Chirp 3 轉錄：提升多語言準確率

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")
REGION = "us"

def transcribe_streaming_chirp3(
   audio_file: str
) -> cloud_speech.StreamingRecognizeResponse:
   """Transcribes audio from audio file stream using the Chirp 3 model of Google Cloud Speech-to-Text v2 API.

   Args:
       audio_file (str): Path to the local audio file to be transcribed.
           Example: "resources/audio.wav"

   Returns:
       cloud_speech.RecognizeResponse: The response from the Speech-to-Text API V2 containing
       the transcription results.
   """

   # Instantiates a client
   client = SpeechClient(
       client_options=ClientOptions(
           api_endpoint=f"{REGION}-speech.googleapis.com",
       )
   )

   # Reads a file as bytes
   with open(audio_file, "rb") as f:
       content = f.read()

   # In practice, stream should be a generator yielding chunks of audio data
   chunk_length = len(content) // 5
   stream = [
       content[start : start + chunk_length]
       for start in range(0, len(content), chunk_length)
   ]
   audio_requests = (
       cloud_speech.StreamingRecognizeRequest(audio=audio) for audio in stream
   )

   recognition_config = cloud_speech.RecognitionConfig(
       auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),
       language_codes=["en-US"],
       model="chirp_3",
   )
   streaming_config = cloud_speech.StreamingRecognitionConfig(
       config=recognition_config
   )
   config_request = cloud_speech.StreamingRecognizeRequest(
       recognizer=f"projects/{PROJECT_ID}/locations/{REGION}/recognizers/_",
       streaming_config=streaming_config,
   )

   def requests(config: cloud_speech.RecognitionConfig, audio: list) -> list:
       yield config
       yield from audio

   # Transcribes the audio into text
   responses_iterator = client.streaming_recognize(
       requests=requests(config_request, audio_requests)
   )
   responses = []
   for response in responses_iterator:
       responses.append(response)
       for result in response.results:
           print(f"Transcript: {result.alternatives[0].transcript}")

   return responses

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")
REGION = "us"

def transcribe_sync_chirp3(
   audio_file: str
) -> cloud_speech.RecognizeResponse:
   """Transcribes an audio file using the Chirp 3 model of Google Cloud Speech-to-Text V2 API.
   Args:
       audio_file (str): Path to the local audio file to be transcribed.
           Example: "resources/audio.wav"
   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=f"{REGION}-speech.googleapis.com",
       )
   )

   # Reads a file as bytes
   with open(audio_file, "rb") as f:
       audio_content = f.read()

   config = cloud_speech.RecognitionConfig(
       auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),
       language_codes=["en-US"],
       model="chirp_3",
   )

   request = cloud_speech.RecognizeRequest(
       recognizer=f"projects/{PROJECT_ID}/locations/{REGION}/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

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")
REGION = "us"

def transcribe_batch_3(
   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=f"{REGION}-speech.googleapis.com",
       )
   )

   config = cloud_speech.RecognitionConfig(
       auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),
       language_codes=["en-US"],
       model="chirp_3",
   )

   file_metadata = cloud_speech.BatchRecognizeFileMetadata(uri=audio_uri)

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

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")
REGION = "us"

def transcribe_sync_chirp3_auto_detect_language(
   audio_file: str
) -> cloud_speech.RecognizeResponse:
   """Transcribes an audio file and auto-detect spoken language using Chirp 3.
   Please see https://cloud.google.com/speech-to-text/docs/encoding for more
   information on which audio encodings are supported.
   Args:
       audio_file (str): Path to the local audio file to be transcribed.
           Example: "resources/audio.wav"
   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=f"{REGION}-speech.googleapis.com",
       )
   )

