docs(samples): a draft that refactors speech_to_storage_beta sample (#…

…276)

* docs(samples): a draft that refactors speech_to_storage_beta sample

* docs(samples): applied changes

* docs(samples): file name changed

* docs(samples): added new line eof

* docs(samples): updated to LongRunningRecognizeResponse

* docs(samples): fixed lint

* docs(samples): removed unwanted line

* docs(samples): removed unwanted line

speech/snippets/speech_to_storage_beta.py

@@ -15,11 +15,19 @@
 
 # [START speech_transcribe_with_speech_to_storage_beta]
 
-from google.cloud import speech_v1p1beta1 as speech
+from google.cloud import speech
+from google.cloud import storage
+from google.cloud.speech_v1 import types
 
 
 def export_transcript_to_storage_beta(
-    input_storage_uri, output_storage_uri, encoding, sample_rate_hertz, language_code
+    input_storage_uri,
+    output_storage_uri,
+    encoding,
+    sample_rate_hertz,
+    language_code,
+    bucket_name,
+    object_name,
 ):
 
     # input_uri URI for audio file in Cloud Storage, e.g. gs://[BUCKET]/[FILE]
@@ -40,20 +48,38 @@ def export_transcript_to_storage_beta(
         audio=audio, config=config, output_config=output_config
     )
 
-    # Create the speech client
+    # create the speech client
     speech_client = speech.SpeechClient()
 
+    # create the storage client
+    storage_client = storage.Client()
+
+    # run the recognizer to export transcript
     operation = speech_client.long_running_recognize(request=request)
 
     print("Waiting for operation to complete...")
-    response = operation.result(timeout=90)
+    operation.result(timeout=90)
+
+    # get bucket with name
+    bucket = storage_client.get_bucket(bucket_name)
+
+    # get blob from bucket
+    blob = bucket.get_blob(object_name)
+
+    # get content as string
+    results_string = blob.download_as_string()
+
+    # get transcript exported in storage bucket
+    storage_transcript = types.LongRunningRecognizeResponse.from_json(
+        results_string, ignore_unknown_fields=True
+    )
 
     # 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:
+    for result in storage_transcript.results:
         # The first alternative is the most likely one for this portion.
-        print("Transcript: {}".format(result.alternatives[0].transcript))
-        print("Confidence: {}".format(result.alternatives[0].confidence))
+        print(f"Transcript: {result.alternatives[0].transcript}")
+        print(f"Confidence: {result.alternatives[0].confidence}")
 
-    # [END speech_transcribe_with_speech_to_storage_beta]
-    return response.results[0].alternatives[0].transcript
+# [END speech_transcribe_with_speech_to_storage_beta]
+    return storage_transcript.results

speech/snippets/speech_to_storage_beta_test.py

@@ -38,14 +38,16 @@
 
 
 def test_export_transcript_to_storage_beta(bucket, capsys):
-    transcript = speech_to_storage_beta.export_transcript_to_storage_beta(
+    results = speech_to_storage_beta.export_transcript_to_storage_beta(
         INPUT_STORAGE_URI,
         OUTPUT_STORAGE_URI,
         encoding,
         sample_rate_hertz,
         language_code,
+        BUCKET_NAME,
+        BUCKET_PREFIX,
     )
-    assert "I'm here" in transcript
+    assert len(results) > 0
 
 
 @pytest.fixture