Open taylerpauls opened 4 years ago
Can we use the subword models in the sample data folder for most datasets? Also, if we train the ASR, do we need to train the LM ?
you can train the ASR and LM respectively,and you can use the LM during the decoding
Can we use the subword models in the sample data folder for most datasets? Also, if we train the ASR, do we need to train the LM ?