Spaces:
Running
Running
Commit History
-
rename: the app is now "The Describatron"
ClaudeRebrand the user-facing name from "Video Guide Maker" to "The Describatron" — and de-video the copy now that it also builds guides from slide images: * Page titles + headers across index / images / edit pages. * FastAPI app title; published-guide and editor footers. * README (HF Space card title + emoji 🎬→🤖 + heading), USER_GUIDE and DATA_HANDLING headings, and the intro prose. * Index eyebrow + sample copy: "lecture video (or slide images) and a transcript" instead of video-only. Infrastructure identifiers left untouched: the GitHub repo (VideoGuideMaker), the HF Space (Video2Guide), the internal package/ logger name (videoguidemaker), and DEPLOY.md's paths — those are real names, not branding. https://claude.ai/code/session_01EM8jiYxdVFy1w3LeJ9GBJg2f32611
-
docs: update README + USER_GUIDE for this session's features
ClaudeBring the docs in line with the current app: * Images-input mode (/images): build from timestamped slide exports + a transcript, no video. Documented in both the README ("Two ways in") and USER_GUIDE ("The two paths" + intro). * Self-contained edits export + /edit: Save edits (JSON) now embeds the slides, and /edit reopens the full editor from that one file. Added to the outputs / sharing sections. * Scene description: the recommended accessibility path (open paragraph under the slide that doubles as the long-form image description, alt emptied when present). Replaces the removed "key terms" entries in the AI-features table and editor descriptions. * Per-element include toggles + bulk "apply to all sections" bar. * Markdown download alongside HTML/ZIP. * Removed stale content: key terms, WCAG 2.1 → 2.2, deterministic frame extraction note. Env-var table gains MAX_IMAGE_MB / MAX_EDIT_MB. Project layout gains image_input.py, images.html, edit.html, jobs.py. * Points at…637c2d1
-
docs: drop pipeline.png so HF deploy doesn't reject the binary
ClaudeHugging Face's pre-receive hook now rejects PNGs over its size threshold, asking for Xet/LFS. The diagram is documentation only — the deployed Space doesn't render it — so the simpler fix is to remove the PNG from the repo (and its embed in USER_GUIDE.md). scripts/gen_pipeline_diagram.py stays so the diagram can be regenerated and published elsewhere if someone wants it back. https://claude.ai/code/session_01EM8jiYxdVFy1w3LeJ9GBJgb346e3e
-
Add pipeline diagram to repo and USER_GUIDE
ClaudeEight-block flow from "upload video + transcript" through scene detection, the two parallel preview paths (plain CV scene picker vs AI topic picker), curate-then-generate, the in-browser editor, and the three downloadable output shapes. Lives at docs/pipeline.png with a descriptive alt-text in USER_GUIDE.md so the embedded image is itself accessible. Generated via matplotlib at 180 dpi (~390 KB PNG) so it renders crisply at full-width on GitHub's markdown preview without bloating clone size.20ff24a -
USER_GUIDE.md: rewrite to cover topic preview, AI toggles, and current UX
ClaudeThe previous guide predated topic segmentation, the two preview buttons, the AI assist groupings, the auto-enable-on-key behaviour, the new sidebar layout, and the inline output-format picker. Rewrite end-to-end with: - A five-step quickstart that names the recommended AI path. - Two clearly-marked paths: A (AI topic-based, recommended) and B (slide-by-slide, no API key). Pick your path based on whether you've got an Anthropic key. - Step-by-step walkthrough of Path A covering every form field (title, video, transcript, API key, video-type dropdown, slide- images sub-toggle, per-segment toggles), the topic preview UI, and the curate-then-generate flow. - Reference sections for the Review & Edit editor, output formats, every AI assist toggle, and every advanced setting — with a note on how each sidebar control still matters when AI features are on. - A "Tips for the best results" cookbook with tuning recipes for common video shapes (inset webcam, animation builds, white…c68a685
-
Add USER_GUIDE.md: end-user walkthrough of upload, AI options, editor, downloads
Claude2403a32