dsh-video-lens
MITGive text-only DeepSeek Harness agents video understanding: scene-aware frame sampling + VLM + optional ASR transcript fused into timeline evidence. / 给纯文本模型的视频理解插件(场景感知抽帧 + VLM + 可选语音转录)
100
Security score
0 known advisories in v0.3.2
Weekly downloads
—
Unpacked size
57.4 kB
Dependencies
1
Last publish
3 hours ago
Security advisories
No known vulnerabilities affect v0.3.2.
Downloads — last 30 days
630 total▲ 117.4% vs prior week
Aug 18Sep 16