A union of curiosity and data science

Knowledgebase and brain dump of a database engineer


Google Translate API - Wav file speech recognition with python3


This api transcribes up to 1 min of audio to text. You'll need a google cloud account. 

https://cloud.google.com/translate/docs/

#!/usr/bin/env python3

import speech_recognition as sr
from os import path

audio = "K:\\random\\part4.wav"
r = sr.Recognizer() #recognizer object, we can use various services with this including  google, microsoft and ibm watson
with sr.AudioFile(audio) as source:
    audio = r.record(source)  # read the entire audio file

# Google Cloud Speech Recognition
Whisper = r"""<entire contents of json credentials from google>"""
try:
    ish =  r.recognize_google_cloud(audio, credentials_json=Whisper)
    print("Transcribed:...  " +ish)
#canwehassavedfile!
    file = open("K:\\random\\part4.txt","w")
    file.write(ish)
    file.close()
except sr.RequestError as e:
    print("Sorry, can't help you. ; {0}".format(e))
except sr.UnknownValueError:
    print("What was that?")

 

Add comment