-
Notifications
You must be signed in to change notification settings - Fork 1
SpeechTest
This is the main file that one member of the QuoteR team used in order to learn how to use the Google Speech API and make it work with the main program. It utilizes the speech_recognition library to take in user input from a microphone, takes that audio, puts it through the Google Speech API, and then outputs that result as a String.
This file is a little outdated in the sense that it still has the code from when we tried to use CMU PocketSphinx instead as our converter from audio to text for speech recognition. This will prompt you to "Say Something!", and then run your audio through both CMU PocketSphinx and the Google Speech API after 5 seconds of not hearing anything. r.recognize_sphinx(audio) and r.recognize_google(audio) are the function that do the magic, calling upon their respective technologies to convert the audio. This is code is modified and then used in the GUI/main.py file.
This is a markdown file a QuoteR member made in order to help guide the user with these dependencies. It also helped create the Dependences and Installation page of this wiki.