Skip to content
This repository has been archived by the owner on Apr 20, 2024. It is now read-only.

docs(samples): remove io dependency in transcribe samples #223

Merged
merged 6 commits into from
Aug 10, 2021
Merged
Show file tree
Hide file tree
Changes from 4 commits
Commits
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
62 changes: 62 additions & 0 deletions samples/snippets/transcribe_async_file.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,62 @@
#!/usr/bin/env python

# Copyright 2021 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 gRPC for async
batch processing.
"""


# [START speech_transcribe_async]
def transcribe_file(speech_file):
"""Transcribe the given audio file asynchronously."""
from google.cloud import speech

client = speech.SpeechClient()

# [START speech_python_migration_async_request]
with open(speech_file, "rb") as audio_file:
content = audio_file.read()

"""
Note that transcription is limited to a 60 seconds audio file.
Use a GCS file for audio longer than 1 minute.
"""
audio = speech.RecognitionAudio(content=content)

config = speech.RecognitionConfig(
encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
sample_rate_hertz=16000,
language_code="en-US",
)

# [START speech_python_migration_async_response]

operation = client.long_running_recognize(config=config, audio=audio)
# [END speech_python_migration_async_request]

print("Waiting for operation to complete...")
response = operation.result(timeout=90)

# Each result is for a consecutive portion of the audio. Iterate through
# them to get the transcripts for the entire audio file.
for result in response.results:
# The first alternative is the most likely one for this portion.
print(u"Transcript: {}".format(result.alternatives[0].transcript))
print("Confidence: {}".format(result.alternatives[0].confidence))
# [END speech_python_migration_async_response]


# [END speech_transcribe_async]
26 changes: 26 additions & 0 deletions samples/snippets/transcribe_async_file_test.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,26 @@
# Copyright 2016, Google, Inc.
# 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.

import os
import re

import transcribe_async_file

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


def test_transcribe(capsys):
transcribe_async_file.transcribe_file(os.path.join(RESOURCES, "audio.raw"))
out, err = capsys.readouterr()

assert re.search(r"how old is the Brooklyn Bridge", out, re.DOTALL | re.I)
47 changes: 47 additions & 0 deletions samples/snippets/transcribe_async_gcs.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,47 @@
#!/usr/bin/env python

# Copyright 2021 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 gRPC for async
batch processing.
"""


# [START speech_transcribe_async_gcs]
def transcribe_gcs(gcs_uri):
"""Asynchronously transcribes the audio file specified by the gcs_uri."""
from google.cloud import speech

client = speech.SpeechClient()

audio = speech.RecognitionAudio(uri=gcs_uri)
config = speech.RecognitionConfig(
encoding=speech.RecognitionConfig.AudioEncoding.FLAC,
sample_rate_hertz=16000,
language_code="en-US",
)

operation = client.long_running_recognize(config=config, audio=audio)

print("Waiting for operation to complete...")
response = operation.result(timeout=90)

# Each result is for a consecutive portion of the audio. Iterate through
# them to get the transcripts for the entire audio file.
for result in response.results:
# The first alternative is the most likely one for this portion.
print(u"Transcript: {}".format(result.alternatives[0].transcript))
print("Confidence: {}".format(result.alternatives[0].confidence))
# [END speech_transcribe_async_gcs]
Original file line number Diff line number Diff line change
Expand Up @@ -14,20 +14,13 @@
import os
import re

import transcribe_async
import transcribe_async_gcs

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


def test_transcribe(capsys):
transcribe_async.transcribe_file(os.path.join(RESOURCES, "audio.raw"))
out, err = capsys.readouterr()

assert re.search(r"how old is the Brooklyn Bridge", out, re.DOTALL | re.I)


def test_transcribe_gcs(capsys):
transcribe_async.transcribe_gcs("gs://python-docs-samples-tests/speech/audio.flac")
transcribe_async_gcs.transcribe_gcs("gs://python-docs-samples-tests/speech/audio.flac")
out, err = capsys.readouterr()

assert re.search(r"how old is the Brooklyn Bridge", out, re.DOTALL | re.I)