Fully open Whisper-style speech foundation models developed by CMU WAVLab: https://www.wavlab.org/activities/2024/owsm/
Yifan Peng
pyf98
AI & ML interests
Multimodal LLMs, Speech-to-Speech, Speech Recognition
Recent Activity
updated
a dataset
about 1 month ago
espnet/yodas_owsmv4
updated
a model
about 1 month ago
espnet/owsm_ctc_v3.2_ft_1B
updated
a model
about 1 month ago
espnet/owsm_ctc_v3.1_1B
Organizations
