Reading formants from audio files into Python by wrapping calls to Praat. To reduce overhead, calls to Praat are memoized. This can be disabled by setting memoize_call=False in the function parameters.
Extract formants at time point 0.5s from wavfile:
import praat_formants_python as pfp
pfp.formants_at_time('/path/to/wavfile/', 0.5)
Extract formants at time interval [0.5, 0.7] from wavfile:
import praat_formants_python as pfp
pfp.formants_at_interval('/path/to/wavfile/', 0.5, 0.7)
Maximum formant, window length and preemphasis can be passed in as keyword arguments. By default, these are set as maxformant=5500, winlen=0.025, preemph=50
import praat_formants_python as pfp
pfp.formants_at_interval('/path/to/wavfile/', 0.5, 0.7,
maxformant=5000, winlen=0.50, preemph=99)
This package requires numpy. See installation instructions there.
Run setup.py:
python setup.py install
To be able to find Praat, the praat executable should be in your PATH. For OSX: the Praat program installs to /Applications/Audio/Praat.app/Contents/MacOS/Praat, which is not in the PATH by default. Easiest way to solve that is to put a symlink in /usr/bin to there, i.e. open a Terminal and do
$ sudo ln -s /Applications/Audio/Praat.app/Contents/MacOS/Praat /usr/bin/praat
For Linux: Praat installs to /usr/bin by default, so you don’t have to do anything.