從 Speech-to-Text v1 遷移至 v2

Speech-to-Text API v2 採用最新的 Google Cloud API 設計，可滿足企業安全性和法規要求。

這些要求是透過下列方式實現：

  • 資料落地：Speech-to-Text v2 提供現有語音轉錄模型的大範圍支援，包括Google Cloud 比利時或新加坡等區域。這可讓您透過完全區域化的服務叫用語音轉錄模型。

  • 辨識器資源：辨識器是可重複使用的辨識設定，可包含模型、語言和特徵的組合。這項資源豐富的實作方式可讓您不必使用專用的服務帳戶進行驗證和授權。

  • 記錄：資源建立和轉錄作業會產生記錄，並顯示在 Google Cloud 控制台中，方便您進行遙測和偵錯。

  • 加密：Speech-to-Text v2 支援客戶自行管理的加密金鑰，適用於所有資源和批次語音轉錄功能。

  • 音訊自動偵測：語音轉文字 V2 可自動偵測音訊檔案的取樣率、聲道數和格式，無須在要求設定中提供這項資訊。

從 v1 遷移至 v2

系統不會自動從 v1 API 遷移至 v2 API。如要使用這組功能，只需進行最少的實作變更。

透過 API 遷移

與 Speech-to-Text v1 類似，如要轉錄音訊，您需要選取音訊語言和所選的辨識模型，藉此建立 RecognitionConfig：

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 quickstart_v2(audio_file: str) -> cloud_speech.RecognizeResponse:
    """Transcribe an audio file.
    Args:
        audio_file (str): Path to the local audio file to be transcribed.
    Returns:
        cloud_speech.RecognizeResponse: The response from the recognize request, containing
        the transcription results
    """
    # Reads a file as bytes
    with open(audio_file, "rb") as f:
        audio_content = f.read()

    # Instantiates a client
    client = SpeechClient()

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

    request = cloud_speech.RecognizeRequest(
        recognizer=f"projects/{PROJECT_ID}/locations/global/recognizers/_",
        config=config,
        content=audio_content,
    )

    # Transcribes the audio into text
    response = client.recognize(request=request)

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

    return response

如有需要，請選取要使用 Speech-to-Text API 的區域，並檢查該區域的語言和模型適用情形：

Python

import os

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

PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")


def change_speech_v2_location(
    audio_file: str, location: str
) -> cloud_speech.RecognizeResponse:
    """Transcribe an audio file in a specific region. It allows for specifying the location
        to potentially reduce latency and meet data residency requirements.
    Args:
        audio_file (str): Path to the local audio file to be transcribed.
        location (str): The region where the Speech API will be accessed.
            E.g., "europe-west3"
    Returns:
        cloud_speech.RecognizeResponse: The full response object which includes the transcription results.
    """
    # Reads a file as bytes
    with open(audio_file, "rb") as f:
        audio_content = f.read()

    # Instantiates a client to a regionalized Speech endpoint.
    client = SpeechClient(
        client_options=ClientOptions(
            api_endpoint=f"{location}-speech.googleapis.com",
        )
    )

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

    request = cloud_speech.RecognizeRequest(
        recognizer=f"projects/{PROJECT_ID}/locations/{location}/recognizers/_",
        config=config,
        content=audio_content,
    )

    # Transcribes the audio into text
    response = client.recognize(request=request)

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

如果需要在多個語音轉錄要求中重複使用特定辨識設定，可以選擇建立辨識工具資源：

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 create_recognizer(recognizer_id: str) -> cloud_speech.Recognizer:
    """Сreates a recognizer with an unique ID and default recognition configuration.
    Args:
        recognizer_id (str): The unique identifier for the recognizer to be created.
    Returns:
        cloud_speech.Recognizer: The created recognizer object with configuration.
    """
    # Instantiates a client
    client = SpeechClient()

    request = cloud_speech.CreateRecognizerRequest(
        parent=f"projects/{PROJECT_ID}/locations/global",
        recognizer_id=recognizer_id,
        recognizer=cloud_speech.Recognizer(
            default_recognition_config=cloud_speech.RecognitionConfig(
                language_codes=["en-US"], model="long"
            ),
        ),
    )
    # Sends the request to create a recognizer and waits for the operation to complete
    operation = client.create_recognizer(request=request)
    recognizer = operation.result()

    print("Created Recognizer:", recognizer.name)
    return recognizer

新版 v2 API 的要求和回應也有其他差異。 詳情請參閱參考說明文件。

在 UI 中遷移

如要透過 Speech Google Cloud 控制台遷移，請按照下列步驟操作：

  1. 前往 Speech Google Cloud 主控台。

  2. 前往「轉錄稿」頁面。

  3. 按一下「新增轉錄稿」，然後在「音訊設定」分頁中選取音訊。

  4. 在「Transcription options」(語音轉錄選項) 分頁中，選取「V2」。