Recognize speech by using enhanced models

funcenhancedModel(wio.Writer)error{
ctx:=context.Background()
client,err:=speech.NewClient(ctx)
iferr!=nil{
returnfmt.Errorf("NewClient: %w",err)
}
deferclient.Close()
data,err:=os.ReadFile("../testdata/commercial_mono.wav")
iferr!=nil{
returnfmt.Errorf("ReadFile: %w",err)
}
resp,err:=client.Recognize(ctx,&speechpb.RecognizeRequest{
Config:&speechpb.RecognitionConfig{
Encoding:speechpb.RecognitionConfig_LINEAR16,
SampleRateHertz:8000,
LanguageCode:"en-US",
UseEnhanced:true,
// A model must be specified to use enhanced model.
Model:"phone_call",
},
Audio:&speechpb.RecognitionAudio{
AudioSource:&speechpb.RecognitionAudio_Content{Content:data},
},
})
iferr!=nil{
returnfmt.Errorf("client.Recognize: %w",err)
}
fori,result:=rangeresp.Results{
fmt.Fprintf(w,"%s\n",strings.Repeat("-",20))
fmt.Fprintf(w,"Result %d\n",i+1)
forj,alternative:=rangeresult.Alternatives{
fmt.Fprintf(w,"Alternative %d: %s\n",j+1,alternative.Transcript)
}
}
returnnil
}

fromgoogle.cloudimport speech
deftranscribe_file_with_enhanced_model(audio_file: str) -> speech.RecognizeResponse:
"""Transcribe the given audio file using an enhanced model.
 Args:
 audio_file (str): Path to the local audio file to be transcribed.
 Example: "resources/commercial_mono.wav"
 Returns:
 speech.RecognizeResponse: The response containing the transcription results.
 """
 client = speech.SpeechClient()
 # audio_file = 'resources/commercial_mono.wav'
 with open(audio_file, "rb") as f:
 audio_content = f.read()
 audio = speech.RecognitionAudio(content=audio_content)
 config = speech.RecognitionConfig(
 encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
 sample_rate_hertz=8000,
 language_code="en-US",
 use_enhanced=True,
 # A model must be specified to use enhanced model.
 model="phone_call",
 )
 response = client.recognize(config=config, audio=audio)
 for i, result in enumerate(response.results):
 alternative = result.alternatives[0]
 print("-" * 20)
 print(f"First alternative of result {i}")
 print(f"Transcript: {alternative.transcript}")
 return response

/**
 * Transcribe the given audio file using an enhanced model.
 *
 * @param fileName the path to an audio file.
 */
publicstaticvoidtranscribeFileWithEnhancedModel(StringfileName)throwsException{
Pathpath=Paths.get(fileName);
byte[]content=Files.readAllBytes(path);
try(SpeechClientspeechClient=SpeechClient.create()){
// Get the contents of the local audio file
RecognitionAudiorecognitionAudio=
RecognitionAudio.newBuilder().setContent(ByteString.copyFrom(content)).build();
// Configure request to enable enhanced models
RecognitionConfigconfig=
RecognitionConfig.newBuilder()
.setEncoding(AudioEncoding.LINEAR16)
.setLanguageCode("en-US")
.setSampleRateHertz(8000)
.setUseEnhanced(true)
// A model must be specified to use enhanced model.
.setModel("phone_call")
.build();
// Perform the transcription request
RecognizeResponserecognizeResponse=speechClient.recognize(config,recognitionAudio);
// Print out the results
for(SpeechRecognitionResultresult:recognizeResponse.getResultsList()){
// There can be several alternative transcripts for a given chunk of speech. Just use the
// first (most likely) one here.
SpeechRecognitionAlternativealternative=result.getAlternatives(0);
System.out.format("Transcript: %s\n\n",alternative.getTranscript());
}
}
}

// Imports the Google Cloud client library for Beta API
/**
 * TODO(developer): Update client library import to use new
 * version of API when desired features become available
 */
constspeech=require('@google-cloud/speech').v1p1beta1;
constfs=require('fs');
// Creates a client
constclient=newspeech.SpeechClient ();
/**
 * TODO(developer): Uncomment the following lines before running the sample.
 */
// const filename = 'Local path to audio file, e.g. /path/to/audio.raw';
// const encoding = 'Encoding of the audio file, e.g. LINEAR16';
// const sampleRateHertz = 16000;
// const languageCode = 'BCP-47 language code, e.g. en-US';
constconfig={
encoding:encoding,
languageCode:languageCode,
useEnhanced:true,
model:'phone_call',
};
constaudio={
content:fs.readFileSync(filename).toString('base64'),
};
constrequest={
config:config,
audio:audio,
};
// Detects speech in the audio file
const[response]=awaitclient.recognize(request);
response.results.forEach(result=>{
constalternative=result.alternatives[0];
console.log(alternative.transcript);
});