whisper large v3加GPT-style wrapper打了 个包，然后就做为新模型发布了？a shame to China
- Issue comment#142HelloWorldU2025-08-12 04:12Confused code in dual-steam logits
- Issue#138Kydon-ai2025-08-08 09:20[BUG]为什么我跑出来全是哀叹的声音，demo跑不动
- Issue comment#138Kydon-ai2025-08-08 07:05[BUG]为什么我跑出来全是哀叹的声音，demo跑不动
- Issue#141jee0192025-08-07 08:04Request for training code and dataset details for reproduction
- Issue comment#2624DavidHuang2025-08-06 05:20加载speech_encoder的时候会报错
- Issue comment#140sunnysouthfire2025-08-05 04:47这就是用openAI的whisper large v3加GPT-style wrapper打了 个包，然后就做为新模型发布了？a shame to China
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1,981 stars here means stars gained during the window, not the repo's star count.