这是一个用C++实现ASR推理的项目，它依赖很少，安装也很简单，推理速度很快，在树莓派4B等ARM平台也可以流畅的运行。 支持的模型是由Google的Transformer模型中优化而来，数据集是开源wenetspeech(10000+小时)或阿里私有数据集(60000+小时)， 所以识别效果也很好，可以媲美许多商用的ASR软件。
active 2023-08-15 → 2026-05-30 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 1020 days from 2023-08-15 to 2026-05-30. Pushes: 0 total, peak 0 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 10 total, peak 2 in a day. Comments: 38 total, peak 5 in a day. Stars: 192 total, peak 3 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 |
|---|---|---|---|---|
| csukuangfj | 12 | 0 | 0 | 12 |
| chenkui164 | 8 | 0 | 0 | 8 |
| Leroy-X | 7 | 0 | 0 | 5 |
| charlesw1234 | 4 | 0 | 0 | 3 |
| yunqiushuiman | 4 | 0 | 0 | 2 |
| flyingdouers | 4 | 0 | 0 | 2 |
| WanzhouW | 2 | 0 | 0 | 2 |
| Thunderltx | 2 | 0 | 0 | 1 |
| LDBS666 | 1 | 0 | 0 | 1 |
| ffhelly | 1 | 0 | 0 | 1 |
| bluesen-zhu | 1 | 0 | 0 | 1 |
| xiayezi2013 | 1 | 0 | 0 | 0 |
| 941tj4iuh-wq | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#80941tj4iuh-wq2026-01-05 09:27大佬，你好，请问最近考虑实习/工作机会吗
- Issue comment#79bluesen-zhu2025-03-31 02:45paddlespeech_stream 运行到一半,就停了
- Issue comment#62WanzhouW2025-03-25 07:06为什么离线用wav文件识别的效果很好 而在线直接读取麦克风音频识别的效果就这么差呢
- Issue comment#62csukuangfj2025-03-25 06:42为什么离线用wav文件识别的效果很好 而在线直接读取麦克风音频识别的效果就这么差呢
- Issue comment#62WanzhouW2025-03-25 06:40为什么离线用wav文件识别的效果很好 而在线直接读取麦克风音频识别的效果就这么差呢
- Issue comment#79ffhelly2024-10-12 09:01paddlespeech_stream 运行到一半,就停了
- Issue#79yunqiushuiman2024-04-18 02:41paddlespeech_stream 运行到一半,就停了
- Issue comment#75yunqiushuiman2024-04-18 02:39如何解决paddlespeech_stream模式CPU占用极高问题?
- Issue comment#78Thunderltx2024-04-01 08:54paraformer模型，为什么预训练模型所在的【仓库地址】,没找到model.pb文件
- Issue comment#77flyingdouers2024-03-28 07:04大佬，基于少量孤立词的模型压缩请指点
- Issue comment#78chenkui1642024-03-27 07:08paraformer模型，为什么预训练模型所在的【仓库地址】,没找到model.pb文件
- Issue#78Thunderltx2024-03-27 06:35paraformer模型，为什么预训练模型所在的【仓库地址】,没找到model.pb文件
- Issue comment#77chenkui1642024-03-08 09:16大佬，基于少量孤立词的模型压缩请指点
- Issue#77flyingdouers2024-03-08 08:58大佬，基于少量孤立词的模型压缩请指点
- Issue#76flyingdouers2024-03-08 08:55无法正确转换成文字
- Issue comment#76flyingdouers2024-03-06 03:01无法正确转换成文字
- Issue comment#76chenkui1642024-03-06 00:13无法正确转换成文字
- Issue comment#75chenkui1642024-01-26 05:46如何解决paddlespeech_stream模式CPU占用极高问题?
- Issue#75xiayezi20132024-01-26 02:52如何解决paddlespeech_stream模式CPU占用极高问题?
- Issue comment#74csukuangfj2024-01-01 14:43希望可以直接输出字幕文件
- Issue comment#74Leroy-X2024-01-01 11:49希望可以直接输出字幕文件
- Issue comment#74csukuangfj2024-01-01 07:07希望可以直接输出字幕文件
- Issue#74Leroy-X2024-01-01 06:38希望可以直接输出字幕文件
- Issue comment#71csukuangfj2024-01-01 04:32求作者来个FastTTS吧
- Issue comment#71Leroy-X2024-01-01 03:22求作者来个FastTTS吧
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 192 stars here means stars gained during the window, not the repo's star count.