Download the pre-trained checkpoints in this repository'srelease page; (checkpoints for a pretrained acoustic model and speaker encoder is provided here. For the pretrained WaveRNN model used in the synthesis demo(debug_syn.ipynb), please seethis repofor information.) ...
set -e # exit on error local/download_and_untar.sh $data $data_url data_aishell local/download_and_untar.sh $data $data_url resource_aishell 数据准备 local/aishell_data_prep.sh $data/data_aishell/wav $data/data_aishell/transcript 这里主要用到data_aishell数据,resource_aishell那里没有怎么用...