Viewing profile — lunixbochs

I think Google's Conformer paper is SOTA at the I think my small Talon models are next, around 3% lsc clean at ~28M (greedy CTC decoding, no external encoder, no LM, not trained in…

Thank you.

I don't think any of your points reflect what I was trying to communicate. > You're not interested in addressing customers' needs I would love to support Wayland, but it is my posi…

Hi, I'm the developer of Talon. It's possible to do the simple compositor specific hacks from Talon's scripting system to give yourself partial Wayland support at roughly the quali…

naive c is just a memcpy. non-temporal uses the streaming instructions.

your single core numbers seem way too low for peak throughput on one core, unless you stipulate that all cores are active and contending with each other for bandwidth e.g. dual cha…

I'm confused why they repeatedly call a slots class larger than a regular dict class, but don't count the size of the dict

I'm not familiar with C# compile at runtime. Are you saying your change was to do an AOT compile locally?

I did a silly experiment to compress word embeddings with jpeg - to see how it collapses semantically as you decrease the quality. https://bochs.info/vec2jpg/ This was a very basic…

Are you using https://github.com/EleutherAI/lm-evaluation-harness ?

> made gl4es Neverball was working in the original glshim project before ptitseb forked it to gl4es. (Not to discount the significant work he's put in since, including the ES2 back…

The Talon model is fairly accurate, but it can be confusing for new users to use the command system correctly. I posted a sibling reply about this, but the most common reason for T…

Fixed commands are fast, precise, and predictable. Assuming you mean speaking in natural language, that's slower to say, and likely less precise and predictable if you want to be a…

Talon's eye tracking functions as a mouse replacement. Is there a specific demo you'd like to see? I can record one.

Depending on when that was: in 2018 the free model was the macOS speech engine, in 2019 it was a fast but relatively weak model, and as of late 2021 it's a much stronger model. I'm…

A handful of the datasets I tested are fully held out (I have reason to believe none of the models have trained on them), and talon was trained on none of the dev or test data of a…

Android voice access blogged about how they use a model to detect and classify buttons: https://ai.googleblog.com/2021/01/improving-mobile-app-acces...

Can you elaborate on how you see this working?

In large scale tests, I observed hallucinations from Whisper in speech regions of audio.

Nice catch. I'll run my test suite [1] on this and report back. [1] https://twitter.com/lunixbochs/status/1574848899897884672

If the target is the words "A A A" and you produce "B B B B", you have more errors than there were words in the target. 3 replacements and 1 insertion.