Loading page...Загружаем страницу...正在加载页面...
AtlasRepo

Turning Family Voice Notes into a Living Digital Ofrenda with Local AI

说明与用途

该应用将家庭语音笔记转换为可搜索、可打印的数字祭坛,所有数据本地处理,确保引用的准确性。

问题

Family members want to preserve oral histories without sending sensitive audio to external services, ensuring privacy and exact quote fidelity.

结果

The app enables private, accurate family oral histories by transcribing and extracting key elements locally, preserving exact quotes and keeping all data on the user's machine.

工作流

  • Upload voice note via browser to /api/transcribe
  • FastAPI forwards audio to faster-whisper (base model) on localhost:8000
  • User edits transcript for accuracy
  • Edited transcript sent to local Ollama (gemma3:4b-it-qat) on localhost:11434 with JSON schema and temperature 0
  • Server validates extracted fields against transcript using guard() to ensure exact matches
  • User reviews and edits extracted items, removing unwanted entries
  • Saved data populates ofrenda page with portrait, offerings, quotes, and original recording
  • User can search, filter by tag, print, or export page as PNG

证据

The app transcribes it on the same computer, gathers the foods, songs, places, tags and exact quotes mentioned, and turns them into an ofrenda page that can be searched, printed and saved as an image.

来源

No accounts, cloud storage, or external AI APIs: the audio, transcripts, photos and database stay on the computer running it.

来源

The server checks the output against the transcript in guard(). Foods, songs and places must match a whole word or phrase in the transcript... Quotes have surrounding quote marks removed and must match a whole phrase in the normalized transcript.

来源

Three things were hard: JSON reliability on a small model... A PyAV version mismatch broke faster-whisper's audio decoding... Windows setup.

来源

  • 记录日期: 2026-11-01T20:14:04.278Z