I highlight paper books. A small open model types my quotes while I sleep

说明与用途

Dogear 使用 OCR 和 Gemma 4 模型自动提取纸质书籍中的高亮段落，并在次日提供审阅，节省手动转录时间。

问题

Copying highlighted passages from paper books into a digital format is time‑consuming and tedious.

结果

Dogear reduces manual transcription from 30–60 minutes per book to a single photo per highlighted page and a brief morning review, costing only a few cents per night.

工作流

• Add a book by typing or photographing its cover
• Photograph each highlighted page while the book is open
• Upload photos to a private bucket
• Nightly cron job runs Tesseract OCR and Gemma 4 on a CPU to extract highlighted passages
• Store each quote with a crop of the passage
• Delete processed photos
• Morning review: keep, edit, delete or add missed quotes
• Export to Notion (planned)

证据

Dogear removes that chore. While reading, the only extra thing I do is take a photo of each page I highlighted. Overnight, a small open-weight model running on a plain CPU in the cloud reads the photos and pulls out exactly the highlighted passages.

来源

The night-run numbers are a real line from the Render log.

来源

The full loop works: library, page capture, night run and morning review.

来源