Simplified next set of Speech Samples (set-3) (GoogleCloudPlatform#12158)

* Simplified set of Speech Samples
* Update comments and imports

Author: Thoughtseize1

speech/snippets/transcribe_feature_in_recognizer.py

@@ -11,51 +11,73 @@
 # 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 argparse
-
-# [START speech_transcribe_feature_in_recognizer]
-from google.cloud.speech_v2 import SpeechClient
 from google.cloud.speech_v2.types import cloud_speech
 
+PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")
+
 
 def transcribe_feature_in_recognizer(
-    project_id: str,
-    recognizer_id: str,
     audio_file: str,
+    recognizer_id: str,
 ) -> cloud_speech.RecognizeResponse:
-    """Transcribe an audio file using an existing recognizer."""
+    """Use an existing recognizer or create a new one to transcribe an audio file.
+    Args:
+        audio_file (str): The path to the audio file to be transcribed.
+            Example: "resources/audio.wav"
+        recognizer_id (str): The ID of the recognizer to be used or created. ID should be unique
+            within the project and location.
+    Returns:
+        cloud_speech.RecognizeResponse: The response containing the transcription results.
+    """
+    # [START speech_transcribe_feature_in_recognizer]
+
+    from google.cloud.speech_v2 import SpeechClient
+    from google.cloud.speech_v2.types import cloud_speech
+
+    from google.api_core.exceptions import NotFound
+
     # Instantiates a client
     client = SpeechClient()
 
-    request = cloud_speech.CreateRecognizerRequest(
-        parent=f"projects/{project_id}/locations/global",
-        recognizer_id=recognizer_id,
-        recognizer=cloud_speech.Recognizer(
-            default_recognition_config=cloud_speech.RecognitionConfig(
-                auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),
-                language_codes=["en-US"],
-                model="latest_long",
-                features=cloud_speech.RecognitionFeatures(
-                    enable_automatic_punctuation=True,
+    # TODO(developer): Update and un-comment below line
+    # PROJECT_ID = "your-project-id"
+    # recognizer_id = "id-recognizer"
+    recognizer_name = (
+        f"projects/{PROJECT_ID}/locations/global/recognizers/{recognizer_id}"
+    )
+    try:
+        # Use an existing recognizer
+        recognizer = client.get_recognizer(name=recognizer_name)
+        print("Using existing Recognizer:", recognizer.name)
+    except NotFound:
+        # Create a new recognizer
+        request = cloud_speech.CreateRecognizerRequest(
+            parent=f"projects/{PROJECT_ID}/locations/global",
+            recognizer_id=recognizer_id,
+            recognizer=cloud_speech.Recognizer(
+                default_recognition_config=cloud_speech.RecognitionConfig(
+                    auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),
+                    language_codes=["en-US"],
+                    model="latest_long",
+                    features=cloud_speech.RecognitionFeatures(
+                        enable_automatic_punctuation=True,
+                    ),
                 ),
             ),
-        ),
-    )
-
-    operation = client.create_recognizer(request=request)
-    recognizer = operation.result()
-
-    print("Created Recognizer:", recognizer.name)
+        )
+        operation = client.create_recognizer(request=request)
+        recognizer = operation.result()
+        print("Created Recognizer:", recognizer.name)
 
     # Reads a file as bytes
     with open(audio_file, "rb") as f:
-        content = f.read()
+        audio_content = f.read()
 
     request = cloud_speech.RecognizeRequest(
-        recognizer=f"projects/{project_id}/locations/global/recognizers/{recognizer_id}",
-        content=content,
+        recognizer=f"projects/{PROJECT_ID}/locations/global/recognizers/{recognizer_id}",
+        content=audio_content,
     )
 
     # Transcribes the audio into text
@@ -64,18 +86,12 @@ def transcribe_feature_in_recognizer(
     for result in response.results:
         print(f"Transcript: {result.alternatives[0].transcript}")
 
-    return response
-
+    # [END speech_transcribe_feature_in_recognizer]
 
