import("context""fmt""io""os""strings"speech"cloud.google.com/go/speech/apiv1""cloud.google.com/go/speech/apiv1/speechpb")// transcribe_diarization_gcs_beta Transcribes a remote audio file using speaker diarization.functranscribe_diarization(wio.Writer)error{ctx:=context.Background()client,err:=speech.NewClient(ctx)iferr!=nil{returnfmt.Errorf("NewClient: %w",err)}deferclient.Close()diarizationConfig:=&speechpb.SpeakerDiarizationConfig{EnableSpeakerDiarization:true,MinSpeakerCount:2,MaxSpeakerCount:2,}recognitionConfig:=&speechpb.RecognitionConfig{Encoding:speechpb.RecognitionConfig_LINEAR16,SampleRateHertz:8000,LanguageCode:"en-US",DiarizationConfig:diarizationConfig,}// Get the contents of the local audio filecontent,err:=os.ReadFile("../resources/commercial_mono.wav")iferr!=nil{returnfmt.Errorf("error reading file %w",err)}audio:=&speechpb.RecognitionAudio{AudioSource:&speechpb.RecognitionAudio_Content{Content:content},}longRunningRecognizeRequest:=&speechpb.LongRunningRecognizeRequest{Config:recognitionConfig,Audio:audio,}operation,err:=client.LongRunningRecognize(ctx,longRunningRecognizeRequest)iferr!=nil{returnfmt.Errorf("error running recognize %w",err)}response,err:=operation.Wait(ctx)iferr!=nil{returnerr}// Speaker Tags are only included in the last result object, which has only one// alternative.alternative:=response.Results[len(response.Results)-1].Alternatives[0]wordInfo:=alternative.GetWords()[0]currentSpeakerTag:=wordInfo.GetSpeakerTag()varspeakerWordsstrings.BuilderspeakerWords.WriteString(fmt.Sprintf("Speaker %d: %s",wordInfo.GetSpeakerTag(),wordInfo.GetWord()))// For each word, get all the words associated with one speaker, once the speaker changes,// add a new line with the new speaker and their spoken words.fori:=1;i <len(alternative.Words);i++{wordInfo:=alternative.Words[i]ifcurrentSpeakerTag==wordInfo.GetSpeakerTag(){speakerWords.WriteString(" ")speakerWords.WriteString(wordInfo.GetWord())}else{speakerWords.WriteString(fmt.Sprintf("\nSpeaker %d: %s",wordInfo.GetSpeakerTag(),wordInfo.GetWord()))currentSpeakerTag=wordInfo.GetSpeakerTag()}}fmt.Fprint(w,speakerWords.String())returnnil}

fromgoogle.cloudimportspeech_v1p1beta1asspeechclient=speech.SpeechClient()speech_file="resources/commercial_mono.wav"withopen(speech_file,"rb")asaudio_file:content=audio_file.read()audio=speech.RecognitionAudio(content=content)diarization_config=speech.SpeakerDiarizationConfig(enable_speaker_diarization=True,min_speaker_count=2,max_speaker_count=10,)config=speech.RecognitionConfig(encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,sample_rate_hertz=8000,language_code="en-US",diarization_config=diarization_config,)print("Waiting for operation to complete...")response=client.recognize(config=config,audio=audio)# The transcript within each result is separate and sequential per result.# However, the words list within an alternative includes all the words# from all the results thus far. Thus, to get all the words with speaker# tags, you only have to take the words list from the last result:result=response.results[-1]words_info=result.alternatives[0].words# Printing out the output:forword_infoinwords_info:print(f"word: '{word_info.word}', speaker_tag:{word_info.speaker_tag}")returnresult