stable-diffusion VS whisper

it's basically the same as deforum but less features and an order of magnitude easier to use. so it's text to img to img.

It's a free and open source project made by a team of volunteers (quite small atm) in our free time. By its very nature, anyone can join and contribute stuff. You can find it on Github https://github.com/deforum/stable-diffusion and on Discord https://discord.gg/deforum

Using a modified version of DeForum notebook, I took the timestamped lyrics generated by whisper as prompt and added " in the style of an isometric video game art" to every prompt to create this video.

*PICK\* (Updated Sep. 5, 2022) Colab notebook Deforum Stable Diffusion by deforum. txt2img. img2img. Inpainting. Uses deforum repo. Video tutorial #1. Video tutorial #2.

Or making your own version with this fork and code from the colab above if you wanna do it locally.

Very nice. Add features from hlky's webui (https://github.com/hlky/stable-diffusion) and deforum-like (https://github.com/deforum/stable-diffusion) features (ideally with some sort of timeline editor for rotation/translation/zoom) and I will support you on the Patreon.

This was generated using an AI model called deforum_stable_diffusion

You can do very similar types of animation with the deforum notebook: https://github.com/deforum/stable-diffusion

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