<![CDATA[Installing Whisper]]>Out of curiosity because a quick search didn't yield the results I was looking for: Is it possible to install Whisper in OpenWebUI? Doesn't seem so.

]]>https://forum.cloudron.io/topic/13018/installing-whisperRSS for NodeSat, 05 Sep 2026 11:55:58 GMTFri, 27 Dec 2024 18:01:27 GMT60<![CDATA[Reply to Installing Whisper on Tue, 14 Jan 2025 13:13:17 GMT]]>BTW it seems to automatically recognize any audio file you throw at it. Either via Microphone or file upload and process TTS locally before passing it on to the selected model. Logs and graphs are pretty clear about this. Documentation however is not lol.

]]>https://forum.cloudron.io/post/99972https://forum.cloudron.io/post/99972Tue, 14 Jan 2025 13:13:17 GMT<![CDATA[Reply to Installing Whisper on Sun, 29 Dec 2024 11:08:09 GMT]]>@robi Nope, just CPU. But seems to be very manageable. Faster Whisper says in the repo that a 13 minute on 8 threads Intel Core i7-12700K CPU takes roughly a minute.

]]>https://forum.cloudron.io/post/99020https://forum.cloudron.io/post/99020Sun, 29 Dec 2024 11:08:09 GMT<![CDATA[Reply to Installing Whisper on Sat, 28 Dec 2024 23:31:27 GMT]]>Do you have a GPU for this? Otherwise it will be very slow.

There are speedups that have been made with JAX, but that still runs on GPUs.

Once you get it working, let me know how long it takes for x minutes of audio.

]]>https://forum.cloudron.io/post/99007https://forum.cloudron.io/post/99007Sat, 28 Dec 2024 23:31:27 GMT<![CDATA[Reply to Installing Whisper on Sat, 28 Dec 2024 11:55:02 GMT]]>Seams like I'm not the only one struggling to understand the whisper implementation: https://github.com/open-webui/open-webui/issues/2248

]]>https://forum.cloudron.io/post/98973https://forum.cloudron.io/post/98973Sat, 28 Dec 2024 11:55:02 GMT<![CDATA[Reply to Installing Whisper on Sat, 28 Dec 2024 08:48:34 GMT]]>@firmansi said in Installing Whisper:

Steps will be

  1. Choose OpenAI STT setting
  2. Fill openAI API
  3. Fill API Key
  4. Fill STT Model with whisper-large-v3 or any other that you prefer

Screenshot 2024-12-28 at 09.47.29.png

Yes I#ve gotten that far. But when you select a new chat, I can not select the whisper models.

]]>https://forum.cloudron.io/post/98962https://forum.cloudron.io/post/98962Sat, 28 Dec 2024 08:48:34 GMT<![CDATA[Reply to Installing Whisper on Sat, 28 Dec 2024 08:46:13 GMT]]>Steps will be

  1. Choose OpenAI STT setting
  2. Fill openAI API
  3. Fill API Key
  4. Fill STT Model with whisper-large-v3 or any other that you prefer
]]>https://forum.cloudron.io/post/98961https://forum.cloudron.io/post/98961Sat, 28 Dec 2024 08:46:13 GMT<![CDATA[Reply to Installing Whisper on Sat, 28 Dec 2024 08:45:12 GMT]]>@firmansi Hmm I see. But how do I select that then in the interface? I.e. I have an audio file. What are the steps in OpenWebUI to get the transcription from said file.

]]>https://forum.cloudron.io/post/98959https://forum.cloudron.io/post/98959Sat, 28 Dec 2024 08:45:12 GMT<![CDATA[Reply to Installing Whisper on Sat, 28 Dec 2024 08:28:57 GMT]]>You mean from voice to text? If that you mean then you can enable it through Admin Settting > Audio

]]>https://forum.cloudron.io/post/98958https://forum.cloudron.io/post/98958Sat, 28 Dec 2024 08:28:57 GMT<![CDATA[Reply to Installing Whisper on Sat, 28 Dec 2024 08:27:47 GMT]]>@firmansi Running the OpenAI Whisper model for transcription purposes

]]>https://forum.cloudron.io/post/98957https://forum.cloudron.io/post/98957Sat, 28 Dec 2024 08:27:47 GMT<![CDATA[Reply to Installing Whisper on Sat, 28 Dec 2024 00:25:45 GMT]]>What do you mean by installing whisper?

]]>https://forum.cloudron.io/post/98952https://forum.cloudron.io/post/98952Sat, 28 Dec 2024 00:25:45 GMT