Spaces:

---

Duplicated from  nvidia/nemo-speech-to-text-models

nvidia

/

parakeet-tdt-0.6b-v2

like 74

Running on Zero

For reference https://github.com/KoljaB/RealtimeSTT allows you to real time asr along with vad. Is it possible to do with this model? I tried to lookup nemo tutorials in github but could not find a relevant script that will do this.
Thanks for all the work