StabilityMatrix VS whisper

On Windows, StabilityMatrix (https://github.com/LykosAI/StabilityMatrix) is a very easy way to get any (or all) of those wrappers installed without conflicts.

do you have a good pc/laptop with a good GPU? is so start with this. A1111 WebUI is no longer being updated so heres a new one https://github.com/LykosAI/StabilityMatrix/ this site you can download checkpoints and loras you have to sign up (its free, and once you do that click on the eye and click everything) https://civitai.com/ you can get prompts from this site (use the search) https://playgroundai.com/ Edited: took out the direct link out and reposted

I then thought, well I just do a new fresh install of A1111. I did 3 different fresh installs and did an install with https://github.com/LykosAI/StabilityMatrix as a portable installation to try and eliminate any outside interference. No luck all installs make pictures horrible, I mean bad, even the portable installation.

If you have a computer powerful enough to run SD, you can install one of the "software" from Stable Diffusion > Local install, the most popular ones are A111, Vlad and comfyUI (but I would advise to start with the first two, as comfyUI may be too complex at the begining). You can install them via StabilityMatrix ; it's a software that manage the installation of the popular webui, their requirements, and their versions; if you're afraid to manage the installation of pyton/miniconda/other things required to run it. NMKD is also a good alternative, as it should work right out of the box (it can even download the base model, if I remember correctly). If you haven't a computer good enough, look at Stable diffusion > Online Websites.

I'd install either via https://github.com/LykosAI/StabilityMatrix or https://civitai.com/models/27574/super-easy-ai-installer-tool.

You can view our source code on our GitHub

Update v1.1 of Stability Matrix has arrived!

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