In [1]:

    

from IPython.display import YouTubeVideo
YouTubeVideo('yZV-XCSmWQY')


    

    
Out[1]:





        
        

In [1]:

    

parm_runtime_env_GCP = True
# parm_runtime_env_GCP = False


    

In [2]:

    

# Copyright 2016 Google Inc.
# Licensed under the Apache License, Version 2.0 (the "License"); 
# import subprocess
# retcode = subprocess.call(['pip', 'install', '-U', 'google-api-python-client'])
# retcode = subprocess.call(['pip', 'install', '-U', 'gTTS'])

# Below is for GCP only: install audio conversion tool
# retcode = subprocess.call(['apt-get', 'update', '-y'])
# retcode = subprocess.call(['apt-get', 'install', 'libav-tools', '-y'])


    

In [3]:

    

import io, os, subprocess, sys, re, codecs, time, datetime, requests, itchat
from itchat.content import *
from googleapiclient.discovery import build


    

    




█

In [4]:

    

# Here I read in my own API_KEY from a file, which is not shared in Github repository:
# with io.open('../../API_KEY.txt') as fp: 
#     for line in fp: APIKEY = line

# You need to un-comment below line and replace 'APIKEY' variable with your own GCP API key:
APIKEY='AIzaSyCvxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx'


    

In [5]:

    

# Below is for Google Speech synthesis: text to voice API
from gtts import gTTS

# Below is for  Google Speech recognition: voice to text API
speech_service = build('speech', 'v1', developerKey=APIKEY)

# Below is for Google Language Tranlation API
service = build('translate', 'v2', developerKey=APIKEY)


    

In [6]:

    

# Import the base64 encoding library.
import base64
# Pass the image data to an encoding function.
def encode_image(image_file):
    with io.open(image_file, "rb") as image_file:
        image_content = image_file.read()
# Python 2
    if sys.version_info[0] < 3:
        return base64.b64encode(image_content)
# Python 3
    else:
        return base64.b64encode(image_content).decode('utf-8')

# Pass the audio data to an encoding function.
def encode_audio(audio_file):
    with io.open(audio_file, 'rb') as audio_file:
        audio_content = audio_file.read()
# Python 2
    if sys.version_info[0] < 3:
        return base64.b64encode(audio_content)
# Python 3
    else:
        return base64.b64encode(audio_content).decode('utf-8')


    

In [7]:

    

# API control parameter for Image API:
parm_image_maxResults = 10 # max objects or faces to be extracted from image analysis

# API control parameter for Language Translation API:
parm_translation_origin_language = 'zh' # original language in text: to be overwriten by TEXT_DETECTION
parm_translation_target_language = 'zh' # target language for translation: Chinese


# API control parameter for 消息文字转成语音 (Speech synthesis: text to voice)
parm_speech_synthesis_language = 'zh' # speech synthesis API 'text to voice' language
# parm_speech_synthesis_language = 'zh-tw' # speech synthesis API 'text to voice' language
# parm_speech_synthesis_language = 'zh-yue' # speech synthesis API 'text to voice' language

# API control parameter for 语音转换成消息文字 (Speech recognition: voice to text)
# parm_speech_recognition_language = 'en' # speech API 'voice to text' language
parm_speech_recognition_language = 'cmn-Hans-CN' # speech API 'voice to text' language


    

In [8]:

    

# Running Speech API
def KudosData_text_to_voice(text2voice): 
    # Python 2
    if sys.version_info[0] < 3: 
        tts = gTTS(text=text2voice.encode('utf-8'), lang=parm_speech_synthesis_language, slow=False)
    # Python 3
    else:
        tts = gTTS(text=text2voice, lang=parm_speech_synthesis_language, slow=False)

    text2voiceMP3name = 'Voice_For_You.mp3'
    tts.save(text2voiceMP3name)
    print('\nCompeleted: Speech synthesis API ( Text -> Voice)')
    print(text2voice)
    return text2voiceMP3name


    

In [9]:

    

