espnet/owls_4B_180K
Automatic Speech Recognition • Updated • 4 • 5
OWLS: Scaling Laws for Speech Recognition and Translation
🦉 A suite of Whisper-style models from 250M to 18B parameters. Trained on up to 360K hours of data. 16k sampling rate.
-
-
espnet/owls_9B_180K
Automatic Speech Recognition • Updated • 1 -
espnet/owls_05B_180K
Automatic Speech Recognition • Updated • 2 -
espnet/owls_025B_180K
Automatic Speech Recognition • Updated • 1 -
espnet/owls_1B_180K
Automatic Speech Recognition • Updated • 4 • 3 -
espnet/owls_2B_180K
Automatic Speech Recognition • Updated • 4 -
espnet/owls_18B_180K
Automatic Speech Recognition • Updated • 4 • 1 -
espnet/owls_18B_360K
Automatic Speech Recognition • Updated • 4 • 1