Skip to content

Latest commit

 

History

History
14 lines (11 loc) · 830 Bytes

README.md

File metadata and controls

14 lines (11 loc) · 830 Bytes

Tedlium

Base VM: TEDLIUM – Training a Kaldi model using the TED-LIUM data set

  • Requirements: 16 GB RAM 4 cores

  • Recommended: Vagrant 1.7.2

  • [Tedlium README](http://speech-kitchen.org/tedlium-readme)

  • FORUM: http://speech-kitchen.org/forums/forum/kaldi-tedlium-forum/

The TEDLIUM VM is a complete training experiment using training data and transcripts from TED talks released in the TEDLIUM_release1 data set. This is an advanced VM that requires a LOT of resources, resulting in pretty good (but still quite large) acoustic and language models. There is additional support (by way of add-on experiment downloads) for:

  • Decoding with DNN models
  • PDNN tools
  • Decoding with DNN and filterbank features
  • Adapting Your Own Language Model