Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recognition capability.
Python · active 2025-03-28 → 2026-07-02 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 462 days from 2025-03-28 to 2026-07-02. Pushes: 4 total, peak 1 in a day. Pull requests: 5 total, peak 1 in a day. Issues: 51 total, peak 9 in a day. Comments: 85 total, peak 6 in a day. Stars: 496 total, peak 22 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 |
|---|---|---|---|---|
| kaituoxu | 36 | 4 | 0 | 17 |
| FireRedTeam | 10 | 0 | 0 | 10 |
| csukuangfj | 9 | 0 | 0 | 9 |
| PatchouliTIS | 5 | 0 | 0 | 4 |
| fastfading | 5 | 0 | 0 | 2 |
| xphh | 4 | 0 | 0 | 3 |
| xsank | 4 | 0 | 0 | 3 |
| luckfu | 3 | 0 | 0 | 1 |
| 2019210489cqupt | 3 | 0 | 0 | 3 |
| Glorainow | 3 | 0 | 0 | 1 |
| vibe-viscot | 3 | 0 | 0 | 1 |
| xinwang0304 | 3 | 0 | 0 | 0 |
| haoming-codes | 2 | 0 | 0 | 0 |
| frenemycode | 2 | 0 | 0 | 0 |
| nwy2010 | 2 | 0 | 0 | 2 |
| twmht | 2 | 0 | 0 | 2 |
| 100apps | 2 | 0 | 2 | 0 |
| yuafowo | 2 | 0 | 0 | 2 |
| lxp3 | 2 | 0 | 0 | 1 |
| redlotus1 | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#45kaituoxu2026-03-19 03:04执行inference_fireredasr_aed.sh inference_fireredasr_llm.sh 脚本报传参错误
- Issue comment#35kaituoxu2026-03-19 03:03我在识别个别的语音的时候 会有报错
- Issue#107kaituoxu2026-03-19 03:01语音转写速度有点慢
- Issue comment#50kaituoxu2026-03-19 03:01VLLM 部署
- Issue#78kaituoxu2026-03-19 03:00音频中静音部分影响转写？
- Issue comment#94kaituoxu2026-03-19 02:59改了一个webui在线使用
- Issue#104kaituoxu2026-03-19 02:585090不支持？
- Issue comment#99kaituoxu2026-03-18 02:51Achieve Over 20% Speedup with PyTorch SDPA
- Issue comment#108PatchouliTIS2026-03-07 06:36[Inference Performance] Enable vLLM support
- Issue comment#53kaituoxu2026-03-05 07:01请问如何用微调后如何在wenet调用aed模型
- Issue#64kaituoxu2026-03-05 06:59方言识别问题
- Issue comment#39kaituoxu2026-03-05 06:58FireRedASR-AED-XS/S/M的版本大佬们方便开源嘛
- Issue comment#39csukuangfj2026-02-25 05:41FireRedASR-AED-XS/S/M的版本大佬们方便开源嘛
- Pull request#116100apps2026-01-29 05:05
- Issue comment#50PatchouliTIS2026-01-08 06:19VLLM 部署
- Issue comment#50PatchouliTIS2026-01-07 12:14VLLM 部署
- Issue comment#502019210489cqupt2026-01-07 11:06VLLM 部署
- Issue comment#50PatchouliTIS2026-01-07 04:58VLLM 部署
- Issue comment#502019210489cqupt2026-01-07 04:08VLLM 部署
- Issue comment#502019210489cqupt2026-01-07 03:40VLLM 部署
- Pull request#116100apps2025-12-28 11:22
- Issue comment#113kaituoxu2025-12-21 05:34目前只支持wav文件输入嘛 直接从麦克风获取音频数据送入模型可以不
- Pull request#115yuekaizhang2025-12-18 08:48
- Issue comment#93Witty-Chloroplast2025-12-12 08:28AttributeError: 'Namespace' object has no attribute 'sos_id'
- Issue#110frenemycode2025-12-09 12:12运行 speech2text.py 报错，FireRedAsr.from_pretrained() takes 2 positional arguments but 3 were given
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 496 stars here means stars gained during the window, not the repo's star count.