工具VIDEO
Datalab 发布 Marker v2 解析管线
Marker v2 把 PDF、图片、DOCX、PPTX 转成干净 Markdown,单张 B200 上最快 23.7 页/秒,支持 90+ 语言,完全开源。
Daily Dose of Data Science
@DailyDoseOfDS_2026.09.22收录原推发布于 2026.09.21
Daily Dose of Data Science @DailyDoseOfDS_原推发布于 2026.09.21
Turn any PDF, image, DOCX, and PPTX into clean markdown. Parsing one PDF is easy. Parsing millions of them is where it gets tricky. Datalab shipped Marker v2, a parsing pipeline that runs up to 23.7 pages/s on a single B200 GPU. Supports 90+ languages. 100% open-source. https://t.co/6H4HuqWX1s
x.com/dailydoseofds_/status/2102057791024476519采集于 2026.09.22 10:36