chore: Simplified speech samples (set-4) (GoogleCloudPlatform#12316)

* Simplify next(4th) set of Speech samples

* Minor doc changes

* 🦉 Updates from OwlBot post-processor

See https://github.com/googleapis/repo-automation-bots/blob/main/packages/owl-bot/README.md

---------

Co-authored-by: Owl Bot <gcf-owl-bot[bot]@users.noreply.github.com>

Author: Thoughtseize1

speech/snippets/transcribe.py

@@ -13,29 +13,28 @@
 # limitations under the License.
 
 """Google Cloud Speech API sample application using the REST API for batch
-processing.
-
-Example usage:
-    python transcribe.py resources/audio.raw
-    python transcribe.py gs://cloud-samples-tests/speech/brooklyn.flac
-"""
+processing."""
 
 # [START speech_transcribe_sync]
-import argparse
-
 from google.cloud import speech
 
 
-def transcribe_file(speech_file: str) -> speech.RecognizeResponse:
-    """Transcribe the given audio file."""
+def transcribe_file(audio_file: str) -> speech.RecognizeResponse:
+    """Transcribe the given audio file.
+    Args:
+        audio_file (str): Path to the local audio file to be transcribed.
+            Example: "resources/audio.wav"
+    Returns:
+        cloud_speech.RecognizeResponse: The response containing the transcription results
+    """
     client = speech.SpeechClient()
 
     # [START speech_python_migration_sync_request]
     # [START speech_python_migration_config]
-    with open(speech_file, "rb") as audio_file:
-        content = audio_file.read()
+    with open(audio_file, "rb") as f:
+        audio_content = f.read()
 
-    audio = speech.RecognitionAudio(content=content)
+    audio = speech.RecognitionAudio(content=audio_content)
     config = speech.RecognitionConfig(
         encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
         sample_rate_hertz=16000,
@@ -61,14 +60,20 @@ def transcribe_file(speech_file: str) -> speech.RecognizeResponse:
 
 
 # [START speech_transcribe_sync_gcs]
-def transcribe_gcs(gcs_uri: str) -> speech.RecognizeResponse:
-    """Transcribes the audio file specified by the gcs_uri."""
+def transcribe_gcs(audio_uri: str) -> speech.RecognizeResponse:
+    """Transcribes the audio file specified by the gcs_uri.
+    Args:
+        audio_uri (str): The Google Cloud Storage URI of the input audio file.
+            E.g., gs://cloud-samples-data/speech/audio.flac
+    Returns:
+        cloud_speech.RecognizeResponse: The response containing the transcription results
+    """
     from google.cloud import speech
 
     client = speech.SpeechClient()
 
     # [START speech_python_migration_config_gcs]
-    audio = speech.RecognitionAudio(uri=gcs_uri)
+    audio = speech.RecognitionAudio(uri=audio_uri)
     config = speech.RecognitionConfig(
         encoding=speech.RecognitionConfig.AudioEncoding.FLAC,
         sample_rate_hertz=16000,
@@ -91,12 +96,9 @@ def transcribe_gcs(gcs_uri: str) -> speech.RecognizeResponse:
 
 
 if __name__ == "__main__":
-    parser = argparse.ArgumentParser(
-        description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter
-    )
-    parser.add_argument("path", help="File or GCS path for audio file to be recognized")
-    args = parser.parse_args()
-    if args.path.startswith("gs://"):
-        transcribe_gcs(args.path)
+    # It could be a local path like: path_to_file = "resources/audio.raw"
+    path_to_file = "gs://cloud-samples-data/speech/audio.flac"
+    if path_to_file.startswith("gs://"):
+        transcribe_gcs(path_to_file)
     else:
-        transcribe_file(args.path)
+        transcribe_file(path_to_file)

speech/snippets/transcribe_multichannel.py

@@ -13,35 +13,27 @@
 # limitations under the License.
 
