如何让语音助手等待命令
How to make voice assistant wait for a command
我正在 Python 上构建我的个人语音助手。
这是代码
import pyttsx3
import speech_recognition as sr
import sys
import subprocess
engine = pyttsx3.init()
en_voice_id_m = "HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech\Voices\Tokens\TTS_MS_EN-US_DAVID_11.0"
en_voice_id_f = "HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech\Voices\Tokens\TTS_MS_EN-US_ZIRA_11.0"
gb_voice_id_f = "HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech\Voices\Tokens\TTS_MS_EN-GB_HAZEL_11.0"
voices = engine.getProperty('voices')
engine.setProperty('voice', en_voice_id_f)
engine.setProperty('rate', 195)
#engine.say("Hello. I'm Elsi, your voice assistant. I can do anything u want")
engine.runAndWait()
while True:
r = sr.Recognizer()
with sr.Microphone() as source:
print("Say something!")
audio = r.listen(source)
if r.recognize_google(audio).lower() == 'hello':
engine = pyttsx3.init()
engine.say("Hi! How are you?")
engine.runAndWait()
elif r.recognize_google(audio).lower() == 'who are you':
engine = pyttsx3.init()
engine.say("I am Elsi, voice assistant")
engine.runAndWait()
elif r.recognize_google(audio).lower() == 'what can you do':
engine = pyttsx3.init()
engine.say("I can turn on film or music, open application and that's all :)")
engine.runAndWait()
elif r.recognize_google(audio).lower() == 'how can I call you?':
engine = pyttsx3.init()
engine.say("You can call me Elsi")
engine.runAndWait()
elif r.recognize_google(audio).lower() == 'stop':
engine = pyttsx3.init()
engine.say("Turning off")
engine.runAndWait()
sys.exit()
elif r.recognize_google(audio).lower() == 'exit':
engine = pyttsx3.init()
engine.say("Goodbye ;)")
engine.runAndWait()
sys.exit()
elif r.recognize_google(audio).lower() == 'turn off':
engine = pyttsx3.init()
engine.say("One moment please...")
engine.runAndWait()
sys.exit()
elif r.recognize_google(audio).lower() == 'telegram':
engine = pyttsx3.init()
engine.say("One moment")
engine.runAndWait()
subprocess.check_output(telegram, shell=True)
elif r.recognize_google(audio).lower() == 'open telegram':
engine = pyttsx3.init()
engine.say("Opening....")
engine.runAndWait()
subprocess.check_output(telegram, shell=True)
elif r.recognize_google(audio).lower() == 'Elsi open telegram':
engine = pyttsx3.init()
engine.say("Yes sir")
engine.runAndWait()
subprocess.check_output(telegram, shell=True)
elif r.recognize_google(audio).lower() == 'viber':
engine = pyttsx3.init()
engine.say("One moment")
engine.runAndWait()
subprocess.check_output(viber, shell=True)
elif r.recognize_google(audio).lower() == 'open viber':
engine = pyttsx3.init()
engine.say("Opening....")
engine.runAndWait()
subprocess.check_output(viber, shell=True)
else:
engine = pyttsx3.init()
engine.say("Didn't catch it, repeat please")
engine.runAndWait()
当我 运行 程序并静静地坐着时，它给出了这个错误 -
Traceback (most recent call last):
File "C:\Users\___\!Python!\Elsi\version#2.py", line 38, in <module>
if r.recognize_google(audio).lower() == 'hello':
File "C:\Users\___\AppData\Local\Programs\Python\Python36-32\lib\site-packages\speech_recognition\__init__.py", line 858, in recognize_google
if not isinstance(actual_result, dict) or len(actual_result.get("alternative", [])) == 0: raise UnknownValueError()
speech_recognition.UnknownValueError
这是我的尝试-
r = sr.Recognizer()
with sr.Microphone() as source:
r.adjust_for_ambient_noise(source, 1)
audio = r.listen(source, 1)
recognize_sphinx() offline
while r.recognize_google(audio).lower() != 'Elsi' or 'Elsea' or 'Elsa' or 'Elsia' or 'Chelsea':
- 这给出了同样的错误。
- 删除与识别短语相关的所有
if、elif 和 else 条件。
- 将短语放在
dict 中作为键。该值可以是一个列表，其中索引 0 是文本响应，索引 2 是命令（'exit'、viber、telegram）或 None。
- 使用
.get() 方法检索值或 return unknown_command_phrase 如果没有键匹配。
r.recognize_google(audio).lower() 到变量 pattern- 添加一个函数来处理来自语音识别引擎的响应。
import pyttsx3
import speech_recognition as sr
import sys
import subprocess
# This function is from Real Python: https://realpython.com/python-speech-recognition/#putting-it-all-together-a-guess-the-word-game
def recognize_speech_from_mic(recognizer, microphone) -> dict:
"""Transcribe speech from recorded from `microphone`.
