importosfromgoogle.cloud.speech_v2importSpeechClientfromgoogle.cloud.speech_v2.typesimportcloud_speechfromgoogle.api_core.client_optionsimportClientOptionsPROJECT_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 clientclient=SpeechClient(client_options=ClientOptions(api_endpoint=f"{REGION}-speech.googleapis.com",))# Reads a file as byteswithopen(audio_file,"rb")asf:content=f.read()# In practice, stream should be a generator yielding chunks of audio datachunk_length=len(content)//5stream=[content[start:start+chunk_length]forstartinrange(0,len(content),chunk_length)]audio_requests=(cloud_speech.StreamingRecognizeRequest(audio=audio)foraudioinstream)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:yieldconfigyield fromaudio# Transcribes the audio into textresponses_iterator=client.streaming_recognize(requests=requests(config_request,audio_requests))responses=[]forresponseinresponses_iterator:responses.append(response)forresultinresponse.results:print(f"Transcript:{result.alternatives[0].transcript}")returnresponses

importosfromgoogle.cloud.speech_v2importSpeechClientfromgoogle.cloud.speech_v2.typesimportcloud_speechfromgoogle.api_core.client_optionsimportClientOptionsPROJECT_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 clientclient=SpeechClient(client_options=ClientOptions(api_endpoint=f"{REGION}-speech.googleapis.com",))# Reads a file as byteswithopen(audio_file,"rb")asf: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 textresponse=client.recognize(request=request)forresultinresponse.results:print(f"Transcript:{result.alternatives[0].transcript}")returnresponse

importosfromgoogle.cloud.speech_v2importSpeechClientfromgoogle.cloud.speech_v2.typesimportcloud_speechfromgoogle.api_core.client_optionsimportClientOptionsPROJECT_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 clientclient=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 textoperation=client.batch_recognize(request=request)print("Waiting for operation to complete...")response=operation.result(timeout=120)forresultinresponse.results[audio_uri].transcript.results:print(f"Transcript:{result.alternatives[0].transcript}")returnresponse.results[audio_uri].transcript

importosfromgoogle.cloud.speech_v2importSpeechClientfromgoogle.cloud.speech_v2.typesimportcloud_speechfromgoogle.api_core.client_optionsimportClientOptionsPROJECT_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 clientclient=SpeechClient(client_options=ClientOptions(api_endpoint=f"{REGION}-speech.googleapis.com",))# Reads a file as byteswithopen(audio_file,"rb")asf: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 textresponse=client.recognize(request=request)forresultinresponse.results:print(f"Transcript:{result.alternatives[0].transcript}")print(f"Detected Language:{result.language_code}")returnresponse

importosfromgoogle.cloud.speech_v2importSpeechClientfromgoogle.cloud.speech_v2.typesimportcloud_speechfromgoogle.api_core.client_optionsimportClientOptionsPROJECT_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 clientclient=SpeechClient(client_options=ClientOptions(api_endpoint=f"{REGION}-speech.googleapis.com",))# Reads a file as byteswithopen(audio_file,"rb")asf: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 localesmodel="chirp_3",)request=cloud_speech.RecognizeRequest(recognizer=f"projects/{PROJECT_ID}/locations/{REGION}/recognizers/_",config=config,content=audio_content,)# Transcribes the audio into textresponse=client.recognize(request=request)forresultinresponse.results:print(f"Transcript:{result.alternatives[0].transcript}")print(f"Detected Language:{result.language_code}")returnresponse

importosfromgoogle.cloud.speech_v2importSpeechClientfromgoogle.cloud.speech_v2.typesimportcloud_speechfromgoogle.api_core.client_optionsimportClientOptionsPROJECT_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)forresultinresponse.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}")returnresponse.results[audio_uri].transcript