Conformer-1: A robust speech recognition model trained on 650K hours of data
AssemblyAI
MARCH 15, 2023
1 – Efficient Conformer encoder model architecture. In an effort to further improve our model’s accuracy on noisy audio , we implemented a modified version of Sparse Attention [ 5 ], a pruning method for achieving sparsity of the model’s weights in order to achieve regularization.
Let's personalize your content