Viewing profile — dylanbfox

We're AssemblyAI - and we're building APIs to transcribe and understand audio data at scale. * About us * - We just raised a $28M Series A from Accel, YC, Stripe's founders, Nat Fr…

Hey HN -- We're AssemblyAI - and we're building APIs to transcribe and understand audio data. Some notes about us: - Just raised a $28M Series A from Accel, YC, Stripe founders, Na…

Looks interesting! Do you guys offer any sort of visibility tools/reports into customer usage of different endpoints, tracking of actual API requests (including payloads/etc) per r…

Agree. The places I go on the web have become more and more centralized/limited. I think projects like this that help to surface and aggregate interesting content from the web (whi…

Nice work! The UI is really simple - and love not having to log in to use it. Have you thought about leveraging the ListenNotes API ( https://www.listennotes.com/api/ ) to automati…

I agree with all your points - but one thing I think about is: how do we fix what we have today? How do you fix the concrete jungles that most cities are today in the US. Or is it …

Hi there - OP here - thanks for reading! This blog is more of an intro to a few high level concepts (multi-GPU and multi-node training, fp32 vs fp16, buying hardware and dedicated …

Author here. Thanks for your comments! In general - this is expensive stuff. Training big, accurate models just requires a lot of compute, and there is a "barrier to entry" wrt cos…

Dylan from Assembly here. If you want to send me one of your audio files (my email is in my profile) I'd be happy to send you back the diarized results from our API. You can also s…

Great question. This is technically referred to as "Wake Word Detection". You run a really small model locally that is just processing 500ms (for example) of audio at a time throug…

Interesting. How do you guys manage spot interruptions when training on spot instances?

This is tricky. The de facto metric to evaluate an ASR model is Word Error Rate (WER). But results can vary widely depending on the pre-processing that's done (or not done) to tran…

> Salary costs are probably even higher than compute costs. Yes exactly. Managing that much compute requires many humans!

Dylan from Assembly here. Most of our customers have actually switched over to us from Google - this Launch HN from a YC startup that uses our API goes into a bit more detail if yo…

Interesting. It seems like in the "real world" WER is not really the metric that matters, it's more about "is this ASR system performing well to solve my use case" - which is bette…

> since less common words tend to be more important for meaning. Exactly. Errors with proper nouns are usually more problematic than errors with stop words, yet they're weighted eq…