Aleksandr Beshkenadze PRO

beshkenadze

AI & ML interests

I develop the best software for noise reduction and audio transcription. Along the way, I improve the models and libraries to ensure they run quickly.

Recent Activity

liked a Space 2 days ago

kaengreg/rusBEIR

liked a model 2 days ago

ai-forever/FRIDA

liked a model 5 days ago

qualcomm/MediaPipe-Face-Detection

View all activity

Organizations

liked a Space 2 days ago

RusBEIR Leaderboard

🔎

View and submit Russian IR benchmark results

liked a model 2 days ago

ai-forever/FRIDA

Feature Extraction • 0.8B • Updated May 26, 2025 • 177k • • 144

liked a model 5 days ago

qualcomm/MediaPipe-Face-Detection

Object Detection • Updated 3 days ago • 740 • 37

liked a model 16 days ago

funasr/campplus

Audio Classification • Updated 30 days ago • 1.21k • 22

liked a Space 17 days ago

Image Upscaler

🔥

329

Upscale images using custom-trained models

liked a model 19 days ago

kandinskylab/KVAE-Audio

Updated 18 days ago • 79 • 54

liked a model 23 days ago

mispeech/ced-base

Audio Classification • 85.7M • Updated Mar 30 • 9.2k • 14

liked 5 models about 1 month ago

liked a Space about 1 month ago

FFASR Leaderboard

🎙

Far-Field ASR — clean / noisy / reverberant benchmark

liked 2 models about 1 month ago

bosonai/higgs-tts-3-4b

Text-to-Speech • 5B • Updated 9 days ago • 304k • 655

llm-semantic-router/mmbert-embed-32k-2d-matryoshka

liked 2 models about 2 months ago

Qwen/Qwen3-Embedding-0.6B

Feature Extraction • 0.6B • Updated Apr 20 • 10.6M • • 1.11k

Qwen/Qwen3-VL-Embedding-8B

liked a Space about 2 months ago

Borealis Blog

🌌

Borealis — audio LLM for Russian. Research notes.

liked 2 models about 2 months ago

meituan-longcat/LongCat-Video-Avatar-1.5

Updated Jun 4 • 1.67k • 676

tencent/Hy-MT2-1.8B

Translation • 2B • Updated May 26 • 157k • • 1.15k