** 한국어 ** · 繁體中文

강의 또는 회의 녹음을 구조화, 슬라이드 설명 노트로 설정 — and into thesynced HTML viewer 비디오, 타임스탬프 성적표, 그리고 curated Summary sit on one page: 비디오는 일치하는 메모를 강조 연극으로, 모든 메모 타임 스탬프가 비디오를 추구합니다.

모든 비싼 단계는 **로컬리 **: GPU의 Whisper ASR, 프레임 추출, OCR, 슬라이드 semantics에 대한 로컬 비전 모델. LLM은 사용 끝에서만, 증거에게서 prose를 이미 조립하는 파이프라인을 씁니다.

디자인 목표는 “동영상을 요약하지 않습니다”. **: 모든 클레임 완료된 메모는 성적표에 있는 순간에 부착되어야 합니다. 그 순간에 화면에 있었다 슬라이드. 기계의 대부분이 존재합니다. 그 링크를 믿을 수 없는 것.

왜 이 존재

재활약학 코스는 눈에 띄는 것이 어렵습니다. 제품정보 치료, 초음파 스캐닝 - 지식은 motion에, 그래서 각 당신이 여행의 숲을 볼 수있는 코스 : 모두가 모든 것을 기록, 계획 저녁 식사에 rewatch. Nobody 실제로 비디오의 시간을 재시계합니다.

lecture-to-notes

English · 繁體中文

Turn a lecture or conference recording into structured, slide-illustrated notes — and into a synced HTML viewer where the video, the timestamped transcript, and the curated summary sit on one page: the video highlights the matching note as it plays, and clicking any note timestamp seeks the video.

Every expensive stage runs locally: Whisper ASR on your GPU, frame extraction, OCR, and a local vision model for slide semantics. An LLM is used only at the end, to write prose from evidence the pipeline already assembled.

The design goal is not “summarize a video”. It is traceability: every claim in the finished note should be attachable to a moment in the transcript and to the slide that was on screen at that moment. Most of the machinery here exists to make that link trustworthy rather than plausible.

Why this exists

Rehabilitation-medicine courses are notoriously hard to take notes on. Manual therapy, ultrasound scanning — the knowledge is in the motion, so at every course you see a forest of tripods: everyone records everything, planning to rewatch over dinner. Nobody actually rewatches hours of video.

With AI the first instinct was to teach it precise screenshotting, to squeeze the video back into a traditional text-plus-figures note. The turn was realizing a note doesn’t have to be that shape at all: build a webpage that ties the video to the transcript, and you can jump straight to the moment you care about. What you actually want to know is how the maneuver is performed — and that only lives in motion. So the summary is for studying, the transcript is for verifying, and the video is one click away from both.

Bring whatever you captured

Real courses never produce one tidy recording. Some talks you filmed, some you only audio-recorded, for some you photographed the slides with your phone, and sometimes the organizer hands out a PDF deck afterwards. This pipeline takes the folder as-is: route_inputs.py figures out what role each file plays, and the alignment stage stitches every source onto one shared timeline — so the finished note cites the right slide at the right moment even when that slide never appeared inside the video.

---

What it does

flowchart TD
    IN["material folder(video / audio / PDF deck / slide images)"]
    IN --> R["route_inputs.pyclassifies the folder, prints the plan"]
    R --> T["transcribe_video.pyfaster-whisper, local GPU"]
    R --> S{"slide source"}

    S -->|video only| A["extract_slides.pyframes + perceptual dedup"]