Trascrivere l'audio da un file video utilizzando Speech-to-Text

func modelSelection(w io.Writer) error {
	ctx := context.Background()

	client, err := speech.NewClient(ctx)
	if err != nil {
		return fmt.Errorf("NewClient: %w", err)
	}
	defer client.Close()

	data, err := ioutil.ReadFile("../testdata/Google_Gnome.wav")
	if err != nil {
		return fmt.Errorf("ReadFile: %w", err)
	}

	req := &speechpb.RecognizeRequest{
		Config: &speechpb.RecognitionConfig{
			Encoding:        speechpb.RecognitionConfig_LINEAR16,
			SampleRateHertz: 16000,
			LanguageCode:    "en-US",
			Model:           "video",
		},
		Audio: &speechpb.RecognitionAudio{
			AudioSource: &speechpb.RecognitionAudio_Content{Content: data},
		},
	}

	resp, err := client.Recognize(ctx, req)
	if err != nil {
		return fmt.Errorf("Recognize: %w", err)
	}

	for i, result := range resp.Results {
		fmt.Fprintf(w, "%s\n", strings.Repeat("-", 20))
		fmt.Fprintf(w, "Result %d\n", i+1)
		for j, alternative := range result.Alternatives {
			fmt.Fprintf(w, "Alternative %d: %s\n", j+1, alternative.Transcript)
		}
	}
	return nil
}

/**
 * Performs transcription of the given audio file synchronously with the selected model.
 *
 * @param fileName the path to a audio file to transcribe
 */
public static void transcribeModelSelection(String fileName) throws Exception {
  Path path = Paths.get(fileName);
  byte[] content = Files.readAllBytes(path);

  try (SpeechClient speech = SpeechClient.create()) {
    // Configure request with video media type
    RecognitionConfig recConfig =
        RecognitionConfig.newBuilder()
            // encoding may either be omitted or must match the value in the file header
            .setEncoding(AudioEncoding.LINEAR16)
            .setLanguageCode("en-US")
            // sample rate hertz may be either be omitted or must match the value in the file
            // header
            .setSampleRateHertz(16000)
            .setModel("video")
            .build();

    RecognitionAudio recognitionAudio =
        RecognitionAudio.newBuilder().setContent(ByteString.copyFrom(content)).build();

    RecognizeResponse recognizeResponse = speech.recognize(recConfig, recognitionAudio);
    // Just print the first result here.
    SpeechRecognitionResult result = recognizeResponse.getResultsList().get(0);
    // There can be several alternative transcripts for a given chunk of speech. Just use the
    // first (most likely) one here.
    SpeechRecognitionAlternative alternative = result.getAlternativesList().get(0);
    System.out.printf("Transcript : %s\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
 */
const speech = require('@google-cloud/speech').v1p1beta1;
const fs = require('fs');

// Creates a client
const client = new speech.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 model = 'Model to use, e.g. phone_call, video, default';
// const encoding = 'Encoding of the audio file, e.g. LINEAR16';
// const sampleRateHertz = 16000;
// const languageCode = 'BCP-47 language code, e.g. en-US';

const config = {
  encoding: encoding,
  sampleRateHertz: sampleRateHertz,
  languageCode: languageCode,
  model: model,
};
const audio = {
  content: fs.readFileSync(filename).toString('base64'),
};

const request = {
  config: config,
  audio: audio,
};

// Detects speech in the audio file
const [response] = await client.recognize(request);
const transcription = response.results
  .map(result => result.alternatives[0].transcript)
  .join('\n');
console.log('Transcription: ', transcription);

from google.cloud import speech

# Instantiates a client
client = speech.SpeechClient()
# Reads a file as bytes
with open("resources/Google_Gnome.wav", "rb") as f:
    audio_content = f.read()

audio = speech.RecognitionAudio(content=audio_content)

config = speech.RecognitionConfig(
    encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
    sample_rate_hertz=16000,
    language_code="en-US",
    model="video",  # Chosen model
)

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}")

import (
	"context"
	"fmt"
	"io"
	"strings"

	speech "cloud.google.com/go/speech/apiv1"
	"cloud.google.com/go/speech/apiv1/speechpb"
)

// transcribe_model_selection_gcs Transcribes the given audio file asynchronously with
// the selected model.
func transcribe_model_selection_gcs(w io.Writer) error {
	ctx := context.Background()

	client, err := speech.NewClient(ctx)
	if err != nil {
		return fmt.Errorf("NewClient: %w", err)
	}
	defer client.Close()

	audio := &speechpb.RecognitionAudio{
		AudioSource: &speechpb.RecognitionAudio_Uri{Uri: "gs://cloud-samples-tests/speech/Google_Gnome.wav"},
	}

	// The speech recognition model to use
	// See, https://cloud.google.com/speech-to-text/docs/speech-to-text-requests#select-model
	recognitionConfig := &speechpb.RecognitionConfig{
		Encoding:        speechpb.RecognitionConfig_LINEAR16,
		SampleRateHertz: 16000,
		LanguageCode:    "en-US",
		Model:           "video",
	}

	longRunningRecognizeRequest := &speechpb.LongRunningRecognizeRequest{
		Config: recognitionConfig,
		Audio:  audio,
	}

	operation, err := client.LongRunningRecognize(ctx, longRunningRecognizeRequest)
	if err != nil {
		return fmt.Errorf("error running recognize %w", err)
	}

	response, err := operation.Wait(ctx)
	if err != nil {
		return err
	}
	for i, result := range response.Results {
		alternative := result.Alternatives[0]
		fmt.Fprintf(w, "%s\n", strings.Repeat("-", 20))
		fmt.Fprintf(w, "First alternative of result %d", i)
		fmt.Fprintf(w, "Transcript: %s", alternative.Transcript)
	}
	return nil
}

/**
 * Performs transcription of the remote audio file asynchronously with the selected model.
 *
 * @param gcsUri the path to the remote audio file to transcribe.
 */
public static void transcribeModelSelectionGcs(String gcsUri) throws Exception {
  try (SpeechClient speech = SpeechClient.create()) {

    // Configure request with video media type
    RecognitionConfig config =
        RecognitionConfig.newBuilder()
            // encoding may either be omitted or must match the value in the file header
            .setEncoding(AudioEncoding.LINEAR16)
            .setLanguageCode("en-US")
            // sample rate hertz may be either be omitted or must match the value in the file
            // header
            .setSampleRateHertz(16000)
            .setModel("video")
            .build();

    RecognitionAudio audio = RecognitionAudio.newBuilder().setUri(gcsUri).build();

    // Use non-blocking call for getting file transcription
    OperationFuture<LongRunningRecognizeResponse, LongRunningRecognizeMetadata> response =
        speech.longRunningRecognizeAsync(config, audio);

    while (!response.isDone()) {
      System.out.println("Waiting for response...");
      Thread.sleep(10000);
    }

    List<SpeechRecognitionResult> results = response.get().getResultsList();

    // Just print the first result here.
    SpeechRecognitionResult result = results.get(0);
    // There can be several alternative transcripts for a given chunk of speech. Just use the
    // first (most likely) one here.
    SpeechRecognitionAlternative alternative = result.getAlternativesList().get(0);
    System.out.printf("Transcript : %s\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
 */
const speech = require('@google-cloud/speech').v1p1beta1;

// Creates a client
const client = new speech.SpeechClient();

/**
 * TODO(developer): Uncomment the following lines before running the sample.
 */
// const gcsUri = 'gs://my-bucket/audio.raw';
// const model = 'Model to use, e.g. phone_call, video, default';
// const encoding = 'Encoding of the audio file, e.g. LINEAR16';
// const sampleRateHertz = 16000;
// const languageCode = 'BCP-47 language code, e.g. en-US';

const config = {
  encoding: encoding,
  sampleRateHertz: sampleRateHertz,
  languageCode: languageCode,
  model: model,
};
const audio = {
  uri: gcsUri,
};

const request = {
  config: config,
  audio: audio,
};

// Detects speech in the audio file.
const [response] = await client.recognize(request);
const transcription = response.results
  .map(result => result.alternatives[0].transcript)
  .join('\n');
console.log('Transcription: ', transcription);

from google.cloud import speech

client = speech.SpeechClient()

audio = speech.RecognitionAudio(
    uri="gs://cloud-samples-tests/speech/Google_Gnome.wav"
)

config = speech.RecognitionConfig(
    encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
    sample_rate_hertz=16000,
    language_code="en-US",
    model="video",  # Chosen model
)

operation = client.long_running_recognize(config=config, audio=audio)

print("Waiting for operation to complete...")
response = operation.result(timeout=90)

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}")