You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
OuNuPo/src/audio_transcribe.py

93 lines
4.4 KiB
Python

#!/usr/bin/env python3
import speech_recognition as sr
import sys
from termcolor import cprint, colored
# obtain path to "english.wav" in the same folder as this script
from os import path
import random
a1 = sys.argv[1] #same as $1 so when you run python3 audio_transcribe.py FOO ... argv[1] is FOO
# print ("transcribing", a1, file=sys.stderr)
AUDIO_FILE = path.join(path.dirname(path.realpath(__file__)), a1) # before it was english.wav
# AUDIO_FILE = path.join(path.dirname(path.realpath(__file__)), "french.aiff")
# AUDIO_FILE = path.join(path.dirname(path.realpath(__file__)), "chinese.flac")
# print (AUDIO_FILE)
# use the audio file as the audio source
r = sr.Recognizer()
with sr.AudioFile(AUDIO_FILE) as source:
audio = r.record(source) # read the entire audio file
color = ["white", "yellow"]
on_color = ["on_red", "on_magenta", "on_blue", "on_grey"]
# recognize speech using Sphinx
try:
cprint( r.recognize_sphinx(audio), random.choice(color), random.choice(on_color))
# print( r.recognize_sphinx(audio))
except sr.UnknownValueError:
print("uknown")
except sr.RequestError as e:
print("Sphinx error; {0}".format(e))
# sleep (1)
# # recognize speech using Google Speech Recognition
# try:
# # for testing purposes, we're just using the default API key
# # to use another API key, use `r.recognize_google(audio, key="GOOGLE_SPEECH_RECOGNITION_API_KEY")`
# # instead of `r.recognize_google(audio)`
# print("Google Speech Recognition thinks you said " + r.recognize_google(audio))
# except sr.UnknownValueError:
# print("Google Speech Recognition could not understand audio")
# except sr.RequestError as e:
# print("Could not request results from Google Speech Recognition service; {0}".format(e))
# # recognize speech using Google Cloud Speech
# GOOGLE_CLOUD_SPEECH_CREDENTIALS = r"""INSERT THE CONTENTS OF THE GOOGLE CLOUD SPEECH JSON CREDENTIALS FILE HERE"""
# try:
# print("Google Cloud Speech thinks you said " + r.recognize_google_cloud(audio, credentials_json=GOOGLE_CLOUD_SPEECH_CREDENTIALS))
# except sr.UnknownValueError:
# print("Google Cloud Speech could not understand audio")
# except sr.RequestError as e:
# print("Could not request results from Google Cloud Speech service; {0}".format(e))
# # recognize speech using Wit.ai
# WIT_AI_KEY = "INSERT WIT.AI API KEY HERE" # Wit.ai keys are 32-character uppercase alphanumeric strings
# try:
# print("Wit.ai thinks you said " + r.recognize_wit(audio, key=WIT_AI_KEY))
# except sr.UnknownValueError:
# print("Wit.ai could not understand audio")
# except sr.RequestError as e:
# print("Could not request results from Wit.ai service; {0}".format(e))
# # recognize speech using Microsoft Bing Voice Recognition
# BING_KEY = "INSERT BING API KEY HERE" # Microsoft Bing Voice Recognition API keys 32-character lowercase hexadecimal strings
# try:
# print("Microsoft Bing Voice Recognition thinks you said " + r.recognize_bing(audio, key=BING_KEY))
# except sr.UnknownValueError:
# print("Microsoft Bing Voice Recognition could not understand audio")
# except sr.RequestError as e:
# print("Could not request results from Microsoft Bing Voice Recognition service; {0}".format(e))
# # recognize speech using Houndify
# HOUNDIFY_CLIENT_ID = "INSERT HOUNDIFY CLIENT ID HERE" # Houndify client IDs are Base64-encoded strings
# HOUNDIFY_CLIENT_KEY = "INSERT HOUNDIFY CLIENT KEY HERE" # Houndify client keys are Base64-encoded strings
# try:
# print("Houndify thinks you said " + r.recognize_houndify(audio, client_id=HOUNDIFY_CLIENT_ID, client_key=HOUNDIFY_CLIENT_KEY))
# except sr.UnknownValueError:
# print("Houndify could not understand audio")
# except sr.RequestError as e:
# print("Could not request results from Houndify service; {0}".format(e))
# # recognize speech using IBM Speech to Text
# IBM_USERNAME = "INSERT IBM SPEECH TO TEXT USERNAME HERE" # IBM Speech to Text usernames are strings of the form XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX
# IBM_PASSWORD = "INSERT IBM SPEECH TO TEXT PASSWORD HERE" # IBM Speech to Text passwords are mixed-case alphanumeric strings
# try:
# print("IBM Speech to Text thinks you said " + r.recognize_ibm(audio, username=IBM_USERNAME, password=IBM_PASSWORD))
# except sr.UnknownValueError:
# print("IBM Speech to Text could not understand audio")
# except sr.RequestError as e:
# print("Could not request results from IBM Speech to Text service; {0}".format(e))