Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Spaces:
red-kit
/
hf-realtime-voice
Like
0
Sleeping
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
hf-realtime-voice
46.5 kB
Ctrl+K
Ctrl+K
1 contributor
History:
10 commits
redkits
VAD hardening: thresh 0.72 + min_speech_ms 480 - echo/noise blips stop cancelling every reply before playback
9d9f501
verified
about 1 month ago
.gitattributes
Safe
1.52 kB
initial commit
about 1 month ago
Dockerfile
Safe
2.46 kB
Put Dockerfile
about 1 month ago
README.md
Safe
2.15 kB
Put README.md
about 1 month ago
dashboard.html
Safe
8.12 kB
Put dashboard.html
about 1 month ago
gateway.py
Safe
13.1 kB
Bump BUILD_ID to v12 (wedge fix deployed: AUDIO_RESPONSE_DONE on every generation path)
about 1 month ago
run_backend.py
Safe
15.7 kB
Fix session wedge: yield AUDIO_RESPONSE_DONE after every clone/higgs/fallback generation - the pipeline cannot drain SESSION_END without it (slot stays occupied forever)
about 1 month ago
start.sh
Safe
3.45 kB
VAD hardening: thresh 0.72 + min_speech_ms 480 - echo/noise blips stop cancelling every reply before playback
about 1 month ago
