marcosremar2
/

dumont-talker

Model card Files Files and versions

275 MB

Ctrl+K

Ctrl+K

3 contributors

History: 27 commits

marcosremar2's picture

Claude Opus 4.5

feat: add multi-user capacity benchmark for gRPC streaming

c751e85 7 months ago

assets
feat: add MuseTalk fast_engine integration and model download script 7 months ago
benchmarks
feat: add multi-user capacity benchmark for gRPC streaming 7 months ago
config
Initial commit: dumont-talker speech-to-speech avatar 7 months ago
docs
feat: add max users and realistic streaming tests for Orpheus TTS 7 months ago
models
Initial commit: dumont-talker speech-to-speech avatar 7 months ago
scripts
feat: add max users and realistic streaming tests for Orpheus TTS 7 months ago
server
perf: add torch.compile, faster-whisper, and xFormers optimizations 7 months ago
tests
Initial commit: dumont-talker speech-to-speech avatar 7 months ago
web
feat: add LiveKit WebRTC streaming support 7 months ago
webrtc-latency-test
chore: Clean up webrtc-latency-test directory - remove POC duplications 7 months ago
.gitattributes

262 Bytes
Revert "feat: add Orpheus TTS benchmark results (RTX 4090)" 7 months ago
.gitignore

78 Bytes
chore: update gitignore to exclude IDE and media files 7 months ago
.gitmodules

461 Bytes
Initial commit: dumont-talker speech-to-speech avatar 7 months ago
README.md

9.05 kB
feat: Add complete microservices architecture for speech-to-speech avatar system 7 months ago