Speech gapic client library

speech/cloud-client/README.rst

@@ -5,6 +5,10 @@ Google Cloud Speech API Python Samples
 
 This directory contains samples for Google Cloud Speech API. The `Google Cloud Speech API`_ enables easy integration of Google speech recognition technologies into developer applications. Send audio and receive a text transcription from the Cloud Speech API service.
 
+- See the `migration guide`_ for information about migrating to Python client library v0.27.
+
+.. _migration guide: https://cloud.google.com/speech/docs/python-client-migration
+
 
 
 

speech/cloud-client/README.rst.in

@@ -9,6 +9,12 @@ product:
     recognition technologies into developer applications. Send audio and receive
     a text transcription from the Cloud Speech API service.
 
+
+    - See the `migration guide`_ for information about migrating to Python client library v0.27.
+
+
+    .. _migration guide: https://cloud.google.com/speech/docs/python-client-migration
+
 setup:
 - auth
 - install_deps

speech/cloud-client/quickstart.py

@@ -21,10 +21,16 @@ def run_quickstart():
     import os
 
     # Imports the Google Cloud client library
+    # [START migration_import]
     from google.cloud import speech
+    from google.cloud.speech import enums
+    from google.cloud.speech import types
+    # [END migration_import]
 
     # Instantiates a client
-    speech_client = speech.Client()
+    # [START migration_client]
+    client = speech.SpeechClient()
+    # [END migration_client]
 
     # The name of the audio file to transcribe
     file_name = os.path.join(
@@ -35,14 +41,16 @@ def run_quickstart():
     # Loads the audio into memory
     with io.open(file_name, 'rb') as audio_file:
         content = audio_file.read()
-        sample = speech_client.sample(
-            content,
-            source_uri=None,
-            encoding='LINEAR16',
-            sample_rate_hertz=16000)
+        audio = types.RecognitionAudio(content=content)
+
+    config = types.RecognitionConfig(
+        encoding=enums.RecognitionConfig.AudioEncoding.LINEAR16,
+        sample_rate_hertz=16000,
+        language_code='en-US')
 
     # Detects speech in the audio file
-    alternatives = sample.recognize('en-US')
+    response = client.recognize(config, audio)
+    alternatives = response.results[0].alternatives
 
     for alternative in alternatives:
         print('Transcript: {}'.format(alternative.transcript))

speech/cloud-client/requirements.txt

@@ -1 +1 @@
-google-cloud-speech==0.26.0
+google-cloud-speech==0.27.0

speech/cloud-client/transcribe.py

@@ -31,33 +31,50 @@
 def transcribe_file(speech_file):
     """Transcribe the given audio file."""
     from google.cloud import speech
-    speech_client = speech.Client()
+    from google.cloud.speech import enums
+    from google.cloud.speech import types
+    client = speech.SpeechClient()
 
+    # [START migration_sync_request]
+    # [START migration_audio_config_file]
     with io.open(speech_file, 'rb') as audio_file:
         content = audio_file.read()
-        audio_sample = speech_client.sample(
-            content=content,
-            source_uri=None,
-            encoding='LINEAR16',
-            sample_rate_hertz=16000)
 
-    alternatives = audio_sample.recognize('en-US')
+    audio = types.RecognitionAudio(content=content)
+    config = types.RecognitionConfig(
+        encoding=enums.RecognitionConfig.AudioEncoding.LINEAR16,
+        sample_rate_hertz=16000,
+        language_code='en-US')
+    # [END migration_audio_config_file]
+
+    # [START migration_sync_response]
+    response = client.recognize(config, audio)
+    # [END migration_sync_request]
+    alternatives = response.results[0].alternatives
+
     for alternative in alternatives:
         print('Transcript: {}'.format(alternative.transcript))
+    # [END migration_sync_response]
 
 
 def transcribe_gcs(gcs_uri):
     """Transcribes the audio file specified by the gcs_uri."""
     from google.cloud import speech
-    speech_client = speech.Client()
+    from google.cloud.speech import enums
+    from google.cloud.speech import types
+    client = speech.SpeechClient()
+
+    # [START migration_audio_config_gcs]
+    audio = types.RecognitionAudio(uri=gcs_uri)
+    config = types.RecognitionConfig(
+        encoding=enums.RecognitionConfig.AudioEncoding.FLAC,
+        sample_rate_hertz=16000,
+        language_code='en-US')
+    # [END migration_audio_config_gcs]
 
-    audio_sample = speech_client.sample(
-        content=None,
-        source_uri=gcs_uri,
-        encoding='FLAC',
-        sample_rate_hertz=16000)
+    response = client.recognize(config, audio)
+    alternatives = response.results[0].alternatives
 
