写真のテキストの翻訳

import html
import os

# Imports the Google Cloud client libraries
from google.api_core.exceptions import AlreadyExists
from google.cloud import texttospeech
from google.cloud import translate_v3beta1 as translate
from google.cloud import vision

// Imports the Google Cloud client library
const textToSpeech = require('@google-cloud/text-to-speech');
const translate = require('@google-cloud/translate').v3beta1;
const vision = require('@google-cloud/vision');

// Import other required libraries
const fs = require('fs');
//const escape = require('escape-html');
const util = require('util');

def pic_to_text(infile: str) -> str:
    """Detects text in an image file

    Args:
    infile: path to image file

    Returns:
    String of text detected in image
    """

    # Instantiates a client
    client = vision.ImageAnnotatorClient()

    # Opens the input image file
    with open(infile, "rb") as image_file:
        content = image_file.read()

    image = vision.Image(content=content)

    # For dense text, use document_text_detection
    # For less dense text, use text_detection
    response = client.document_text_detection(image=image)
    text = response.full_text_annotation.text
    print(f"Detected text: {text}")

    return text

/**
 * Detects text in an image file
 *
 * ARGS
 * inputFile: path to image file
 * RETURNS
 * string of text detected in the input image
 **/
async function picToText(inputFile) {
  // Creates a client
  const client = new vision.ImageAnnotatorClient();

  // Performs text detection on the local file
  const [result] = await client.textDetection(inputFile);
  return result.fullTextAnnotation.text;
}

def create_glossary(
    languages: list,
    project_id: str,
    glossary_name: str,
    glossary_uri: str,
) -> str:
    """Creates a GCP glossary resource
    Assumes you've already manually uploaded a glossary to Cloud Storage

    Args:
    languages: list of languages in the glossary
    project_id: GCP project id
    glossary_name: name you want to give this glossary resource
    glossary_uri: the uri of the glossary you uploaded to Cloud Storage

    Returns:
    name of the created or existing glossary
    """

    # Instantiates a client
    client = translate.TranslationServiceClient()

    # Designates the data center location that you want to use
    location = "us-central1"

    # Set glossary resource name
    name = client.glossary_path(project_id, location, glossary_name)

    # Set language codes
    language_codes_set = translate.Glossary.LanguageCodesSet(language_codes=languages)

    gcs_source = translate.GcsSource(input_uri=glossary_uri)

    input_config = translate.GlossaryInputConfig(gcs_source=gcs_source)

    # Set glossary resource information
    glossary = translate.Glossary(
        name=name, language_codes_set=language_codes_set, input_config=input_config
    )

    parent = f"projects/{project_id}/locations/{location}"

    # Create glossary resource
    # Handle exception for case in which a glossary
    #  with glossary_name already exists
    try:
        operation = client.create_glossary(parent=parent, glossary=glossary)
        operation.result(timeout=90)
        print("Created glossary " + glossary_name + ".")
    except AlreadyExists:
        print(
            "The glossary "
            + glossary_name
            + " already exists. No new glossary was created."
        )

    return glossary_name

/** Creates a GCP glossary resource
 * Assumes you've already manually uploaded a glossary to Cloud Storage
 *
 * ARGS
 * languages: list of languages in the glossary
 * projectId: GCP project id
 * glossaryName: name you want to give this glossary resource
 * glossaryUri: the uri of the glossary you uploaded to Cloud Storage
 * RETURNS
 * nothing
 **/
async function createGlossary(
  languages,
  projectId,
  glossaryName,
  glossaryUri
) {
  // Instantiates a client
  const translationClient = await new translate.TranslationServiceClient();

  // Construct glossary
  const glossary = {
    languageCodesSet: {
      languageCodes: languages,
    },
    inputConfig: {
      gcsSource: {
        inputUri: glossaryUri,
      },
    },
    name: translationClient.glossaryPath(
      projectId,
      'us-central1',
      glossaryName
    ),
  };

