I need to create a speech recognition program where a user can speak into a microphone and have the program continuously recognize the speech event and return a results object with audio, time stats, the transcription and more along those lines. Like the ResObj in Natlink. Unfortunately, due to system incompatibilities, Natlink is not an option. Alteratives?
Also, if you have ideas on how to make Natlink work with Python 2.4, I'd be interested in hearing your thoughts too.