Name		Name	Last commit message	Last commit date
parent directory ..
s5		s5
README.md		README.md

README.md

ASR

Description

A collection of scripts for speech recognition based on Kaldi and meant to simplify the training process as much as possible.

Speech Recognition

1. Data prep
1. Lexicon generation
1. Grammar generation (pocolm & srilm)
1. Feature extraction
1. HMM-GMM training
1. Data augmentation (speed, volume, reverb, music, noise, babble)
1. Embedding (i-vector, x-vector)
1. DNN training
1. RNNLM training
1. Rescoring

Datasets

English	Spanish
common voice	common voice
	heroico
	dimex

License

Authors

(c) 2020 Sylvain Le Groux slegroux@ccrma.stanford.edu