github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-08-02 06:39:02 -05:00
Code Issues 2.4k Packages Projects Releases 129 Wiki Activity

Docker image: open-webui:cuda: Fails to transcribe audio to text #2017

New Issue
Closed
opened 2025-11-11 14:58:45 -06:00 by GiteaMirror · 0 comments
GiteaMirror commented 2025-11-11 14:58:45 -06:00
Owner
Copy Link
Copy Source

Originally created by @larsvik on GitHub (Sep 7, 2024).

Bug Report

Installation Method

Docker (docker-compose) Docker-Desktop, WSL (Windows)

Environment

  • **Open WebUI Version: v0.3.20 (ghcr.io/open-webui/open-webui:cuda)

  • **Operating System: Official Docker image, WSL.

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.
  • [x ] I have included the Docker container logs.
  • [x ] I have provided the exact steps to reproduce the bug in the "Steps to Reproduce" section below.

Expected Behavior:

Expected audio files to be transcribed

Actual Behavior:

The transcription fails. No text returned.

Description

Open WebUI/Whisper looking for non-existing library files.

Reproduction Details

Install and use the docker CUDA version and record a voice for transcription using a web browser

Logs and Screenshots

Docker container log:
Startup log:

CUDA is enabled, appending LD_LIBRARY_PATH to include torch/cudnn & cublas libraries.

export LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/usr/local/lib/python3.11/site-packages/torch/lib:/usr/local/lib/python3.11/site-packages/nvidia/cudnn/lib"

Failing log entries:

webui  | INFO  [open_webui.apps.audio.main] file.content_type: audio/wav
webui  | 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
webui exited with code 0

Additional Information

Content of nvidia/cudnn/lib directory:

ls /usr/local/lib/python3.11/site-packages/nvidia/cudnn/lib
__init__.py
__pycache__
libcudnn.so.9
libcudnn_adv.so.9
libcudnn_cnn.so.9
libcudnn_engines_precompiled.so.9
libcudnn_engines_runtime_compiled.so.9
libcudnn_graph.so.9
libcudnn_heuristic.so.9
libcudnn_ops.so.9

nvidia-smi output ran from within the Docker container:

+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 560.35.02              Driver Version: 560.94         CUDA Version: 12.6     |
|-----------------------------------------+------------------------+----------------------+
| 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 2080        On  |   00000000:1A:00.0 Off |                  N/A |
| 24%   38C    P8              1W /  215W |      30MiB /   8192MiB |      0%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+
|   1  NVIDIA GeForce RTX 3090        On  |   00000000:68:00.0  On |                  N/A |
|  0%   54C    P8             44W /  420W |    4482MiB /  24576MiB |      1%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+
                                                                                         
+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI        PID   Type   Process name                              GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
|    0   N/A  N/A         1      C   /python3.11                                 N/A      |
|    0   N/A  N/A        45      G   /Xwayland                                   N/A      |
|    0   N/A  N/A        45      G   /Xwayland                                   N/A      |
|    1   N/A  N/A         1      C   /python3.11                                 N/A      |
|    1   N/A  N/A        45      G   /Xwayland                                   N/A      |
|    1   N/A  N/A        45      G   /Xwayland                                   N/A      |
+-----------------------------------------------------------------------------------------+

Note

I have tried with ghcr.io/open-webui/open-webui:cuda back to 0.3.17
ghcr.io/open-webui/open-webui:main (CPU) works just fine.

Originally created by @larsvik on GitHub (Sep 7, 2024). # Bug Report ## Installation Method Docker (docker-compose) Docker-Desktop, WSL (Windows) ## Environment - **Open WebUI Version: v0.3.20 (ghcr.io/open-webui/open-webui:cuda) - **Operating System: Official Docker image, WSL. **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. - [x ] I have included the Docker container logs. - [x ] I have provided the exact steps to reproduce the bug in the "Steps to Reproduce" section below. ## Expected Behavior: Expected audio files to be transcribed ## Actual Behavior: The transcription fails. No text returned. ## Description Open WebUI/Whisper looking for non-existing library files. ## Reproduction Details Install and use the docker CUDA version and record a voice for transcription using a web browser ## Logs and Screenshots **Docker container log:** Startup log: ```txt CUDA is enabled, appending LD_LIBRARY_PATH to include torch/cudnn & cublas libraries. ``` ```sh export LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/usr/local/lib/python3.11/site-packages/torch/lib:/usr/local/lib/python3.11/site-packages/nvidia/cudnn/lib" ``` Failing log entries: ```txt webui | INFO [open_webui.apps.audio.main] file.content_type: audio/wav webui | 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 webui exited with code 0 ``` ## Additional Information Content of nvidia/cudnn/lib directory: ```sh ls /usr/local/lib/python3.11/site-packages/nvidia/cudnn/lib __init__.py __pycache__ libcudnn.so.9 libcudnn_adv.so.9 libcudnn_cnn.so.9 libcudnn_engines_precompiled.so.9 libcudnn_engines_runtime_compiled.so.9 libcudnn_graph.so.9 libcudnn_heuristic.so.9 libcudnn_ops.so.9 ``` nvidia-smi output ran from within the Docker container: ```txt +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 560.35.02 Driver Version: 560.94 CUDA Version: 12.6 | |-----------------------------------------+------------------------+----------------------+ | 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 2080 On | 00000000:1A:00.0 Off | N/A | | 24% 38C P8 1W / 215W | 30MiB / 8192MiB | 0% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ | 1 NVIDIA GeForce RTX 3090 On | 00000000:68:00.0 On | N/A | | 0% 54C P8 44W / 420W | 4482MiB / 24576MiB | 1% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ +-----------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=========================================================================================| | 0 N/A N/A 1 C /python3.11 N/A | | 0 N/A N/A 45 G /Xwayland N/A | | 0 N/A N/A 45 G /Xwayland N/A | | 1 N/A N/A 1 C /python3.11 N/A | | 1 N/A N/A 45 G /Xwayland N/A | | 1 N/A N/A 45 G /Xwayland N/A | +-----------------------------------------------------------------------------------------+ ``` ## Note I have tried with ghcr.io/open-webui/open-webui:cuda back to 0.3.17 ghcr.io/open-webui/open-webui:main (CPU) works just 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#2017