chore: updated quickstart (#94)

* I updated the comment on the transcribe_async file to reflect time limitations on local files for the long_running_recognize

* I updated the comment on the transcribe_async file to reflect time limitations on local files for the long_running_recognize

* docs: I updated the comment on the transcribe_async file to reflect time limitations on local files for the long_running_recognize

* chore: I updated the comments on the transcribe_async file to reflect time limitations on local files for the long_running_recognize

* fix: resolved conflicts

    pick f510e8f chore: I updated the comments on the transcribe_async file to reflect time limitations on local files for the long_running_recognize

* chore: added a profanity filter sample

* docs: fixed region tag

* chore: updated the quickstart to gcs

Author: b-loved-dreamer

speech/snippets/profanity_filter.py

@@ -0,0 +1,55 @@
+# Copyright 2020 Google LLC
+# 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 gs://cloud-samples-tests/speech/brooklyn.flac
+"""
+
+import argparse
+
+
+# [START speech_recognize_with_profanity_filter_gcs]
+def sync_recognize_with_profanity_filter_gcs(storage_uri):
+
+    from google.cloud import speech
+
+    client = speech.SpeechClient()
+
+    audio = {"uri": storage_uri}
+
+    config = speech.RecognitionConfig(
+        encoding=speech.RecognitionConfig.AudioEncoding.FLAC,
+        sample_rate_hertz=16000,
+        language_code="en-US",
+        profanity_filter=True,
+    )
+
+    response = client.recognize(config=config, audio=audio)
+
+    for i, result in enumerate(response.results):
+        alternative = result.alternatives[0]
+        print(u"Transcript: {}".format(alternative.transcript))
+
+
+# [END speech_recognize_with_profanity_filter_gcs]
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(
+        description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter
+    )
+    parser.add_argument("path", help="GCS path for audio file to be recognized")
+    args = parser.parse_args()
+    sync_recognize_with_profanity_filter_gcs(args.path)

speech/snippets/profanity_filter_test.py

@@ -0,0 +1,24 @@
+# Copyright 2020 Google LLC
+# 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 re
+
+import profanity_filter
+
+
+def test_profanity_filter(capsys):
+    profanity_filter.sync_recognize_with_profanity_filter_gcs(
+        "gs://cloud-samples-tests/speech/brooklyn.flac"
+    )
+    out, err = capsys.readouterr()
+    assert re.search(r"how old is the Brooklyn Bridge", out, re.DOTALL | re.I)

speech/snippets/quickstart.py

@@ -17,8 +17,6 @@
 
 def run_quickstart():
     # [START speech_quickstart]
-    import io
-    import os
 
     # Imports the Google Cloud client library
     # [START speech_python_migration_imports]
@@ -32,12 +30,9 @@ def run_quickstart():
     # [END speech_python_migration_client]
 
     # The name of the audio file to transcribe
-    file_name = os.path.join(os.path.dirname(__file__), "resources", "audio.raw")
+    gcs_uri = "gs://cloud-samples-data/speech/brooklyn_bridge.raw"
 
-    # Loads the audio into memory
-    with io.open(file_name, "rb") as audio_file:
-        content = audio_file.read()
-        audio = speech.RecognitionAudio(content=content)
+    audio = speech.RecognitionAudio(uri=gcs_uri)
 
     config = speech.RecognitionConfig(
         encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,

speech/snippets/transcribe_async.py

@@ -38,7 +38,7 @@ def transcribe_file(speech_file):
         content = audio_file.read()
 
     """
-     Note that transcription is limited to 60 seconds audio.
+     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)