[Python] How to make Google Cloud V2 ASR to transcribe 2 audios in parallel?

I have a web app where users can use Google Cloud v2 ASR for transcription. However, when two logged-in users try to transcribe simultaneously, the platform processes the requests in a queue (the first one gets transcribed first). I want to implement parallel transcription using Google Cloud v2 ASR in Python. How can I achieve this?

This is the function which I am calling from endpoint for each user:

def upload_to_gcs(local_file: str, bucket_name: str, destination_blob_name: str):
destination_blob_name=destination_blob_name
storage_client = storage.Client(credentials=credentials)
bucket = storage_client.bucket(bucket_name)
blob = bucket.blob(destination_blob_name)
blob.upload_from_filename(local_file)
return f"gs://{bucket_name}/{destination_blob_name}"

def transcribe_chirp_2_asynch(audio_file: str, is_punct_capit: bool = False) -> str:
client = SpeechClient(credentials=credentials, client_options=ClientOptions(api_endpoint="us-central1-speech.googleapis.com",))

#Reads a file as bytes
with open(audio_file, "rb") as f:
audio_content = f.read()
destination_blob_name = os.path.basename(audio_file)
uri_file = upload_to_gcs(audio_file, "xxx", destination_blob_name)
long_audio_files = [{"uri": uri_file}]
features=cloud_speech.RecognitionFeatures(
profanity_filter=False,
enable_word_time_offsets=False,
enable_word_confidence = False,
enable_automatic_punctuation = is_punct_capit,
#enable_spoken_punctuation = False,
enable_spoken_emojis = False,
multi_channel_mode = False,
#diarization_config = diarizarion_config,
max_alternatives = 0,
)
config = cloud_speech.RecognitionConfig(
language_codes=["en-US"],
model="chirp_2",
features = features,
auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),
)

file_metadata = cloud_speech.BatchRecognizeFileMetadata(uri=uri_file)
request = cloud_speech.BatchRecognizeRequest(
recognizer=f"projects/{PROJECT_ID}/locations/us-central1/recognizers/_",
config=config,
files=[file_metadata],
recognition_output_config=cloud_speech.RecognitionOutputConfig(
inline_response_config=cloud_speech.InlineOutputConfig(),
),
)
# Transcribes the audio into text
operation = client.batch_recognize(request=request)

print("Waiting for operation to complete...")
response = operation.result(timeout=120)
for result in response.results[uri_file].transcript.results:
print(f"Transcript: {result.alternatives[0].transcript}")
return result.alternatives[0].transcript


Should I use other functions provided by Google?

Continue reading...