Explore
Models
Blueprints
Docs
Forums
Login
openai
/
whisper-large-v3
RUN ANYWHERE
Robust Speech Recognition via Large-Scale Weak Supervision.
asr
ast
multilingual
nvidia nim
nvidia riva
openai
whisper
batch
speech-to-text
Build
Experience
Model Card
Try API
Docker
API Reference
Input
Source Language
Task
0:00
Your audio input will not be stored by NVIDIA and will only be used to generate the output on this page.
Reset
Run
Output
