egpu-switcher VS whisper

If you're ok with running X11, you can use egpu-switcher and modify the Xorg configuration yourself afterwards.

Only using Xorg since Wayland gave me more issues than fixes. I'm using egpu-switcher

Try installing eGPU-switcher, make sure you have the right drivers installed, and as others have said make sure you have the right cable. Last thing, only plug in or unplug the eGPU when the laptop is off.

You didn't mention the problems you ran into but it should be plug and play. You will have to set up the proper config for it to work properly, and I would recommend using hertg's egpu-switcher if you are having issues: https://github.com/hertg/egpu-switcher

I've been using egpu-switcher every single time.

The scripts are all-ways-egpu for Wayland and egpu-switcher for X11.

here is the hotplug script that seemed promising, but did not work for me (nVIDIA only) here is a more sophisticated-looking script that seems intended for Desktop-users though, and also specifically excludes hotplugging options...

It is not plug&play, but almost. https://github.com/hertg/egpu-switcher

The A750 is now a recognized PCIe device, and works with connected displays to an extent. During boot, KMS/Plymouth shows on connected displays, as well as GDM (albeit, laggy, but it did that before anyways). The problem starts with Xorg, where during startx, I get a No screens found error. My Xorg configuration was autogenerated by egpu-switcher, where it only fails in egpu mode (connected displays do not work in internal mode). GNOME on Wayland works surprisingly with my laptop display working as normal, but the eGPU's external displays come with various graphical glitches, stuttering, outputting to 1080i30 on a 1440p60 display, etc.

Let’s not talk about local models as the hardware requirements are way beyond most of these people’s reach. I have a MacBook Air with an M2 chip and 8GB of RAM and can hardly run Whisper locally, so I use this HuggingFace space.

Last week, I launched notesGPT, a free and open source voice note app that has 35,000 visitors, 7,000 users, and over 1,000 GitHub stars so far in the last week. It allows you to record a voice note, transcribes it uses Whisper, and uses Mixtral via Together to extract action items and display them in an action items view. It’s also fully open source and comes equipped with authentication, storage, vector search, action items, and is fully responsive on mobile for ease of use.

I found a pretty good discussion in the topic here:

https://github.com/openai/whisper/discussions/1243

There is a plot of language performance on their repo: https://github.com/openai/whisper

I am not aware of a multi-lingual leaderboard for speech recognition models.

I don't know how OP does it, but here's how I'd do it:

* Generate a transcript by runing Whisper against the podcast audio file: https://github.com/openai/whisper

* Upload transcript to ChatGPT and ask it to summarize.

* Automate all the above.

Ahh, that makes sense. I've been building something like that, but only from other languages into English using Whisper

Whisper already generates subtitles[0], supporting VTT and SRT so this is just a thin wrapper around that.

[0]: https://github.com/openai/whisper/blob/e58f28804528831904c3b...

> although it does require you to wear headphones so the bot doesn't hear itself and get interrupted.

Maybe you can rely on some sort of speaker identification to sort this out?

https://github.com/openai/whisper/discussions/264