List of Automatic Speech Recognition (ASR) models evaluated for ASTRA's end-to-end speech-to-speech communications pipeline
-
openai/whisper-small
Automatic Speech Recognition • 0.2B • Updated • 3.4M • 500 -
openai/whisper-large-v3
Automatic Speech Recognition • 2B • Updated • 6.38M • • 5.24k -
nvidia/parakeet-tdt-0.6b-v3
Automatic Speech Recognition • Updated • 70k • 485 -
MERaLiON/MERaLiON-2-10B-ASR
Automatic Speech Recognition • 10B • Updated • 13.9k • 9