香港中文大学（深圳）开源的一款语音理解模型：Soundwave，核心是它的语音文本智能对齐和理解能力 Soundwave 不仅能“听懂”话，把语音转换为文字，它更注重理解语音内容含义，支持更复杂的语音交互，比如语音翻译、语音问答等 具备智能对话能力，能基于语音内容进行智能对话，且保持对话的连贯性和智能性 用了1/50的训练数据（1万小时）就达到了与Qwen2-Audio相当的性能
active 2025-02-18 → 2026-02-19 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 367 days from 2025-02-18 to 2026-02-19. Pushes: 21 total, peak 10 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 7 total, peak 3 in a day. Comments: 11 total, peak 2 in a day. Stars: 202 total, peak 18 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 |
|---|---|---|---|---|
| Puccho729 | 22 | 21 | 0 | 1 |
| xiaozhang521 | 4 | 0 | 0 | 3 |
| xxchauncey | 2 | 0 | 0 | 1 |
| world1tree | 2 | 0 | 0 | 1 |
| NielsRogge | 2 | 0 | 0 | 1 |
| ovaiscse | 1 | 0 | 0 | 1 |
| wx-333 | 1 | 0 | 0 | 1 |
| njzheng | 1 | 0 | 0 | 0 |
| cdliang11 | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 202 stars here means stars gained during the window, not the repo's star count.