本课题主要用于阅读科技论文场景。基本思路是：根据作者语音和文本内容，合成近乎真实的 音频，并结合作者的人脸图像，生成生动自然的作者讲解论文的视频。音频特征包驱动面部图像控 制分为两部分：一是提取语音特征，利用深度学习的技术生成个性化的声音。二是利用深度学习的 技术，以语音音频和人脸图像为条件，生成动态的语音同步的说话人脸视频。
active 2024-07-12 → 2024-07-12 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 1 days from 2024-07-12 to 2024-07-12. Pushes: 15 total, peak 15 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 0 total, peak 0 in a day. Comments: 0 total, peak 0 in a day. Stars: 0 total, peak 0 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| Bitnoc12 | 15 | 15 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
No issue or PR events — this repo's activity is pushes only.
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.