New answers tagged


You can use model='bert-base-uncased' with transformers.pipeline: pip install transformers from transformers import pipeline unmasker = pipeline('fill-mask', model='bert-base-uncased') unmasker("a [MASK] in the watergate saga") This works for me on Google Colab.


We find some justifications in the Conformer paper: Convolutions are better than Transformers at detecting fine-grained patterns: While Transformers are good at modeling long-range global context, they are less capable to extract fine-grained local feature patterns. Convolution neural networks (CNNs), on the other hand, exploit local information and are ...

Top 50 recent answers are included