teratail
回答率
85.48%
質問するログイン新規登録
トップに関する質問Google Speech APIでの時間付き出力の方法

編集履歴

質問編集履歴

2

pythonのコメントアウト記号を使うと挙動がおかしくなるため、「-」を使用しています

2017/04/04 10:07

投稿

kohhi
kohhi

スコア18

test CHANGED
File without changes
test CHANGED
@@ -18,35 +18,35 @@
18
18
 
19
19
 
20
20
 
21
- # Copyright 2017 Google Inc. All Rights Reserved.
21
+ - Copyright 2017 Google Inc. All Rights Reserved.-
22
-
22
+
23
- #
23
+ - -
24
-
24
+
25
- # Licensed under the Apache License, Version 2.0 (the "License");
25
+ - Licensed under the Apache License, Version 2.0 (the "License");-
26
-
26
+
27
- # you may not use this file except in compliance with the License.
27
+ - you may not use this file except in compliance with the License.-
28
-
28
+
29
- # You may obtain a copy of the License at
29
+ - You may obtain a copy of the License at-
30
-
30
+
31
- #
31
+ -
32
-
32
+
33
- # http://www.apache.org/licenses/LICENSE-2.0
33
+ - http://www.apache.org/licenses/LICENSE-2.0-
34
-
34
+
35
- #
35
+ --
36
-
36
+
37
- # Unless required by applicable law or agreed to in writing, software
37
+ - Unless required by applicable law or agreed to in writing, software-
38
-
38
+
39
- # distributed under the License is distributed on an "AS IS" BASIS,
39
+ - distributed under the License is distributed on an "AS IS" BASIS,-
40
-
40
+
41
- # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
41
+ - WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.-
42
-
42
+
43
- # See the License for the specific language governing permissions and
43
+ - See the License for the specific language governing permissions and-
44
-
44
+
45
- # limitations under the License.
45
+ - limitations under the License.-
46
-
47
-
48
-
46
+
47
+
48
+
49
- """Google Cloud Speech API sample application using the REST API for async
49
+ ---Google Cloud Speech API sample application using the REST API for async
50
50
 
51
51
  batch processing.
52
52
 
@@ -58,7 +58,7 @@
58
58
 
59
59
  python transcribe_async.py gs://cloud-samples-tests/speech/brooklyn.flac
60
60
 
61
- """
61
+ ---
62
62
 
63
63
 
64
64
 
@@ -74,7 +74,7 @@
74
74
 
75
75
  def transcribe_file(speech_file):
76
76
 
77
- """Transcribe the given audio file asynchronously."""
77
+ ---Transcribe the given audio file asynchronously.---
78
78
 
79
79
  from google.cloud import speech
80
80
 
@@ -126,7 +126,7 @@
126
126
 
127
127
  print('Confidence: {}'.format(alternative.confidence))
128
128
 
129
- # [END send_request]
129
+ - [END send_request] -
130
130
 
131
131
 
132
132
 
@@ -134,7 +134,7 @@
134
134
 
135
135
  def transcribe_gcs(gcs_uri):
136
136
 
137
- """Asynchronously transcribes the audio file specified by the gcs_uri."""
137
+ ---Asynchronously transcribes the audio file specified by the gcs_uri.---
138
138
 
139
139
  from google.cloud import speech
140
140
 
@@ -186,7 +186,7 @@
186
186
 
187
187
  print('Confidence: {}'.format(alternative.confidence))
188
188
 
189
- # [END send_request_gcs]
189
+ -[END send_request_gcs]-
190
190
 
191
191
 
192
192
 

1

ソースコードを付けたしました

2017/04/04 10:07

投稿

kohhi
kohhi

スコア18

test CHANGED
File without changes
test CHANGED
@@ -4,10 +4,212 @@
4
4
 
5
5
  出力に、各単語が音声ファイル内のどの時間に発話されたものであるかを知りたいのですが、どのように行えばいいかわかりません、お詳しい方宜しくお願いします。
6
6
 
7
+
8
+
9
+ https://github.com/GoogleCloudPlatform/python-docs-samples/blob/master/speech/cloud-client/transcribe_async.py
10
+
11
+
12
+
13
+ 上記のコードにマイナーチェンジを行ったもので出力を行っています。ここにどのようにコードを足せば、時間つきのファイルになるのかを知りたいです
14
+
7
15
  ###該当のソースコード
8
16
 