  // Construct request
  const request = {
    parent: translationClient.locationPath(projectId, 'us-central1'),
    glossary: glossary,
  };

  // Create glossary using a long-running operation.
  try {
    const [operation] = await translationClient.createGlossary(request);
    // Wait for operation to complete.
    await operation.promise();
    console.log('Created glossary ' + glossaryName + '.');
  } catch (AlreadyExists) {
    console.log(
      'The glossary ' +
        glossaryName +
        ' already exists. No new glossary was created.'
    );
  }
}

def translate_text(
    text: str,
    source_language_code: str,
    target_language_code: str,
    project_id: str,
    glossary_name: str,
) -> str:
    """Translates text to a given language using a glossary

    Args:
    text: String of text to translate
    source_language_code: language of input text
    target_language_code: language of output text
    project_id: GCP project id
    glossary_name: name you gave your project's glossary
        resource when you created it

    Return:
    String of translated text
    """

    # Instantiates a client
    client = translate.TranslationServiceClient()

    # Designates the data center location that you want to use
    location = "us-central1"

    glossary = client.glossary_path(project_id, location, glossary_name)

    glossary_config = translate.TranslateTextGlossaryConfig(glossary=glossary)

    parent = f"projects/{project_id}/locations/{location}"

    result = client.translate_text(
        request={
            "parent": parent,
            "contents": [text],
            "mime_type": "text/plain",  # mime types: text/plain, text/html
            "source_language_code": source_language_code,
            "target_language_code": target_language_code,
            "glossary_config": glossary_config,
        }
    )

    # Extract translated text from API response
    return result.glossary_translations[0].translated_text

/**
 * Translates text to a given language using a glossary
 *
 * ARGS
 * text: String of text to translate
 * sourceLanguageCode: language of input text
 * targetLanguageCode: language of output text
 * projectId: GCP project id
 * glossaryName: name you gave your project's glossary
 *     resource when you created it
 * RETURNS
 * String of translated text
 **/
async function translateText(
  text,
  sourceLanguageCode,
  targetLanguageCode,
  projectId,
  glossaryName
) {
  // Instantiates a client
  const translationClient = new translate.TranslationServiceClient();
  const glossary = translationClient.glossaryPath(
    projectId,
    'us-central1',
    glossaryName
  );
  const glossaryConfig = {
    glossary: glossary,
  };
  // Construct request
  const request = {
    parent: translationClient.locationPath(projectId, 'us-central1'),
    contents: [text],
    mimeType: 'text/plain', // mime types: text/plain, text/html
    sourceLanguageCode: sourceLanguageCode,
    targetLanguageCode: targetLanguageCode,
    glossaryConfig: glossaryConfig,
  };

  // Run request
  const [response] = await translationClient.translateText(request);
  // Extract the string of translated text
  return response.glossaryTranslations[0].translatedText;
}

def text_to_speech(text: str, outfile: str) -> str:
    """Converts plaintext to SSML and
    generates synthetic audio from SSML

    Args:

    text: text to synthesize
    outfile: filename to use to store synthetic audio

    Returns:
    String of synthesized audio
    """

    # Replace special characters with HTML Ampersand Character Codes
    # These Codes prevent the API from confusing text with
    # SSML commands
    # For example, '<' --> '&lt;' and '&' --> '&amp;'
    escaped_lines = html.escape(text)

    # Convert plaintext to SSML in order to wait two seconds
    #   between each line in synthetic speech
    ssml = "<speak>{}</speak>".format(
        escaped_lines.replace("\n", '\n<break time="2s"/>')
    )

    # Instantiates a client
    client = texttospeech.TextToSpeechClient()

    # Sets the text input to be synthesized
    synthesis_input = texttospeech.SynthesisInput(ssml=ssml)

    # Builds the voice request, selects the language code ("en-US") and
    # the SSML voice gender ("MALE")
    voice = texttospeech.VoiceSelectionParams(
        language_code="en-US", ssml_gender=texttospeech.SsmlVoiceGender.MALE
    )

