Hacker Newsnew | past | comments | ask | show | jobs | submit | fittingopposite's commentslogin

With the remote setup of Claude Code (e.g. [1]) I can know (vibe)code from my phone. But typing has been a pain. Didn't find a great speech to text app for Android featuring Nvidia's Parakeet v3, which is the (?) leading STT model. Found this repo. It's working flawlessly. Checked it with adb (I am always a bit suspicious). And it's really fully local. Highly recommend :)

[1] https://github.com/rberg27/doom-coding


I had not heard of Parakeet until earlier today with Handy [1].

I've previously had good luck with FUTO's keyboard and it's companion voice input app [2] on my Android, both of which are local-only after downloading the model. I'll have to try this one out and compare them.

[1] https://handy.computer/

[2] https://voiceinput.futo.org/


Interesting. Du you know which model they use? Yeah would be curious to hear your experience comparing them.

From their repo, it looks like OpenAI Whisper?

Language support

FUTO Voice Input is currently based on the OpenAI Whisper model, and could theoretically support all of the languages that OpenAI Whisper supports. However, in practice, the smaller models tend to not perform too good with languages that had fewer training hours. To avoid presenting something worse than nothing, only languages with more than 1,000 training hours are included as options in the UI:

<List of supported languages>

Language support and accuracy may expand in the future with better optimization and fine-tuned models. Feedback is welcomed about language-related issues or general language accuracy.


Is there any good android app featuring parakeet v3?

Went into a rabbit hole and found this: https://github.com/notune/android_transcribe_app Solid app that uses Parakeet V3. With these random apps on the internet I am always a bit sceptical. Checked it with adb and it is really fully local. I now have a voice keyboard that is a lot better than Google's and has local multilanguage support. I am stoked :)

Now I can continue coding via tmux/Claude Code with the https://github.com/rberg27/doom-coding setup while going for a walk in nature.

Diverting from Epstein files?

TLDR and context?

Pretty new graph clustering algorithm (published in 2019). Original publication which is actually fairly readable: https://www.nature.com/articles/s41598-019-41695-z

Yes. Please publish. Sounds very interesting

Click bait title but interesting read

Are there any ways to type email in markdown? Never thought of it so far...


On macOS there is MailMate: https://freron.com

40 USD/year just for markdown support + vendor lockin? Not sure I buy the value.

Broken homepage

This might be the new location:

https://gistdeck.github.io/


Can you do the same to remotely wake up my MacBook on demand via WoL and ssh into it from my phone? What are the security risks?


I don't think WOL works over Wi-Fi and whether you can get WOL from a USB ethernet adapter.

My proxy doesn't attempt to handle security. Most folks use either Tailscale or some other VPN solution. In my case I use the wireguard server in my router to VPN into home which gives me access to the proxy and consequently to the machine.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: