demo: replace vs-PyTorch race with a capability reel for socials#1
Merged
Conversation
The old demo raced ced.cpp against PyTorch but showed no audio: two empty
boxes typing abstract tags, leading with a speed flex. The new front-page
demo is a silent-readable capability reel: three real Public-Domain sounds
(rooster, thunderstorm, acoustic guitar), each shown as a mel-spectrogram
wiping in under a playhead, then the real top-5 AudioSet tags snapping in
with confidence bars, tagged in ~55 ms on CPU, ending on the LocalAI card.
Every tag, confidence and latency is a real ced-cli output captured in
benchmarks/demo/spec.json; clips are Public Domain (see clips/SOURCES.md).
The renderer is now committed (the old one never was): pure Pillow + numpy +
ffmpeg, rendering a 16:9 hero and a 1:1 square cut in one pass. Regenerate
with benchmarks/demo/make.sh.
- benchmarks/demo/: ced_reel.py, make.sh, spec.json, clips/ + SOURCES.md, logo
- media/demo.{mp4,gif} regenerated (16:9 hero); media/demo_square.{mp4,gif} new
- README "See it run" reframed to the capability demo
- .gitignore: ignore generated benchmarks/demo/out/
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
mudler
force-pushed
the
demo-capability-reel
branch
from
40ca58d to
d7fd869
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The old demo raced ced.cpp against PyTorch but showed no audio: two empty boxes typing abstract tags, leading with a speed flex. The new front-page demo is a silent-readable capability reel: three real Public-Domain sounds (rooster, thunderstorm, acoustic guitar), each shown as a mel-spectrogram wiping in under a playhead, then the real top-5 AudioSet tags snapping in with confidence bars, tagged in ~55 ms on CPU, ending on the LocalAI card.
Every tag, confidence and latency is a real ced-cli output captured in benchmarks/demo/spec.json; clips are Public Domain (see clips/SOURCES.md). The renderer is now committed (the old one never was): pure Pillow + numpy + ffmpeg, rendering a 16:9 hero and a 1:1 square cut in one pass. Regenerate with benchmarks/demo/make.sh.