toloka/CrowdSpeech
Updated • 62 • 6
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 dataset about 5 hours ago
toloka/CrowdSpeech liked a model 4 days ago
pyannote/speaker-diarization-community-1 liked a model 4 days ago
pyannote/speaker-diarization-3.1Organizations
liked a
dataset about 5 hours ago
liked 3
models 4 days ago
liked 2
models 12 days ago
liked a
model 15 days ago
liked a
Space 18 days ago
liked a
model 18 days ago
liked a
model 20 days ago
liked a
model about 1 month ago
liked a
Space about 1 month ago
liked 2
models about 1 month ago
liked 5
models about 2 months ago
edwixx/diffusiongemma-26B-A4B-it-HERETIC-Uncensored
Text Generation • 26B • Updated • 1.28k • 26
marksverdhei/Qwen3-Voice-Embedding-12Hz-1.7B
Feature Extraction • 12M • Updated • 17.2k • 27
Zyphra/ZONOS2
Text-to-Speech • Updated • 510 • 138
nvidia/nemotron-3.5-asr-streaming-0.6b
Automatic Speech Recognition • 0.6B • Updated • 1.04M • • 984
facebook/seamless-m4t-v2-large
Automatic Speech Recognition • 2B • Updated • 294k • 997
liked a
Space about 2 months ago