Returns a dictionary with three keys:
"success": a boolean indicating whether or not the API request was successful
"error": `None` if no error occured, otherwise a string containing an error message if the API could not be reached or speech was unrecognizable
"transcription": `None` if speech could not be transcribed, otherwise a string containing the transcribed text
"""
# check that recognizer and microphone arguments are appropriate type
if not isinstance(recognizer, sr.Recognizer):
raise TypeError("`recognizer` must be `Recognizer` instance")
if not isinstance(microphone, sr.Microphone):
raise TypeError("`microphone` must be `Microphone` instance")
# adjust the recognizer sensitivity to ambient noise and record audio from the microphone
with microphone as source:
recognizer.adjust_for_ambient_noise(source)
audio = recognizer.listen(source)
# set up the response object
response = {"success": True,
"error": None,
"transcription": None}
# try recognizing the speech in the recording if a RequestError or UnknownValueError exception is caught, update the response object accordingly
try:
response["transcription"] = recognizer.recognize_google(audio)
except sr.RequestError:
# API was unreachable or unresponsive
response["success"] = False
response["error"] = "API unavailable"
except sr.UnknownValueError:
# speech was unintelligible
response["error"] = "Unable to recognize speech"
return response
my_phrases = {'hello': ['Hi!, How are you?', None],
'who are you': ['I am Elsi, voice assistant', None],
'what can you do': ["I can turn on film or music, open application and that's all :)", None],
'how can I call you?': ['You can call me Elsi', None],
'stop': ['Turning off', 'exit'],
'exit': ['Goodbye ;)', 'exit'],
'turn off': ['One moment please...', 'exit'],
'telegram': ['One moment', telegram],
'open telegram': ['Opening....', telegram],
'Elsi open telegram': ['Yes sir', telegram],
'viber': ['One moment', viber],
'open viber': ['Opening....', viber]}
unknown_command_phrase = ["Didn't catch it, repeat please", None]
engine = pyttsx3.init()
en_voice_id_m = "HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech\Voices\Tokens\TTS_MS_EN-US_DAVID_11.0"
en_voice_id_f = "HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech\Voices\Tokens\TTS_MS_EN-US_ZIRA_11.0"
gb_voice_id_f = "HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech\Voices\Tokens\TTS_MS_EN-GB_HAZEL_11.0"
voices = engine.getProperty('voices')
engine.setProperty('voice', en_voice_id_f)
engine.setProperty('rate', 195)
#engine.say("Hello. I'm Elsi, your voice assistant. I can do anything u want")
while True:
engine.runAndWait()
# create recognizer and mic instances
recognizer = sr.Recognizer()
microphone = sr.Microphone()
print("Say something!")
