This repo contains simple code example for reading audio files, plotting it, extracting spectral energy features, and plotting word / phone level alignments.
- 1-AudioToSpectrogram.ipynb shows how to plot a spectrogram.
- 2-SpectrogramTranscriptAlignment.ipynb shows how to plot word- and phone-level alignments.
- data/ contains an example audio file, transcript, word-level alignment, and phone-level alignment.
- figures/ contains the output of figures generated.
You can setup a virtual environment as follows:
virtualenv venv
source venv/bin/activate
pip install librosa