Speech GCS

speech/cloud-client/README.rst

@@ -93,18 +93,20 @@ To run this sample:
 
     $ python transcribe.py
 
-    usage: transcribe.py [-h] speech_file
+    usage: transcribe.py [-h] path
 
     Google Cloud Speech API sample application using the REST API for batch
     processing.
 
-    Example usage: python transcribe.py resources/audio.raw
+    Example usage:
+        python transcribe.py resources/audio.raw
+        python transcribe.py gs://cloud-samples-tests/speech/brooklyn.flac
 
     positional arguments:
-      speech_file  Full path of audio file to be recognized
+      path        File or GCS path for audio file to be recognized
 
     optional arguments:
-      -h, --help   show this help message and exit
+      -h, --help  show this help message and exit
 
 
 Transcribe async
@@ -118,18 +120,20 @@ To run this sample:
 
     $ python transcribe_async.py
 
-    usage: transcribe_async.py [-h] speech_file
+    usage: transcribe_async.py [-h] path
 
     Google Cloud Speech API sample application using the REST API for async
     batch processing.
 
-    Example usage: python transcribe_async.py resources/audio.raw
+    Example usage:
+        python transcribe_async.py resources/audio.raw
+        python transcribe_async.py gs://cloud-samples-tests/speech/brooklyn.flac
 
     positional arguments:
-      speech_file  Full path of audio file to be recognized
+      path        File or GCS path for audio file to be recognized
 
     optional arguments:
-      -h, --help   show this help message and exit
+      -h, --help  show this help message and exit
 
 
 

speech/cloud-client/transcribe.py

@@ -17,7 +17,9 @@
 """Google Cloud Speech API sample application using the REST API for batch
 processing.
 
-Example usage: python transcribe.py resources/audio.raw
+Example usage:
+    python transcribe.py resources/audio.raw
+    python transcribe.py gs://cloud-samples-tests/speech/brooklyn.flac
 """
 
 # [START import_libraries]
@@ -26,44 +28,48 @@
 # [END import_libraries]
 
 
-def main(speech_file):
-    """Transcribe the given audio file.
-
-    Args:
-        speech_file: the name of the audio file.
-    """
-    # [START authenticating]
-    # Application default credentials provided by env variable
-    # GOOGLE_APPLICATION_CREDENTIALS
+def transcribe_file(speech_file):
+    """Transcribe the given audio file."""
     from google.cloud import speech
     speech_client = speech.Client()
-    # [END authenticating]
 
-    # [START construct_request]
-    # Loads the audio into memory
     with io.open(speech_file, 'rb') as audio_file:
         content = audio_file.read()
         audio_sample = speech_client.sample(
-            content,
+            content=content,
             source_uri=None,
             encoding='LINEAR16',
             sample_rate=16000)
-    # [END construct_request]
 
-    # [START send_request]
     alternatives = speech_client.speech_api.sync_recognize(audio_sample)
     for alternative in alternatives:
         print('Transcript: {}'.format(alternative.transcript))
-    # [END send_request]
 
 
-# [START run_application]
+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(
-        'speech_file', help='Full path of audio file to be recognized')
+        'path', help='File or GCS path for audio file to be recognized')
     args = parser.parse_args()
-    main(args.speech_file)
-    # [END run_application]
+    if args.path.startswith('gs://'):
+        transcribe_gcs(args.path)
+    else:
+        transcribe_file(args.path)

speech/cloud-client/transcribe_async.py

@@ -17,41 +17,29 @@
 """Google Cloud Speech API sample application using the REST API for async
 batch processing.
 
-Example usage: python transcribe_async.py resources/audio.raw
+Example usage:
+    python transcribe_async.py resources/audio.raw
+    python transcribe_async.py gs://cloud-samples-tests/speech/brooklyn.flac
 """
 
-# [START import_libraries]
 import argparse
 import io
 import time
-# [END import_libraries]
 
 
-def main(speech_file):
-    """Transcribe the given audio file asynchronously.
-
-    Args:
-        speech_file: the name of the audio file.
-    """
-    # [START authenticating]
-    # Application default credentials provided by env variable
-    # GOOGLE_APPLICATION_CREDENTIALS
+def transcribe_file(speech_file):
+    """Transcribe the given audio file asynchronously."""
     from google.cloud import speech
     speech_client = speech.Client()
-    # [END authenticating]
 
-    # [START construct_request]
-    # Loads the audio into memory
     with io.open(speech_file, 'rb') as audio_file:
         content = audio_file.read()
         audio_sample = speech_client.sample(
             content,
             source_uri=None,
             encoding='LINEAR16',
             sample_rate=16000)
-    # [END construct_request]
 
-    # [START send_request]
     operation = speech_client.speech_api.async_recognize(audio_sample)
 
     retry_count = 100
@@ -61,7 +49,7 @@ def main(speech_file):
         operation.poll()
 
     if not operation.complete:
-        print("Operation not complete and retry limit reached.")
+        print('Operation not complete and retry limit reached.')
         return
 
     alternatives = operation.results
@@ -71,13 +59,44 @@ def main(speech_file):
     # [END send_request]
 
 
-# [START run_application]
+def transcribe_gcs(gcs_uri):
+    """Asynchronously 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)
+
+    operation = speech_client.speech_api.async_recognize(audio_sample)
+
+    retry_count = 100
+    while retry_count > 0 and not operation.complete:
+        retry_count -= 1
+        time.sleep(2)
+        operation.poll()
+
+    if not operation.complete:
+        print('Operation not complete and retry limit reached.')
+        return
+
+    alternatives = operation.results
+    for alternative in alternatives:
+        print('Transcript: {}'.format(alternative.transcript))
+        print('Confidence: {}'.format(alternative.confidence))
+    # [END send_request_gcs]
+
+
 if __name__ == '__main__':
     parser = argparse.ArgumentParser(
         description=__doc__,
         formatter_class=argparse.RawDescriptionHelpFormatter)
     parser.add_argument(
-        'speech_file', help='Full path of audio file to be recognized')
+        'path', help='File or GCS path for audio file to be recognized')
     args = parser.parse_args()
-    main(args.speech_file)
-    # [END run_application]
+    if args.path.startswith('gs://'):
+        transcribe_gcs(args.path)
+    else:
+        transcribe_file(args.path)

speech/cloud-client/transcribe_async_test.py

@@ -13,11 +13,18 @@
 
 import re
 
-from transcribe_async import main
+from transcribe_async import transcribe_file, transcribe_gcs
 
 
-def test_main(resource, capsys):
-    main(resource('audio.raw'))
+def test_transcribe(resource, capsys):
+    transcribe_file(resource('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(resource, capsys):
+    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)

speech/cloud-client/transcribe_test.py

@@ -13,11 +13,18 @@
 
 import re
 
-from transcribe import main
+from transcribe import transcribe_file, transcribe_gcs
 
 
-def test_main(resource, capsys):
-    main(resource('audio.raw'))
+def test_transcribe_file(resource, capsys):
+    transcribe_file(resource('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(resource, capsys):
+    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)