-
Notifications
You must be signed in to change notification settings - Fork 1
/
speech-to-speech-translation.py
268 lines (217 loc) · 9.07 KB
/
speech-to-speech-translation.py
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
#!/usr/bin/env python
# Copyright 2018 Google Inc. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Google Cloud Speech API sample application using the streaming API.
NOTE: This module requires the additional dependency `pyaudio` and `playsound`.
To install using pip:
pip install pyaudio
pip install playsound
Example usage:
python speech-to-speech-translation.py
"""
from __future__ import division
import argparse
import time
import re
import sys
import six
import html
from google.cloud import speech
from google.cloud import texttospeech
from google.cloud import translate
import pyaudio
from playsound import playsound
from six.moves import queue
# Audio recording parameters
STREAMING_LIMIT = 55000
SAMPLE_RATE = 16000
CHUNK_SIZE = int(SAMPLE_RATE / 10) # 100ms
RECORD_INC = 0
PLAY_INC = 0
def get_current_time():
return int(round(time.time() * 1000))
def duration_to_secs(duration):
return duration.seconds + (duration.nanos / float(1e9))
class ResumableMicrophoneStream:
"""Opens a recording stream as a generator yielding the audio chunks."""
def __init__(self, rate, chunk_size):
self._rate = rate
self._chunk_size = chunk_size
self._num_channels = 1
self._max_replay_secs = 5
# Create a thread-safe buffer of audio data
self._buff = queue.Queue()
self.closed = True
self.start_time = get_current_time()
# 2 bytes in 16 bit samples
self._bytes_per_sample = 2 * self._num_channels
self._bytes_per_second = self._rate * self._bytes_per_sample
self._bytes_per_chunk = (self._chunk_size * self._bytes_per_sample)
self._chunks_per_second = (
self._bytes_per_second // self._bytes_per_chunk)
def __enter__(self):
self.closed = False
self._audio_interface = pyaudio.PyAudio()
self._audio_stream = self._audio_interface.open(
format=pyaudio.paInt16,
channels=self._num_channels,
rate=self._rate,
input=True,
frames_per_buffer=self._chunk_size,
# Run the audio stream asynchronously to fill the buffer object.
# This is necessary so that the input device's buffer doesn't
# overflow while the calling thread makes network requests, etc.
stream_callback=self._fill_buffer,
)
return self
def __exit__(self, type, value, traceback):
self._audio_stream.stop_stream()
self._audio_stream.close()
self.closed = True
# Signal the generator to terminate so that the client's
# streaming_recognize method will not block the process termination.
self._buff.put(None)
self._audio_interface.terminate()
def _fill_buffer(self, in_data, *args, **kwargs):
"""Continuously collect data from the audio stream, into the buffer."""
self._buff.put(in_data)
return None, pyaudio.paContinue
def generator(self):
while not self.closed:
if get_current_time() - self.start_time > STREAMING_LIMIT:
self.start_time = get_current_time()
break
# Use a blocking get() to ensure there's at least one chunk of
# data, and stop iteration if the chunk is None, indicating the
# end of the audio stream.
chunk = self._buff.get()
if chunk is None:
return
data = [chunk]
# Now consume whatever other data's still buffered.
while True:
try:
chunk = self._buff.get(block=False)
if chunk is None:
return
data.append(chunk)
except queue.Empty:
break
yield b''.join(data)
def synthesize_text(text, language_code):
global RECORD_INC
global PLAY_INC
# print(text)
"""Synthesizes speech from the input string of text."""
client = texttospeech.TextToSpeechClient()
input_text = texttospeech.types.SynthesisInput(text=text)
# Note: the voice can also be specified by name.
# Names of voices can be retrieved with client.list_voices().
voice = texttospeech.types.VoiceSelectionParams(
language_code='it-IT',
ssml_gender=texttospeech.enums.SsmlVoiceGender.FEMALE)
audio_config = texttospeech.types.AudioConfig(
audio_encoding=texttospeech.enums.AudioEncoding.MP3)
response = client.synthesize_speech(input_text, voice, audio_config)
# The response's audio_content is binary.
with open('output_' + str(RECORD_INC) + '.mp3', 'wb') as out:
out.write(response.audio_content)
print('Audio content written to file output_' + str(RECORD_INC) + '.mp3')
playsound('output_' + str(RECORD_INC) + '.mp3', False)
def translate_text(text):
translate_client = translate.Client()
target = 'it'
translation = translate_client.translate(
text,
target_language=target)
translation = html.unescape(translation['translatedText'])
synthesize_text(translation, target)
#print(text)
print("Translation: " + translation)
def listen_loop(responses, stream):
"""Iterates through server responses and prints them.
The responses passed is a generator that will block until a response
is provided by the server.
Each response may contain multiple results, and each result may contain
multiple alternatives; for details, see https://goo.gl/tjCPAU. Here we
print only the transcription for the top alternative of the top result.
In this case, responses are provided for interim results as well. If the
response is an interim one, print a line feed at the end of it, to allow
the next result to overwrite it, until the response is a final one. For the
final one, print a newline to preserve the finalized transcription.
"""
global RECORD_INC
global PLAY_INC
responses = (r for r in responses if (
r.results and r.results[0].alternatives))
num_chars_printed = 0
for response in responses:
if not response.results:
continue
# The `results` list is consecutive. For streaming, we only care about
# the first result being considered, since once it's `is_final`, it
# moves on to considering the next utterance.
result = response.results[0]
if not result.alternatives:
continue
# Display the transcription of the top alternative.
top_alternative = result.alternatives[0]
transcript = top_alternative.transcript
# Display interim results, but with a carriage return at the end of the
# line, so subsequent lines will overwrite them.
#
# If the previous result was longer than this one, we need to print
# some extra spaces to overwrite the previous result
overwrite_chars = ' ' * (num_chars_printed - len(transcript))
if not result.is_final:
sys.stdout.write(transcript + overwrite_chars + '\r')
sys.stdout.flush()
num_chars_printed = len(transcript)
else:
print(transcript + overwrite_chars)
# Exit recognition if any of the transcribed phrases could be
# one of our keywords.
if re.search(r'\b(exit|quit)\b', transcript, re.I):
print('Exiting..')
stream.closed = True
break
translate_text(transcript)
RECORD_INC += 1
PLAY_INC += 1
num_chars_printed = 0
def main():
client = speech.SpeechClient()
config = speech.types.RecognitionConfig(
encoding=speech.enums.RecognitionConfig.AudioEncoding.LINEAR16,
sample_rate_hertz=SAMPLE_RATE,
language_code='en-US',
max_alternatives=1,
enable_word_time_offsets=True)
streaming_config = speech.types.StreamingRecognitionConfig(
config=config,
interim_results=True)
mic_manager = ResumableMicrophoneStream(SAMPLE_RATE, CHUNK_SIZE)
print('Say "Quit" or "Exit" to terminate the program.')
with mic_manager as stream:
while not stream.closed:
audio_generator = stream.generator()
requests = (speech.types.StreamingRecognizeRequest(
audio_content=content)
for content in audio_generator)
responses = client.streaming_recognize(streaming_config,
requests)
# Now, put the transcription responses to use.
listen_loop(responses, stream)
if __name__ == '__main__':
main()