Alexander-H-Liu / End-to-end-ASR-Pytorch

This is an open source project (formerly named Listen, Attend and Spell - PyTorch Implementation) for end-to-end ASR implemented with Pytorch, the well known deep learning toolkit.
MIT License
1.18k stars 317 forks source link

Step 0 : text encoding #60

Open taylerpauls opened 4 years ago

taylerpauls commented 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 ?

durian1023 commented 3 years ago

you can train the ASR and LM respectively,and you can use the LM during the decoding