Mentranskripsikan file audio panjang menjadi teks

Halaman ini menunjukkan cara mentranskripsikan file audio yang panjang (dengan durasi lebih dari satu menit) ke teks menggunakan Speech-to-Text API dan pengenalan ucapan asinkron.

Tentang pengenalan ucapan asinkron

Pengenalan ucapan batch memulai operasi panjang pemrosesan audio. Gunakan pengenalan ucapan asinkron untuk mentranskripsikan audio yang berdurasi lebih dari 60 detik. Untuk audio berdurasi lebih pendek, pengenalan ucapan sinkron lebih cepat dan lebih mudah. Batas atas untuk pengenalan ucapan asinkron adalah 480 menit (8 jam).

Pengenalan ucapan batch hanya dapat mentranskripsikan audio yang disimpan di Cloud Storage. Output transkripsi dapat diberikan inline sebagai bagian dari respons (untuk permintaan pengenalan batch file tunggal) atau ditulis ke Cloud Storage.

Permintaan pengenalan batch menampilkan Operation yang berisi informasi tentang pemrosesan pengenalan yang sedang berlangsung atas permintaan Anda. Anda dapat melakukan polling operasi untuk mengetahui kapan operasi selesai dan transkripnya tersedia.

Sebelum memulai

  1. Sign in to your Google Cloud account. If you're new to Google Cloud, create an account to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.
  2. In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

    Go to project selector

  3. Make sure that billing is enabled for your Google Cloud project.

  4. Enable the Speech-to-Text APIs.

    Enable the APIs

  5. Make sure that you have the following role or roles on the project: Cloud Speech Administrator

    Check for the roles

    1. In the Google Cloud console, go to the IAM page.

      Go to IAM
    2. Select the project.
    3. In the Principal column, find all rows that identify you or a group that you're included in. To learn which groups you're included in, contact your administrator.

    4. For all rows that specify or include you, check the Role column to see whether the list of roles includes the required roles.

    Grant the roles

    1. In the Google Cloud console, go to the IAM page.

      Buka IAM
    2. Pilih project.
    3. Klik Berikan akses.
    4. Di kolom New principals, masukkan ID pengguna Anda. Ini biasanya adalah alamat email untuk Akun Google.

    5. Di daftar Pilih peran, pilih peran.
    6. Untuk memberikan peran tambahan, klik Tambahkan peran lain, lalu tambahkan setiap peran tambahan.
  6. Install the Google Cloud CLI.
  7. To initialize the gcloud CLI, run the following command:

    gcloud init
  8. In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

    Go to project selector

  9. Make sure that billing is enabled for your Google Cloud project.

  10. Enable the Speech-to-Text APIs.

    Enable the APIs

  11. Make sure that you have the following role or roles on the project: Cloud Speech Administrator

    Check for the roles

    1. In the Google Cloud console, go to the IAM page.

      Go to IAM
    2. Select the project.
    3. In the Principal column, find all rows that identify you or a group that you're included in. To learn which groups you're included in, contact your administrator.

    4. For all rows that specify or include you, check the Role column to see whether the list of roles includes the required roles.

    Grant the roles

    1. In the Google Cloud console, go to the IAM page.

      Buka IAM
    2. Pilih project.
    3. Klik Berikan akses.
    4. Di kolom New principals, masukkan ID pengguna Anda. Ini biasanya adalah alamat email untuk Akun Google.

    5. Di daftar Pilih peran, pilih peran.
    6. Untuk memberikan peran tambahan, klik Tambahkan peran lain, lalu tambahkan setiap peran tambahan.
  12. Install the Google Cloud CLI.
  13. To initialize the gcloud CLI, run the following command:

    gcloud init
  14. Library klien dapat menggunakan Kredensial Default Aplikasi untuk dengan mudah melakukan autentikasi dengan Google API dan mengirim permintaan ke API tersebut. Dengan Kredensial Default Aplikasi, Anda dapat menguji aplikasi secara lokal dan men-deploy aplikasi tanpa mengubah kode yang mendasarinya. Untuk informasi selengkapnya, lihat Lakukan autentikasi untuk menggunakan library klien.

  15. If you're using a local shell, then create local authentication credentials for your user account:

    gcloud auth application-default login

    You don't need to do this if you're using Cloud Shell.

Selain itu, pastikan Anda telah menginstal library klien.

Mengaktifkan akses ke Cloud Storage

Speech-to-Text menggunakan akun layanan untuk mengakses file Anda di Cloud Storage. Secara default, akun layanan memiliki akses ke file Cloud Storage dalam project yang sama.

Alamat email akun layanan adalah sebagai berikut:

service-PROJECT_NUMBER@gcp-sa-speech.iam.gserviceaccount.com

Untuk mentranskripsikan file Cloud Storage di project lain, Anda dapat memberikan peran Agen Layanan Speech-to-Text ke project layanan ini:

gcloud projects add-iam-policy-binding PROJECT_ID \
    --member=serviceAccount:service-PROJECT_NUMBER@gcp-sa-speech.iam.gserviceaccount.com \
    --role=roles/speech.serviceAgent

Informasi selengkapnya tentang kebijakan IAM project tersedia di bagian Mengelola akses ke project, folder, dan organisasi.