 """Google Cloud Speech API sample that demonstrates multichannel recognition.
-
-Example usage:
-    python transcribe_multichannel.py resources/multi.wav
-    python transcribe_multichannel.py \
-        gs://cloud-samples-tests/speech/multi.wav
 """
 
 # [START speech_transcribe_multichannel]
-import argparse
 
 from google.cloud import speech
 
 
-def transcribe_file_with_multichannel(speech_file: str) -> speech.RecognizeResponse:
-    """Transcribe the given audio file synchronously with
-    multi channel.
-
+def transcribe_file_with_multichannel(audio_file: str) -> speech.RecognizeResponse:
+    """Transcribe the given audio file synchronously with multi channel.
     Args:
-        speech_file: A path to audio file to be recognized.
-
+        audio_file (str): Path to the local audio file to be transcribed.
+            Example: "resources/multi.wav"
     Returns:
-        The RecognizeResponse results.
+         cloud_speech.RecognizeResponse: The full response object which includes the transcription results.
     """
     client = speech.SpeechClient()
 
-    with open(speech_file, "rb") as audio_file:
-        content = audio_file.read()
+    with open(audio_file, "rb") as f:
+        audio_content = f.read()
 
-    audio = speech.RecognitionAudio(content=content)
+    audio = speech.RecognitionAudio(content=audio_content)
 
     config = speech.RecognitionConfig(
         encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
@@ -64,22 +56,20 @@ def transcribe_file_with_multichannel(speech_file: str) -> speech.RecognizeRespo
     # [END speech_transcribe_multichannel]
 
 
-def transcribe_gcs_with_multichannel(gcs_uri: str) -> speech.RecognizeResponse:
-    """Transcribe the given audio file on GCS with
-    multi channel.
-
+def transcribe_gcs_with_multichannel(audio_uri: str) -> speech.RecognizeResponse:
+    """Transcribe the given audio file from Google Cloud Storage synchronously with multichannel.
     Args:
-        gcs_uri: A path to audio file to be recognized.
-
+        audio_uri (str): The Cloud Storage URI of the input audio.
+            E.g., gs://cloud-samples-data/speech/multi.wav
     Returns:
-        The RecognizeResponse results.
+        speech.RecognizeResponse: The full response object which includes the transcription results.
     """
     # [START speech_transcribe_multichannel_gcs]
     from google.cloud import speech
 
     client = speech.SpeechClient()
 
-    audio = speech.RecognitionAudio(uri=gcs_uri)
+    audio = speech.RecognitionAudio(uri=audio_uri)
 
     config = speech.RecognitionConfig(
         encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
@@ -103,12 +93,9 @@ def transcribe_gcs_with_multichannel(gcs_uri: str) -> speech.RecognizeResponse:
 
 
 if __name__ == "__main__":
-    parser = argparse.ArgumentParser(
-        description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter
-    )
-    parser.add_argument("path", help="File or GCS path for audio file to be recognized")
-    args = parser.parse_args()
-    if args.path.startswith("gs://"):
-        transcribe_gcs_with_multichannel(args.path)
+    # It could be a local path like: path_to_file = "resources/multi.wav"
+    path_to_file = "gs://cloud-samples-data/speech/multi.wav"
+    if path_to_file.startswith("gs://"):
+        transcribe_gcs_with_multichannel(path_to_file)
     else:
-        transcribe_file_with_multichannel(args.path)
+        transcribe_file_with_multichannel(path_to_file)

speech/snippets/transcribe_multichannel_v2.py

@@ -12,25 +12,31 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
-import argparse
-
 # [START speech_transcribe_multichannel_v2]
+import os
+
 from google.cloud.speech_v2 import SpeechClient
 from google.cloud.speech_v2.types import cloud_speech
 
