Is there an existing issue for this?
Current Behavior
Hey I'm running into the following error. I've tried both gpu and gpu-legacy with no luck and same results. Anyone could point me to the right direction, please?
Expected Behavior
No response
Steps To Reproduce
- create container using docker-compose with the gpu-legacy image
- observe container logs
- container not starting properly due to the following error: RuntimeError: CUDA failed with error CUDA driver version is insufficient for CUDA runtime version
Environment
- OS: Debian 12
- How docker service was installed:
apt install docker
CPU architecture
x86-64
Docker creation
faster-whisper:
image: lscr.io/linuxserver/faster-whisper:gpu-legacy
container_name: faster-whisper
environment:
- PUID=1000
- PGID=1000
- TZ=Europe/London
- WHISPER_MODEL=turbo
#- LOCAL_ONLY= #optional
- WHISPER_BEAM=2 #optional
- WHISPER_LANG=en #optional
volumes:
- ./faster-whisper/data:/config
ports:
- 10300:10300
restart: unless-stoppedContainer logs
Traceback (most recent call last):
File "<frozen runpy>", line 198, in _run_module_as_main
File "<frozen runpy>", line 88, in _run_code
File "/lsiopy/lib/python3.12/site-packages/wyoming_faster_whisper/__main__.py", line 353, in <module>
�
)
File "/lsiopy/lib/python3.12/site-packages/wyoming_faster_whisper/__main__.py", line 348, in run
asyncio.run(main())
File "/usr/lib/python3.12/asyncio/runners.py", line 194, in run
return runner.run(main)
^^^^^^^^^^^^^^^^
File "/usr/lib/python3.12/asyncio/runners.py", line 118, in run
return self._loop.run_until_complete(task)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.12/asyncio/base_events.py", line 687, in run_until_complete
return future.result()
^^^^^^^^^^^^^^^
File "/lsiopy/lib/python3.12/site-packages/wyoming_faster_whisper/__main__.py", line 218, in main
whisper_model = faster_whisper.WhisperModel(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/lsiopy/lib/python3.12/site-packages/faster_whisper/transcribe.py", line 689, in __init__
self.model = ctranslate2.models.Whisper(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: CUDA failed with error CUDA driver version is insufficient for CUDA runtime version
Is there an existing issue for this?
Current Behavior
Hey I'm running into the following error. I've tried both gpu and gpu-legacy with no luck and same results. Anyone could point me to the right direction, please?
Expected Behavior
No response
Steps To Reproduce
Environment
CPU architecture
x86-64
Docker creation
faster-whisper: image: lscr.io/linuxserver/faster-whisper:gpu-legacy container_name: faster-whisper environment: - PUID=1000 - PGID=1000 - TZ=Europe/London - WHISPER_MODEL=turbo #- LOCAL_ONLY= #optional - WHISPER_BEAM=2 #optional - WHISPER_LANG=en #optional volumes: - ./faster-whisper/data:/config ports: - 10300:10300 restart: unless-stoppedContainer logs