# call function
response = recognize_speech_from_mic(recognizer, microphone)
pattern = response['transcription'] # get transcription from response dict
say, command = my_phrases.get(pattern, unknown_command_phrase) # retrieve response from my_phrases
engine = pyttsx3.init()
engine.say(say)
if command == None:
print(f'The response returned by the speech recognition engine was:\n{pattern}.\n')
pass
elif command == 'exit':
sys.exit()
else:
subprocess.check_output(command, shell=True) # assumes you have these properly configured
pass
我正在 Python 上构建我的个人语音助手。
这是代码
import pyttsx3
import speech_recognition as sr
import sys
import subprocess
engine = pyttsx3.init()
en_voice_id_m = "HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech\Voices\Tokens\TTS_MS_EN-US_DAVID_11.0"
en_voice_id_f = "HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech\Voices\Tokens\TTS_MS_EN-US_ZIRA_11.0"
gb_voice_id_f = "HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech\Voices\Tokens\TTS_MS_EN-GB_HAZEL_11.0"
voices = engine.getProperty('voices')
engine.setProperty('voice', en_voice_id_f)
engine.setProperty('rate', 195)
#engine.say("Hello. I'm Elsi, your voice assistant. I can do anything u want")
engine.runAndWait()
while True:
r = sr.Recognizer()
with sr.Microphone() as source:
print("Say something!")
audio = r.listen(source)
if r.recognize_google(audio).lower() == 'hello':
engine = pyttsx3.init()
engine.say("Hi! How are you?")
engine.runAndWait()
elif r.recognize_google(audio).lower() == 'who are you':
engine = pyttsx3.init()
engine.say("I am Elsi, voice assistant")
engine.runAndWait()
elif r.recognize_google(audio).lower() == 'what can you do':
engine = pyttsx3.init()
engine.say("I can turn on film or music, open application and that's all :)")
engine.runAndWait()
elif r.recognize_google(audio).lower() == 'how can I call you?':
engine = pyttsx3.init()
engine.say("You can call me Elsi")
engine.runAndWait()
elif r.recognize_google(audio).lower() == 'stop':
engine = pyttsx3.init()
engine.say("Turning off")
engine.runAndWait()
sys.exit()
elif r.recognize_google(audio).lower() == 'exit':
engine = pyttsx3.init()
engine.say("Goodbye ;)")
engine.runAndWait()
sys.exit()
elif r.recognize_google(audio).lower() == 'turn off':
engine = pyttsx3.init()
engine.say("One moment please...")
engine.runAndWait()
sys.exit()
elif r.recognize_google(audio).lower() == 'telegram':
engine = pyttsx3.init()
engine.say("One moment")
engine.runAndWait()
subprocess.check_output(telegram, shell=True)
elif r.recognize_google(audio).lower() == 'open telegram':
engine = pyttsx3.init()
engine.say("Opening....")
engine.runAndWait()
subprocess.check_output(telegram, shell=True)
elif r.recognize_google(audio).lower() == 'Elsi open telegram':
engine = pyttsx3.init()
engine.say("Yes sir")
engine.runAndWait()
subprocess.check_output(telegram, shell=True)
elif r.recognize_google(audio).lower() == 'viber':
engine = pyttsx3.init()
engine.say("One moment")
engine.runAndWait()
subprocess.check_output(viber, shell=True)
elif r.recognize_google(audio).lower() == 'open viber':
engine = pyttsx3.init()
engine.say("Opening....")
engine.runAndWait()
subprocess.check_output(viber, shell=True)
else:
engine = pyttsx3.init()
engine.say("Didn't catch it, repeat please")
engine.runAndWait()
当我 运行 程序并静静地坐着时，它给出了这个错误 -
Traceback (most recent call last):
File "C:\Users\___\!Python!\Elsi\version#2.py", line 38, in <module>
if r.recognize_google(audio).lower() == 'hello':
File "C:\Users\___\AppData\Local\Programs\Python\Python36-32\lib\site-packages\speech_recognition\__init__.py", line 858, in recognize_google
if not isinstance(actual_result, dict) or len(actual_result.get("alternative", [])) == 0: raise UnknownValueError()
speech_recognition.UnknownValueError
这是我的尝试-
r = sr.Recognizer()
with sr.Microphone() as source:
r.adjust_for_ambient_noise(source, 1)
audio = r.listen(source, 1)
recognize_sphinx() offline
while r.recognize_google(audio).lower() != 'Elsi' or 'Elsea' or 'Elsa' or 'Elsia' or 'Chelsea':
- 这给出了同样的错误。
- 删除与识别短语相关的所有
if、elif和else条件。 - 将短语放在
dict中作为键。该值可以是一个列表，其中索引 0 是文本响应，索引 2 是命令（'exit'、viber、telegram）或None。- 使用
.get()方法检索值或 returnunknown_command_phrase如果没有键匹配。
- 使用
r.recognize_google(audio).lower()到变量pattern- 添加一个函数来处理来自语音识别引擎的响应。
import pyttsx3
import speech_recognition as sr
import sys
import subprocess
# This function is from Real Python: https://realpython.com/python-speech-recognition/#putting-it-all-together-a-guess-the-word-game
def recognize_speech_from_mic(recognizer, microphone) -> dict:
"""Transcribe speech from recorded from `microphone`.