+PROJECT_ID = os.environ["GOOGLE_CLOUD_PROJECT"]
+
 
 def transcribe_multichannel_v2(
-    project_id: str,
     audio_file: str,
 ) -> cloud_speech.RecognizeResponse:
-    """Transcribe a multi-channel audio file."""
+    """Transcribe the given audio file synchronously with multichannel.
+    Args:
+        audio_file (str): Path to the local audio file to be transcribed.
+            Example: "resources/two_channel_16k.wav"
+    Returns:
+        cloud_speech.RecognizeResponse: The full response object which includes the transcription results.
+    """
     # Instantiates a client
     client = SpeechClient()
 
     # Reads a file as bytes
     with open(audio_file, "rb") as f:
-        content = f.read()
+        audio_content = f.read()
 
     config = cloud_speech.RecognitionConfig(
         auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),
@@ -42,9 +48,9 @@ def transcribe_multichannel_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
@@ -61,10 +67,4 @@ def transcribe_multichannel_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_multichannel_v2(args.project_id, args.audio_file)
+    transcribe_multichannel_v2("resources/two_channel_16k.wav")

speech/snippets/transcribe_multichannel_v2_test.py

@@ -24,10 +24,8 @@
 
 @Retry()
 def test_transcribe_multichannel_v2() -> None:
-    project_id = os.getenv("GOOGLE_CLOUD_PROJECT")
-
     response = transcribe_multichannel_v2.transcribe_multichannel_v2(
-        project_id, os.path.join(_RESOURCES, "two_channel_16k.wav")
+        os.path.join(_RESOURCES, "two_channel_16k.wav")
     )
 
     assert re.search(

speech/snippets/transcribe_multiple_languages_v2.py

@@ -12,28 +12,36 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
-import argparse
-
 # [START speech_transcribe_multiple_languages_v2]
+import os
+
 from typing import List
 
 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_multiple_languages_v2(
-    project_id: str,
-    language_codes: List[str],
     audio_file: str,
+    language_codes: List[str],
 ) -> cloud_speech.RecognizeResponse:
-    """Transcribe an audio file."""
-    # Instantiates a client
+    """Transcribe an audio file using Google Cloud Speech-to-Text API with support for multiple languages.
+    Args:
+        audio_file (str): Path to the local audio file to be transcribed.
+            Example: "resources/audio.wav"
+        language_codes (List[str]): A list of BCP-47 language codes to be used for transcription.
+            Example: ["en-US", "fr-FR"]
+    Returns:
+        cloud_speech.RecognizeResponse: The response from the Speech-to-Text API containing the
+            transcription results.
+    """
     client = SpeechClient()
 
     # Reads a file as bytes
     with open(audio_file, "rb") as f:
-        content = f.read()
+        audio_content = f.read()
 
     config = cloud_speech.RecognitionConfig(
         auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),
@@ -42,14 +50,14 @@ def transcribe_multiple_languages_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
     response = client.recognize(request=request)
-
+    # Prints the transcription results
     for result in response.results:
         print(f"Transcript: {result.alternatives[0].transcript}")
 
@@ -60,15 +68,7 @@ def transcribe_multiple_languages_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(
-        "language_codes", nargs="+", help="Language codes to transcribe"
-    )
-    parser.add_argument("audio_file", help="Audio file to stream")
-    args = parser.parse_args()
+    # Language codes to transcribe
     transcribe_multiple_languages_v2(
-        args.project_id, args.language_codes, args.audio_file
+        audio_file="resources/audio.wav", language_codes=["en-US", "fr-FR"]
     )

speech/snippets/transcribe_multiple_languages_v2_test.py

@@ -24,10 +24,9 @@
 
 @Retry()
 def test_transcribe_multiple_languages_v2() -> None:
-    project_id = os.getenv("GOOGLE_CLOUD_PROJECT")
-
     response = transcribe_multiple_languages_v2.transcribe_multiple_languages_v2(
-        project_id, ["en-US", "fr-FR"], os.path.join(RESOURCES, "audio.wav")
+        os.path.join(RESOURCES, "audio.wav"),
+        ["en-US", "fr-FR"],
     )
 
     assert re.search(