Commit d673a27

authored

Merge pull request avinashkranjan#1800 from Shivansh-Jain-github/SJ_PR3

Adding python script to convert audio input to text input.

2 parents 8fafc50 + a966283 commit d673a27Copy full SHA for d673a27

File tree

+58

-0

lines changed

+58

-0

lines changed

Lines changed: 21 additions & 0 deletions

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,21 @@`
	`1`	`+# Speech to Text Conversion`
	`2`	`+`
	`3`	+This Python script demonstrates how to convert audio input into text using the `speech_recognition` library. It utilizes the `recognize_google` function from the library to convert the speech into text.
	`4`	`+`
	`5`	`+## Prerequisites`
	`6`	`+- Python`
	`7`	+- `speech_recognition` library (install using `pip install SpeechRecognition`)
	`8`	+- `pyaudio` library (install using `pip install pyaudio`)
	`9`	`+`
	`10`	+Note: The `pyaudio` library is required for microphone access and recording audio.
	`11`	`+`
	`12`	`+## Usage`
	`13`	`+1. Ensure that you have a working microphone connected to your computer.`
	`14`	`+2. Run the script and speak into the microphone when prompted.`
	`15`	`+3. The script will convert the audio to text using the Google Speech Recognition service.`
	`16`	`+4. If the speech is recognized, the converted text will be displayed.`
	`17`	`+5. Now, you can do whatever operations you want with the input text.`
	`18`	`+`
	`19`	`+`
	`20`	`+`
	`21`	`+Feel free to use this code as a starting point for your speech-to-text conversion tasks.`

Lines changed: 37 additions & 0 deletions

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,37 @@`
	`1`	`+import speech_recognition as sr`
	`2`	`+`
	`3`	`+def convert_audio_to_text():`
	`4`	`+ # Initialize the recognizer`
	`5`	`+ r = sr.Recognizer()`
	`6`	`+`
	`7`	`+ # Open the microphone and start recording`
	`8`	`+ with sr.Microphone() as source:`
	`9`	`+ print("Speak something...")`
	`10`	`+ audio = r.listen(source) # Record audio from the microphone`
	`11`	`+`
	`12`	`+ try:`
	`13`	`+ # Use the recognizer to convert audio to text`
	`14`	`+ text = r.recognize_google(audio) # Convert audio to text using Google Speech Recognition service`
	`15`	`+ return text`
	`16`	`+ except sr.UnknownValueError:`
	`17`	`+ print("Unable to recognize speech.") # Handle the case when speech cannot be recognized`
	`18`	`+ except sr.RequestError as e:`
	`19`	`+ print("Error: {0}".format(e)) # Handle any errors that occur during speech recognition`
	`20`	`+`
	`21`	`+# Example usage`
	`22`	`+audio_text = convert_audio_to_text() # Call the function to convert audio to text`
	`23`	`+if audio_text:`
	`24`	`+ print("You said:", audio_text) # Print the converted text`
	`25`	`+`
	`26`	`+# Manipulate the text for further operations`
	`27`	`+if audio_text:`
	`28`	`+ # Convert the text to lowercase`
	`29`	`+ lowercase_text = audio_text.lower()`
	`30`	`+ print("Lowercase text:", lowercase_text)`
	`31`	`+`
	`32`	`+ # Split the text into words`
	`33`	`+ words = lowercase_text.split()`
	`34`	`+ print("Words:", words)`
	`35`	`+`
	`36`	`+ # Perform other operations on the text as needed`
	`37`	`+`

Comments

(0)