Loay Amin's picture

Open to Work

Loay Amin

loay

·

AI & ML interests

Natural Language Processing

Recent Activity

reacted to YatharthS's post with 🔥 about 23 hours ago

Just open sourced LavaSR v2: a model that can enhance 5000 seconds of audio in 1 second while being higher quality than giant and slow 6gb diffusion models! It works with any sampling rate from 8-48khz and is nearly 5000x faster than competition while being superior in objective benchmarks. LavaSR v2 is Perfect for - Enhancing TTS models. - Fixing old audio datasets. - Restoring low quality recordings. You can check out the examples and run it locally or online: Repo: https://github.com/ysharma3501/LavaSR.git Demo: https://huggingface.co/spaces/YatharthS/LavaSR Model: https://huggingface.co/YatharthS/LavaSR

updated a collection 2 days ago

Open Arabic Vision, Layout & OCR Models by Loay

updated a collection 2 days ago

Open Arabic Vision, Layout & OCR Models by Loay

View all activity

Organizations

None yet

loay 's models 2

loay/Arabic-OCR-DeepSeek-OCR-2

Image-to-Text • 3B • Updated 3 days ago • 22

loay/Arabic-OCR-Qwen2.5-VL-7B-Vision

Image-to-Text • 8B • Updated Jul 18, 2025 • 242 • 3