forked from GoogleCloudPlatform/python-docs-samples
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathtranscribe.py
More file actions
75 lines (61 loc) · 2.33 KB
/
transcribe.py
File metadata and controls
75 lines (61 loc) · 2.33 KB
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
#!/usr/bin/env python
# Copyright 2017 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 REST API for batch
processing.
Example usage:
python transcribe.py resources/audio.raw
python transcribe.py gs://cloud-samples-tests/speech/brooklyn.flac
"""
# [START import_libraries]
import argparse
import io
# [END import_libraries]
def transcribe_file(speech_file):
"""Transcribe the given audio file."""
from google.cloud import speech
speech_client = speech.Client()
with io.open(speech_file, 'rb') as audio_file:
content = audio_file.read()
audio_sample = speech_client.sample(
content=content,
source_uri=None,
encoding='LINEAR16',
sample_rate=16000)
alternatives = speech_client.speech_api.sync_recognize(audio_sample)
for alternative in alternatives:
print('Transcript: {}'.format(alternative.transcript))
def transcribe_gcs(gcs_uri):
"""Transcribes the audio file specified by the gcs_uri."""
from google.cloud import speech
speech_client = speech.Client()
audio_sample = speech_client.sample(
content=None,
source_uri=gcs_uri,
encoding='FLAC',
sample_rate=16000)
alternatives = speech_client.speech_api.sync_recognize(audio_sample)
for alternative in alternatives:
print('Transcript: {}'.format(alternative.transcript))
if __name__ == '__main__':
parser = argparse.ArgumentParser(
description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument(
'path', help='File or GCS path for audio file to be recognized')
args = parser.parse_args()
if args.path.startswith('gs://'):
transcribe_gcs(args.path)
else:
transcribe_file(args.path)