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 model about 23 hours ago

funasr/campplus

liked a Space 3 days ago

Phips/Upscaler

liked a model 4 days ago

kandinskylab/KVAE-Audio

View all activity

Organizations

liked a model about 23 hours ago

funasr/campplus

Audio Classification • Updated 15 days ago • 1.27k • 21

liked a Space 3 days ago

Image Upscaler

🔥

324

Upscale images using custom-trained models

liked a model 4 days ago

kandinskylab/KVAE-Audio

Updated 3 days ago • 27 • 46

updated a model 6 days ago

mlx-community/OmniVoice-bf16

0.6B • Updated 6 days ago • 317 • 7

liked a model 8 days ago

mispeech/ced-base

Audio Classification • 85.7M • Updated Mar 30 • 6.35k • 14

updated a model 14 days ago

beshkenadze/privacy-filter-mlx

Token Classification • 1B • Updated 14 days ago • 35

published a model 14 days ago

beshkenadze/privacy-filter-mlx

Token Classification • 1B • Updated 14 days ago • 35

liked a model 21 days ago

edwixx/diffusiongemma-26B-A4B-it-HERETIC-Uncensored

Text Generation • 26B • Updated 9 days ago • 1.79k • 24

updated a model 21 days ago

mlx-community/Hunyuan-MT-7B-8bit

Text Generation • 8B • Updated 21 days ago • 69

published a model 21 days ago

mlx-community/Hunyuan-MT-7B-8bit

Text Generation • 8B • Updated 21 days ago • 69

updated a model 21 days ago

mlx-community/Hunyuan-MT-7B-4bit

Text Generation • 1B • Updated 21 days ago • 61

published a model 21 days ago

mlx-community/Hunyuan-MT-7B-4bit

Text Generation • 1B • Updated 21 days ago • 61

liked a model 21 days ago

marksverdhei/Qwen3-Voice-Embedding-12Hz-1.7B

Feature Extraction • Updated Feb 23 • 11.8k • 27

liked a model 22 days ago

Zyphra/ZONOS2

Text-to-Speech • Updated 12 days ago • 1.71k • 131

liked 2 models 23 days ago

nvidia/nemotron-3.5-asr-streaming-0.6b

Automatic Speech Recognition • 0.6B • Updated 8 days ago • 150k • • 774

facebook/seamless-m4t-v2-large

Automatic Speech Recognition • 2B • Updated Jan 4, 2024 • 276k • 990

liked a Space 23 days ago

FFASR Leaderboard

🎙

Far-Field ASR — clean / noisy / reverberant benchmark

updated 2 models 24 days ago

beshkenadze/nemotron-3.5-asr-streaming-0.6b-coreml-ane

Updated 24 days ago • 23

beshkenadze/nemotron-3.5-asr-streaming-0.6b-coreml-ane-stream

Updated 24 days ago • 22

published a model 25 days ago