17
+ #!/usr/bin/env python
18
+
19
+
20
+
21
+ # Copyright 2017 Google Inc. All Rights Reserved.
22
+
23
+ #
24
+
25
+ # Licensed under the Apache License, Version 2.0 (the "License");
26
+
27
+ # you may not use this file except in compliance with the License.
28
+
29
+ # You may obtain a copy of the License at
30
+
31
+ #
32
+
33
+ # http://www.apache.org/licenses/LICENSE-2.0
34
+
35
+ #
36
+
37
+ # Unless required by applicable law or agreed to in writing, software
38
+
39
+ # distributed under the License is distributed on an "AS IS" BASIS,
40
+
41
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
42
+
43
+ # See the License for the specific language governing permissions and
44
+
45
+ # limitations under the License.
46
+
47
+
48
+
49
+ """Google Cloud Speech API sample application using the REST API for async
50
+
51
+ batch processing.
52
+
53
+
54
+
55
+ Example usage:
56
+
57
+ python transcribe_async.py resources/audio.raw
58
+
59
+ python transcribe_async.py gs://cloud-samples-tests/speech/brooklyn.flac
60
+
61
+ """
62
+
63
+
64
+
65
+ import argparse
66
+
67
+ import io
68
+
69
+ import time
70
+
71
+
72
+
73
+
74
+
75
+ def transcribe_file(speech_file):
76
+
77
+ """Transcribe the given audio file asynchronously."""
78
+
79
+ from google.cloud import speech
80
+
81
+ speech_client = speech.Client()
82
+
83
+
84
+
85
+ with io.open(speech_file, 'rb') as audio_file:
86
+
87
+ content = audio_file.read()
88
+
89
+ audio_sample = speech_client.sample(
90
+
91
+ content,
92
+
93
+ source_uri=None,
94
+
95
+ encoding='FLAC',
96
+
97
+ sample_rate=16000)
98
+
99
+
100
+
9
- https://github.com/GoogleCloudPlatform/python-docs-samples/blob/master/speech/cloud-client/transcribe_async.py
101
+ operation = speech_client.speech_api.async_recognize(audio_sample, language_code='en-GB', speech_context=['<登録した単語>'], retry_count = 100
102
+
10
-
103
+ while retry_count > 0 and not operation.complete:
104
+
11
-
105
+ retry_count -= 1
106
+
12
-
107
+ time.sleep(2)
108
+
109
+ operation.poll()
110
+
111
+
112
+
113
+ if not operation.complete:
114
+
13
- 上記のコードにマイナーチェンジを行ったもので出力を行っています。ここにどのようにコードを足せば、時間つきのファイルになるのかを知りたいです。
115
+ print('Operation not complete and retry limit reached.')
116
+
117
+ return
118
+
119
+
120
+
121
+ alternatives = operation.results
122
+
123
+ for alternative in alternatives:
124
+
125
+ print('Transcript: {}'.format(alternative.transcript))
126
+
127
+ print('Confidence: {}'.format(alternative.confidence))
128
+
129
+ # [END send_request]
130
+
131
+
132
+
133
+
134
+
135
+ def transcribe_gcs(gcs_uri):
136
+
137
+ """Asynchronously transcribes the audio file specified by the gcs_uri."""
138
+
139
+ from google.cloud import speech
140
+
141
+ speech_client = speech.Client()
142
+
143
+
144
+
145
+ audio_sample = speech_client.sample(
146
+
147
+ content=None,
148
+
149
+ source_uri=gcs_uri,
150
+
151
+ encoding='FLAC',
152
+
153
+ sample_rate=16000)
154
+
155
+
156
+
157
+ operation = speech_client.speech_api.async_recognize(audio_sample)
158
+
159
+
160
+
161
+ retry_count = 100
162
+
163
+ while retry_count > 0 and not operation.complete:
164
+
165
+ retry_count -= 1
166
+
167
+ time.sleep(2)
168
+
169
+ operation.poll()
170
+
171
+
172
+
173
+ if not operation.complete:
174
+
175
+ print('Operation not complete and retry limit reached.')
176
+
177
+ return
178
+
179
+
180
+
181
+ alternatives = operation.results
182
+
183
+ for alternative in alternatives:
184
+
185
+ print('Transcript: {}'.format(alternative.transcript))
186
+
187
+ print('Confidence: {}'.format(alternative.confidence))
188
+
189
+ # [END send_request_gcs]
190
+
191
+
192
+
193
+
194
+
195
+ if __name__ == '__main__':
196
+
197
+ parser = argparse.ArgumentParser(
198
+
199
+ description=__doc__,
200
+
201
+ formatter_class=argparse.RawDescriptionHelpFormatter)
202
+
203
+ parser.add_argument(
204
+
205
+ 'path', help='File or GCS path for audio file to be recognized')
206
+
207
+ args = parser.parse_args()
208
+
209
+ if args.path.startswith('gs://'):
210
+
211
+ transcribe_gcs(args.path)
212
+
213
+ else:
214
+
215
+ transcribe_file(args.path)