openspeech
openspeech copied to clipboard
hydra_lm_train.py
model: joint_ctc_conformer_lstm criterion: joint_ctc_cross_entropy
Details
Is this script used to train the entire model, including the encoder and decoder, or just the language model?
@wuxiuzhi738 I'm so sorry for late reply. This is not a language model, it is a script that trains the conformer encoder and lstm decoder together.