1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
| from vosk import Model, KaldiRecognizer
import speech_recognition
import googletrans # внизу второй вариант так же не помог что по отдельности что вместе
#from googletrans import Translator
import pyttsx3
import random
import json
import os
class Translation:
with open("translations.json", "r", encoding="UTF-8") as file:
translations = json.load(file)
def get(self, text: str):
if text in self.translations:
return self.translations[text][assistant.speech_language]
else:
print(colored("Not translated phrase: {}".format(text), "red"))
return text
class OwnerPerson:
name = ""
home_city = ""
native_language = ""
target_language = ""
class VoiceAssistant:
name = ""
sex = ""
speech_language = ""
recognition_language = ""
def setup_assistant_voice():
voices = ttsEngine.getProperty("voices")
if assistant.speech_language == "en":
assistant.recognition_language = "en-US"
if assistant.sex == "female":
ttsEngine.setProperty("voice", voices[1].id)
else:
ttsEngine.setProperty("voice", voices[2].id)
else:
assistant.recognition_language = "ru-RU"
# Microsoft Irina Desktop - Russian
ttsEngine.setProperty("voice", voices[0].id)
def record_and_recognize_audio(*args: tuple):
with microphone:
recognized_data = ""
recognizer.adjust_for_ambient_noise(microphone, duration=2)
try:
print("Listening...")
audio = recognizer.listen(microphone, 5, 5)
with open("microphone-results.wav", "wb") as file:
file.write(audio.get_wav_data())
except speech_recognition.WaitTimeoutError:
play_voice_assistant_speech(translator.get("Can you check if your microphone is on, please?"))
traceback.print_exc()
return
try:
print("Started recognition...")
recognized_data = recognizer.recognize_google(audio, language=assistant.recognition_language).lower()
except speech_recognition.UnknownValueError:
pass # play_voice_assistant_speech("What did you say again?")
except speech_recognition.RequestError:
print(colored("Trying to use offline recognition...", "cyan"))
recognized_data = use_offline_recognition()
return recognized_data
def use_offline_recognition():
recognized_data = ""
try:
if not os.path.exists("models/vosk-model-small-" + assistant.speech_language + "-0.4"):
print(colored("Please download the model from:\n"
"https://alphacephei.com/vosk/models and unpack as 'model' in the current folder.",
"red"))
exit(1)
wave_audio_file = wave.open("microphone-results.wav", "rb")
model = Model("models/vosk-model-small-" + assistant.speech_language + "-0.4")
offline_recognizer = KaldiRecognizer(model, wave_audio_file.getframerate())
data = wave_audio_file.readframes(wave_audio_file.getnframes())
if len(data) > 0:
if offline_recognizer.AcceptWaveform(data):
recognized_data = offline_recognizer.Result()
recognized_data = json.loads(recognized_data)
recognized_data = recognized_data["text"]
except:
traceback.print_exc()
print(colored("Sorry, speech service is unavailable. Try again later", "red"))
return recognized_data
def play_voice_assistant_speech(text_to_speech):
ttsEngine.say(str(text_to_speech))
ttsEngine.runAndWait()
def play_thankfull(*args: tuple):
thankfulls = [
translator.get("Don't say thanks! It's my job").format(person.name),
translator.get("Your welcome!").format(person.name)
]
play_voice_assistant_speech(thankfulls[random.randint(0, len(thankfulls) - 1)])
def play_greetings(*args: tuple):
greetings = [
translator.get("Hello, {}! How can I help you today?").format(person.name),
translator.get("Good day to you {}! How can I help you today?").format(person.name)
]
play_voice_assistant_speech(greetings[random.randint(0, len(greetings) - 1)])
def play_farewell_and_quit(*args: tuple):
farewells = [
translator.get("Goodbye, {}! Have a nice day!").format(person.name),
translator.get("See you soon, {}!").format(person.name)
]
play_voice_assistant_speech(farewells[random.randint(0, len(farewells) - 1)])
ttsEngine.stop()
quit()
def get_translation(*args: tuple):
if not args[0]: return
search_term = " ".join(args[0])
google_translator = Translator()
translation_result = ""
old_assistant_language = assistant.speech_language
try:
if assistant.speech_language != person.native_language:
translation_result = google_translator.translate(search_term,
src=person.target_language,
dest=person.native_language)
play_voice_assistant_speech("The translation for {} in Russian is".format(search_term))
assistant.speech_language = person.native_language
setup_assistant_voice()
else:
translation_result = google_translator.translate(search_term,
src=person.native_language,
dest=person.target_language)
play_voice_assistant_speech("По-английски {} будет как".format(search_term))
assistant.speech_language = person.target_language
setup_assistant_voice()
play_voice_assistant_speech(translation_result.text)
except:
play_voice_assistant_speech(translator.get("Seems like we have a trouble. See logs for more information"))
traceback.print_exc()
finally:
assistant.speech_language = old_assistant_language
setup_assistant_voice()
def change_language(*args: tuple):
assistant.speech_language = "ru" if assistant.speech_language == "en" else "en"
setup_assistant_voice()
print(colored("Language switched to " + assistant.speech_language, "cyan"))
def execute_command_with_name(command_name: str, *args: list):
for key in commands.keys():
if command_name in key:
commands[key](*args)
else:
pass # print("Command not found")
commands = {
("hello", "hi", "morning", "привет"): play_greetings,
("thanks", "thank you", "спасибо", "благодарю"): play_thankfull,
("bye", "goodbye", "quit", "exit", "stop", "пока"): play_farewell_and_quit,
("translate", "interpretation", "translation", "перевод", "перевести", "переведи"): get_translation,
("language", "язык"): change_language,
}
if __name__ == "__main__":
recognizer = speech_recognition.Recognizer()
microphone = speech_recognition.Microphone()
ttsEngine = pyttsx3.init()
person = OwnerPerson()
person.name = "Андрей"
person.home_city = "---"
person.native_language = "ru"
person.target_language = "en"
assistant = VoiceAssistant()
assistant.name = "Луна"
assistant.sex = "female"
assistant.speech_language = "ru"
setup_assistant_voice()
translator = Translation()
while True:
voice_input = record_and_recognize_audio()
os.remove("microphone-results.wav")
print(colored(voice_input, "blue"))
voice_input = voice_input.split(" ")
command = voice_input[0]
command_options = [str(input_part) for input_part in voice_input[1:len(voice_input)]]
execute_command_with_name(command, command_options) |
(
