Chirp 3 Transcription: Enhanced multilingual accuracy

importos
fromgoogle.cloud.speech_v2import SpeechClient
fromgoogle.cloud.speech_v2.typesimport cloud_speech
fromgoogle.api_core.client_optionsimport ClientOptions
PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")
REGION = "us"
deftranscribe_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,
 )
 defrequests(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

importos
fromgoogle.cloud.speech_v2import SpeechClient
fromgoogle.cloud.speech_v2.typesimport cloud_speech
fromgoogle.api_core.client_optionsimport ClientOptions
PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")
REGION = "us"
deftranscribe_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

importos
fromgoogle.cloud.speech_v2import SpeechClient
fromgoogle.cloud.speech_v2.typesimport cloud_speech
fromgoogle.api_core.client_optionsimport ClientOptions
PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")
REGION = "us"
deftranscribe_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

importos
fromgoogle.cloud.speech_v2import SpeechClient
fromgoogle.cloud.speech_v2.typesimport cloud_speech
fromgoogle.api_core.client_optionsimport ClientOptions
PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")
REGION = "us"
deftranscribe_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

importos
fromgoogle.cloud.speech_v2import SpeechClient
fromgoogle.cloud.speech_v2.typesimport cloud_speech
fromgoogle.api_core.client_optionsimport ClientOptions
PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")
REGION = "us"
deftranscribe_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

importos
fromgoogle.cloud.speech_v2import SpeechClient
fromgoogle.cloud.speech_v2.typesimport cloud_speech
fromgoogle.api_core.client_optionsimport ClientOptions
PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")
REGION = "us"
deftranscribe_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

importos
fromgoogle.cloud.speech_v2import SpeechClient
fromgoogle.cloud.speech_v2.typesimport cloud_speech
fromgoogle.api_core.client_optionsimport ClientOptions
PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")
REGION = "us"
deftranscribe_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

 importos
 fromgoogle.cloud.speech_v2import SpeechClient
 fromgoogle.cloud.speech_v2.typesimport cloud_speech
 fromgoogle.api_core.client_optionsimport ClientOptions
 PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")
 REGION = "us"
deftranscribe_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,
 # Medium snr threshold
 snr_threshold: 20.0,
 }
 )
 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