Skip to content

SpecAugment, Optuna, N-gram language modelling, and bug fixes

Pre-release
Pre-release
Compare
Choose a tag to compare
@sdrobert sdrobert released this 25 Feb 17:22
· 29 commits to master since this release
v0.2.0
b17a038
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.

EDIT: Overnight, pytorch released a version that caused an error. Do not use this version! I'll update and release v0.2.1.

Too many bits-and-bobs to count. I should keep a change log. Main features seem to be

  • Optuna hooks for data loaders (see pydrobert-param)
  • N-gram language modelling on the GPU. Can read in ARPA-LM files. Good for shallow fusion AM+LM.
  • SpecAugment layer for, well, SpecAugment
  • A variety of fixes and new features to my data loaders.
Assets 2
Loading