coroot VS whisper

I'm Peter Zaitsev, co-founder at Coroot. I come from the database world where observability, or monitoring, was crucial for keeping databases running smoothly. But as technology evolves, so do the challenges we face.

Today, many applications are built using microservices architecture, making it harder to pinpoint issues. Developers now have more ownership over the entire environment, but they lack the expertise to navigate intricate infrastructure details. And with the complexity of modern observability systems, crucial components often go unmonitored, leaving blind spots.

That's where Coroot comes in!

We're excited to announce the release of Coroot 1.0 – a simplified observability platform designed to provide actionable insights for modern environments. With Coroot you get:

- Comprehensive Visibility: Coroot covers your entire environment, ensuring no information gaps. Whether you're on Kubernetes, traditional VMs, or cloud services, Coroot has you covered.

- Simple Deployment: We've made deploying Coroot a breeze. Leveraging modern Linux features like eBPF and Netlink, setup requires zero configuration. Coroot also identifies and configures additional components for you.

- Actionable Insights: Coroot prioritizes the most important information, helping you resolve issues up to 80% faster than with legacy solutions.

And the best part? Coroot has open-source version. If you prefer a hosted solution, there is Coroot Cloud, which comes with a free trial and transparent affordable pricing.

While Coroot is already an awesome open-source observability platform, we're not stopping there. We have ambitious plans to automate issue resolution and minimize human intervention.

Got ideas? Let us know on GitHub - https://github.com/coroot/coroot

See detailed overview of Coroot Features - https://coroot.com/overview

Take a look at https://github.com/coroot/coroot (Apache 2.0). It offers plenty of ready-to-use dashboards and inspections

I think ClickHouse is becoming a default storage for observability nowdays: https://clickhouse.com/use-cases/logging-and-metrics

And there are quite a few solutions on top of it.

A couple of examples that seem to be interesting (however I didn't use them in real life):

https://coroot.com/

Landing page: https://coroot.com

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