tinykerneldev
tinykerneldev on Hacker News
omp (oh-my-pi) all the time. I just loved embracing the terminal and being able to switch between providers freely.
oh-my-pi works great with Anthropic, OpenAI and xAI subscriptions. Being able to quickly to switch between models without changing your workflow is such a joy - for me at least.
Interesting. Even more interesting would have been seeing if/how C# SIMD intrinsics would have improved performance.
Wait, Usenet downloads is still a thing? Thought torrents have taken over for decades.
Meta, the gift that keeps on giving.
Interestingly Grok passed all three prompts.
You can get pretty far even using the CPU. Just did a bit of testing with a 20-minute Family Guy episode. Took 14 minutes using Whisper Small (500 MB model) on an older Intel i5-9600T CPU. Obviously, that might be fine for the occasional transcription and a total show-stopper for high volume transcription. For comparison the same video took just two minutes using Whisper Large v3 Turbo on my 4080 (tested in TrueScribe on Linux).
Thats one of the limitations of small Whisper models, which often loop like that on non-English content.
TrueScribe supports tranlating Hindi transcripts in both directions. Not free though.
Posted by
tinykerneldev on Thursday October 01, 2026 @11:50AM
from the show-hn dept.
https://truescribe.app/
Switched to Fedora a year ago. And because I needed to transcribe interviews offline from time to time, I was looking for something like MacWhisper for Linux. When I couldn't find one, I decided to build one. Because in this day and age, why the hell not! And yes, AI coding-agents were used.I work as a .NET Software Engineer and I despise Electron Apps, so I decided to go with a semi-native...