    # Selects the type of audio file to return
    audio_config = texttospeech.AudioConfig(
        audio_encoding=texttospeech.AudioEncoding.MP3
    )

    # Performs the text-to-speech request on the text input with the selected
    # voice parameters and audio file type

    request = texttospeech.SynthesizeSpeechRequest(
        input=synthesis_input, voice=voice, audio_config=audio_config
    )

    response = client.synthesize_speech(request=request)

    # Writes the synthetic audio to the output file.
    with open(outfile, "wb") as out:
        out.write(response.audio_content)
        print("Audio content written to file " + outfile)

/**
 * Generates synthetic audio from plaintext tagged with SSML.
 *
 * Given the name of a text file and an output file name, this function
 * tags the text in the text file with SSML. This function then
 * calls the Text-to-Speech API. The API returns a synthetic audio
 * version of the text, formatted according to the SSML commands. This
 * function saves the synthetic audio to the designated output file.
 *
 * ARGS
 * text: String of plaintext
 * outFile: String name of file under which to save audio output
 * RETURNS
 * nothing
 *
 */
async function syntheticAudio(text, outFile) {
  // Replace special characters with HTML Ampersand Character Codes
  // These codes prevent the API from confusing text with SSML tags
  // For example, '<' --> '&lt;' and '&' --> '&amp;'
  let escapedLines = text.replace(/&/g, '&amp;');
  escapedLines = escapedLines.replace(/"/g, '&quot;');
  escapedLines = escapedLines.replace(/</g, '&lt;');
  escapedLines = escapedLines.replace(/>/g, '&gt;');

  // Convert plaintext to SSML
  // Tag SSML so that there is a 2 second pause between each address
  const expandedNewline = escapedLines.replace(/\n/g, '\n<break time="2s"/>');
  const ssmlText = '<speak>' + expandedNewline + '</speak>';

  // Creates a client
  const client = new textToSpeech.TextToSpeechClient();

  // Constructs the request
  const request = {
    // Select the text to synthesize
    input: {ssml: ssmlText},
    // Select the language and SSML Voice Gender (optional)
    voice: {languageCode: 'en-US', ssmlGender: 'MALE'},
    // Select the type of audio encoding
    audioConfig: {audioEncoding: 'MP3'},
  };

  // Performs the Text-to-Speech request
  const [response] = await client.synthesizeSpeech(request);
  // Write the binary audio content to a local file
  const writeFile = util.promisify(fs.writeFile);
  await writeFile(outFile, response.audioContent, 'binary');
  console.log('Audio content written to file ' + outFile);
}

def main() -> None:
    """This method is called when the tutorial is run in the Google Cloud
    Translation API. It creates a glossary, translates text to
    French, and speaks the translated text.

    Args:
    None

    Returns:
    None
    """
    # Photo from which to extract text
    infile = "resources/example.png"
    # Name of file that will hold synthetic speech
    outfile = "resources/example.mp3"

    # Defines the languages in the glossary
    # This list must match the languages in the glossary
    #   Here, the glossary includes French and English
    glossary_langs = ["fr", "en"]
    # Name that will be assigned to your project's glossary resource
    glossary_name = "bistro-glossary"
    # uri of .csv file uploaded to Cloud Storage
    glossary_uri = "gs://cloud-samples-data/translation/bistro_glossary.csv"

    created_glossary_name = create_glossary(
        glossary_langs, PROJECT_ID, glossary_name, glossary_uri
    )

    # photo -> detected text
    text_to_translate = pic_to_text(infile)
    # detected text -> translated text
    text_to_speak = translate_text(
        text_to_translate, "fr", "en", PROJECT_ID, created_glossary_name
    )
    # translated text -> synthetic audio
    text_to_speech(text_to_speak, outfile)

await createGlossary(glossaryLangs, projectId, glossaryName, glossaryUri);
const text = await picToText(inFile);
const translatedText = await translateText(
  text,
  'fr',
  'en',
  projectId,
  glossaryName
);
syntheticAudio(translatedText, outFile);