Multimodel audio - a bezzam Collection

bezzam 's Collections

Omnilingual ASR (1,600+ Languages)

Multimodel audio

Speech recognition datasets

Text-to-speech datasets

DigiCam (CelebA)

DiffuserCam Mirflickr

Multimodel audio

updated Dec 8, 2025

facebook/seamless-m4t-v2-large

Automatic Speech Recognition • 2B • Updated Jan 4, 2024 • 64k • 957
stepfun-ai/Step-Audio-2-mini

Any-to-Any • Updated 10 days ago • 1.86k • 250
bosonai/higgs-audio-v2-generation-3B-base

Text-to-Speech • Updated Jul 28, 2025 • 199k • 658