Hi everyone, I need help understanding why my BMO won't wake up with the Wake Word "Hey BMO". I am very new with the Raspberrypi and coding in general, but was inspired by this project so wanted to make my own.
I am running it on a Raspberry Pi 5 with 8GB Ram and a Pi Hat+2.
If I run the script BMO will only wake up if I press "Enter" on the keyboard and then everything else works (it responds to voice prompts etc, but it wont "Wake Up" with the "Hey BMO" or any other models like "Hey Jarvis" etc.
OpenWakeWord is installed, so I am stuck & need your help please.
Below is what I see when stopping the program.
(venv) regy@Regy:~/be-more-agent $ source venv/bin/activate
python agent.py
2026-04-25 09:24:44.328384495 [W:onnxruntime:Default, device_discovery.cc:325 DiscoverDevicesForPlatform] GPU device discovery failed: device_discovery.cc:92 ReadFileContents Failed to open file: "/sys/class/drm/card1/device/vendor"
--- SYSTEM STARTING ---
[INIT] Loading Wake Word...
/home/regy/be-more-agent/venv/lib/python3.13/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py:123: UserWarning: Specified provider 'CUDAExecutionProvider' is not in available provider names.Available providers: 'AzureExecutionProvider, CPUExecutionProvider'
warnings.warn(
[INIT] Wake Word Loaded.
[STATE] WARMUP: Warming up brains...
Models loaded.
[AUDIO DEBUG] Device Info: > 0 USB PnP Sound Device: Audio (hw:2,0), ALSA (1 in, 0 out)
< 1 UACDemoV1.0: USB Audio (hw:3,0), ALSA (0 in, 2 out)
[STATE] IDLE: Waiting...
[AUDIO] Listening with rate 44100 and block 3528
![AUDIO] Stream failed with defaults: Audio read failed: Audio Buffer Overflow - Triggering Safe Mode. Retrying with loose settings...
[AUDIO] Listening with rate 44100 and block 1024
[PTT] Toggle ON
Recording (PTT)...
[STATE] LISTENING: I'm listening!
[AUDIO DEBUG] Device Info: > 0 USB PnP Sound Device: Audio (hw:2,0), ALSA (1 in, 0 out)
< 1 UACDemoV1.0: USB Audio (hw:3,0), ALSA (0 in, 2 out)
[PTT] Toggle OFF
Hi everyone, I need help understanding why my BMO won't wake up with the Wake Word "Hey BMO". I am very new with the Raspberrypi and coding in general, but was inspired by this project so wanted to make my own.
I am running it on a Raspberry Pi 5 with 8GB Ram and a Pi Hat+2.
If I run the script BMO will only wake up if I press "Enter" on the keyboard and then everything else works (it responds to voice prompts etc, but it wont "Wake Up" with the "Hey BMO" or any other models like "Hey Jarvis" etc.
OpenWakeWord is installed, so I am stuck & need your help please.
Below is what I see when stopping the program.
(venv) regy@Regy:~/be-more-agent $ source venv/bin/activate
python agent.py
2026-04-25 09:24:44.328384495 [W:onnxruntime:Default, device_discovery.cc:325 DiscoverDevicesForPlatform] GPU device discovery failed: device_discovery.cc:92 ReadFileContents Failed to open file: "/sys/class/drm/card1/device/vendor"
--- SYSTEM STARTING ---
[INIT] Loading Wake Word...
/home/regy/be-more-agent/venv/lib/python3.13/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py:123: UserWarning: Specified provider 'CUDAExecutionProvider' is not in available provider names.Available providers: 'AzureExecutionProvider, CPUExecutionProvider'
warnings.warn(
[INIT] Wake Word Loaded.
[STATE] WARMUP: Warming up brains...
Models loaded.
[AUDIO DEBUG] Device Info: > 0 USB PnP Sound Device: Audio (hw:2,0), ALSA (1 in, 0 out)
< 1 UACDemoV1.0: USB Audio (hw:3,0), ALSA (0 in, 2 out)
[STATE] IDLE: Waiting...
[AUDIO] Listening with rate 44100 and block 3528
![AUDIO] Stream failed with defaults: Audio read failed: Audio Buffer Overflow - Triggering Safe Mode. Retrying with loose settings...
[AUDIO] Listening with rate 44100 and block 1024
[PTT] Toggle ON
Recording (PTT)...
[STATE] LISTENING: I'm listening!
[AUDIO DEBUG] Device Info: > 0 USB PnP Sound Device: Audio (hw:2,0), ALSA (1 in, 0 out)
< 1 UACDemoV1.0: USB Audio (hw:3,0), ALSA (0 in, 2 out)
[PTT] Toggle OFF