An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.
Python · active 2025-03-07 → 2026-06-30 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 481 days from 2025-03-07 to 2026-06-30. Pushes: 33 total, peak 19 in a day. Pull requests: 16 total, peak 4 in a day. Issues: 38 total, peak 4 in a day. Comments: 63 total, peak 5 in a day. Stars: 784 total, peak 14 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 |
|---|---|---|---|---|
| alibabasglab | 31 | 12 | 6 | 9 |
| zexupan | 30 | 20 | 0 | 6 |
| gemini-code-assist[bot] | 11 | 0 | 0 | 6 |
| sriyachakravarthy | 5 | 0 | 0 | 1 |
| mayankpathak4513 | 3 | 0 | 0 | 1 |
| Paul-HenriBJT | 2 | 0 | 0 | 2 |
| northagain | 2 | 0 | 0 | 1 |
| DDR-noise | 2 | 0 | 0 | 0 |
| JasonLeon01 | 2 | 0 | 0 | 1 |
| ZJH17778383963 | 2 | 0 | 0 | 1 |
| drunkenQCat | 2 | 0 | 0 | 0 |
| Axel-Verite | 2 | 0 | 2 | 0 |
| sandsc | 2 | 0 | 0 | 2 |
| chu0118 | 2 | 0 | 0 | 2 |
| DakeQQ | 2 | 0 | 0 | 2 |
| hjj-lmx | 2 | 0 | 0 | 1 |
| Lamamanx | 2 | 0 | 0 | 1 |
| Dawsonqw | 2 | 0 | 0 | 2 |
| vizagite | 2 | 0 | 0 | 2 |
| chenqy2018 | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#161hassanforcrack-cloud2026-05-17 10:13pip install Fails in ClearerVoice-Studio
- Issue#163cslvjt2026-03-07 09:32关于modelscope里音频增强的数据流程
- Issue comment#114qinshuang2026-02-03 05:43能提供onnx的方案吗？
- Issue comment#138ChiuTC2026-01-30 08:43音视频语音提取任务，似乎默认都是各个角色都在说话的，但实际场景有可能目标说话人是没有在说话的
- Issue comment#144h12487594742026-01-09 03:40语音分离为什么在modelscope平台上测试和源码测试效果不一样?
- Issue comment#89ArkFun2026-01-07 06:29demo6 不能正常运行，生成的音频有尖锐的电子音
- Pull request#158Axel-Verite2026-01-05 14:21
- Pull request#157Axel-Verite2026-01-05 14:14
- Issue comment#157gemini-code-assist[bot]2026-01-05 14:13[LAB-T-1411] Rename aux files
- Issue#156xym48692025-12-31 23:18Trigger exception when use AV_MossFormer2_TSE_16K model
- Issue#155xinan-chen2025-12-19 08:24train/speech_enhancement/losses /loss.py 代码错误
- Issue#154meizhong9862025-12-13 23:25Memory requirements and minimum safe decode_window
- Pull request#152WarmCongee2025-12-09 10:19
- Issue comment#150gemini-code-assist[bot]2025-11-24 09:57feat: support gpu & support invoke speechscore via code
- Issue#149TobiasPfeifer2025-11-21 21:55missing model?
- Issue#147Zijun-Mo2025-11-11 08:12Bug Report: Redundant Conditional Block for `MCD_mode == "plain"`
- Issue comment#1443276353282025-10-28 12:56语音分离为什么在modelscope平台上测试和源码测试效果不一样?
- Issue comment#64fenghe122025-10-27 06:56中文二人对话对话音频分离效果差
- Issue comment#131Dawsonqw2025-10-24 03:08Numpy2Numpy需求极其庞大的显存
- Issue#145NanZheng-com2025-10-23 03:10是否支持流式
- Issue comment#131Dawsonqw2025-10-21 02:33Numpy2Numpy需求极其庞大的显存
- Issue comment#143mukherjeesougata-eros2025-10-07 06:10Usage for TSE for a particular speaker
- Issue comment#142gemini-code-assist[bot]2025-09-20 23:36Fixed minor typo in mossformer2_sr_wrapper.py
- Issue comment#75zhaoliang1983x2025-09-10 08:49跑完模型后，文件变化
- Issue#139ELK-milu2025-08-27 13:57使用av_mossformer2_tse模型实现实时的说话人音频提取可行吗？
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 784 stars here means stars gained during the window, not the repo's star count.