Intends to reproduce the segmentation method of the 2015 Panayotov et al. Librispeech paper.
pocketspinx, ffmpeg and sox.
For now:
python align.py <audiofile> <textfile>
Needs pocketsphinx install and also all the necessary resources for the language (acoustic model, language model, phonetic dictionary).
python -m unittest discover -s tests -p "test_*.py"