Spaces:

---

espnet

/

OWSM_V4_Demo

like 8

Running on Zero

We would like to release our ASR foundation model created by an Open Whisper-style Speech Models (OWSM) project by CMU https://www.wavlab.org/activities/2024/owsm/
This is a fully transparent foundation model.
This will also be used at the CMU lecture on "11751/18781 Speech Recognition and Understanding" and "11492/11692/18495: Speech Technology for Conversational AI"