Table 6.

Training configurations of MIMICA across different data sets

Data setAISHELL-1TEDLIUM-2LibriSpeech
Epochs101010
Batch size161616
Gradient accumulation228
Learning rate1e-51e-51e-5
Warm up Ratio0.10.10.1
[ViewLarge]
This Feature Is Available To Subscribers Only

or Create an Account

Close subscription notice
Close access options