   # Reads a file as bytes
   with open(audio_file, "rb") as f:
       audio_content = f.read()

   config = cloud_speech.RecognitionConfig(
       auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),
       language_codes=["auto"],  # Set language code to auto to detect language.
       model="chirp_3",
   )

   request = cloud_speech.RecognizeRequest(
       recognizer=f"projects/{PROJECT_ID}/locations/{REGION}/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}")
       print(f"Detected Language: {result.language_code}")

   return response

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")
REGION = "us"

def transcribe_sync_3_auto_detect_language(
   audio_file: str
) -> cloud_speech.RecognizeResponse:
   """Transcribes an audio file and auto-detect spoken language using Chirp 3.
   Please see https://cloud.google.com/speech-to-text/docs/encoding for more
   information on which audio encodings are supported.
   Args:
       audio_file (str): Path to the local audio file to be transcribed.
           Example: "resources/audio.wav"
   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=f"{REGION}-speech.googleapis.com",
       )
   )

   # Reads a file as bytes
   with open(audio_file, "rb") as f:
       audio_content = f.read()

   config = cloud_speech.RecognitionConfig(
       auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),
       language_codes=["en-US", "fr-FR"],  # Set language codes of the expected spoken locales
       model="chirp_3",
   )

   request = cloud_speech.RecognizeRequest(
       recognizer=f"projects/{PROJECT_ID}/locations/{REGION}/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}")
       print(f"Detected Language: {result.language_code}")

   return response

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")
REGION = "us"

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=f"{REGION}-speech.googleapis.com",
       )
   )

   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(
           # Enable diarization by setting empty diarization configuration.
           diarization_config=cloud_speech.SpeakerDiarizationConfig(),
       ),
   )

   file_metadata = cloud_speech.BatchRecognizeFileMetadata(uri=audio_uri)

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

   # Creates audio transcription job.
   operation = client.batch_recognize(request=request)

   print("Waiting for transcription job 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

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")
REGION = "us"

def transcribe_sync_chirp3_model_adaptation(
   audio_file: str
) -> cloud_speech.RecognizeResponse:
   """Transcribes an audio file using the Chirp 3 model with adaptation, improving accuracy for specific audio characteristics or vocabulary.
   Args:
       audio_file (str): Path to the local audio file to be transcribed.
           Example: "resources/audio.wav"
   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=f"{REGION}-speech.googleapis.com",
       )
   )

   # Reads a file as bytes
   with open(audio_file, "rb") as f:
       audio_content = f.read()

   config = cloud_speech.RecognitionConfig(
       auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),
       language_codes=["en-US"],
       model="chirp_3",
       # Use model adaptation
       adaptation=cloud_speech.SpeechAdaptation(
         phrase_sets=[
             cloud_speech.SpeechAdaptation.AdaptationPhraseSet(
                 inline_phrase_set=cloud_speech.PhraseSet(phrases=[
                   {
                       "value": "alphabet",
                   },
                   {
                         "value": "cell phone service",
                   }
                 ])
             )
         ]
       )
   )

   request = cloud_speech.RecognizeRequest(
       recognizer=f"projects/{PROJECT_ID}/locations/{REGION}/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

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")
REGION = "us"

def transcribe_sync_chirp3_custom_prompt(
 audio_file: str,
 custom_prompt: str,
 ) -> cloud_speech.RecognizeResponse:
     """Transcribes an audio file and auto-detect spoken language using Chirp 3.
     Args:
         audio_file (str): Path to the local audio file to be transcribed.
             Example: "resources/audio.wav"
         custom_prompt: the customized formatting instructions.
             Example: "Capitalize the following special words: GOOGLE, CHIRP."
             Example: "For dates don't use the 'December 23rd, 1939' format!
             But strictly use the '12/23/1939' format."
     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=f"{REGION}-speech.googleapis.com",
         )
     )

     # Reads a file as bytes
     with open(audio_file, "rb") as f:
         audio_content = f.read()

     config = cloud_speech.RecognitionConfig(
         auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),
         language_codes=["en-US"],
         model="chirp_3",
         features=cloud_speech.RecognitionFeatures(
             custom_prompt_config=cloud_speech.CustomPromptConfig(
                 custom_prompt= custom_prompt,
             )
         ),
     )

