Make decompress submission self-contained

Adds the committed demo MP4 and embeds it in the Space README so the Backyard entry validates without an external post.
Keeps the app code untouched and limits the change to submission metadata/media.

Co-authored-by: Codex <codex@openai.com>

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+eval/decompress_capture.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -37,12 +37,14 @@ models:
 
 # Decompress
 
+Decompress proves the same small, training-free timing policy can make a companion wait through stress, backchannel lightly, then answer with one grounded step.
+
 Decompress is a calm five-minute voice/text check-in companion. It is built for
 the practical Backyard track: after a stressful moment, the app listens without
 over-talking, gives a small backchannel when appropriate, and responds at the
 pause with one grounded next step.
 
-Live app: https://build-small-hackathon-decompress.hf.space<br>
+Try it on Hugging Face Space: https://build-small-hackathon-decompress.hf.space<br>
 GitHub repo: https://github.com/Hcoder10/whentospeak
 
 This is wellness support only. It is not medical advice, diagnosis, therapy, or
@@ -73,8 +75,18 @@ In the cached live-model timing eval, the controller reaches F1 `0.788` versus
   cited, open-access wellness corpus.
 - **OpenAI:** the public repo history is Codex-attributed.
 
-The app uses small weights: MiniCPM3-4B for the brain, a 2B Cohere ASR model,
-Kokoro-82M for speech, and a compact local embedder.
+The live demo runs on Modal, but the timing path uses small, on-device-class
+weights: MiniCPM3-4B for the brain, a 2B Cohere ASR model, Kokoro-82M for
+speech, and a compact local embedder. There is no supervised turn-taking head
+and no cloud LLM call for the core when-to-speak policy.
+
+## Demo
+
+<video controls src="eval/decompress_capture.mp4"></video>
+
+Plain link fallback: [eval/decompress_capture.mp4](eval/decompress_capture.mp4)
+
+Social post: SOCIAL_URL_PLACEHOLDER
 
 ## Grounding Sources
 
@@ -110,8 +122,3 @@ DECOMPRESS_BRAIN_ENDPOINT_TOKEN
 DECOMPRESS_TRANSCRIBE_ENDPOINT_URL
 DECOMPRESS_TRANSCRIBE_ENDPOINT_TOKEN
 ```
-
-## Links
-
-- Demo video: PLACEHOLDER - add recording link after capture.
-- Social post: PLACEHOLDER - add post link after publishing.

eval/decompress_capture.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bef78c1b30e7e1bbf1d6d7277904b299f7f5aeac052a040e56e51f295f37816
+size 1726946