Anda juga dapat memberikan akses yang lebih terperinci kepada akun layanan dengan memberinya izin ke bucket Cloud Storage tertentu:

gcloud storage buckets add-iam-policy-binding gs://BUCKET_NAME \
    --member=serviceAccount:service-PROJECT_NUMBER@gcp-sa-speech.iam.gserviceaccount.com \
    --role=roles/storage.admin

Informasi selengkapnya tentang cara mengelola akses ke Cloud Storage tersedia di bagian Membuat dan Mengelola daftar kontrol akses dalam dokumentasi Cloud Storage.

Melakukan pengenalan batch dengan hasil inline

Berikut adalah contoh menjalankan pengenalan ucapan batch pada file audio di Cloud Storage dan membaca hasil transkripsi secara inline dari respons:

Python

import os

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_batch_gcs_input_inline_output_v2(
    audio_uri: str,
) -> cloud_speech.BatchRecognizeResults:
    """Transcribes audio from a Google Cloud Storage URI using the Google Cloud Speech-to-Text API.
        The transcription results are returned inline in the response.
    Args:
        audio_uri (str): The Google Cloud Storage URI of the input audio file.
            E.g., gs://[BUCKET]/[FILE]
    Returns:
        cloud_speech.BatchRecognizeResults: The response containing the transcription results.
    """
    # Instantiates a client
    client = SpeechClient()

    config = cloud_speech.RecognitionConfig(
        auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),
        language_codes=["en-US"],
        model="long",
    )

    file_metadata = cloud_speech.BatchRecognizeFileMetadata(uri=audio_uri)

    request = cloud_speech.BatchRecognizeRequest(
        recognizer=f"projects/{PROJECT_ID}/locations/global/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}")

    return response.results[audio_uri].transcript

Melakukan pengenalan batch dan menulis hasilnya ke Cloud Storage

Berikut adalah contoh melakukan pengenalan ucapan batch pada file audio di Cloud Storage dan membaca hasil transkripsi dari file output di Cloud Storage. Perhatikan bahwa file yang ditulis ke Cloud Storage adalah pesan BatchRecognizeResults dalam format JSON:

Python

import os

import re

from google.cloud import storage
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_batch_gcs_input_gcs_output_v2(
    audio_uri: str,
    gcs_output_path: str,
) -> cloud_speech.BatchRecognizeResults:
    """Transcribes audio from a Google Cloud Storage URI using the Google Cloud Speech-to-Text API.
    The transcription results are stored in another Google Cloud Storage bucket.
    Args:
        audio_uri (str): The Google Cloud Storage URI of the input audio file.
            E.g., gs://[BUCKET]/[FILE]
        gcs_output_path (str): The Google Cloud Storage bucket URI where the output transcript will be stored.
            E.g., gs://[BUCKET]
    Returns:
        cloud_speech.BatchRecognizeResults: The response containing the URI of the transcription results.
    """
    # Instantiates a client
    client = SpeechClient()

    config = cloud_speech.RecognitionConfig(
        auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),
        language_codes=["en-US"],
        model="long",
    )

    file_metadata = cloud_speech.BatchRecognizeFileMetadata(uri=audio_uri)

    request = cloud_speech.BatchRecognizeRequest(
        recognizer=f"projects/{PROJECT_ID}/locations/global/recognizers/_",
        config=config,
        files=[file_metadata],
        recognition_output_config=cloud_speech.RecognitionOutputConfig(
            gcs_output_config=cloud_speech.GcsOutputConfig(
                uri=gcs_output_path,
            ),
        ),
    )

    # Transcribes the audio into text
    operation = client.batch_recognize(request=request)

    print("Waiting for operation to complete...")
    response = operation.result(timeout=120)

    file_results = response.results[audio_uri]

    print(f"Operation finished. Fetching results from {file_results.uri}...")
    output_bucket, output_object = re.match(
        r"gs://([^/]+)/(.*)", file_results.uri
    ).group(1, 2)

    # Instantiates a Cloud Storage client
    storage_client = storage.Client()

    # Fetch results from Cloud Storage
    bucket = storage_client.bucket(output_bucket)
    blob = bucket.blob(output_object)
    results_bytes = blob.download_as_bytes()
    batch_recognize_results = cloud_speech.BatchRecognizeResults.from_json(
        results_bytes, ignore_unknown_fields=True
    )

    for result in batch_recognize_results.results:
        print(f"Transcript: {result.alternatives[0].transcript}")

    return batch_recognize_results

Melakukan pengenalan batch pada beberapa file

Berikut adalah contoh cara melakukan pengenalan ucapan batch pada beberapa file audio di Cloud Storage dan membaca hasil transkripsi dari file output di Cloud Storage:

