Seeed-Jetson-DevelopTool / whisper-realtime-stt
AGENTS.md57 starsChanged 4 months agoMITView on GitHub
Deploy OpenAI Whisper on NVIDIA Jetson Orin for real-time speech-to-text. Clones the deployment repo, installs dependencies including ffmpeg, tests the environment, and runs real-time STT from a USB microphone (e.g. reSpeaker). Includes Riva vs Whisper comparison context.
- Installs packages
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository297 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ai-nvrAGENTS.md
- allxon-ota-updateAGENTS.md
- allxon-setupAGENTS.md
- alwaysai-setupAGENTS.md
- backup-restoreAGENTS.md
- bsp-source-buildAGENTS.md
- clawdbot-developmentAGENTS.md
- cochl-sense-setupAGENTS.md
- cvedia-setupAGENTS.md
- dashcamnet-xavier-nx-multicameraAGENTS.md
- deciai-setupAGENTS.md
- deepseek-quick-deployAGENTS.md
- deploy-deepseek-mlcAGENTS.md
- deploy-depth-anything-v3AGENTS.md
- deploy-diaAGENTS.md
- deploy-efficient-vision-engineAGENTS.md
- deploy-frigateAGENTS.md
- deploy-live-vlm-webuiAGENTS.md
- deploy-nvbloxAGENTS.md
- deploy-ollama-anythingllmAGENTS.md
- deploy-riva-llama2AGENTS.md
- developtool-deviceAGENTS.md
- disk-encryptionAGENTS.md
- diy-bsp-buildAGENTS.md
- ethercat-communicationAGENTS.md
- ethercat-setupAGENTS.md
- finetune-llm-llama-factoryAGENTS.md
- fix-browser-snap-jetsonAGENTS.md
- gapi-setupAGENTS.md
- generative-ai-introAGENTS.md
- gpt-oss-liveAGENTS.md
- gr00t-n1-5-deploy-thorAGENTS.md
- gr00t-n1-6-deploy-agxAGENTS.md
- hardhat-setupAGENTS.md
- hybrid-bsp-dk-to-recomputerAGENTS.md
- imx477-a603-setupAGENTS.md
- j501-viola-fruit-sortingAGENTS.md
- jetpack5-ssd-boot-fixAGENTS.md
- jetpack-flash-wsl2AGENTS.md
- jetpack-jetson-overviewAGENTS.md
- jetpack-ota-updateAGENTS.md
- jetson-ai-toolsAGENTS.md
- jetson-docker-setupAGENTS.md
- jetson-faqAGENTS.md
- jetson-pc-wired-shareAGENTS.md
- jetson-project-galleryAGENTS.md
- jetson-resource-indexAGENTS.md
- jetson-tutorial-exercisesAGENTS.md
- ko-module-buildAGENTS.md
- l4t-differencesAGENTS.md
- langchain-output-formattingAGENTS.md
- lerobot-env-setupAGENTS.md
- llama-cpp-rpc-distributedAGENTS.md
- llm-interface-controlAGENTS.md
- local-chatbot-multimodalAGENTS.md
- local-chatbot-physicalAGENTS.md
- local-llm-text-to-imageAGENTS.md
- local-rag-llamaindexAGENTS.md
- lumeo-setupAGENTS.md
- The first 60 shown.
The file
We split this AGENTS.md into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Run one phase at a time. After each phase:
- Very specific: line 16
If output contains [STOP] → stop immediately, consult the failure decision tree.
- Very specific: line 17
If output ends with [OK] → tell the user "Phase N complete" and proceed to the next phase.
- Distinctive: line 57
Verify ffmpeg is installed:
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Real-Time Speech-to-Text with Whisper on Jetson Orin
Deploy Whisper on Jetson Orin for real-time speech-to-text processing directly on-device, eliminating network dependency and enhancing privacy. Uses a USB microphone for audio input.
Execution model
Run one phase at a time. After each phase:
- Relay all output to the user.
- If output contains
[STOP]→ stop immediately, consult the failure decision tree. - If output ends with
[OK]→ tell the user "Phase N complete" and proceed to the next phase.
Prerequisites
| Requirement | Detail |
| Jetson device | reComputer or other Jetson Orin-based device |
| Microphone | reSpeaker Mic Array v2.0 or other USB microphone |
| JetPack | With CUDA support |
| Network | Internet access for cloning repo and installing packages |
Phase 1 — Install dependencies (~5 min)
git clone https://github.com/LJ-Hao/Deploy-Whisper-on-NVIDIA-Jetson-Orin-for-Real-time-Speech-to-Text.git
cd Deploy-Whisper-on-NVIDIA-Jetson-Orin-for-Real-time-Speech-to-Text
pip install -r requirements.txt
sudo apt update && sudo apt install ffmpegConfigure the microphone sample rate:
arecord -D hw:2,0 --dump-hw-params[OK] when all packages install and ffmpeg is available. [STOP] if pip or apt install fails.
Phase 2 — Test environment (~1 min)
python test.pyVerify ffmpeg is installed:
ffmpeg -version[OK] when test.py prints successful library import messages and ffmpeg -version shows version info. [STOP] if imports fail or ffmpeg is not found.
Phase 3 — Run real-time speech-to-text
python main.pySpeak into the microphone and observe real-time transcription output.
[OK] when transcription appears in the terminal as you speak. [STOP] if audio device errors or model loading fails.
Failure decision tree
| Symptom | Action |
pip install -r requirements.txt fails | Check Python version ≥ 3.8. Try pip install --upgrade pip first. |
ffmpeg not found after install | Run sudo apt install ffmpeg again. Verify with which ffmpeg. |
arecord — no soundcard found | Check USB microphone connection. Run arecord -l to list devices. Adjust device ID (hw:X,0). |
test.py import errors | Re-run pip install -r requirements.txt. Check for missing system libraries. |
main.py — CUDA out of memory | Close other GPU processes. Use a smaller Whisper model variant. |
main.py — no audio input | Verify microphone with arecord -D hw:2,0 -f S16_LE -r 16000 -d 5 test.wav. |
| Poor transcription accuracy | Ensure microphone sample rate is 16000 Hz. Reduce background noise. |
Reference files
references/source.body.md— Full Seeed Wiki tutorial with hardware setup photos, environment test screenshots, Riva vs Whisper comparison video, and project outlook (reference only)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.