Skip to content

SSE v1.0

Latest
Compare
Choose a tag to compare
@RF5 RF5 released this 15 Dec 13:21
· 16 commits to master since this release
a474a57

Adds

  • new training code supporting distributed training, fp16, logging, and more!
  • new pretrained model for 16kHz audio that operates directly on raw waveforms.
  • benchmarks of the new and old model in terms of EER metrics for Librispeech test dataset
  • updated readme and usage notes
  • bug fixes