jamescham
Re:Moonshine, the new state of the art for speech to text
on Monday October 21, 2024 @04:30PM (#41908227)
Pete Warden and team just published a paper on Moonshine, their speech to text model.
Key features include:
- 1.7x overall speed boost compared to Whisper - Flexible-sized input window, allowing for more efficient processing of shorter audio clips - Up to 5x faster performance on 10-second audio clips - Matches or exceeds Whisper's accuracy
Re:Microsoft Semantic Kernel for LLM Integration
on Thursday March 16, 2023 @10:23PM (#35192110)
How is this not getting any news?
Re:SF’s Market Street Subway Runs on Reagan-Era Floppy Disks
on Monday February 06, 2023 @02:15AM (#34674309)
The actual interview is kind of amazing.
https://twitter.com/priyadclemens/status/1621229630765125639...
Re:Ask HN: What are those strategic skills to master for the next 5, 1...
on Sunday January 29, 2023 @12:08AM (#34565151)
This is a great point! (And kind of terrifying.)
Ask HN: Is there a way to follow people on Hacker News?
I'm sure there's a way to do it but I haven't figured it out.
Re:Report from demo day (in a pocket universe)
on Saturday September 10, 2022 @01:33PM (#32792713)
“Some good companies this year”—observations from my friend Joshua.
Report from demo day (in a pocket universe)
The New Matrix movie as the “culmination of modern hacker culture”
Re:Autodesk criticised by architects
on Monday August 03, 2020 @02:37AM (#24034774)
This is exactly right—we now live in a world in which most jobs are knowledge work, and we should look to those who are the most productive (and lazy) knowledge workers: software developers.
Re:Speech to Text on iPhone vs. Pixel
on Wednesday May 27, 2020 @10:21PM (#23332726)
My understanding is that Google’s big advantage is that they’ve collected so much good, annotated voice data.
Re:Speech to Text on iPhone vs. Pixel
on Wednesday May 27, 2020 @10:19PM (#23332717)
Yeah. I’m convinced the current model is just too confusing. But I really wish there were new interaction patterns that took advantage of low latency speech recognition...
Re:Speech to Text on iPhone vs. Pixel
on Wednesday May 27, 2020 @10:16PM (#23332692)
Oh! Good to know!
Re:Notes from The Valley: The real social network
on Sunday March 17, 2013 @01:36AM (#5388289)
ardit33 is right. My experience is that most successful startups are so hungry for talent that they really don't care where you come from or who you know.
Re:Have you ever uninstalled an app based on aesthetics?
on Monday December 19, 2011 @12:37AM (#3368630)
I often uninstall apps based on how the UI looks.
Re:Show HN: KernType, a typography game made with Raphaël
on Friday October 07, 2011 @08:04PM (#3086532)
Disappointed that I got 86/100 but this reminds me of sitting in front of a Mac in college obsessively adjusting the distance between Y and o.