How do I train and eval using my own audio&text data?
JeonJunHyuk opened this issue · comments
I have .wav files & script+label csv file.
Data on this github is a pickle type.
How can I handle my data to use your model?
please let me know.
JeonJunHyuk opened this issue · comments
I have .wav files & script+label csv file.
Data on this github is a pickle type.
How can I handle my data to use your model?
please let me know.