Skip to content

Pytorch implementation of conformer with with training script for end-to-end speech recognition on the LibriSpeech dataset.

License

Notifications You must be signed in to change notification settings

jreremy/conformer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Pytorch Conformer

Pytorch implementation of conformer model with training script for end-to-end speech recognition on the LibriSpeech dataset.

Usage

Train model from scratch:

python train.py --data_dir=./data --train_set=train-clean-100 --test_set=test_clean --checkpoint_path=model_best.pt

Resume training from checkpoint

python train.py --load_checkpoint --checkpoint_path=model_best.pt

Train with mixed precision:

python train.py --use_amp

For a full list of command line arguments, run python train.py --help. Smart batching is used by default but may need to be disabled for larger datasets. For valid train_set and test_set values, see torchaudio's LibriSpeech dataset. The model parameters default to the Conformer (S) configuration. For the Conformer (M) and Conformer (L) models, refer to the table below:

Other Implementations

TODO:

  • Language Model (LM) implementation
  • Multi-GPU support
  • Support for full LibriSpeech960h train set
  • Support for other decoders (ie: transformer decoder, etc.)

About

Pytorch implementation of conformer with with training script for end-to-end speech recognition on the LibriSpeech dataset.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages