openspeech-team / openspeech

Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.
https://openspeech-team.github.io/openspeech/
MIT License
677 stars 114 forks source link

hydra_lm_train.py #97

Open wuxiuzhi738 opened 3 years ago

wuxiuzhi738 commented 3 years ago

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?

upskyy commented 3 years ago

@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.