Prerequisite: fairseq installation, LibriSpeech dataset For installing fairseq library, please follow the offical installation instruction in fairseq github page. Below tutorial is based on LibriSpeech train-100hr (training set) and dev-clean (validation set). learned kmeans(hubert large/20 layer/libri-train-100) : https://github.com/voidful/hubert-cluster-code hubert cluster id asr: https://huggingface.co/voidful/asr_hubert_cluster_bart_base Label preparation

:::success Welcome to MLSS-2021 Taipei! ::: :::info Visit the official website for more information MLSS-2021 Taipei. This is a page to enter all the collaborative notes. If you have contributed to the notes, you can write down your name after "Author:". We may make the collaborative notes public in the further. :::

:::success Please first login to HackMD and click upper right "edit" buttom then you can start taking notes! ::: :::info The collaborative notes entry: https://hackmd.io/@MLSS-2021/BkI-9Ea0d :::