Aleksandr Beshkenadze's picture

Aleksandr Beshkenadze PRO

beshkenadze

·

https://bshk.app

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 about 18 hours ago

mlx-community/OmniVoice-bf16

liked a model 3 days ago

mispeech/ced-base

updated a model 9 days ago

beshkenadze/privacy-filter-mlx

View all activity

Organizations

liked a model 3 days ago

mispeech/ced-base

Audio Classification • 85.7M • Updated Mar 30 • 13.4k • 14

liked 2 models 16 days ago

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

Text Generation • 26B • Updated 4 days ago • 1.45k • 24

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

Feature Extraction • Updated Feb 23 • 9.6k • 27

liked a model 17 days ago

Zyphra/ZONOS2

Text-to-Speech • Updated 7 days ago • 1.57k • 126

liked 2 models 18 days ago

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

Automatic Speech Recognition • 0.6B • Updated 3 days ago • 76.2k • • 737

facebook/seamless-m4t-v2-large

Automatic Speech Recognition • 2B • Updated Jan 4, 2024 • 457k • 989

liked a Space 18 days ago

FFASR Leaderboard

Far-Field ASR — clean / noisy / reverberant benchmark

liked 2 models 24 days ago

bosonai/higgs-tts-3-4b

Text-to-Speech • 5B • Updated 4 days ago • 91.2k • 550

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

Sentence Similarity • 0.3B • Updated Mar 6 • 5.74k • • 15

liked 2 models 29 days ago

Qwen/Qwen3-Embedding-0.6B

Feature Extraction • 0.6B • Updated Apr 20 • 10.2M • • 1.09k

Qwen/Qwen3-VL-Embedding-8B

Sentence Similarity • 8B • Updated Apr 16 • 1.26M • 450

liked a Space about 1 month ago

Borealis Blog

Borealis — audio LLM for Russian. Research notes.

liked 2 models about 1 month ago

meituan-longcat/LongCat-Video-Avatar-1.5

Updated 25 days ago • 2.32k • 593

tencent/Hy-MT2-1.8B

Translation • 2B • Updated May 26 • 23k • • 1.13k

liked 2 models about 2 months ago

matbee/sam-audio-large-onnx

Updated Dec 23, 2025 • 8

Kansallisarkisto/cyrillic-htr-model

Image-to-Text • Updated Jun 18, 2025 • 373 • 5

liked a Space about 2 months ago

Cyrillic HTR Demo

Demo for cyrillic handwritten text recognition

liked 2 models about 2 months ago

LocalAI-io/LocalVQE

Audio-to-Audio • 578k • Updated 7 days ago • 4.23k • 58

bond005/whisper-podlodka-turbo

Automatic Speech Recognition • 0.8B • Updated Jan 29 • 1.86k • 41

liked a model 2 months ago

Qwen/Qwen3.6-27B

Image-Text-to-Text • 28B • Updated Apr 24 • 5.4M • • 1.83k