github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-08-30 17:25:30 -05:00
Code Issues 2.4k Packages Projects Releases 129 Wiki Activity

WhisperAI crashes the docker-container #1653

New Issue
Closed
opened 2025-11-11 14:49:26 -06:00 by GiteaMirror · 0 comments
GiteaMirror commented 2025-11-11 14:49:26 -06:00
Owner
Copy Link
Copy Source

Originally created by @Husky110 on GitHub (Aug 1, 2024).

Bug Report

Description

Bug Summary:
Whenever I try to use the audio-recording feature my docker container crashes.
Here's the container logs on the crash-event:

INFO  [apps.audio.main] file.content_type: audio/wav
Could not load library libcudnn_ops_infer.so.8. Error: libcudnn_ops_infer.so.8: cannot open shared object file: No such file or directory
Loading WEBUI_SECRET_KEY from file, not provided as an environment variable.Loading WEBUI_SECRET_KEY from .webui_secret_keyUSE_OLLAMA is set to true, starting ollama serve.CUDA is enabled, appending LD_LIBRARY_PATH to include torch/cudnn & cublas libraries.2024/08/01 05:20:28 routes.go:1099: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/root/.ollama/models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_RUNNERS_DIR: OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]"time=2024-08-01T05:20:28.659Z level=INFO source=images.go:784 msg="total blobs: 53"time=2024-08-01T05:20:28.660Z level=INFO source=images.go:791 msg="total unused blobs removed: 0"time=2024-08-01T05:20:28.660Z level=INFO source=routes.go:1146 msg="Listening on 127.0.0.1:11434 (version 0.3.0)"time=2024-08-01T05:20:28.661Z level=WARN source=assets.go:94 msg="found running ollama" pid=10 path=/tmp/ollama1439945203time=2024-08-01T05:20:28.661Z level=WARN source=assets.go:94 msg="found running ollama" pid=13 path=/tmp/ollama2009279848time=2024-08-01T05:20:28.661Z level=WARN source=assets.go:94 msg="found running ollama" pid=10 path=/tmp/ollama2237447354time=2024-08-01T05:20:28.661Z level=WARN source=assets.go:94 msg="found running ollama" pid=10 path=/tmp/ollama3584355008time=2024-08-01T05:20:28.661Z level=WARN source=assets.go:100 msg="unable to cleanup stale tmpdir" path=/tmp/ollama868162921 error="remove /tmp/ollama868162921: directory not empty"time=2024-08-01T05:20:28.661Z level=INFO source=payload.go:30 msg="extracting embedded files" dir=/tmp/ollama161789335/runners

At the beginning it tried to download the whisperai-model, but was unable to do so:

INFO  [apps.audio.main] file.content_type: audio/wavWARNI [faster_whisper] An error occured while synchronizing the model Systran/faster-whisper-base from the Hugging Face Hub:Cannot find an appropriate cached snapshot folder for the specified revision on the local disk and outgoing traffic has been disabled. To enable repo look-ups and downloads online, pass 'local_files_only=False' as input.WARNI [faster_whisper] Trying to load the model directly from the local cache, if it exists.WARNI [apps.audio.main] WhisperModel initialization failed, attempting download with local_files_only=Falsebdb5e801-8e76-472e-923e-f780a5ca5cf0.wavINFO:     127.0.0.1:52588 - "GET /health HTTP/1.1" 200 OKCould not load library libcudnn_ops_infer.so.8. Error: libcudnn_ops_infer.so.8: cannot open shared object file: No such file or directory

Steps to Reproduce:
Run Open WebUI in docker an try to use the voice-recognition.

Expected Behavior:
Working...

Actual Behavior:
Container-crash

Environment

  • Open WebUI Version: 0.3.10

  • Ollama (if applicable): 0.3.0

  • Operating System: Ubuntu 22.04

  • Browser (if applicable): Ungoogled Chromium

Reproduction Details

Confirmation:

  • [x ] I have read and followed all the instructions provided in the README.md.
  • [x ] I am on the latest version of both Open WebUI and Ollama. (<--- well... the current DockerImage does not ship with the latest version... had to build it myself...)
  • I have included the browser console logs. -> Nope... There are none...
  • [x ] I have included the Docker container logs. -> see above

Logs and Screenshots

Docker Container Logs:
See above

Installation Method

Docker via Dockerfile setting "USE_CUDA" to true and "USE_OLLAMA" to true.
nvidia-smi-output on my system:

+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.183.06             Driver Version: 535.183.06   CUDA Version: 12.2     |
|-----------------------------------------+----------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |         Memory-Usage | GPU-Util  Compute M. |
|                                         |                      |               MIG M. |
|=========================================+======================+======================|
|   0  NVIDIA GeForce RTX 3080 ...    On  | 00000000:01:00.0  On |                  N/A |
| N/A   46C    P8              20W / 115W |   7684MiB / 16384MiB |     21%      Default |
|                                         |                      |                  N/A |
+-----------------------------------------+----------------------+----------------------+

Additional Information

I am not sure what actually happened there. I'm guessing that there was something wrong during the whisper-download and everything else is a subsequent error.. Maybe there need to be some commands run and everything is fine...

