I like sharing technical details. Here are a selection of blogs I wrote over the years.
Please refer to this ariticle for details.
I dove into the world of Automatic Speech Recognition (ASR) by building a Large Vocabulary Continuous Speech Recognition (LVCSR) system using the Kaldi toolkit.
This project is a complete implementation of Vision Transformer (ViT) applied to small-scale datasets (especially CIFAR-10), including extensive exploration.
I conducted extensive experiments comparing frame division methods and model performances, with rich visualizations.