Skip to content

add Speech API auto punctuation sample #1446

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Apr 12, 2018
Merged

add Speech API auto punctuation sample #1446

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3d2b943
add auto punctuation sample
dizcology Apr 10, 2018
e2eedc5
correct docstring
dizcology Apr 12, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
29 changes: 29 additions & 0 deletions speech/cloud-client/beta_snippets.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@
Example usage:
python beta_snippets.py enhanced-model resources/commercial_mono.wav
python beta_snippets.py metadata resources/commercial_mono.wav
python beta_snippets.py punctuation resources/commercial_mono.wav
"""

import argparse
Expand Down Expand Up @@ -99,6 +100,32 @@ def transcribe_file_with_metadata(path):
# [END speech_transcribe_file_with_metadata]


# [START speech_transcribe_file_with_auto_punctuation]
def transcribe_file_with_auto_punctuation(path):
"""Transcribe the given audio file with auto punctuation enabled."""
client = speech.SpeechClient()

with io.open(path, 'rb') as audio_file:
content = audio_file.read()

audio = speech.types.RecognitionAudio(content=content)
config = speech.types.RecognitionConfig(
encoding=speech.enums.RecognitionConfig.AudioEncoding.LINEAR16,
sample_rate_hertz=8000,
language_code='en-US',
# Enable automatic punctuation
enable_automatic_punctuation=True)

response = client.recognize(config, audio)

for i, result in enumerate(response.results):
alternative = result.alternatives[0]
print('-' * 20)
print('First alternative of result {}'.format(i))
print('Transcript: {}'.format(alternative.transcript))
# [END speech_transcribe_file_with_auto_punctuation]


if __name__ == '__main__':
parser = argparse.ArgumentParser(
description=__doc__,
Expand All @@ -113,3 +140,5 @@ def transcribe_file_with_metadata(path):
transcribe_file_with_enhanced_model(args.path)
elif args.command == 'metadata':
transcribe_file_with_metadata(args.path)
elif args.command == 'punctuation':
transcribe_file_with_auto_punctuation(args.path)
11 changes: 10 additions & 1 deletion speech/cloud-client/beta_snippets_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,8 @@
import os

from beta_snippets import (
transcribe_file_with_enhanced_model, transcribe_file_with_metadata)
transcribe_file_with_auto_punctuation, transcribe_file_with_enhanced_model,
transcribe_file_with_metadata)

RESOURCES = os.path.join(os.path.dirname(__file__), 'resources')

Expand All @@ -33,3 +34,11 @@ def test_transcribe_file_with_metadata(capsys):
out, _ = capsys.readouterr()

assert 'Chrome' in out


def test_transcribe_file_with_auto_punctuation(capsys):
transcribe_file_with_auto_punctuation(
os.path.join(RESOURCES, 'commercial_mono.wav'))
out, _ = capsys.readouterr()

assert 'Okay. Sure.' in out