def RecognizeSpeech(AUDIO_FILENAME, num_seconds=5): # record audio of specified length in specified audio file record_audio(num_seconds, AUDIO_FILENAME) # reading audio audio = read_audio(AUDIO_FILENAME) # defining headers for HTTP request headers = { 'authorization': 'Bearer ' + wit_access_token, 'Content-Type': 'audio/wav' } # making an HTTP post request resp = requests.post(API_ENDPOINT, headers=headers, data=audio) # converting response content to JSON format data = json.loads(resp.content) # get text from data text = data['_text'] # return the text return text
def RecognizeSpeech(AUDIO_FILENAME, num_seconds): # record audio of specified length in specified audio file record_audio(num_seconds, AUDIO_FILENAME) # reading audio audio = read_audio(AUDIO_FILENAME) # defining headers for HTTP request headers = {'authorization': 'Bearer ' + wit_access_token, 'Content-Type': 'audio/wav'} # making an HTTP post request resp = requests.post(API_ENDPOINT, headers = headers, data = audio) #print('Http post request=',resp) # converting response content to JSON format data = json.loads(resp.content) #print(data) entities = list(data['entities'].keys()) #print('data dictionary = ',entities) # get text from data text = data['text'] print("\nYou said: {}".format(text)) # return the text return entities
def RecognizeSpeechGoogle(AUDIO_FILENAME, num_seconds=5): recogniser = sr.Recognizer() record_audio(num_seconds,AUDIO_FILENAME) audio_file = sr.AudioFile(AUDIO_FILENAME) with audio_file as source: recogniser.adjust_for_ambient_noise(source) audio = recogniser.record(source) try: text = recogniser.recognize_google(audio) return text except: return ""
def RecognizeSpeech(AUDIO_FILENAME, num_seconds = 5): record_audio(num_seconds, AUDIO_FILENAME) audio = read_audio(AUDIO_FILENAME) headers = {'authorization': 'Bearer ' + wit_access_token, 'Content-Type': 'audio/wav'} resp = requests.post(API_ENDPOINT, headers = headers, data = audio) # print(resp.content) # input() data = json.loads(resp.content) text = data['_text'] return text
def start_record_audio(): # record audio and save in memory (BytesIO) temp_file = io.BytesIO() audio_bytes = record_audio(config, temp_file) # reading audio audio = read_audio(audio_bytes) thread_text_from_audio = threading.Thread(target=get_text_from_audio, args={audio: audio}) thread_text_from_audio.start()
def RecognizeSpeech(AUDIO_FILENAME, num_seconds = 5): # record audio of specified length in specified audio file record_audio(num_seconds, AUDIO_FILENAME) # reading audio audio = read_audio(AUDIO_FILENAME) # defining headers for HTTP request headers = {'authorization': 'Bearer ' + wit_access_token, 'Content-Type': 'audio/wav'} # making an HTTP post request resp = requests.post(API_ENDPOINT, headers = headers, data = audio) # converting response content to JSON format data = json.loads(resp.content) # get text from data try: text = data['_text'] print("\nYou said: {}".format(text)) except: text = "" print("\nYou said: {}".format(text)) text = re.sub("srf 1","srf1",text.lower()) text = re.sub("sf1","srf1",text.lower()) text = re.sub("sr1","srf1",text.lower()) text = re.sub("srf 3","srf3",text.lower()) text = re.sub("sf3","srf3",text.lower()) text = re.sub("sr3","srf3",text.lower()) text = re.sub("ruhr","ruhe",text.lower()) text = re.sub("einruhr","ruhe",text.lower()) text = re.sub("hansgrohe","ruhe",text.lower()) text = re.sub("heimpsiel","heidi spiel",text) text = re.sub("hayden spiel","heidi spiel",text) text = re.sub("highspeed","heidi spiel",text) text = re.sub("handyspiel","heidi spiel",text) #understand what i need resp = requests.get('https://api.wit.ai/message?v=01.03.2018&q=(%s)' % text, headers = headers) data = json.loads(resp.content) print(resp.content) try: sender = data["entities"]['spiel'][0]["value"] print("\nI got entity : {}".format(sender)) except: if text != "": os.system("mplayer nocomprendo1.wav") sender = "" if sender == "srf1" : kill_mplayer() os.system("mplayer http://stream.srg-ssr.ch/m/drs1/aacp_96 </dev/null >/dev/null 2>&1 &") if sender == "srf3": kill_mplayer() os.system("mplayer http://stream.srg-ssr.ch/m/drs3/aacp_96 </dev/null >/dev/null 2>&1 &") if sender == "espresso": kill_mplayer() os.system("mplayer $(youtube-dl -g http://tp.srgssr.ch/p/srf/inline\?urn\=urn:srf:audio:b88af97b-8d44-4b29-9b81-28e3e9be8657) </dev/null >/dev/null 2>&1 &") if sender == "ruhe": kill_mplayer() os.system("mplayer ja1.wav")