#    msg.download(msg.fileName)
#    print('\nDownloaded image file name is: %s' % msg['FileName'])

#    audio_file_input = msg['FileName']
#    audio_type = ['flac', 'wav']

# Running Speech API
def KudosData_voice_to_text(audio_file_input, audio_type):
    audio_file_output = str(audio_file_input) + '.' + str(audio_type)
#     print('audio_file_input             : %s' % audio_file_input)
    print('Converted  audio file for API: %s' % audio_file_output)
    
    # convert mp3 file to target GCP audio file:

# remove audio_file_output, is exist
    retcode = subprocess.call(['rm', audio_file_output])
    # print(retcode)
    
    if parm_runtime_env_GCP: # using Datalab in Google Cloud Platform
        # GCP: use avconv to convert audio
        retcode = subprocess.call(['avconv', '-i', audio_file_input, '-ac', '1', audio_file_output])
    else: # using a Kudos Data Virtual Machine, or local machine
        # VM : use ffmpeg to convert audio
        retcode = subprocess.call(['ffmpeg', '-i', audio_file_input, '-ac', '1', audio_file_output])
    # print(retcode)

    # Call GCP Speech API:
    # response = speech_service.speech().syncrecognize(
    response = speech_service.speech().recognize(
        body={
            'config': {
#                 'encoding': 'LINEAR16',
#                 'sampleRateHertz': 16000,
                'languageCode': parm_speech_recognition_language
            },
            'audio': {
                'content': encode_audio(audio_file_output) # base64 of converted audio file, for speech recognition
                }
            }).execute()    
    print('Compeleted: Speech recognition API ( Voice -> Text )')
    return response


    

In [10]:

    

def KudosData_TEXT_TRANSLATION(text, origin_language_code, target_language_code):
    # Call translation if parm_translation_origin_language is not parm_translation_target_language
    if origin_language_code != target_language_code:
        outputs = service.translations().list(source=origin_language_code, 
                                              target=target_language_code, q=text).execute()
        translated_text = ''
        translated_text += u'---- Start Translation ----\n'
        translated_text += u'( Origin Lang 原文: ' + origin_language_code + ' )\n'
        translated_text += u'( Target Lang 译文: ' + target_language_code + ' )\n'
        translated_text += outputs['translations'][0]['translatedText'] + '\n' + '----- End Translation -----\n'
        print('Compeleted: Translation    API : From Language \'%s\' to \'%s\'' 
              % (origin_language_code, target_language_code))
    else:
        translated_text = text
        
    return translated_text


    

In [11]:

    

itchat.auto_login(hotReload=True) # hotReload=True: 退出程序后暂存登陆状态。即使程序关闭，一定时间内重新开启也可以不用重新扫码。


    

In [12]:

    

# Obtain my own Nick Name
MySelf = itchat.search_friends()
NickName4RegEx = '@' + MySelf['NickName'] + '\s*'


    

In [ ]:

    

# 1. 消息文字转成语音 (Speech synthesis: text to voice)

# 在群里，如果收到 @ 自己的文字信息，会自动将文字转换成语音，再以 mp3 文件方式发送回复：
@itchat.msg_register(TEXT, isGroupChat=True)
def text_to_voice_reply(msg):
    if msg['isAt']:
        # Remove my own Nick Name from message:
        text2voice = re.sub(NickName4RegEx, '', msg['Content'])
        text2voiceMP3name = KudosData_text_to_voice(text2voice)
        itchat.send('@%s@%s' % ('fil', text2voiceMP3name), msg['FromUserName'])


    

In [13]:

    

# 2. 语音转换成消息文字 (Speech recognition: voice to text)

@itchat.msg_register([RECORDING], isGroupChat=True)
@itchat.msg_register([RECORDING])
def download_files(msg):
    parm_translation_origin_language = 'zh' # will be overwriten by TEXT_DETECTION
    msg.download(msg.fileName)
    print('\nDownloaded audio file name is: %s' % msg['FileName'])
    
    ##############################################################################################################
    #                                          call audio analysis APIs                                          #
    ##############################################################################################################
    
    audio_analysis_reply = u'[ Audio Analysis 音频处理结果 ]\n'

