Open m00nwtchr opened 3 months ago
I'm getting this error when running the latest-gpu variant of the image using podman:
latest-gpu
podman
Could not load library libcudnn_cnn_infer.so.8. Error: libcuda.so: cannot open shared object file: No such file or directory
Any help would be appreciated.
(Both libraries do appear to be present in the container)
whisperasr.container (systemd/quadlet container definition)
[Unit] Description=whisperasr container Wants=network-online.target After=network-online.target nss-lookup.target [Container] Image=docker.io/onerahmet/openai-whisper-asr-webservice:latest-gpu AutoUpdate=registry PublishPort=9000:9000 Environment=ASR_ENGINE=faster_whisper Environment=ASR_MODEL=medium AddDevice=nvidia.com/gpu=all Volume=%h/.cache/whisper:/root/.cache/whisper [Service] Restart=on-failure TimeoutStartSec=300 ExecStartPre=mkdir -p %h/.cache/whisper [Install] WantedBy=default.target
I'm getting this error when running the
latest-gpu
variant of the image usingpodman
:Any help would be appreciated.
(Both libraries do appear to be present in the container)
whisperasr.container (systemd/quadlet container definition)