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

81–90 of 233 posts

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

#81

Post by com2kid »

arkensaw wrote: post #77

This is great, and I'm not knocking it, but every time I see these apps it reminds me of my phone. My 2021 Google Pixel 6, when offline, can transcribe speech to text, and also corrects things contextually. it can make a mistake, and as I continue to speak, it will go back and correct something earlier in the sentence. What tech does Google have shoved in there that predates Whisper and Qwen by five years? And why do…

Microsoft OneNote had this back in 2007 or so, granted the speech to text model wasn't nearly as advanced as they are now.

I was actually on the OneNote team when they were transitioning to an online only transcription model because there was no one left to maintain the on device legacy system.

It wasn't any sort of planned technical direction, just a lack of anyone wanting to maintain the old system.

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

#82

Post by adamsmark »

arkensaw wrote: post #77

This is great, and I'm not knocking it, but every time I see these apps it reminds me of my phone. My 2021 Google Pixel 6, when offline, can transcribe speech to text, and also corrects things contextually. it can make a mistake, and as I continue to speak, it will go back and correct something earlier in the sentence. What tech does Google have shoved in there that predates Whisper and Qwen by five years? And why do…

The accuracy is much lower though.

I've switched away from Gboard to Futo on Android and exclusively use MacWhisper on MacOS instead of the default Apple transcription model.

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

#84

Post by cootsnuck »

arkensaw wrote: post #77

This is great, and I'm not knocking it, but every time I see these apps it reminds me of my phone. My 2021 Google Pixel 6, when offline, can transcribe speech to text, and also corrects things contextually. it can make a mistake, and as I continue to speak, it will go back and correct something earlier in the sentence. What tech does Google have shoved in there that predates Whisper and Qwen by five years? And why do…

Interesting. My Pixel 7 transcription is barely usable for me. Makes way too many mistakes and defeats the purpose of me not having to type, but maybe that's just my experience.

The latest open source local STT models people are running on devices are significantly more robust (e.g. whisper models, parakeet models, etc.). So background noise, mumbling, and/or just not having a perfect audio environment doesn't trip up the SoTA models as much (all of them still do get tripped up).

I work in voice AI and am using these models (both proprietary and local open source) every day. Night and day different for me.

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

#85

Post by patja »

naikrovek wrote: post #75
romeroej wrote: post #45

always mac. when windows? why can you just make things multios

Because like all other modern Macs, the GPU in my Mac uses the same API as the GPU in your Mac. Also, on a Mac with 32GB of RAM, 24GB of that (75%) is available to the GPU, and that makes the models run much faster. On my 64GB MacBook Pro, 48GB is available to the GPU. Have you priced an nvidia GPU with 48GB of RAM? It’s simply cheaper to do this on Macs. Macs are just better for getting started with this kind of thi…

Fair enough for GPU-intensive stuff like running Qwen locally. But do you really need a GPU for decent local TTS? I run parakeet just on CPU.

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

#86

Post by cootsnuck »

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

Yup, Handy is the one that made me stop looking for local open source alternatives to Wispr Flow.

I'll give a shoutout as well to Glimpse: https://github.com/LegendarySpy/Glimpse

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

#90

Post by rahimnathwani »

lloyd-christmas wrote: post #62
rahimnathwani wrote: post #9

Earlier quoted context omitted.

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.

There's a fork of FluidAudio that supports the recent Cohere model: https://github.com/altic-dev/FluidAudio/tree/B/cohere-coreml...

It's used by this dictation app: https://github.com/altic-dev/FluidVoice/

Post reply on HN