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

Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS

github.com

Post reply on HN
Print view View original

61–70 of 233 posts

Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS

#61

Post by goodroot »

VorpalWay wrote: post #59
goodroot wrote: post #4

Nice one! For Linux folks, I developed https://github.com/goodroot/hyprwhspr . On Linux, there's access to the latest Cohere Transcribe model and it works very, very well. Requires a GPU though. Larger local models generally shouldn't require a subordinate model for clean up. Have you compared WhisperKit to faster-whisper or similar? You might be able to run turbov3 successfully and negate the need for cleanup. Incid…

How does it compare to the more well established https://github.com/cjpais/handy ? Are there any stand out features (for either option)? What was the reason for writing your own rather than using or improving existing software?

Not sure I know what you mean by IR...

But in this case I built hyprwhspr for Linux (Arch at first).

The goal was (is) the absolute best performance, in both accuracy & speed.

Python, via CUDA, on a NVIDIA GPU, is where that exists.

For example:

The #1 model on the ASR (automatic speech recognition) hugging face board is Cohere Transcribe and it is not yet 2 weeks old.

The ecosystem choices allowed me to hook it up in a night.

Other hardware types also work great on Linux due to its adaptability.

In short, the local stt peak is Linux/Wayland.

Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS

#62

Post by lloyd-christmas »

rahimnathwani wrote: post #9
ipsum2 wrote: post #3

Parakeet is significantly more accurate and faster than Whisper if it supports your language.

Right, and if you're on MacOS you can use it for free with Hex: https://github.com/kitlangton/Hex

Or write your own custom one with the library that backs it: https://github.com/FluidInference/FluidAudio

I did that so that I could record my own inputs and finetune parakeet to make it accurate enough to skip post-processing.

Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS

#63

Post by VorpalWay »

goodroot wrote: post #61
VorpalWay wrote: post #59

Earlier quoted context omitted.

How does it compare to the more well established https://github.com/cjpais/handy ? Are there any stand out features (for either option)? What was the reason for writing your own rather than using or improving existing software?

Not sure I know what you mean by IR... But in this case I built hyprwhspr for Linux (Arch at first). The goal was (is) the absolute best performance, in both accuracy & speed. Python, via CUDA, on a NVIDIA GPU, is where that exists. For example: The #1 model on the ASR (automatic speech recognition) hugging face board is Cohere Transcribe and it is not yet 2 weeks old. The ecosystem choices allowed me to hook it up i…

IR was a typo, meant "it" (fixed it). I blame the phone keyboard plus insufficient proof reading on my part.

If this needs nvidia CPU acceleration for good performance it is not useful to me, I have Intel graphics and handy works fine.

Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS

#64

Post by ipsum2 »

yeutterg wrote: post #6
ipsum2 wrote: post #3

Parakeet is significantly more accurate and faster than Whisper if it supports your language.

Are you running Parakeet with VoiceInk[0]? [0]: https://github.com/beingpax/VoiceInk

I'm using https://github.com/senstella/parakeet-mlx library.

Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS

#66

Post by MattDamonSpace »

jonwinstanley wrote: post #52
qq66 wrote: post #49

Earlier quoted context omitted.

I haven't used this one but WisprFlow is vastly better than the built-in functionality on MacOS. Apple is way behind even startups, even for fundamental AI functionality like transcribing speech

I use the baked in Apple transcription and haven't had any issues. But what I do is usually pretty simple. What makes the others vastly better?

I’ve rarely had macOS TTS produce a sentence I didn’t have to edit

Whisper models I barely bother checking anymore

Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS

#67

Post by JohnPDickerson »

konaraddi wrote: post #5

That’s awesome! Do you know how it compares to Handy? Handy is open source and local only too. It’s been around a while and what I’ve been using. https://github.com/cjpais/handy

Handy is an awesome project, highly recommended - many of our engineers and PMs use it! CJ, Handy's creator, recently joined us as a Builder in Residence at Mozilla.ai. So for those interested in deploying a more raw/lightweight approach to local speech-to-text (or other multimodal) models, feel free to check out llamafile - which includes whisperfile, a single-file whisper.cpp + cosmopolitan framework-based executable. We're hoping to build some bridges between the two projects as well. https://github.com/mozilla-ai/llamafile

Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS

#68

Post by bonkler59 »

ericmcer wrote: post #29

I see quite a few of these, the killer feature to me will be one that fine tunes the model based on your own voice. E.G. if your name is `Donold` (pronounced like Donald) there is not a transcription model in existence that will transcribe your name correctly. That means forget inputting your name or email ever, it will never output it correctly. Combine that with any subtleties of speech you have, or industry jargon…

My experience is that Aqua voice does a good job of this with custom dictionary and replacements.

Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS

#69

Post by janalsncm »

ibero wrote: post #51
qq66 wrote: post #49

Earlier quoted context omitted.

I haven't used this one but WisprFlow is vastly better than the built-in functionality on MacOS. Apple is way behind even startups, even for fundamental AI functionality like transcribing speech

WisprFlow has a lot of good recommendations behind it but the fact they used Delve for SOC2 compliance gives me major pause.

The fact that a company could slurp up all of your data and then use Delve for their SOC2 is a great reason to use local models.

Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS

#70

Post by goodroot »

VorpalWay wrote: post #63
goodroot wrote: post #61

Earlier quoted context omitted.

Not sure I know what you mean by IR... But in this case I built hyprwhspr for Linux (Arch at first). The goal was (is) the absolute best performance, in both accuracy & speed. Python, via CUDA, on a NVIDIA GPU, is where that exists. For example: The #1 model on the ASR (automatic speech recognition) hugging face board is Cohere Transcribe and it is not yet 2 weeks old. The ecosystem choices allowed me to hook it up i…

IR was a typo, meant "it" (fixed it). I blame the phone keyboard plus insufficient proof reading on my part. If this needs nvidia CPU acceleration for good performance it is not useful to me, I have Intel graphics and handy works fine.

It works well with anything. :)

That said: If handy works, no need whatsoever to change.

Post reply on HN