Skip to main content

← All model recipe tasks

Automatic Speech Recognition

Speech-to-text models, including offline and streaming contracts.

Classification follows the Hugging Face task taxonomy. See the Hugging Face Automatic Speech Recognition task page for the ecosystem-level task definition.

Model families

Model familyDeclared recipesExact checkpoint examplesRuntime CLI
canary2
nvidia/canary-1b-v2
trtmc transcribe
nemotron_speech_streaming3
nvidia/nemotron-3.5-asr-streaming-0.6b
nvidia/nemotron-speech-streaming-en-0.6b
trtmc transcribe
whisper4
openai/whisper-large-v3-turbo
openai/whisper-tiny
trtmc transcribe