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

On Voice Coding

dusty.phillips.codes

Post reply on HN
Print view View original

141–150 of 186 posts

Re: On Voice Coding

#141

Post by lbj »

lunixbochs wrote: post #60
lbj wrote: post #49

Just a quick shout out to Microsoft (no affiliation) - Their Sculpt keyboard has taken all the discomfort out of 15hour coding sessions. If you're a professional developer, get one.

The Sculpt and Kensington expert trackball (big trackball, not thumb trackball), while not fixing my issues completely, did improve things for me quite a bit. That said, barring genetic lottery, as the sibling said: enough 15 hour sessions are going to give you RSI no matter what you’re typing on. There’s no way to do that every day, and exercise, take breaks, and sleep enough. Balance is important.

I agree. Worst streak was 18 months of those session nearly daily. Was a bit rough at the end.

Re: On Voice Coding

#142

Post by nshm »

cjbassi wrote: post #54

For those on Linux, I've been working on a Talon inspired voice coding program called Osprey that uses the Google Cloud speech to text API: https://github.com/osprey-voice/osprey . It's still very much a work in progress but it's already been working very well for me and I'm actually using it to type out this response right now.

Why would you work with google when there are much more accurate open source speech recognizers based on Kaldi? With that specific usecase it is very easy to beat Google on accuracy.

Re: On Voice Coding

#143

Post by lunixbochs »

tucosan wrote: post #134
lunixbochs wrote: post #22

This post starts out talking about expecting to spend around $1,000. There are at least two cross-platform projects where the biggest expense is a microphone instead of software. 1. My project, Talon. Windows/Linux/Mac support, and a first party local speech recognition engine that is pretty good and getting better. It’s free, but the engine is in a private beta (which is $15/mo to support development, optional if th…

Here's a video outlining Talon's [1] UX: https://youtu.be/ddFI63dgpaI [1]: https://talonvoice.com/

That video is fairly old. I’ve polished my workflow a fair bit since then. My advent of code videos described here [1] are probably more representative, and the later videos in the playlist even show the keys that are pressed with each command.

[1] https://news.ycombinator.com/item?id=22405178

Fun tidbit: Most of the commands I use in vim are just the Talon alphabet.

Re: On Voice Coding

#144

Post by pumanoir »

lunixbochs wrote: post #126
pumanoir wrote: post #123

Earlier quoted context omitted.

When using vim keys for example, to jump to the beginning of the line I press ^ then press 'dw' keys delete first word in a line. So I do the caret with my voice and the other press with my hand which is faster than doing it by hand alone.

Interesting, is that something you’d consider using the noise input for once I finish that? (As noise will be lower latency, you’ll have about 40 noises to map, and it’s “out of band” with speech)

Sure! Id love that. I only use one noise at the moment for mouse clicking (since I only know one sound). Could you point me to a video that shows an example of each of the 40 available sounds?

Re: On Voice Coding

#145

Post by lunixbochs »

pumanoir wrote: post #144
lunixbochs wrote: post #126

Earlier quoted context omitted.

Interesting, is that something you’d consider using the noise input for once I finish that? (As noise will be lower latency, you’ll have about 40 noises to map, and it’s “out of band” with speech)

Sure! Id love that. I only use one noise at the moment for mouse clicking (since I only know one sound). Could you point me to a video that shows an example of each of the 40 available sounds?

They aren’t available for use yet. https://noise.talonvoice.com is the submission collection site for the training data. Each noise there has a description and audio example. When they’re available you’ll be able to bind them just like voice commands.

Re: On Voice Coding

#147

Post by singularity2001 »

lunixbochs wrote: post #38
melling wrote: post #2

“I type fast enough that I have never had much use for snippets in my text editor. Perhaps if I’d used them more effectively, I would not have developed the RSI symptoms that I have!" Often we have discussions about advanced code completion on HN. Many developers feel they don’t need it, or that it gets in their way, for example. Reading stories like this convinces me even more that our editors (tools) need to be sma…

Deep TabNine looks so good it’s downright spooky: https://tabnine.com/blog/deep

This will result in a whole new class of copy paste bugs.

Great anyways

Re: On Voice Coding

#149

Post by lunixbochs »

nshm wrote: post #142
cjbassi wrote: post #54

For those on Linux, I've been working on a Talon inspired voice coding program called Osprey that uses the Google Cloud speech to text API: https://github.com/osprey-voice/osprey . It's still very much a work in progress but it's already been working very well for me and I'm actually using it to type out this response right now.

Why would you work with google when there are much more accurate open source speech recognizers based on Kaldi? With that specific usecase it is very easy to beat Google on accuracy.

I think google as the primary engine results in stuff like this: https://github.com/osprey-voice/osprey-starter-pack/blob/mas...

On the other hand it’s probably better at general (non command) English.

Re: On Voice Coding

#150

Post by singularity2001 »

lunixbochs wrote: post #33
qixxiq wrote: post #23

It's still surprising to see Dragon Speech Recognition as the recommended (and only) choice here. Is anyone working on decent speech recognition for Mac/Linux or know good resources for that? The ideal output is a stream of what could have been said, as well as some alternatives, each with a confidence. Every alternative I've tried has not been as effective as the version of Dragon I used from 2011. I think the focus…

The Talon beta ships with wav2letter and a really good many-accent English model that can handle both arbitrary commands and free form English. All of my trained models and some information is posted here: https://talonvoice.com/research/

Why not wrap it in an easily installAble Linux package
Post reply on HN