    # Voice to Text:
    audio_analysis_reply += u'\n[ Voice -> Text 语音识别 ]\n'
    response = KudosData_voice_to_text(msg['FileName'], 'flac')
#     response = KudosData_voice_to_text(msg['FileName'], 'wav')
    if response != {}:
        print (response['results'][0]['alternatives'][0]['transcript'])
        print ('( confidence %f )' % response['results'][0]['alternatives'][0]['confidence'])
        audio_analysis_reply += response['results'][0]['alternatives'][0]['transcript'] + '\n'
        audio_analysis_reply += '( confidence ' + str(response['results'][0]['alternatives'][0]['confidence']) + ' )\n'
        # Translate recognised text to another language:
        parm_translation_origin_language = 'zh'
        parm_translation_target_language = 'en'
        translated_text_reply = KudosData_TEXT_TRANSLATION(response['results'][0]['alternatives'][0]['transcript'], 
                                                           parm_translation_origin_language, parm_translation_target_language)
        print(translated_text_reply)
        audio_analysis_reply += translated_text_reply
    
    return audio_analysis_reply


    

In [ ]:

    

# 3. 消息文字的多语言互译 (Text based language translation)

# 在群里，如果收到 @ 自己的文字信息，会自动进行文字翻译，再发送回复：
@itchat.msg_register(TEXT, isGroupChat=True)
def text_to_translation_reply(msg):
    if msg['isAt']:
        text4translation = re.sub(NickName4RegEx, '', msg['Content'])
        parm_translation_origin_language = 'zh'
        parm_translation_target_language = 'en'
        translated_text_reply = KudosData_TEXT_TRANSLATION(text4translation, 
                                                           parm_translation_origin_language, parm_translation_target_language)
        print(translated_text_reply)
        return translated_text_reply


    

In [14]:

    

@itchat.msg_register(TEXT, isGroupChat=True)
def text_reply(msg):
    if msg['isAt']:
        # 1. 消息文字转成语音 (Speech synthesis: text to voice)
        text2voice = re.sub(NickName4RegEx, '', msg['Content']) # Remove my own Nick Name from message
        text2voiceMP3name = KudosData_text_to_voice(text2voice)
        itchat.send('@%s@%s' % ('fil', text2voiceMP3name), msg['FromUserName'])
        # 3. 消息文字的多语言互译 (Text based language translation)
        text4translation = re.sub(NickName4RegEx, '', msg['Content'])
        parm_translation_origin_language = 'zh'
        parm_translation_target_language = 'en'
        translated_text_reply = KudosData_TEXT_TRANSLATION(text4translation, 
                                                           parm_translation_origin_language, parm_translation_target_language)
        print(translated_text_reply)
        return translated_text_reply


    

In [15]:

    

itchat.run()


    

    




Start auto replying.






    




Compeleted: Speech synthesis API ( Text -> Voice)
 张学友的夕阳醉了。夕阳醉了，落霞醉了，任谁都掩饰不了。因我的心，因我的心，早醉掉。是谁带笑，是谁带俏。默然将心偷取了。酒醉的心，酒醉的心，被燃烧。唯愿心底一个梦，变真。
Compeleted: Translation    API : From Language 'zh' to 'en'
---- Start Translation ----
( Origin Lang 原文: zh )
( Target Lang 译文: en )
Jacky Cheung's sunset drunk. Sunset drunk, drop drunk, any who can not cover up. Because of my heart, because of my heart, early drunk. Who is laughing, who is with Qiao. Silently steal the heart. Drunk heart, drunk heart, burned. Is willing to mind a dream, real.
----- End Translation -----







    




Bye~

In [42]:

    

# interupt kernel, then logout
itchat.logout() # 安全退出


    

    
Out[42]:





<ItchatReturnValue: {'BaseResponse': {'Ret': 0, 'ErrMsg': u'\u8bf7\u6c42\u6210\u529f', 'RawMsg': 'logout successfully.'}}>