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 • 4.45M • 650 -
openai/whisper-large-v3
Automatic Speech Recognition • 2B • Updated • 3.3M • • 6.82k -
nvidia/parakeet-tdt-0.6b-v3
Automatic Speech Recognition • 0.6B • Updated • 528k • 1.28k -
MERaLiON/MERaLiON-2-10B-ASR
Automatic Speech Recognition • 10B • Updated • 1.47k • 15