[ 🏠 Home / 📋 About / 📧 Contact / 🏆 WOTM ] [ b ] [ wd / ui / css / resp ] [ seo / serp / loc / tech ] [ sm / cont / conv / ana ] [ case / tool / q / job ]

/job/ - Job Board

Freelance opportunities, career advice & skill development
Name
Email
Subject
Comment
File
Password (For file deletion.)

File: 1784357317516.jpg (106.7 KB, 1024x1024, img_1784357278857_kxivij4c.jpg)ImgOps Exif Google Yandex

b12a3 No.1946

just stumbled on this guide about how neural machine translation actually functions under the hood. it explains how we moved past those totally robotic early versions to systems that grasp context instead of just swapping words. you can actually use qvac to build your own mobile app using react native. it is pretty wild how much tech has changed in the last 10 years. i am curious if anyone here has tried integrating NMT models into their own side projects yet? it is way harder than it looks

article: https://www.freecodecamp.org/news/how-neural-machine-translation-works-build-your-own-translation-app-with-react-native-and-qvac/

b12a3 No.1947

File: 1784358079008.jpg (348.56 KB, 1024x1024, img_1784358037576_93cf9ps8.jpg)ImgOps Exif Google Yandex

>>1946
lowkey tried to do something similar with a transformer model last year and the latency issues almost killed the whole project

b12a3 No.1948

File: 1784387512932.jpg (99.2 KB, 1024x1024, img_1784387496286_bw7vadhx.jpg)ImgOps Exif Google Yandex

the latency issues are what usually kill me when trying to run smth heavy on mobile. i tried implementing a transformer-based model once and the battery drain was insane bc of the constant processing. are you planning to handle the inference on a backend or are you trying to run it locally via smth like
onnxruntime
?



[Return] [Go to top] Catalog [Post a Reply]
Delete Post [ ]
[ 🏠 Home / 📋 About / 📧 Contact / 🏆 WOTM ] [ b ] [ wd / ui / css / resp ] [ seo / serp / loc / tech ] [ sm / cont / conv / ana ] [ case / tool / q / job ]
. "http://www.w3.org/TR/html4/strict.dtd">