Python

import os
import re
from typing import List

from google.cloud import storage
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_batch_multiple_files_v2(
    audio_uris: List[str],
    gcs_output_path: str,
) -> cloud_speech.BatchRecognizeResponse:
    """Transcribes audio from multiple Google Cloud Storage URIs using the Google Cloud Speech-to-Text API.
    The transcription results are stored in another Google Cloud Storage bucket.
    Args:
        audio_uris (List[str]): The list of Google Cloud Storage URIs of the input audio files.
            E.g., ["gs://[BUCKET]/[FILE]", "gs://[BUCKET]/[FILE]"]
        gcs_output_path (str): The Google Cloud Storage bucket URI where the output transcript will be stored.
            E.g., gs://[BUCKET]
    Returns:
        cloud_speech.BatchRecognizeResponse: The response containing the URIs of the transcription results.
    """
    # Instantiates a client
    client = SpeechClient()

    config = cloud_speech.RecognitionConfig(
        auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),
        language_codes=["en-US"],
        model="long",
    )

    files = [cloud_speech.BatchRecognizeFileMetadata(uri=uri) for uri in audio_uris]

    request = cloud_speech.BatchRecognizeRequest(
        recognizer=f"projects/{PROJECT_ID}/locations/global/recognizers/_",
        config=config,
        files=files,
        recognition_output_config=cloud_speech.RecognitionOutputConfig(
            gcs_output_config=cloud_speech.GcsOutputConfig(
                uri=gcs_output_path,
            ),
        ),
    )

    # Transcribes the audio into text
    operation = client.batch_recognize(request=request)

    print("Waiting for operation to complete...")
    response = operation.result(timeout=120)

    print("Operation finished. Fetching results from:")
    for uri in audio_uris:
        file_results = response.results[uri]
        print(f"  {file_results.uri}...")
        output_bucket, output_object = re.match(
            r"gs://([^/]+)/(.*)", file_results.uri
        ).group(1, 2)

        # Instantiates a Cloud Storage client
        storage_client = storage.Client()

        # Fetch results from Cloud Storage
        bucket = storage_client.bucket(output_bucket)
        blob = bucket.blob(output_object)
        results_bytes = blob.download_as_bytes()
        batch_recognize_results = cloud_speech.BatchRecognizeResults.from_json(
            results_bytes, ignore_unknown_fields=True
        )

        for result in batch_recognize_results.results:
            print(f"     Transcript: {result.alternatives[0].transcript}")

    return response

Mengaktifkan pembuatan batch dinamis pada pengenalan batch

Pembuatan batch dinamis memungkinkan transkripsi dengan biaya yang lebih rendah untuk latensi yang lebih tinggi. Fitur ini hanya tersedia untuk pengenalan batch.

Berikut adalah contoh melakukan pengenalan batch pada file audio di Cloud Storage dengan mengaktifkan pembuatan batch dinamis:

Python

import os

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_batch_dynamic_batching_v2(
    audio_uri: str,
) -> cloud_speech.BatchRecognizeResults:
    """Transcribes audio from a Google Cloud Storage URI using dynamic batching.
    Args:
        audio_uri (str): The Cloud Storage URI of the input audio.
        E.g., gs://[BUCKET]/[FILE]
    Returns:
        cloud_speech.BatchRecognizeResults: The response containing the transcription results.
    """
    # Instantiates a client
    client = SpeechClient()

    config = cloud_speech.RecognitionConfig(
        auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),
        language_codes=["en-US"],
        model="long",
    )

    file_metadata = cloud_speech.BatchRecognizeFileMetadata(uri=audio_uri)

    request = cloud_speech.BatchRecognizeRequest(
        recognizer=f"projects/{PROJECT_ID}/locations/global/recognizers/_",
        config=config,
        files=[file_metadata],
        recognition_output_config=cloud_speech.RecognitionOutputConfig(
            inline_response_config=cloud_speech.InlineOutputConfig(),
        ),
        processing_strategy=cloud_speech.BatchRecognizeRequest.ProcessingStrategy.DYNAMIC_BATCHING,
    )

    # 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}")

    return response.results[audio_uri].transcript

Mengganti fitur pengenalan per file

Pengenalan batch secara default menggunakan konfigurasi pengenalan yang sama untuk setiap file dalam permintaan pengenalan batch. Jika file yang berbeda memerlukan konfigurasi atau fitur yang berbeda, konfigurasi dapat diganti per file menggunakan kolom config dalam pesan [BatchRecognizeFileMetadata][batch-file -metadata-grpc]. Lihat dokumentasi pengenal untuk mengetahui contoh penggantian fitur pengenalan.

Pembersihan

Agar akun Google Cloud Anda tidak dikenai biaya untuk resource yang digunakan di halaman ini, ikuti langkah-langkah berikut.

  1. Optional: Revoke the authentication credentials that you created, and delete the local credential file.

    gcloud auth application-default revoke
  2. Optional: Revoke credentials from the gcloud CLI.

    gcloud auth revoke

Konsol

  • In the Google Cloud console, go to the Manage resources page.

    Go to Manage resources

  • In the project list, select the project that you want to delete, and then click Delete.
  • In the dialog, type the project ID, and then click Shut down to delete the project.
  • gcloud

    Delete a Google Cloud project:

    gcloud projects delete PROJECT_ID

    Langkah berikutnya