GitHub - 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

Create symlinks for aishell2 at aishell2/wav and for magicdata at magicdata/wav
Run generate_data.sh to generate a subset of the aishell2+magicdata consisting of (relatively) standard Mandarin
Enter scripts/ and run run.sh

Name		Name	Last commit message	Last commit date
Latest commit History 16 Commits
aishell2		aishell2
magicdata		magicdata
model		model
scripts		scripts
.gitignore		.gitignore
README.md		README.md
create_dataset.py		create_dataset.py
generate_dataset.sh		generate_dataset.sh

Provide feedback