marcosremar2
/

dumont-talker

Model card Files Files and versions

dumont-talker / scripts

61.6 kB

Ctrl+K

Ctrl+K

3 contributors

History: 8 commits

marcosremar2's picture

feat: add TTFT latency benchmark for Orpheus TTS

fddfe2b 9 months ago

download_models.sh

6.23 kB
feat: add MuseTalk fast_engine integration and model download script 9 months ago
install.sh

3.71 kB
Initial commit: dumont-talker speech-to-speech avatar 9 months ago
install_musetalk.sh

5.75 kB
feat: Add complete microservices architecture for speech-to-speech avatar system 9 months ago
install_webrtc.sh

4.53 kB
feat: Add complete microservices architecture for speech-to-speech avatar system 9 months ago
orpheus_continuous_batching.py

11.9 kB
feat: add Orpheus TTS continuous batching benchmark 9 months ago
orpheus_stress_test.py

7.03 kB
feat: add Orpheus TTS continuous batching benchmark 9 months ago
orpheus_ttft_test.py

6.8 kB
feat: add TTFT latency benchmark for Orpheus TTS 9 months ago
start.sh

5.13 kB
feat: add warmup to start.sh (5 inferences per service) 9 months ago
start_webrtc.sh

6.12 kB
feat: Add complete microservices architecture for speech-to-speech avatar system 9 months ago
stop.sh

578 Bytes
Initial commit: dumont-talker speech-to-speech avatar 9 months ago
stop_webrtc.sh

3.87 kB
feat: Add complete microservices architecture for speech-to-speech avatar system 9 months ago