[GH-ISSUE #2248] enhancement: external stt #12810

Closed
opened 2026-04-19 19:40:48 -05:00 by GiteaMirror · 6 comments
Owner

Originally created by @Stargate256 on GitHub (May 14, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/2248

Originally assigned to: @tjbck on GitHub.

Is your feature request related to a problem? Please describe.
Would it be possible to allow running whisper on another server?

Describe the solution you'd like
Adding the ability to connect to whisper via some kind of API.

Additional context
I am running open-webui on a server without GPUs, and LLMs, TTS on another server.

Originally created by @Stargate256 on GitHub (May 14, 2024). Original GitHub issue: https://github.com/open-webui/open-webui/issues/2248 Originally assigned to: @tjbck on GitHub. **Is your feature request related to a problem? Please describe.** Would it be possible to allow running whisper on another server? **Describe the solution you'd like** Adding the ability to connect to whisper via some kind of API. **Additional context** I am running open-webui on a server without GPUs, and LLMs, TTS on another server.
Author
Owner

@fedirz commented on GitHub (May 27, 2024):

I've recently developed faster-whisper-server which provides an OpenAI compatible transcription/translation (and some extras as well) which could be used as a transcription backend if OpenWebUI adds support for having an external STT

<!-- gh-comment-id:2133633391 --> @fedirz commented on GitHub (May 27, 2024): I've recently developed [faster-whisper-server](https://github.com/fedirz/faster-whisper-server) which provides an OpenAI compatible transcription/translation (and some extras as well) which could be used as a transcription backend if OpenWebUI adds support for having an external STT
Author
Owner

@tjbck commented on GitHub (Jun 8, 2024):

@colaber2

STT & TTS settings have been refactored on dev and you can now configure external OpenAI STT from Admin Settings!

image

image

<!-- gh-comment-id:2155794910 --> @tjbck commented on GitHub (Jun 8, 2024): @colaber2 STT & TTS settings have been refactored on dev and you can now configure external OpenAI STT from Admin Settings! ![image](https://github.com/open-webui/open-webui/assets/25473318/b2f1f881-ca24-4f61-805f-b8c6025cceff) ![image](https://github.com/open-webui/open-webui/assets/25473318/9266a41b-4462-4505-9e4f-ceb7f5549246)
Author
Owner

@bannert1337 commented on GitHub (Jun 8, 2024):

I tried this and the model name for STT is not correctly used.
Screenshot 2024-06-08 at 16-30-36 Admin Panel Open WebUI

ValueError: Invalid model size 'whisper-1', 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
<!-- gh-comment-id:2156058572 --> @bannert1337 commented on GitHub (Jun 8, 2024): I tried this and the model name for STT is not correctly used. ![Screenshot 2024-06-08 at 16-30-36 Admin Panel Open WebUI](https://github.com/open-webui/open-webui/assets/58707896/1902a3a5-b19e-4eda-bc95-aef4b1750c24) ``` ValueError: Invalid model size 'whisper-1', 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 ```
Author
Owner

@colaber2 commented on GitHub (Jun 10, 2024):

@colaber2

STT & TTS settings have been refactored on dev and you can now configure external OpenAI STT from Admin Settings!

image

image

Amazing.. well done!!

<!-- gh-comment-id:2158590595 --> @colaber2 commented on GitHub (Jun 10, 2024): > @colaber2 > > STT & TTS settings have been refactored on dev and you can now configure external OpenAI STT from Admin Settings! > > ![image](https://private-user-images.githubusercontent.com/25473318/337831319-b2f1f881-ca24-4f61-805f-b8c6025cceff.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.Ox1mbSchCgVqee3RAzQH_jhLNHQAi6wY2Vaa31rfJuo) > > ![image](https://private-user-images.githubusercontent.com/25473318/337831349-9266a41b-4462-4505-9e4f-ceb7f5549246.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.s7jEgVekC6K9sq4l-KPTMdFm8UWWXPEwmdJKI5o_x_w) Amazing.. well done!!
Author
Owner

@JohnSmithToYou commented on GitHub (Jun 12, 2024):

I tried this and the model name for STT is not correctly used. Screenshot 2024-06-08 at 16-30-36 Admin Panel Open WebUI

ValueError: Invalid model size 'whisper-1', 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

@tjbck The model name is being ignored. As a result we can't use @fedirz's faster-whisper-server because it doesn't know what "whisper-1" is.
I modified faster-whisper-server to treat "whisper-1" as the default model and it worked great! @fedirz, maybe this is a good feature you could add? @tjbck, could you make the fix so we can choose the models?

Thank you both for your work!

<!-- gh-comment-id:2162997623 --> @JohnSmithToYou commented on GitHub (Jun 12, 2024): > I tried this and the model name for STT is not correctly used. ![Screenshot 2024-06-08 at 16-30-36 Admin Panel Open WebUI](https://private-user-images.githubusercontent.com/58707896/337881085-1902a3a5-b19e-4eda-bc95-aef4b1750c24.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.tXXy6HVhkg3kbiII3R0Ep0AfHbK8s3O72woKpMqaM7Y) > > ``` > ValueError: Invalid model size 'whisper-1', 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 > ``` @tjbck The model name is being ignored. As a result we can't use @fedirz's [faster-whisper-server](https://github.com/fedirz/faster-whisper-server) because it doesn't know what "whisper-1" is. I modified faster-whisper-server to treat "whisper-1" as the default model and it worked great! @fedirz, maybe this is a good feature you could add? @tjbck, could you make the fix so we can choose the models? Thank you both for your work!
Author
Owner

@fedirz commented on GitHub (Jun 12, 2024):

@JohnSmithToYou yeah, I'll add special handling for whisper-1

<!-- gh-comment-id:2163149875 --> @fedirz commented on GitHub (Jun 12, 2024): @JohnSmithToYou yeah, I'll add special handling for `whisper-1`
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#12810