def listen_command():
t2i_en = {
'play': 0,
'next': 1,
'stop': 2,
'search': 3,
'select song': 4,
'exit': 5
}
t2i_vn = {
'phát': 0,
'tiếp tục': 0,
'tiếp theo': 1,
'kế tiếp': 1,
'dừng lại': 2,
'tìm kiếm': 3,
'chọn bài hát': 4,
'chọn bài': 4,
'thoát': 5,
'thoát chương trình': 5
}
match = False
while match != True:
t2s('speech command')
text = recognize()
if text in t2i_en.keys() or text in t2i_vn.keys():
if text in t2i_en.keys():
command = t2i_en[text]
match = True
elif text in t2i_vn.keys():
command = t2i_vn[text]
match = True
return int(command)
def selectAndPlaySongByIndex(self):
title_audio = list(self.listAudio_text.keys())[self.idx_audio]
link_audio = list(self.listAudio_text.values())[self.idx_audio]
link_audio = getLinkAudio(link_audio)
t2s('Start play: {}'.format(self.idx_audio + 1))
self.setMediaPlayerUrl(link_audio)
self.PlayPause()
self.status.setText('Đang phát: {}'.format(title_audio))
def VoiceSearch(self):
self.Pause()
t2s('Start Voice Search')
self.status.setText('Nói từ khóa')
keyword = getVoiceKeyWord() # có xác nhận key
#t2s('')
# keyword = recognize('keyword')# không cần xác nhận
t2s('search for {}'.format(keyword))
self.status.setText('Tìm kiếm cho: "{}"'.format(keyword))
self.searchInput.setText(keyword)
self.Search()
def getVoiceKeyWord():
match = False
while match != True:
key = recognize('keyword')
t2s('you are want to find: {}'.format(key))
cf = recognize('YES or OK to confirm and NO to try again')
if cf in ['yes', 'ok', 'oke', 'đúng', 'phải', 'đồng ý']:
t2s('ok')
match = True
else:
t2s('oh sorry! please speech keyword again')
return key
def excCommand(self):
self.Pause()
t2s('OK. Im here')
t2s('Please speech a command')
command = listen_command()
if command == 0:
self.PlayPause()
elif command == 1:
self.voiceNext()
elif command == 2:
self.Stop()
elif command == 3:
self.VoiceSearch()
elif command == 4:
self.voiceSelect()
elif command == 5:
t2s('You are sure to exit!')
t2s('Speech Yes or OK to comfirm!')
cf_exit = recognize('')
if cf_exit == 'yes' or cf_exit == 'ok' or cf_exit == 'oke':
exit()
else:
print('no exit')
def recognize(note=''):
with sr.Microphone() as source:
r.adjust_for_ambient_noise(source)
t2s('start speech ' + note)
t2s('START')
#print('start speech')
# while True:
audio = r.listen(source)
t2s('DONE')
#print('done')
try:
#print('infering...')
text = r.recognize_google(audio, language='vi-VN').lower()
except:
print('speech recognition error')
text = 'error'
print('#speech2text:' + text)
return text
def Search(self, get_idx_by_user=False):
self.Pause()
self.listAudio.clear()
if self.searchInput.text() != '':
print('keyword:', self.searchInput.text())
print('searching...')
results = YoutubeSearch(self.searchInput.text(),
max_results=10).to_json()
results = json.loads(results)
results = results["videos"]
if len(results) == 0:
self.status.setText('Không có kết quả hoặc lỗi')
t2s('try again')
#self.searchInput.setText('')
else:
self.listAudio_text = {}
self.list_title = [e["title"] for e in results]
print(results)
for i, item in enumerate(results):
itemtitle = item['title']
itemlink = 'https://www.youtube.com' + item['link']
self.listAudio.insertItem(
i + 1,
str(i + 1) + ': ' + itemtitle + '#link#' + itemlink)
self.listAudio_text[itemtitle] = itemlink
self.status.setText('Kết quả cho: "{}"'.format(
self.searchInput.text()))
#self.searchInput.setText('')
t2s('seach done')
if get_idx_by_user:
#sau khi search, cho người dùng chọn bài hát bằng voice
self.idx_audio = select_by_speech()
else:
#cho chế độ tự động phát ramdom. phát bài đầu tiên trong list. không cần chọn bằng voice
self.idx_audio = 0
sleep(1)
self.selectAndPlaySongByIndex()
else:
self.status.setText('Nhập từ khóa hoặc tìm bằng giọng nói')
t2s('enter keyword or voice search')
def Wellcome(self):
#sleep(1)
t2s('Hello! Wellcome to music player')
t2s('Let search a song!')
self.VoiceSearch()
def select_by_speech():
t2i_en = {
'one': 1,
'two': 2,
'three': 3,
'four': 4,
'five': 5,
'six': 6,
'seven': 7,
'eight': 8,
'nine': 9,
'ten': 10
}
t2i_en2 = {
'number one': 1,
'number two': 2,
'number three': 3,
'number four': 4,
'number five': 5,
'number six': 6,
'number seven': 7,
'number eight': 8,
'number nine': 9,
'number ten': 10
}
t2i_vn = {
'một': 1,
'hai': 2,
'ba': 3,
'bốn': 4,
'năm': 5,
'sáu': 6,
'bẩy': 7,
'tám': 8,
'chín': 9,
'mười': 10
}
t2i_vn2 = {
'số 1': 1,
'số 2': 2,
'số 3': 3,
'số 4': 4,
'số 5': 5,
'số 6': 6,
'số 7': 7,
'số 8': 8,
'số 9': 9,
'số 10': 10
}
t2i = {
'1': 1,
'2': 2,
'3': 3,
'4': 4,
'5': 5,
'6': 6,
'7': 7,
'8': 8,
'9': 9,
'10': 10
}
match = False
while match != True:
t2s('select song')
text = recognize()
if text in t2i_en.keys() or text in t2i_en2.keys(
) or text in t2i_vn.keys() or t2i_vn2.keys() or text in t2i.keys():
if text in t2i_en.keys():
number = t2i_en[text]
match = True
elif text in t2i_en2.keys():
number = t2i_en2[text]
match = True
elif text in t2i_vn.keys():
number = t2i_vn[text]
match = True
elif text in t2i_vn2.keys():
number = t2i_vn2[text]
match = True
elif text in t2i.keys():
number = t2i[text]
match = True
return int(number) - 1
def waitForSpeech():
t2s('I am listing')