Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Transcribe.cpp

workshop.cjpais.com

Post reply on HN
Print view View original

171–180 of 180 posts

Re: Transcribe.cpp

#171

Post by espetro »

sipjca wrote: post #26
bengotow wrote: post #13

This is an incredible contribution to the community and it's just... one guy? I kept reading expecting a Series A funding announcement at the bottom. It's a nice reminder: You can use AI to slop cannon at maximum speed, or you can use it to scale your ambitions and build something more rigorous and lasting than ever before. I'd build Transcribe.cpp into the apps I maintain, but I feel like this functionality should (…

Hey, yep author and maintainer here! Certainly sponsors help and the wonderful community who donates to Handy as well! Mozilla AI was very helpful in getting this work off the ground. It was a pipe dream for me to build for Handy and they helped to sponsor me so I could make time to take this project seriously and get a v0.1.0 release out the door I agree this should be everywhere and I hope to distribute libtranscri…

Hey, for all of us builders out there, this is some quality work you're putting out there. How do you handle to talk about it, distribute it, just basically making it known to people, and still have time to focus on delivering actually useful, extensible quality work?

Re: Transcribe.cpp

#172

Post by aghilmort »

_medihack_ wrote: post #93
sipjca wrote: post #49

Earlier quoted context omitted.

Out of the box no probably not, but if people are interested there’s probably ways forward

Absolutely interested

wip WASM-tested baseline models yesterday / doing webgpu binds

required pinned ggml patch & OMP,SIMD,etc. tweaks to make all models efficient, this work meshes well with other builds been doing with all-way sherpa onnx etc.

Re: Transcribe.cpp

#173

Post by aghilmort »

lxe wrote: post #39

What's the best local TTS model right now? I'm running parakeet on a mac which transcribes all my uh's and aahs. I'm running whisper on linux/cuda and I by far prefer that one over parakeet.

audio.cpp @ github repo has good collection of TTS models

Re: Transcribe.cpp

#174

Post by Leftium »

abdullahkhalids wrote: post #46

For anyone looking to build on top of this. I have tried a few different STT systems, and they accurately capture what I am saying. Unfortunately, they don't support the reasonable workflow I want to open an office document, for example, and start talking. And I want the software to continuously type what I am saying at the cursor with minimal latency. The continuous part is crucial. Many software will paste whatever…

That was one of the main motivations for: https://rift-transcription.vercel.app

I think I prototyped the most fluid real-time streaming transcription experience. For example, you can interrupt/intersperse the realtime transcription with keyboard input.

If you click "Replay..." in the demo above, it shows an actual transcription use case (Black represents typed text, the colored text was dictated):

- Say "Left"

- Type `ium:` (because no model has been able to transcribe my username; special characters are hard)

- Continue dictating...

Re: Transcribe.cpp

#175

Post by therealpygon »

qntmfred wrote: post #22
zuzululu wrote: post #21

Earlier quoted context omitted.

I installed it but I don't think I see the streaming transcriptions. I do think the transcription is a bit faster. I am using the latest version.

You have to change the model to one that supports streaming. The latest parakeet does. I've been using it the last week or so. It's good stuff :)

I tried nemotron but the zero punctuation was a no go. I also used unified but didn’t see streaming. That said, I had to disable direct input because my shortcut for handy includes a ctrl-, so direct causes menu and shortcut activations at lightning speed, so I am only getting output when recording stops.

Still, you can pry Handy from my cold dead hands-y either way. So useful.

Re: Transcribe.cpp

#176

Post by lxe »

jv22222 wrote: post #40
lxe wrote: post #39

What's the best local TTS model right now? I'm running parakeet on a mac which transcribes all my uh's and aahs. I'm running whisper on linux/cuda and I by far prefer that one over parakeet.

> parakeet on a mac which transcribes all my uh's and aahs You should be able to fix this by playing with the mic speech floor. It happens when to much ambient stuff slurps in. It's actually gaslighting you, you don't say that many ums and ahs ;)

That is definitely not the case. It transcribes everything very accurately, especially all the "ahs" and "uhms".

Re: Transcribe.cpp

#177

Post by sipjca »

sorenjan wrote: post #170
sipjca wrote: post #161

Earlier quoted context omitted.

Right now I intend to maintain this as a library. The examples are just that, examples for programmers/agents. If someone in the community wants to step up to maintaining release binaries I will gladly have that support, it's just impossible to do as a sole maintainer

That's up to you of course, but is it that much more work to compile the cli binary at the same time as you compile the libraries? How am I supposed to actually use the Cuda binaries available in the releases section, through a separately downloaded Python wheel?

It's not that much extra work to compile, the extra work comes from the maintenance and feature requests. By not shipping the binary directly I am defending my time until other contributors want to step up and maintain things. I am one person with limited time and I don't want to spend all of it in front of a computer

Yes you use them through a wheel. If you have specific questions on packaging and how to use things lets move it over to the discussions/issues in the repo itself so it can be more broadly accessible to more people and we can make the packaging of the library as useful as possible

Re: Transcribe.cpp

#178

Post by ctas »

sipjca wrote: post #110
ctas wrote: post #98

Earlier quoted context omitted.

Really appreciate your work. Is there any way people can help? From your last sentence, it sounds like another PR isn't it and the opposite might be needed. But would love to contribute with testing if helpful. I'm regularly jumping between XFCE, KDE, GNOME, Niri, etc..

Testers by far as the most needed thing, I do maintain a list of per platform people who help to test so if you drop a GitHub username (or email me) I will add you to the list and ping for help Basically the biggest blocker is me being the sole maintainer and reviewer at the moment and it just ends up taking a lot of time for the scale of the project. Which is why it moves slow and features typically are much slower…

Feel free to add @cihantas. I'm also developing my own Wayland DE, so hopefully I can give better feedback than just "it doesn't work". :-)
Post reply on HN