antonygn / speech-to-text

speech-to-text recognition using a microphone

Speech-to-Text Recognition in Python

This is a simple Python script that demonstrates how to perform speech-to-text recognition using a microphone and the speech_recognition library. It uses Google's speech recognition service to transcribe the audio.

Requirements

To use this script, you'll need the following dependencies installed on your system:

• Python 3.x
• speech_recognition library
• pyaudio library (for microphone input)

Installation

For Windows

1. Install Python 3.x from the official website.

2. Install pip, the package installer for Python, by following the instructions in the official documentation.

3. Install pyaudio library by running the following command in a terminal or command prompt:

pip install pyaudio

If you encounter an error during installation, you may need to install portaudio separately. You can download portaudio from the official website or install it using a package manager such as Chocolatey.

4. Install speech_recognition library by running the following command in a terminal or command prompt:

pip install SpeechRecognition

For Mac OS

1. Install Homebrew by following the instructions on the official website.
2. Install Python 3.x by running the following command in a terminal:

brew install python

3. Install pyaudio library by running the following command in a terminal:

brew install portaudio
pip install pyaudio

If you encounter an error during installation, you may need to specify the path to portaudio manually. You can do this by running the following command instead:

pip install --global-option='build_ext' --global-option='-I/usr/local/include' --global-option='-L/usr/local/lib' pyaudio

4. Install speech_recognition library by running the following command in a terminal:

pip install SpeechRecognition

Usage

1. Open Jupyter Notebook and create a new notebook.
2. Copy the following code into a cell:

import speech_recognition as sr
r = sr.Recognizer()
with sr.Microphone() as source:
    print("Speak Anything :")
    audio = r.listen(source)
    try:
        text = r.recognize_google(audio)
        print("You said : {}".format(text))
    except:
        print("Sorry could not recognize what you said")

3. Run the cell.
4. Speak into your microphone when prompted by the script.
5. The script will transcribe your speech and print the result to the console. If the script is unable to recognize your speech, it will print an error message.

Acknowledgments

• This script was adapted from the speech_recognition library's documentation.