Try out Speech-to-Text

This guide walks you through the process of running a Speech-to-Text test using Google's Vertex AI Speech service.

Before trying this sample, follow the Python setup instructions in the Vertex AI quickstart using client libraries. For more information, see the Vertex AI Python API reference documentation.

1. Create a python file speech-to-text-test.py. Replace the image_uri_to_test value with the URI of a source image, as shown:

   from google.cloud import speech
   
   def transcribe_gcs_audio(gcs_uri: str) -> speech.RecognizeResponse:
       client = speech.SpeechClient()
   
       audio = speech.RecognitionAudio(uri=gcs_uri)
       config = speech.RecognitionConfig(
           encoding=speech.RecognitionConfig.AudioEncoding.FLAC,
           sample_rate_hertz=16000,
           language_code="en-US", # Specify the language code (e.g., "en-US" for US English)
           # You can add more features here, e.g.:
           # enable_automatic_punctuation=True,
           # model="default" # or "latest_long", "phone_call", "video", "chirp" (v2 API)
       )
   
       # Performs synchronous speech recognition on the audio file
       response = client.recognize(config=config, audio=audio)
   
       # Print the transcription
       for result in response.results:
           print(f"Transcript: {result.alternatives[0].transcript}")
           if result.alternatives[0].confidence:
               print(f"Confidence: {result.alternatives[0].confidence:.2f}")
   
       return response
   
   if __name__ == "__main__":
       # Replace with the URI of your audio file in Google Cloud Storage
       audio_file_uri = "AUDIO_FILE_URI"
   
       print(f"Transcribing audio from: {audio_file_uri}")
       transcribe_gcs_audio(audio_file_uri)
   

   Replace the following:

   • AUDIO_FILE_URI: the URI of an audio file "gs://your-bucket/your-image.png"

2. Create a Dockerfile:

   ROM python:3.9-slim
   
   WORKDIR /app
   
   COPY speech-to-text-test.py /app/
   
   # Install 'requests' for HTTP calls
   RUN pip install --no-cache-dir requests
   
   CMD ["python", "speech-to-text-test.py"]
   

3. Build the Docker image for the Speech-to-Text application:

   docker build -t speech-to-text-app .
   

4. Follow instructions at Configure Docker to:

   1. Configure Docker,
   2. Create a secret, and
   3. Upload the image to HaaS.

5. Sign in to the user cluster and generate its kubeconfig file with a user identity. Make sure that you set the kubeconfig path as an environment variable:

   export KUBECONFIG=${CLUSTER_KUBECONFIG_PATH}
   

6. Create a Kubernetes secret by running the following command in your terminal, pasting your API key:

   kubectl create secret generic gcp-api-key-secret \
     --from-literal=GCP_API_KEY='PASTE_YOUR_API_KEY_HERE'
   

   This command creates a secret named gcp-api-key-secret with a key GCP_API_KEY.

7. Apply the Kubernetes manifest:

   apiVersion: batch/v1
   kind: Job
   metadata:
     name: speech-to-text-test-job
   spec:
     template:
       spec:
         containers:
         - name: speech-to-text-test-container
           image: HARBOR_INSTANCE_URL/HARBOR_PROJECT/speech-to-text-app:latest # Your image path
           # Mount the API key from the secret into the container
           # as an environment variable named GCP_API_KEY.
           imagePullSecrets:
           - name: SECRET
           envFrom:
           - secretRef:
               name: gcp-api-key-secret
         restartPolicy: Never
     backoffLimit: 4
   
   

   Replace the following:

   • HARBOR_INSTANCE_URL: the Harbor instance URL.
   • HARBOR_PROJECT: the Harbor project.
   • SECRET: the name of the secret created to store docker credentials.

8. Check the job status:

   kubectl get jobs/speech-to-text-test-job
   # It will show 0/1 completions, then 1/1 after it succeeds
   

9. After the job has completed, you can view the output in the pod logs:

   kubectl logs -l job-name=speech-to-text-test-job