- Create symlinks for aishell2 at
aishell2/wav
and for magicdata atmagicdata/wav
- Run
generate_data.sh
to generate a subset of the aishell2+magicdata consisting of (relatively) standard Mandarin - Enter
scripts/
and runrun.sh
tjysdsg/std-mandarin-kaldi
Script for training a non-chain tdnn model for standard mandarin GOP scoring. The training data is from a filtered subset of AISHELL2 and MAGICDATA which contain (relatively) standard Mandarin pronunciation
Shell