Kaldi-based ASR system for Amharic now available to the public

All the data and scripts to build a complete ASR system for Amharic (based on Kaldi toolkit) is made available to the public on GitHub.

Amharic repository is composed of the transcribed speech corpus with audio, pronunciation lexicon and LM.

More details on Amharic ASR (read speech transcription, MER=8.43%) can be found on https://github.com/besacier/ALFFA_PUBLIC/blob/master/ASR/AMHARIC/README