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

updated a model 4 days ago

beshkenadze/murmur-translation-ct2

updated a model 4 days ago

beshkenadze/parakeet-ultra-mlx-fp16

published a model 4 days ago

beshkenadze/parakeet-ultra-mlx-fp16

View all activity

Organizations

liked 3 models 6 days ago

liked 2 models 12 days ago

fastino/gliner2.5-small-v1

Token Classification • 73.9M • Updated 4 days ago • 26.2k • 39

convaiinnovations/laya

Text Classification • 0.4B • Updated 8 days ago • 4.89k

liked a model 18 days ago

OpenMed/privacy-filter-nemotron-v2

Token Classification • 1B • Updated 2 days ago • 85k • 54

liked a model 19 days ago

stabilityai/stable-audio-3-medium

Text-to-Audio • 2B • Updated Jun 16 • 65.5k • • 366

liked a model 21 days ago

tencent/AuK

Text-to-Speech • Updated 22 days ago • 4.8k • 374

liked a Space 21 days ago

AuK

🎙

125

Unified speech generation and editing with AuK

liked a model 21 days ago

Supertone/supertonic-3

Text-to-Speech • Updated May 18 • 29.3k • 977

liked 2 models 22 days ago

baidu/Unlimited-OCR

Image-Text-to-Text • 3B • Updated Jul 29 • 1.48M • 4.32k

nvidia/canary-1b-v2

Automatic Speech Recognition • 1.0B • Updated Aug 31 • 62.6k • 427

liked a model 24 days ago

nvidia/nemotron-ocr-v2

Image-to-Text • Updated May 22 • 1.71k • 262

liked 3 models about 1 month ago

ByteDance-Seed/Seed-X-Instruct-7B

Translation • 8B • Updated Jul 28, 2025 • 1.22k • 129

ai-sage/GigaAM-v3

Automatic Speech Recognition • Updated Nov 19, 2025 • 638k • 170

OpenMOSS-Team/MOSS-Transcribe-Diarize

Audio-Text-to-Text • 0.9B • Updated about 1 month ago • 225k • 456

liked a model about 2 months ago

fishaudio/s2-pro

Text-to-Speech • 5B • Updated Mar 11 • 34.9k • 1.39k

liked a Space about 2 months ago

StuPASE Speech Enhancement

🎙

Studio-quality generative speech enhancement

liked a model about 2 months ago

QuarkAudio/QuarkAudio-UniSE

Updated Dec 25, 2025 • 58