-# [END speech_transcribe_feature_in_recognizer]
+    return response
 
 
 if __name__ == "__main__":
-    parser = argparse.ArgumentParser(
-        description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter
+    transcribe_feature_in_recognizer(
+        audio_file="resources/audio.wav", recognizer_id="id-recognizer"
     )
-    parser.add_argument("project_id", help="GCP Project ID")
-    parser.add_argument("recognizer_id", help="Recognizer ID to use for recogniition")
-    parser.add_argument("audio_file", help="Audio file to stream")
-    args = parser.parse_args()
-    transcribe_feature_in_recognizer(args.project_id, args.audio_file)

speech/snippets/transcribe_feature_in_recognizer_test.py

@@ -24,33 +24,46 @@
 import transcribe_feature_in_recognizer
 
 _RESOURCES = os.path.join(os.path.dirname(__file__), "resources")
+PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")
 
 
-def delete_recognizer(project_id: str, recognizer_id: str) -> None:
+def delete_recognizer(recognizer_id: str) -> None:
     client = SpeechClient()
     request = cloud_speech.DeleteRecognizerRequest(
-        name=f"projects/{project_id}/locations/global/recognizers/{recognizer_id}"
+        name=f"projects/{PROJECT_ID}/locations/global/recognizers/{recognizer_id}"
     )
     client.delete_recognizer(request=request)
 
 
 def test_transcribe_feature_in_recognizer(
     capsys: pytest.CaptureFixture, request: pytest.FixtureRequest
 ) -> None:
-    project_id = os.getenv("GOOGLE_CLOUD_PROJECT")
     recognizer_id = "recognizer-" + str(uuid4())
 
     def cleanup() -> None:
-        delete_recognizer(project_id, recognizer_id)
+        delete_recognizer(recognizer_id)
 
     request.addfinalizer(cleanup)
 
-    response = transcribe_feature_in_recognizer.transcribe_feature_in_recognizer(
-        project_id, recognizer_id, os.path.join(_RESOURCES, "audio.wav")
+    response_with_new_recognizer = (
+        transcribe_feature_in_recognizer.transcribe_feature_in_recognizer(
+            os.path.join(_RESOURCES, "audio.wav"), recognizer_id
+        )
     )
-
+    # Call function one more time to test work with the existing recognizer
+    response_with_existing_recognizer = (
+        transcribe_feature_in_recognizer.transcribe_feature_in_recognizer(
+            os.path.join(_RESOURCES, "fair.wav"), recognizer_id
+        )
+    )
+    out, _ = capsys.readouterr()
     assert re.search(
         r"How old is the Brooklyn Bridge?",
-        response.results[0].alternatives[0].transcript,
+        response_with_new_recognizer.results[0].alternatives[0].transcript,
+        re.DOTALL | re.I,
+    )
+    assert re.search(
+        r"is fair",
+        response_with_existing_recognizer.results[0].alternatives[0].transcript,
         re.DOTALL | re.I,
     )

speech/snippets/transcribe_file_v2.py

@@ -12,24 +12,32 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+import os
 
-import argparse
-
-# [START speech_transcribe_file_v2]
-from google.cloud.speech_v2 import SpeechClient
 from google.cloud.speech_v2.types import cloud_speech
 
+PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")
+
+
+def transcribe_file_v2() -> cloud_speech.RecognizeResponse:
+    """Transcribe an audio file using Google Cloud Speech-to-Text API v2.
+    Returns:
+        cloud_speech.RecognizeResponse: The response containing the transcription results.
+    """
+    # [START speech_transcribe_file_v2]
+
+    from google.cloud.speech_v2 import SpeechClient
+    from google.cloud.speech_v2.types import cloud_speech
+
+    # TODO(developer): Update and un-comment below line
+    # PROJECT_ID = "your-project-id"
 
-def transcribe_file_v2(
-    project_id: str,
-    audio_file: str,
-) -> cloud_speech.RecognizeResponse:
     # Instantiates a client
     client = SpeechClient()
 
     # Reads a file as bytes
-    with open(audio_file, "rb") as f:
-        content = f.read()
+    with open("resources/audio.wav", "rb") as f:
+        audio_content = f.read()
 
     config = cloud_speech.RecognitionConfig(
         auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),
@@ -38,9 +46,9 @@ def transcribe_file_v2(
     )
 
     request = cloud_speech.RecognizeRequest(
-        recognizer=f"projects/{project_id}/locations/global/recognizers/_",
+        recognizer=f"projects/{PROJECT_ID}/locations/global/recognizers/_",
         config=config,
-        content=content,
+        content=audio_content,
     )
 
     # Transcribes the audio into text
@@ -49,17 +57,6 @@ def transcribe_file_v2(
     for result in response.results:
         print(f"Transcript: {result.alternatives[0].transcript}")
 
