Mar-04-2018, 12:47 AM
The next step would be to use Natural Language Processing to change
the mp3. Here are some packages that you may be interested in investigating:
General on speech Recognition packages: https://pypi.python.org/pypi/SpeechRecognition/
note that two of these (only) work offline, which is what you want,
snowboy: https://snowboy.kitt.ai/
and CMU Sphinx, but that's on SourceForge which apparently has some major issues after a fire, and
may not be available for some time.
the mp3. Here are some packages that you may be interested in investigating:
General on speech Recognition packages: https://pypi.python.org/pypi/SpeechRecognition/
note that two of these (only) work offline, which is what you want,
snowboy: https://snowboy.kitt.ai/
and CMU Sphinx, but that's on SourceForge which apparently has some major issues after a fire, and
may not be available for some time.