I have searched the existing issues and discussions.
I am using the latest version of Open WebUI.
Installation Method
Pip Install
Open WebUI Version
v0.6.14
Ollama Version (if applicable)
No response
Operating System
Ubuntu 24.04
Browser (if applicable)
No response
Confirmation
I have read and followed all instructions in README.md.
I am using the latest version of both Open WebUI and Ollama.
I have included the browser console logs.
I have included the Docker container logs.
I have provided every relevant configuration, setting, and environment variable used in my setup.
I have clearly listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
I have documented step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation. My steps:
Start with the initial platform/version/OS and dependencies used,
Specify exact install/launch/configure commands,
List URLs visited, user input (incl. example values/emails/passwords if needed),
Describe all options and toggles enabled or changed,
Include any files or environmental changes,
Identify the expected and actual result at each stage,
Ensure any reasonably skilled user can follow and hit the same issue.
Expected Behavior
In settings/audio I want to change the faster-whisper model from 'base' to another model i.e. 'large-v2' by typing in the modelname and download it, after download it works.
Actual Behavior
trying to download the new model causes: | WARNING | faster_whisper.utils:download_model:113 - An error occured while synchronizing the model Systran/faster-whisper-large-v2 from the Hugging Face 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. - {} | WARNING | faster_whisper.utils:download_model:118 - Trying to load the model directly from the local cache, if it exists. - {} | WARNING | open_webui.routers.audio:set_faster_whisper_model:138 - WhisperModel initialization failed, attempting download with local_files_only=False - {}
causing the main process to die - or even worse - freeze.
Steps to Reproduce
pip install open-webui -U
go to settings/audio in WebUI
set "large-v2" or any other than "base" as a model
hit "download" button
application crashes or freezes
Logs & Screenshots
| WARNING | faster_whisper.utils:download_model:113 - An error occured while synchronizing the model Systran/faster-whisper-large-v2 from the Hugging Face 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. - {} | WARNING | faster_whisper.utils:download_model:118 - Trying to load the model directly from the local cache, if it exists. - {} | WARNING | open_webui.routers.audio:set_faster_whisper_model:138 - WhisperModel initialization failed, attempting download with local_files_only=False - {}
Additional Information
Surprisingly I find the model downloaded in /open_webui/data/cache/whisper/models even though it states otherwise!
Keeping settings/audio page open in browser during application restart, then hitting "save" seem actually to work although I cannot verify as logs don't indicate which model is used for transcribe.
Originally created by @apunkt on GitHub (Jun 11, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/14880
### Check Existing Issues
- [x] I have searched the existing issues and discussions.
- [x] I am using the latest version of Open WebUI.
### Installation Method
Pip Install
### Open WebUI Version
v0.6.14
### Ollama Version (if applicable)
_No response_
### Operating System
Ubuntu 24.04
### Browser (if applicable)
_No response_
### Confirmation
- [x] I have read and followed all instructions in `README.md`.
- [x] I am using the latest version of **both** Open WebUI and Ollama.
- [x] I have included the browser console logs.
- [x] I have included the Docker container logs.
- [x] I have **provided every relevant configuration, setting, and environment variable used in my setup.**
- [x] I have clearly **listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup** (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
- [x] I have documented **step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation**. My steps:
- Start with the initial platform/version/OS and dependencies used,
- Specify exact install/launch/configure commands,
- List URLs visited, user input (incl. example values/emails/passwords if needed),
- Describe all options and toggles enabled or changed,
- Include any files or environmental changes,
- Identify the expected and actual result at each stage,
- Ensure any reasonably skilled user can follow and hit the same issue.
### Expected Behavior
In settings/audio I want to change the faster-whisper model from 'base' to another model i.e. 'large-v2' by typing in the modelname and download it, after download it works.
### Actual Behavior
trying to download the new model causes:
`| WARNING | faster_whisper.utils:download_model:113 - An error occured while synchronizing the model Systran/faster-whisper-large-v2 from the Hugging Face
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. - {}
| WARNING | faster_whisper.utils:download_model:118 - Trying to load the model directly from the local cache, if it exists. - {}
| WARNING | open_webui.routers.audio:set_faster_whisper_model:138 - WhisperModel initialization failed, attempting download with local_files_only=False - {}`
causing the main process to die - or even worse - freeze.
### Steps to Reproduce
1. pip install open-webui -U
2. go to settings/audio in WebUI
3. set "large-v2" or any other than "base" as a model
4. hit "download" button
5. application crashes or freezes
### Logs & Screenshots
`| WARNING | faster_whisper.utils:download_model:113 - An error occured while synchronizing the model Systran/faster-whisper-large-v2 from the Hugging Face
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. - {}
| WARNING | faster_whisper.utils:download_model:118 - Trying to load the model directly from the local cache, if it exists. - {}
| WARNING | open_webui.routers.audio:set_faster_whisper_model:138 - WhisperModel initialization failed, attempting download with local_files_only=False - {}`
### Additional Information
Surprisingly I find the model downloaded in /open_webui/data/cache/whisper/models even though it states otherwise!
Keeping settings/audio page open in browser during application restart, then hitting "save" seem actually to work although I cannot verify as logs don't indicate which model is used for transcribe.
GiteaMirror
added the bug label 2026-04-25 06:46:05 -05:00
It's not about updating a model but changing it and it still crashes the application.
<!-- gh-comment-id:2965218748 -->
@apunkt commented on GitHub (Jun 12, 2025):
It's not about updating a model but changing it and it still crashes the application.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @apunkt on GitHub (Jun 11, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/14880
Check Existing Issues
Installation Method
Pip Install
Open WebUI Version
v0.6.14
Ollama Version (if applicable)
No response
Operating System
Ubuntu 24.04
Browser (if applicable)
No response
Confirmation
README.md.Expected Behavior
In settings/audio I want to change the faster-whisper model from 'base' to another model i.e. 'large-v2' by typing in the modelname and download it, after download it works.
Actual Behavior
trying to download the new model causes:
| WARNING | faster_whisper.utils:download_model:113 - An error occured while synchronizing the model Systran/faster-whisper-large-v2 from the Hugging Face 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. - {} | WARNING | faster_whisper.utils:download_model:118 - Trying to load the model directly from the local cache, if it exists. - {} | WARNING | open_webui.routers.audio:set_faster_whisper_model:138 - WhisperModel initialization failed, attempting download with local_files_only=False - {}causing the main process to die - or even worse - freeze.
Steps to Reproduce
Logs & Screenshots
| WARNING | faster_whisper.utils:download_model:113 - An error occured while synchronizing the model Systran/faster-whisper-large-v2 from the Hugging Face 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. - {} | WARNING | faster_whisper.utils:download_model:118 - Trying to load the model directly from the local cache, if it exists. - {} | WARNING | open_webui.routers.audio:set_faster_whisper_model:138 - WhisperModel initialization failed, attempting download with local_files_only=False - {}Additional Information
Surprisingly I find the model downloaded in /open_webui/data/cache/whisper/models even though it states otherwise!
Keeping settings/audio page open in browser during application restart, then hitting "save" seem actually to work although I cannot verify as logs don't indicate which model is used for transcribe.
@tjbck commented on GitHub (Jun 11, 2025):
WHISPER_MODEL_AUTO_UPDATEshould be enabled.@apunkt commented on GitHub (Jun 12, 2025):
It's not about updating a model but changing it and it still crashes the application.