dream-factory VS whisper

Good stuff! For anyone else that uses Dream Factory, I've converted this to a .prompts file for use with it here:

BTW if you aren't already using dream factory to manage your GPUs in stable diffusion you should be. It works with automatic1111 too so you won't be losing any abilities.

Take a look at Dream Factory - it's a multi-GPU capable front-end for Auto1111. It'll let you run as many GPUs as you want in parallel, and adds a bunch of automation and remote management features as well.

I compiled these into a single Dream Factory .prompt file here: https://github.com/rbbrdckybk/dream-factory-prompt-files/tree/main/prompts

Correct and you can use Dream Factory to help manage your queue across GPUs. But keep in mind you are still only using individual cards for individual prompts meaning multiple cards can't improve the speeds of individual prompt generation nor allow for larger images.

Wow 24 instances! Just in case you weren't aware, Dream Factory is a multi-GPU frontend for Auto1111. It'll let you manage sending work to all those GPUs from one place!

Dream Factory will let you use multiple GPUs in parallel. So essentially adding a 2nd identical GPU will double your output.

No worries - Dream Factory is essentially a front-end for the popular Automatic1111 SD repo. It adds a bunch of prompt automation and remote management features, along with a multi-GPU engine (works fine with just 1 GPU too) to Auto1111.

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