Deep graph convolutional networks (GCNs) have shown promising performance in traffic prediction tasks, but their practical deployment on resource-constrained devices faces challenges. First, few ...

In encoder-decoder framework for Automatic Speech Recognition (ASR) systems, the decoder of the well-trained ASR model is largely tuned towards the source-domain, hurting the performance of ...

[Paper] [Citations] [Clip Colab] [Coca Colab] Welcome to an open source implementation of OpenAI's CLIP (Contrastive Language-Image Pre-training). Using this codebase, we have trained several models ...