-    alternatives = audio_sample.recognize('en-US')
     for alternative in alternatives:
         print('Transcript: {}'.format(alternative.transcript))
 

speech/cloud-client/transcribe_async.py

@@ -30,63 +30,69 @@
 def transcribe_file(speech_file):
     """Transcribe the given audio file asynchronously."""
     from google.cloud import speech
-    speech_client = speech.Client()
+    from google.cloud.speech import enums
+    from google.cloud.speech import types
+    client = speech.SpeechClient()
 
+    # [START migration_async_request]
     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_hertz=16000)
 
-    operation = audio_sample.long_running_recognize('en-US')
+    audio = types.RecognitionAudio(content=content)
+    config = types.RecognitionConfig(
+        encoding=enums.RecognitionConfig.AudioEncoding.LINEAR16,
+        sample_rate_hertz=16000,
+        language_code='en-US')
 
+    # [START migration_async_response]
+    operation = client.long_running_recognize(config, audio)
+    # [END migration_async_request]
+
+    # Sleep and poll operation.done()
     retry_count = 100
-    while retry_count > 0 and not operation.complete:
+    while retry_count > 0 and not operation.done():
         retry_count -= 1
         time.sleep(2)
-        operation.poll()
 
-    if not operation.complete:
+    if not operation.done():
         print('Operation not complete and retry limit reached.')
         return
 
-    alternatives = operation.results
+    alternatives = operation.result().results[0].alternatives
     for alternative in alternatives:
         print('Transcript: {}'.format(alternative.transcript))
         print('Confidence: {}'.format(alternative.confidence))
-    # [END send_request]
+    # [END migration_async_response]
 
 
 def transcribe_gcs(gcs_uri):
     """Asynchronously transcribes the audio file specified by the gcs_uri."""
     from google.cloud import speech
-    speech_client = speech.Client()
+    from google.cloud.speech import enums
+    from google.cloud.speech import types
+    client = speech.SpeechClient()
 
-    audio_sample = speech_client.sample(
-        content=None,
-        source_uri=gcs_uri,
-        encoding='FLAC',
-        sample_rate_hertz=16000)
+    audio = types.RecognitionAudio(uri=gcs_uri)
+    config = types.RecognitionConfig(
+        encoding=enums.RecognitionConfig.AudioEncoding.FLAC,
+        sample_rate_hertz=16000,
+        language_code='en-US')
 
-    operation = audio_sample.long_running_recognize('en-US')
+    operation = client.long_running_recognize(config, audio)
 
     retry_count = 100
-    while retry_count > 0 and not operation.complete:
+    while retry_count > 0 and not operation.done():
         retry_count -= 1
         time.sleep(2)
-        operation.poll()
 
-    if not operation.complete:
+    if not operation.done():
         print('Operation not complete and retry limit reached.')
         return
 
-    alternatives = operation.results
+    alternatives = operation.result().results[0].alternatives
     for alternative in alternatives:
         print('Transcript: {}'.format(alternative.transcript))
         print('Confidence: {}'.format(alternative.confidence))
-    # [END send_request_gcs]
 
 
 if __name__ == '__main__':

speech/cloud-client/transcribe_streaming.py

@@ -29,20 +29,39 @@
 def transcribe_streaming(stream_file):
     """Streams transcription of the given audio file."""
     from google.cloud import speech
-    speech_client = speech.Client()
+    from google.cloud.speech import enums
+    from google.cloud.speech import types
+    client = speech.SpeechClient()
 
+    # [START migration_streaming_request]
     with io.open(stream_file, 'rb') as audio_file:
-        audio_sample = speech_client.sample(
-            stream=audio_file,
-            encoding=speech.encoding.Encoding.LINEAR16,
-            sample_rate_hertz=16000)
-        alternatives = audio_sample.streaming_recognize('en-US')
-
-        for alternative in alternatives:
-            print('Finished: {}'.format(alternative.is_final))
-            print('Stability: {}'.format(alternative.stability))
-            print('Confidence: {}'.format(alternative.confidence))
-            print('Transcript: {}'.format(alternative.transcript))
+        content = audio_file.read()
+
+    # In practice, stream should be a generator yielding chunks of audio data.
+    stream = [content]
+    requests = (types.StreamingRecognizeRequest(audio_content=chunk)
+                for chunk in stream)
+
+    config = types.RecognitionConfig(
+        encoding=enums.RecognitionConfig.AudioEncoding.LINEAR16,
+        sample_rate_hertz=16000,
+        language_code='en-US')
+    streaming_config = types.StreamingRecognitionConfig(config=config)
+
+    # streaming_recognize returns a generator.
+    # [START migration_streaming_response]
+    responses = client.streaming_recognize(streaming_config, requests)
+    # [END migration_streaming_request]
+
+    for response in responses:
+        for result in response.results:
+            print('Finished: {}'.format(result.is_final))
+            print('Stability: {}'.format(result.stability))
+            alternatives = result.alternatives
+            for alternative in alternatives:
+                print('Confidence: {}'.format(alternative.confidence))
+                print('Transcript: {}'.format(alternative.transcript))
+    # [END migration_streaming_response]
 
 
 if __name__ == '__main__':