home-assistant-glow VS whisper

Seconding this. I was able to just run it with docker compose on a cheap mini PC and it chugs away happily, interfacing with all manner of devices (Phillips/Lifx/IKEA/Airpurifier/Bunnings brands). Only gets tricky to set up devices when you're dealing with some hostile cloud based gadget that doesn't want to play nice.

Unbelievable it can all be controlled offline using Siri on an iPhone, or other voice assistants.

It can even display your electricity consumption by counting the LED pulses on your smart electricity meter that fires every 1000th of a kw/h, only takes a cheap ESP32 and a photodiode: https://github.com/klaasnicolaas/home-assistant-glow

Such a wonderful project.

You want to build this https://github.com/klaasnicolaas/home-assistant-glow

Alternatively if you want to measure your overall energy consumption and aren't too worried what is generating the load, then I would suggest looking into the Home Assistant Glow project on github (https://github.com/klaasnicolaas/home-assistant-glow) - assuming you have a suitable electricity meter - for a couple of pounds you can put together a light sensitive diode and an ESP8266 (or similar) to create a device to sit over the flashing light on the meter to calculate usage. I have found it pretty accurate - it seems to match my billed usage pretty closely (within 3-5kw per month).

Check out Home Assistant Glow for a similar DIY device.

If folks want to make one of these theirselves (themselves? whatever), the "home assistant glow" project makes it pretty straightforward: https://github.com/klaasnicolaas/home-assistant-glow (I can never find the link, so I might as well drop it here). It uses ESPHome + a config file + a photo-diode thingy. It's more or less the same thing with a photoresistor. The server-side works easiest with Home Assistant, but you can access the device on its own too.

I have two questions: I already have my DIY MultiSensor hardware that was built around an ESP8266. It's main functionality is to count power pulses from my power meter via an LDR, and the hardware seems to run fine. I am aware of the Glow project, https://github.com/klaasnicolaas/home-assistant-glow , but for some reason this didn't play well with my self-created hardware. Also, I do think that my measure algorithm has a slight advantage, but that's not the point here :)

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