seb/saltylab-firmware
1
0
Fork 0
Code Issues Pull Requests 3 Actions Packages Projects Releases Wiki Activity

feat(social): Orin dev environment — JetPack 6 + TRT conversion + systemd (#88) #101

Merged
sl-jetson merged 1 commits from sl-jetson/social-orin-dev into main 2026-03-02 08:23:08 -05:00
Conversation 0 Commits 1 Files Changed 8 +703
sl-jetson commented 2026-03-02 08:18:50 -05:00
Collaborator
Copy Link

Summary

  • Dockerfile.social: social-bot container — faster-whisper, llama-cpp-python (CUDA), piper-tts, insightface, pyannote.audio, OpenWakeWord, pyaudio, Silero VAD
  • scripts/convert_models.sh: TRT FP16 conversion for SCRFD-10GF, ArcFace-R100, ECAPA-TDNN + faster-whisper CTranslate2 setup + Piper voice download + benchmark suite
  • config/asound.conf: ALSA USB mic (card1) + USB speaker (card2) config for ReSpeaker arrays
  • models/README.md: version-pinned model table (/models/ layout), performance targets, LLM download instructions
  • systemd/: saltybot-social.service + saltybot.target + install_systemd.sh (auto-start on boot)
  • docker-compose.yml: saltybot-social service with NVIDIA GPU access, audio device passthrough, NVMe mounts for /models and /social_db

Closes #88

## Summary - **Dockerfile.social**: social-bot container — faster-whisper, llama-cpp-python (CUDA), piper-tts, insightface, pyannote.audio, OpenWakeWord, pyaudio, Silero VAD - **scripts/convert_models.sh**: TRT FP16 conversion for SCRFD-10GF, ArcFace-R100, ECAPA-TDNN + faster-whisper CTranslate2 setup + Piper voice download + benchmark suite - **config/asound.conf**: ALSA USB mic (card1) + USB speaker (card2) config for ReSpeaker arrays - **models/README.md**: version-pinned model table (/models/ layout), performance targets, LLM download instructions - **systemd/**: saltybot-social.service + saltybot.target + install_systemd.sh (auto-start on boot) - **docker-compose.yml**: saltybot-social service with NVIDIA GPU access, audio device passthrough, NVMe mounts for /models and /social_db Closes #88
sl-jetson added 1 commit 2026-03-02 08:18:51 -05:00 
- Dockerfile.social: social-bot container with faster-whisper, llama-cpp-python
  (CUDA), piper-tts, insightface, pyannote.audio, OpenWakeWord, pyaudio
- scripts/convert_models.sh: TRT FP16 conversion for SCRFD-10GF, ArcFace-R100,
  ECAPA-TDNN; CTranslate2 setup for Whisper; Piper voice download; benchmark suite
- config/asound.conf: ALSA USB mic (card1) + USB speaker (card2) config
- models/README.md: version-pinned model table, /models/ layout, perf targets
- systemd/: saltybot-social.service + saltybot.target + install_systemd.sh
- docker-compose.yml: saltybot-social service with GPU, audio device passthrough,
  NVMe volume mounts for /models and /social_db

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
sl-jetson merged commit efc7f0f815 into main 2026-03-02 08:23:08 -05:00
Sign in to join this conversation.
Reviewers
No Reviewers
Labels
No items
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
shaytac sl-controls sl-firmware sl-jetson sl-mechanical sl-perception sl-uwb sl-webui seb
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: seb/saltylab-firmware#101
No description provided.
Delete Branch "sl-jetson/social-orin-dev"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?