阿里语音交互端到端大模型
active 2025-12-23 → 2026-06-27 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 187 days from 2025-12-23 to 2026-06-27. Pushes: 12 total, peak 5 in a day. Pull requests: 2 total, peak 2 in a day. Issues: 28 total, peak 6 in a day. Comments: 45 total, peak 10 in a day. Stars: 386 total, peak 70 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 |
|---|---|---|---|---|
| lxchtan | 35 | 10 | 0 | 17 |
| Junehom | 7 | 0 | 2 | 5 |
| nemoramo | 4 | 0 | 0 | 3 |
| scikkk | 3 | 0 | 0 | 3 |
| triumph | 3 | 0 | 0 | 1 |
| neotech2025 | 2 | 0 | 0 | 2 |
| zhangyj21-lh | 2 | 0 | 0 | 1 |
| lukecq1231 | 2 | 2 | 0 | 0 |
| Byte-Coder2020 | 2 | 0 | 0 | 2 |
| vipcxj | 2 | 0 | 0 | 2 |
| JoshonSmith | 2 | 0 | 0 | 0 |
| yangyyt | 1 | 0 | 0 | 0 |
| chengzhen123 | 1 | 0 | 0 | 0 |
| siddharth1712 | 1 | 0 | 0 | 0 |
| keunlee | 1 | 0 | 0 | 1 |
| skrtskrtfb | 1 | 0 | 0 | 1 |
| BadDeveloper2022 | 1 | 0 | 0 | 1 |
| tuyen-tran1 | 1 | 0 | 0 | 1 |
| Gaojian00 | 1 | 0 | 0 | 0 |
| wllcpp | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#2skrtskrtfb2026-02-20 01:58请问duplex版有开源计划吗？
- Issue comment#45nemoramo2026-02-11 02:46how to achieve acceleration for the S2S Speech-to-Speech mode？
- Issue#44Saoyu992026-02-10 06:25SpeechFCEval运行脚本
- Issue#42wllcpp2026-02-02 06:00运行server报错，提示找不到matcha，但是我现在使用的是py3.12,安装matcha-tts安装不了
- Issue comment#35keunlee2026-02-01 21:14Web Demo audio output has breaks
- Issue comment#36tsinzz2026-01-31 07:19web_demo对话不回答？
- Issue comment#39nemoramo2026-01-29 08:46support funaudiochat ST2T mode inference-only in vLLM, speed up around 20x+ in short audios (1-30s) ,and around 50x+ in long audios
- Issue comment#39tuyen-tran12026-01-29 04:03support funaudiochat ST2T mode inference-only in vLLM, speed up around 20x+ in short audios (1-30s) ,and around 50x+ in long audios
- Issue comment#39BadDeveloper20222026-01-29 03:35support funaudiochat ST2T mode inference-only in vLLM, speed up around 20x+ in short audios (1-30s) ,and around 50x+ in long audios
- Issue comment#39nemoramo2026-01-28 05:56support funaudiochat ST2T mode inference-only in vLLM, speed up around 20x+ in short audios (1-30s) ,and around 50x+ in long audios
- Issue comment#39lxchtan2026-01-28 03:14support funaudiochat ST2T mode inference-only in vLLM, speed up around 20x+ in short audios (1-30s) ,and around 50x+ in long audios
- Issue comment#36zhangyj21-lh2026-01-27 06:53web_demo对话不回答？
- Issue#40njzheng2026-01-27 03:23Question in data processing, why use the output audio length for input text token?
- Issue#39nemoramo2026-01-26 10:54support funaudiochat ST2T mode inference-only in vLLM, speed up around 20x+ in short audios (1-30s) ,and around 50x+ in long audios
- Issue comment#31neotech20252026-01-26 02:17求个docker镜像地址，感谢
- Issue comment#36vipcxj2026-01-19 08:44web_demo对话不回答？
- Issue comment#36vipcxj2026-01-19 08:38web_demo对话不回答？
- Issue comment#35Mousaic2026-01-19 06:50Web Demo audio output has breaks
- Issue comment#36lxchtan2026-01-19 05:50web_demo对话不回答？
- Issue#36zhangyj21-lh2026-01-16 07:16web_demo对话不回答？
- Issue comment#30Mukil072026-01-15 06:31训练中间出现tokens，feature长度没对齐的报错
- Issue comment#34neotech20252026-01-13 06:22AttributeError: 'Loader' object has no attribute 'max_depth' when loading cosyvoice
- Issue comment#35lxchtan2026-01-12 05:44Web Demo audio output has breaks
- Issue#35siddharth17122026-01-09 06:14Web Demo audio output has breaks
- Issue#34housebaby2026-01-09 03:35AttributeError: 'Loader' object has no attribute 'max_depth' when loading cosyvoice
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 386 stars here means stars gained during the window, not the repo's star count.