For speech recognition, XLS-R improves over the best known prior work on BABEL, MLS, CommonVoice as well as | |
VoxPopuli, lowering error rates by 14-34% relative on average. |
For speech recognition, XLS-R improves over the best known prior work on BABEL, MLS, CommonVoice as well as | |
VoxPopuli, lowering error rates by 14-34% relative on average. |