Chirp 3: Enhanced multilingual accuracy

Stay organized with collections Save and categorize content based on your preferences.

gcloud storage buckets add-iam-policy-binding gs://<YOUR_BUCKET_NAME_HERE> --member=serviceAccount:service-727103546492@gcp-sa-aiplatform.iam.gserviceaccount.com --role=roles/storage.objectViewer

import os

from google.cloud.speech_v2 import SpeechClient
from google.cloud.speech_v2.types import cloud_speech
from google.api_core.client_options import ClientOptions

PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")

def transcribe_batch_chirp3(
    audio_uri: str,
) -> cloud_speech.BatchRecognizeResults:
    """Transcribes an audio file from a Google Cloud Storage URI using the Chirp 3 model of Google Cloud Speech-to-Text V2 API.
    Args:
        audio_uri (str): The Google Cloud Storage URI of the input
          audio file. E.g., gs://[BUCKET]/[FILE]
    Returns:
        cloud_speech.RecognizeResponse: The response from the
           Speech-to-Text API containing the transcription results.
    """

    # Instantiates a client
    client = SpeechClient(
        client_options=ClientOptions(
            api_endpoint="us-west1-speech.googleapis.com",
        )
    )

    speaker_diarization_config = cloud_speech.SpeakerDiarizationConfig(
        min_speaker_count=1,  # minimum number of speakers
        max_speaker_count=6,  # maximum expected number of speakers
    )

    config = cloud_speech.RecognitionConfig(
        auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),
        language_codes=["en-US"],  # Use "auto" to detect language
        model="chirp_3",
        features=cloud_speech.RecognitionFeatures(
            diarization_config=speaker_diarization_config,
        ),
    )

    file_metadata = cloud_speech.BatchRecognizeFileMetadata(uri=audio_uri)

    request = cloud_speech.BatchRecognizeRequest(
        recognizer=f"projects/{PROJECT_ID}/locations/us-west1/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[audio_uri].transcript.results:
        print(f"Transcript: {result.alternatives[0].transcript}")
        print(f"Detected Language: {result.language_code}")
        print(f"Speakers per word: {result.alternatives[0].words}")

    return response.results[audio_uri].transcript