Multi-Stage Multi-Modal Pre-Training for Automatic Speech Recognition
Paper
•
2403.19822
•
Published
Yash Jain
jingalala
AI & ML interests
Computer Vision, Multi-modal, Self-supervised learning
Recent Activity
new activity
about 13 hours ago
allenai/Sera-4.6-Lite-T1:Changes in previous data file vs current file
new activity
about 18 hours ago
allenai/Sera-4.6-Lite-T1:Changes in previous data file vs current file
upvoted
a
paper
8 months ago
Essential-Web v1.0: 24T tokens of organized web data
Organizations
authored
a
paper
over 1 year ago