Hugging Face's logo
espnet 's Collections
OpenBEATs
ARECHO Series
OpusLM
UniVERSA
Codec Survey - Pre-trained Models
OWSM: Fully Open Speech Recognition and Translation Models
OWLS: Scaling Laws for Speech Recognition and Translation
OWSM-CTC: Ultra-Fast Speech Foundation Models
Neural Codecs
XEUS Model and Data

OWSM-CTC: Ultra-Fast Speech Foundation Models

CTC-based models from the OWSM project, designed for fast non-autoregressive inference: https://www.wavlab.org/activities/2024/owsm/

Upvote
1