-    return response
+    # [END speech_transcribe_file_v2]
 
-
-# [END speech_transcribe_file_v2]
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser(
-        description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter
-    )
-    parser.add_argument("project_id", help="GCP Project ID")
-    parser.add_argument("audio_file", help="Audio file to stream")
-    args = parser.parse_args()
-    transcribe_file_v2(args.project_id, args.audio_file)
+    return response

speech/snippets/transcribe_file_v2_test.py

@@ -12,23 +12,15 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-import os
 import re
 
 import pytest
 
 import transcribe_file_v2
 
-_RESOURCES = os.path.join(os.path.dirname(__file__), "resources")
-
 
 def test_transcribe_file_v2(capsys: pytest.CaptureFixture) -> None:
-    project_id = os.getenv("GOOGLE_CLOUD_PROJECT")
-
-    response = transcribe_file_v2.transcribe_file_v2(
-        project_id, os.path.join(_RESOURCES, "audio.wav")
-    )
-
+    response = transcribe_file_v2.transcribe_file_v2()
     assert re.search(
         r"how old is the Brooklyn Bridge",
         response.results[0].alternatives[0].transcript,

speech/snippets/transcribe_gcs_v2.py

@@ -11,41 +11,39 @@
 # 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 argparse
-
-# [START speech_transcribe_gcs_v2]
-from google.cloud.speech_v2 import SpeechClient
 from google.cloud.speech_v2.types import cloud_speech
 
+PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")
 
-def transcribe_gcs_v2(
-    project_id: str,
-    gcs_uri: str,
-) -> cloud_speech.RecognizeResponse:
-    """Transcribes audio from a Google Cloud Storage URI.
-
-    Args:
-        project_id: The GCP project ID.
-        gcs_uri: The Google Cloud Storage URI.
 
+def transcribe_gcs_v2() -> cloud_speech.RecognizeResponse:
+    """Transcribe an audio file using Google Cloud Speech-to-Text API v2.
     Returns:
-        The RecognizeResponse.
+        cloud_speech.RecognizeResponse: The response containing the transcription results.
     """
+    # [START speech_transcribe_gcs_v2]
+
+    from google.cloud.speech_v2 import SpeechClient
+    from google.cloud.speech_v2.types import cloud_speech
+
     # Instantiates a client
     client = SpeechClient()
 
+    # TODO(developer): Update and un-comment below line
+    # PROJECT_ID = "your-project-id"
+
     config = cloud_speech.RecognitionConfig(
         auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),
         language_codes=["en-US"],
         model="long",
     )
 
     request = cloud_speech.RecognizeRequest(
-        recognizer=f"projects/{project_id}/locations/global/recognizers/_",
+        recognizer=f"projects/{PROJECT_ID}/locations/global/recognizers/_",
         config=config,
-        uri=gcs_uri,
+        uri="gs://cloud-samples-data/speech/audio.flac",  # URI of the audio file in GCS
     )
 
     # Transcribes the audio into text
@@ -54,17 +52,6 @@ def transcribe_gcs_v2(
     for result in response.results:
         print(f"Transcript: {result.alternatives[0].transcript}")
 
-    return response
-
-
-# [END speech_transcribe_gcs_v2]
+    # [END speech_transcribe_gcs_v2]
 
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser(
-        description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter
-    )
-    parser.add_argument("project_id", help="GCP Project ID")
-    parser.add_argument("gcs_uri", help="URI to GCS file")
-    args = parser.parse_args()
-    transcribe_gcs_v2(args.project_id, args.gcs_uri)
+    return response

speech/snippets/transcribe_gcs_v2_test.py

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-import os
 import re
 
 from google.api_core.retry import Retry
@@ -21,14 +20,9 @@
 import transcribe_gcs_v2
 
 
-_TEST_AUDIO_FILE_PATH = "gs://cloud-samples-data/speech/audio.flac"
-
-
 @Retry()
 def test_transcribe_gcs_v2(capsys: pytest.CaptureFixture) -> None:
-    project_id = os.getenv("GOOGLE_CLOUD_PROJECT")
-
-    response = transcribe_gcs_v2.transcribe_gcs_v2(project_id, _TEST_AUDIO_FILE_PATH)
+    response = transcribe_gcs_v2.transcribe_gcs_v2()
 
     assert re.search(
         r"how old is the Brooklyn Bridge",