When choosing Whisper (Local) as Speech-to-Text Engine and change the STT Model from base to turbo, there is an error show in docker log:
File "/usr/local/lib/python3.11/site-packages/faster_whisper/utils.py", line 78, in download_model
raise ValueError(
ValueError: Invalid model size 'turbo', expected one of: tiny.en, tiny, base.en, base, small.en, small, medium.en, medium, large-v1, large-v2, large-v3, large, distil-large-v2, distil-medium.en, distil-small.en, distil-large-v3
It looks like the faster_whisper inside open-webui doesn't support faster-large-v3-turbo model. When checking faster_whisper model list, it already supports this turbo model. Please see the benchmark.
Installation Method
Install from Docker latest image
Environment
Open WebUI Version: [v0.4.1]
Ollama (if applicable): [v0.4.2]
Operating System: [Windows 11]
Originally created by @kitaev-chen on GitHub (Nov 20, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/7115
# Bug Report
When choosing Whisper (Local) as Speech-to-Text Engine and change the STT Model from **base** to **turbo**, there is an error show in docker log:
```
File "/usr/local/lib/python3.11/site-packages/faster_whisper/utils.py", line 78, in download_model
raise ValueError(
ValueError: Invalid model size 'turbo', expected one of: tiny.en, tiny, base.en, base, small.en, small, medium.en, medium, large-v1, large-v2, large-v3, large, distil-large-v2, distil-medium.en, distil-small.en, distil-large-v3
```
It looks like the faster_whisper inside open-webui doesn't support [faster-large-v3-turbo](https://huggingface.co/deepdml/faster-whisper-large-v3-turbo-ct2) model. When checking faster_whisper [model list](https://github.com/SYSTRAN/faster-whisper/blob/master/faster_whisper/utils.py), it already supports this turbo model. Please see the [benchmark](https://github.com/SYSTRAN/faster-whisper/issues/1030).
---
## Installation Method
Install from Docker latest image
## Environment
- **Open WebUI Version:** [v0.4.1]
- **Ollama (if applicable):** [v0.4.2]
- **Operating System:** [Windows 11]
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 @kitaev-chen on GitHub (Nov 20, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/7115
Bug Report
When choosing Whisper (Local) as Speech-to-Text Engine and change the STT Model from base to turbo, there is an error show in docker log:
It looks like the faster_whisper inside open-webui doesn't support faster-large-v3-turbo model. When checking faster_whisper model list, it already supports this turbo model. Please see the benchmark.
Installation Method
Install from Docker latest image
Environment