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

     # Transcribes the audio into text
     response = client.recognize(request=request)
     print(f"Prompt used: {response.metadata.prompt}")

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

     return response

 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")
 REGION = "us"

def transcribe_sync_chirp3_with_timestamps(
   audio_file: str
) -> cloud_speech.RecognizeResponse:
   """Transcribes an audio file using the Chirp 3 model of Google Cloud Speech-to-Text v2 API, which provides word-level timestamps for each transcribed word.
   Args:
       audio_file (str): Path to the local audio file to be transcribed.
           Example: "resources/audio.wav"
   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=f"{REGION}-speech.googleapis.com",
       )
   )

   # Reads a file as bytes
   with open(audio_file, "rb") as f:
       audio_content = f.read()

   config = cloud_speech.RecognitionConfig(
       auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),
       language_codes=["en-US"],
       model="chirp_3",
       denoiser_config={
           denoise_audio: True,
           snr_threshold: 0.0, # snr_threshold is deprecated in Chirp3; set to 0.0 to maintain compatibility.
       }
   )

   request = cloud_speech.RecognizeRequest(
       recognizer=f"projects/{PROJECT_ID}/locations/{REGION}/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

import time
from google.api_core.client_options import ClientOptions
from google.cloud import speech_v2

RATE = 16000

def transcribe_streaming(
    project_id: str,
    audio_file: str,
    # 'us' is a multi-region that currently supports the 'chirp_3' model.
    # Other valid regions include 'eu' or specific regions like 'asia-southeast1'.
    region: str = "us"
):
    recognizer_path = f"projects/{project_id}/locations/{region}/recognizers/_"

    # Setup client with the correct regional endpoint
    client = speech_v2.SpeechClient(
        client_options=ClientOptions(
            api_endpoint=f"{region}-speech.googleapis.com",
            quota_project_id=project_id
        )
    )

    recognition_config_obj = speech_v2.RecognitionConfig(
        explicit_decoding_config=speech_v2.ExplicitDecodingConfig(
            encoding=speech_v2.ExplicitDecodingConfig.AudioEncoding.LINEAR16,
            sample_rate_hertz=RATE,
            audio_channel_count=1,
        ),
        language_codes=["en-US"],
        model="chirp_3",
        features=speech_v2.RecognitionFeatures(
            enable_automatic_punctuation=True,
        ),
    )

    config_request = speech_v2.StreamingRecognizeRequest(
        recognizer=recognizer_path,
        streaming_config=speech_v2.StreamingRecognitionConfig(
            config=recognition_config_obj,
            streaming_features=speech_v2.StreamingRecognitionFeatures(
                interim_results=False,
                enable_voice_activity_events=True,
                # Set sensitivity to SUPERSHORT (Low Latency)
                endpointing_sensitivity=speech_v2.StreamingRecognitionFeatures.EndpointingSensitivity.ENDPOINTING_SENSITIVITY_SUPERSHORT,
            ),
        )
    )

    def request_generator():
        yield config_request
        with open(audio_file, "rb") as f:
            while chunk := f.read(4096):
                yield speech_v2.StreamingRecognizeRequest(audio=chunk)

    start_time = time.time()

    print(f"Streaming audio to {region}-speech.googleapis.com...")

    for response in client.streaming_recognize(requests=request_generator()):
        if response.results:
            for result in response.results:
                if result.is_final:
                    print(f"Transcript: {result.alternatives[0].transcript}")
                    print(f"Time taken: {time.time() - start_time:.3f}s")

def main() -> None:
    # TODO: Replace with your Project ID and File Path
    PROJECT_ID = "your-project-id"
    AUDIO_FILE_PATH = "path/to/your/audio.wav"

    transcribe_streaming(
        project_id=PROJECT_ID,
        audio_file=AUDIO_FILE_PATH
    )

if __name__ == "__main__":
    main()