Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Appearance settings

Commit 5f66d30

Browse filesBrowse files
author
Jerjou Cheng
committed
Audio can be from gs:// or local
1 parent a9d914b commit 5f66d30
Copy full SHA for 5f66d30

File tree

Expand file treeCollapse file tree

1 file changed

+10
-6
lines changed
Filter options
Expand file treeCollapse file tree

1 file changed

+10
-6
lines changed

‎speech/grpc/transcribe.py

Copy file name to clipboardExpand all lines: speech/grpc/transcribe.py
+10-6Lines changed: 10 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -54,6 +54,11 @@ def main(input_uri, encoding, sample_rate, language_code='ja-JP'):
5454
# grpc client lib was generated. See:
5555
# https://github.com/googleapis/googleapis/blob/master/google/cloud/speech/v1/cloud_speech.proto
5656
start = time.time()
57+
if input_uri.startswith('gs://'):
58+
audio = cloud_speech_pb2.RecognitionAudio(uri=input_uri)
59+
else:
60+
with open(input_uri, 'rb') as f:
61+
audio = cloud_speech_pb2.RecognitionAudio(content=f.read())
5762
response = service.Recognize(cloud_speech_pb2.RecognizeRequest(
5863
config=cloud_speech_pb2.RecognitionConfig(
5964
# There are a bunch of config options you can specify. See
@@ -64,11 +69,10 @@ def main(input_uri, encoding, sample_rate, language_code='ja-JP'):
6469
# supported languages.
6570
language_code=language_code, # a BCP-47 language tag
6671
),
67-
audio=cloud_speech_pb2.RecognitionAudio(
68-
uri=input_uri,
69-
)
72+
audio=audio
7073
), DEADLINE_SECS)
7174
print('Time: %s' % (time.time() - start))
75+
print(response)
7276

7377
# Print the recognition result alternatives and confidence scores.
7478
for result in response.results:
@@ -91,13 +95,13 @@ def _gcs_uri(text):
9195
parser = argparse.ArgumentParser(
9296
description=__doc__,
9397
formatter_class=argparse.RawDescriptionHelpFormatter)
94-
parser.add_argument('input_uri', type=_gcs_uri)
98+
parser.add_argument('filename')
9599
parser.add_argument(
96100
'--encoding', default='LINEAR16', choices=[
97-
'LINEAR16', 'FLAC', 'MULAW', 'AMR', 'AMR_WB', 'SPEEX_WITH_HEADER_BYTE'],
101+
'LINEAR16', 'FLAC', 'MULAW', 'AMR', 'AMR_WB', 'SPEEX_WITH_HEADER_BYTE', 'OGG_OPUS'],
98102
help='How the audio file is encoded. See {}#L67'.format(PROTO_URL))
99103
parser.add_argument('--sample_rate', type=int, default=16000)
100104
parser.add_argument('--lang', default='en-US')
101105

102106
args = parser.parse_args()
103-
main(args.input_uri, args.encoding, args.sample_rate, args.lang)
107+
main(args.filename, args.encoding, args.sample_rate, args.lang)

0 commit comments

Comments
0 (0)
Morty Proxy This is a proxified and sanitized view of the page, visit original site.