whisper VS FFmpeg

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

FFmpeg (https://ffmpeg.org/)

GPL2

Since FFmpeg is GPL2, doesn’t that require CompressX to disclose its source code?

IANAL, apologies if I miss understand license requirements.

https://github.com/FFmpeg/FFmpeg?tab=License-1-ov-file

This turns out to be a lot of assembly macros to help write one x86 assembly. https://github.com/FFmpeg/FFmpeg/blob/master/libavutil/x86/x...

The sibling comment recommending compiler intrinsics is probably the best way to go for writing SIMD code. A mixture of `` style types and intrinsics to specify instructions is a solid 90% solution compared to assembly.

If you want that last 10%, I think macros are putting the emphasis in the wrong place. They're a somewhat easy way to build up a language abstraction which will work if held carefully, but I'm confident the dev experience using this abstraction when you write invalid code will be deeply confusing.

I would suggest to write a parser instead of the macros. That'll tell you clearly when the syntax is invalid (though possibly not with much precision) and it'll give you a place to put semantic analysis for where valid syntax encodes nonsense. Do the equivalent of the macro expansions on the parsed tree instead of on the text. Emit asm as the "back end".

You might have heard of FFMPEG or ImageMagick for image and video edition in a programmatic way. MoviePy is a Python module for video editing (Python wrapper for FFMPEG and ImageMagick). It provides functions for cutting, concatenations, title insertions, video compositing, video processing, and the creation of custom effects. It can read and write common video and audio formats and be run on any platform with Python 2.7 or 3+.

There are many cloud-based tools and websites that can convert your images, but the problem with these tools is that you usually have to upload the files for them to be processed, and some of their services are not free. In this article, I'd like to introduce a piece of software called FFmpeg, which allows you convert the images locally with one simple command.

To run the demo locally, be sure to have Python 3.11 and FFmpeg installed.