Originally created by @privacy-advo on GitHub (May 11, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/13782
### Expected Behavior
Hyperlink in the admin settings leads to a list of available models.
### Actual Behavior
https://github.com/SYSTRAN/faster-whisper
Does not list models and the syntax for open-webui.
### Steps to Reproduce
http://localhost:42003/admin/settings
Section STT model
### Installation Method
Git Clone
### Open WebUI Version
0.6.9
### Ollama Version (if applicable)
0.6.8
### Operating System
Win11
GiteaMirror
added the bug label 2026-05-18 01:40:35 -05:00
From the benchmark section you could assume Large-v2, distil-whisper-large-v3 and small are options. But the default option in open-webui base is not even listed. That's why I assume that this is not the list of available models.
<!-- gh-comment-id:2869941509 -->
@privacy-advo commented on GitHub (May 11, 2025):
Thank you. Maybe it is a language barrier, as I'm not a native speaker.
That's exactly the link I'm referring to. It leads to https://github.com/SYSTRAN/faster-whisper. But I can't find a list of models in the README.
From the benchmark section you could assume _Large-v2, distil-whisper-large-v3_ and _small_ are options. But the default option in open-webui _base_ is not even listed. That's why I assume that this is not the list of available models.
Args: model_size_or_path: Size of the model to use (tiny, tiny.en, base, base.en, small, small.en, distil-small.en, medium, medium.en, distil-medium.en, large-v1, large-v2, large-v3, large, distil-large-v2, distil-large-v3, large-v3-turbo, or turbo), a path to a converted model directory, or a CTranslate2-converted Whisper model ID from the HF Hub. When a size or a model ID is configured, the converted model is downloaded from the Hugging Face Hub.
<!-- gh-comment-id:2877914729 -->
@privacy-advo commented on GitHub (May 13, 2025):
For everbody else who's searching, I hope this is the right sources. I didn't test all options yet.
https://github.com/SYSTRAN/faster-whisper/blob/master/faster_whisper/transcribe.py
> Args: model_size_or_path: Size of the model to use (tiny, tiny.en, base, base.en, small, small.en, distil-small.en, medium, medium.en, distil-medium.en, large-v1, large-v2, large-v3, large, distil-large-v2, distil-large-v3, large-v3-turbo, or turbo), a path to a converted model directory, or a CTranslate2-converted Whisper model ID from the HF Hub. When a size or a model ID is configured, the converted model is downloaded from the Hugging Face Hub.
Systran's whisper models on HF:
https://huggingface.co/Systran
I hope this helps others.
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 @privacy-advo on GitHub (May 11, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/13782
Expected Behavior
Hyperlink in the admin settings leads to a list of available models.
Actual Behavior
https://github.com/SYSTRAN/faster-whisper
Does not list models and the syntax for open-webui.
Steps to Reproduce
http://localhost:42003/admin/settings
Section STT model
Installation Method
Git Clone
Open WebUI Version
0.6.9
Ollama Version (if applicable)
0.6.8
Operating System
Win11
@privacy-advo commented on GitHub (May 11, 2025):
Thanks. Can you give a hint where to find the info?
@tjbck commented on GitHub (May 11, 2025):
@privacy-advo commented on GitHub (May 11, 2025):
Thank you. Maybe it is a language barrier, as I'm not a native speaker.
That's exactly the link I'm referring to. It leads to https://github.com/SYSTRAN/faster-whisper. But I can't find a list of models in the README.
From the benchmark section you could assume Large-v2, distil-whisper-large-v3 and small are options. But the default option in open-webui base is not even listed. That's why I assume that this is not the list of available models.
@privacy-advo commented on GitHub (May 13, 2025):
For everbody else who's searching, I hope this is the right sources. I didn't test all options yet.
https://github.com/SYSTRAN/faster-whisper/blob/master/faster_whisper/transcribe.py
Systran's whisper models on HF:
https://huggingface.co/Systran
I hope this helps others.
@privacy-advo commented on GitHub (Apr 2, 2026):
#7779
https://github.com/open-webui/open-webui/issues/7779#issuecomment-2557263850