Sheldon1999 / speech-recognition

a device-state based speech recognition script

Repository from Github https://github.comSheldon1999/speech-recognitionRepository from Github https://github.comSheldon1999/speech-recognition

ssGrapher

A smart Stenographer

This is a python script that will first recognize whether device is connected to internet or not, on the basis of that information it will choose proper speech recognition engine and apply to the service. I have also added a model(Indian english) which i have trained with my voice you can try that model.

Dependencies

  1. python
  2. pip
  3. SpeechRecognition
  4. python3-pyaudio
  5. pyttx3
  6. pocketsphinx

Local setup

  1. install all the dependencies above.
  2. download or clone repo.
  3. open command prompt or terminal.
  4. go to the repo folder.
  5. run script.

Add your own model

You can make your own speech recognition model and just replace my model with your model.To replace go to line.68 in script.py and add the path specified in comments.

Screenshots

scrnshot1 scrnshot2 scrnshot3

About

a device-state based speech recognition script

License:MIT License


Languages

Language:Python 100.0%