Long Audio Aligner

Intends to reproduce the segmentation method of the 2015 Panayotov et al. Librispeech paper.

Required tools

pocketspinx, ffmpeg and sox.

Use

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).

Tests

python -m unittest discover -s tests -p "test_*.py"