no code implementations • 3 Feb 2024 • Nay San, Georgios Paraskevopoulos, Aryaman Arora, Xiluo He, Prabhjot Kaur, Oliver Adams, Dan Jurafsky
Continued pre-training on 70-200 hours of untranscribed speech in these languages can help -- but what about languages without that much recorded data?
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1