Returns a dictionary with three keys:
"success": a boolean indicating whether or not the API request was successful
"error": `None` if no error occured, otherwise a string containing an error message if the API could not be reached or speech was unrecognizable
"transcription": `None` if speech could not be transcribed, otherwise a string containing the transcribed text
"""
# check that recognizer and microphone arguments are appropriate type
if not isinstance(recognizer, sr.Recognizer):
raise TypeError("`recognizer` must be `Recognizer` instance")
if not isinstance(microphone, sr.Microphone):
raise TypeError("`microphone` must be `Microphone` instance")
# adjust the recognizer sensitivity to ambient noise and record audio from the microphone
with microphone as source:
recognizer.adjust_for_ambient_noise(source)
audio = recognizer.listen(source)
# set up the response object
response = {"success": True,
"error": None,
"transcription": None}
# try recognizing the speech in the recording if a RequestError or UnknownValueError exception is caught, update the response object accordingly
try:
response["transcription"] = recognizer.recognize_google(audio)
except sr.RequestError:
# API was unreachable or unresponsive
response["success"] = False
response["error"] = "API unavailable"
except sr.UnknownValueError:
# speech was unintelligible
response["error"] = "Unable to recognize speech"
return response
my_phrases = {'hello': ['Hi!, How are you?', None],
'who are you': ['I am Elsi, voice assistant', None],
'what can you do': ["I can turn on film or music, open application and that's all :)", None],
'how can I call you?': ['You can call me Elsi', None],
'stop': ['Turning off', 'exit'],
'exit': ['Goodbye ;)', 'exit'],
'turn off': ['One moment please...', 'exit'],
'telegram': ['One moment', telegram],
'open telegram': ['Opening....', telegram],
'Elsi open telegram': ['Yes sir', telegram],
'viber': ['One moment', viber],
'open viber': ['Opening....', viber]}
unknown_command_phrase = ["Didn't catch it, repeat please", None]
engine = pyttsx3.init()
en_voice_id_m = "HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech\Voices\Tokens\TTS_MS_EN-US_DAVID_11.0"
en_voice_id_f = "HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech\Voices\Tokens\TTS_MS_EN-US_ZIRA_11.0"
gb_voice_id_f = "HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Speech\Voices\Tokens\TTS_MS_EN-GB_HAZEL_11.0"
voices = engine.getProperty('voices')
engine.setProperty('voice', en_voice_id_f)
engine.setProperty('rate', 195)
#engine.say("Hello. I'm Elsi, your voice assistant. I can do anything u want")
while True:
engine.runAndWait()
# create recognizer and mic instances
recognizer = sr.Recognizer()
microphone = sr.Microphone()
print("Say something!")
# call function
response = recognize_speech_from_mic(recognizer, microphone)
pattern = response['transcription'] # get transcription from response dict
say, command = my_phrases.get(pattern, unknown_command_phrase) # retrieve response from my_phrases
engine = pyttsx3.init()
engine.say(say)
if command == None:
print(f'The response returned by the speech recognition engine was:\n{pattern}.\n')
pass
elif command == 'exit':
sys.exit()
else:
subprocess.check_output(command, shell=True) # assumes you have these properly configured
pass