Originally created by @Husky110 on GitHub (Aug 1, 2024). # Bug Report ## Description **Bug Summary:** Whenever I try to use the audio-recording feature my docker container crashes. Here's the container logs on the crash-event: ``` INFO [apps.audio.main] file.content_type: audio/wav Could not load library libcudnn_ops_infer.so.8. Error: libcudnn_ops_infer.so.8: cannot open shared object file: No such file or directory Loading WEBUI_SECRET_KEY from file, not provided as an environment variable.Loading WEBUI_SECRET_KEY from .webui_secret_keyUSE_OLLAMA is set to true, starting ollama serve.CUDA is enabled, appending LD_LIBRARY_PATH to include torch/cudnn & cublas libraries.2024/08/01 05:20:28 routes.go:1099: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/root/.ollama/models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_RUNNERS_DIR: OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]"time=2024-08-01T05:20:28.659Z level=INFO source=images.go:784 msg="total blobs: 53"time=2024-08-01T05:20:28.660Z level=INFO source=images.go:791 msg="total unused blobs removed: 0"time=2024-08-01T05:20:28.660Z level=INFO source=routes.go:1146 msg="Listening on 127.0.0.1:11434 (version 0.3.0)"time=2024-08-01T05:20:28.661Z level=WARN source=assets.go:94 msg="found running ollama" pid=10 path=/tmp/ollama1439945203time=2024-08-01T05:20:28.661Z level=WARN source=assets.go:94 msg="found running ollama" pid=13 path=/tmp/ollama2009279848time=2024-08-01T05:20:28.661Z level=WARN source=assets.go:94 msg="found running ollama" pid=10 path=/tmp/ollama2237447354time=2024-08-01T05:20:28.661Z level=WARN source=assets.go:94 msg="found running ollama" pid=10 path=/tmp/ollama3584355008time=2024-08-01T05:20:28.661Z level=WARN source=assets.go:100 msg="unable to cleanup stale tmpdir" path=/tmp/ollama868162921 error="remove /tmp/ollama868162921: directory not empty"time=2024-08-01T05:20:28.661Z level=INFO source=payload.go:30 msg="extracting embedded files" dir=/tmp/ollama161789335/runners ``` At the beginning it tried to download the whisperai-model, but was unable to do so: ``` INFO [apps.audio.main] file.content_type: audio/wavWARNI [faster_whisper] An error occured while synchronizing the model Systran/faster-whisper-base from the Hugging Face Hub:Cannot find an appropriate cached snapshot folder for the specified revision on the local disk and outgoing traffic has been disabled. To enable repo look-ups and downloads online, pass 'local_files_only=False' as input.WARNI [faster_whisper] Trying to load the model directly from the local cache, if it exists.WARNI [apps.audio.main] WhisperModel initialization failed, attempting download with local_files_only=Falsebdb5e801-8e76-472e-923e-f780a5ca5cf0.wavINFO: 127.0.0.1:52588 - "GET /health HTTP/1.1" 200 OKCould not load library libcudnn_ops_infer.so.8. Error: libcudnn_ops_infer.so.8: cannot open shared object file: No such file or directory ``` **Steps to Reproduce:** Run Open WebUI in docker an try to use the voice-recognition. **Expected Behavior:** Working... **Actual Behavior:** Container-crash ## Environment - **Open WebUI Version:** 0.3.10 - **Ollama (if applicable):** 0.3.0 - **Operating System:** Ubuntu 22.04 - **Browser (if applicable):** Ungoogled Chromium ## Reproduction Details **Confirmation:** - [x ] I have read and followed all the instructions provided in the README.md. - [x ] I am on the latest version of both Open WebUI and Ollama. (<--- well... the current DockerImage does not ship with the latest version... had to build it myself...) - [ ] I have included the browser console logs. -> Nope... There are none... - [x ] I have included the Docker container logs. -> see above ## Logs and Screenshots **Docker Container Logs:** See above ## Installation Method Docker via Dockerfile setting "USE_CUDA" to true and "USE_OLLAMA" to true. nvidia-smi-output on my system: ``` +---------------------------------------------------------------------------------------+ | NVIDIA-SMI 535.183.06 Driver Version: 535.183.06 CUDA Version: 12.2 | |-----------------------------------------+----------------------+----------------------+ | GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |=========================================+======================+======================| | 0 NVIDIA GeForce RTX 3080 ... On | 00000000:01:00.0 On | N/A | | N/A 46C P8 20W / 115W | 7684MiB / 16384MiB | 21% Default | | | | N/A | +-----------------------------------------+----------------------+----------------------+ ``` ## Additional Information I am not sure what actually happened there. I'm guessing that there was something wrong during the whisper-download and everything else is a subsequent error.. Maybe there need to be some commands run and everything is fine...
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
confirmed
confirmed issue
core
documentation
enhancement
good first issue
help wanted
non-core
pull-request
Mirrored from GitHub Pull Request
 python
question
testing wanted
No labels
Milestone
No items
No Milestone
Projects
Clear projects
No projects
Assignees
Clear assignees
GiteaMirror ninjasurge (Kaehlen Rog)
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#1653