How to query text reading from Google Cloud Translation API - google-translate

Question

I want to be able to convert Japanese kanji to their readings, e.g. 日本語 to nihongo or にほんご.
Google translate website allows you to do that - https://translate.google.com/?sl=ja&tl=en&text=%E6%97%A5%E6%9C%AC%E8%AA%9E&op=translate.
You can see that it shows Nihongo for 日本語 input.
But I can't find any API in Google Cloud Translate that allows to do the same from my app.
Maybe google don't offer that as an API, and some other service allows you to do that, but can't find such service either.

Answer 1

Google offers Translation API which is fit to your requirement.
Using this documentation to replicate your scenario in python:
20220314.py:
import argparse
# [START translate_detect_language]
def detect_language(text):
"""Detects the text's language."""
from google.cloud import translate_v2 as translate
translate_client = translate.Client()
# Text can also be a sequence of strings, in which case this method
# will return a sequence of results for each text.
result = translate_client.detect_language(text)
print("Text: {}".format(text))
print("Confidence: {}".format(result["confidence"]))
print("Language: {}".format(result["language"]))
# [END translate_detect_language]
# [START translate_list_codes]
def list_languages():
"""Lists all available languages."""
from google.cloud import translate_v2 as translate
translate_client = translate.Client()
results = translate_client.get_languages()
for language in results:
print(u"{name} ({language})".format(**language))
# [END translate_list_codes]
# [START translate_list_language_names]
def list_languages_with_target(target):
"""Lists all available languages and localizes them to the target language.
Target must be an ISO 639-1 language code.
See https://g.co/cloud/translate/v2/translate-reference#supported_languages
"""
from google.cloud import translate_v2 as translate
translate_client = translate.Client()
results = translate_client.get_languages(target_language=target)
for language in results:
print(u"{name} ({language})".format(**language))
# [END translate_list_language_names]
# [START translate_text_with_model]
def translate_text_with_model(target, text, model="nmt"):
"""Translates text into the target language.
Make sure your project is allowlisted.
Target must be an ISO 639-1 language code.
See https://g.co/cloud/translate/v2/translate-reference#supported_languages
"""
from google.cloud import translate_v2 as translate
translate_client = translate.Client()
if isinstance(text, bytes):
text = text.decode("utf-8")
# Text can also be a sequence of strings, in which case this method
# will return a sequence of results for each text.
result = translate_client.translate(text, target_language=target, model=model)
print(u"Text: {}".format(result["input"]))
print(u"Translation: {}".format(result["translatedText"]))
print(u"Detected source language: {}".format(result["detectedSourceLanguage"]))
# [END translate_text_with_model]
# [START translate_translate_text]
def translate_text(target, text):
"""Translates text into the target language.
Target must be an ISO 639-1 language code.
See https://g.co/cloud/translate/v2/translate-reference#supported_languages
"""
import six
from google.cloud import translate_v2 as translate
translate_client = translate.Client()
if isinstance(text, six.binary_type):
text = text.decode("utf-8")
# Text can also be a sequence of strings, in which case this method
# will return a sequence of results for each text.
result = translate_client.translate(text, target_language=target)
print(u"Text: {}".format(result["input"]))
print(u"Translation: {}".format(result["translatedText"]))
print(u"Detected source language: {}".format(result["detectedSourceLanguage"]))
# [END translate_translate_text]
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter
)
subparsers = parser.add_subparsers(dest="command")
detect_langage_parser = subparsers.add_parser(
"detect-language", help=detect_language.__doc__
)
detect_langage_parser.add_argument("text")
list_languages_parser = subparsers.add_parser(
"list-languages", help=list_languages.__doc__
)
list_languages_with_target_parser = subparsers.add_parser(
"list-languages-with-target", help=list_languages_with_target.__doc__
)
list_languages_with_target_parser.add_argument("target")
translate_text_parser = subparsers.add_parser(
"translate-text", help=translate_text.__doc__
)
translate_text_parser.add_argument("target")
translate_text_parser.add_argument("text")
args = parser.parse_args()
if args.command == "detect-language":
detect_language(args.text)
elif args.command == "list-languages":
list_languages()
elif args.command == "list-languages-with-target":
list_languages_with_target(args.target)
elif args.command == "translate-text":
translate_text(args.target, args.text)
Output:
(venv) a#cloudshell:~/python_cases$ python 20220314.py translate-text en 日本語
Text: 日本語
Translation: Japanese
Detected source language: ja
Instead of nihongo in Detected source language, it displays the ISO language code: ja for japanese. For the list of language and its ISO language code you can also use this python script:
(venv) a#cloudshell:~/python_cases$ python 20220314.py list-languages
Afrikaans (af)
Albanian (sq)
Amharic (am)
Arabic (ar)
Armenian (hy)
Azerbaijani (az)
Basque (eu)
Belarusian (be)
Bengali (bn)
Bosnian (bs)
Bulgarian (bg)
Catalan (ca)
Cebuano (ceb)
Chichewa (ny)
Chinese (Simplified) (zh-CN)
Chinese (Traditional) (zh-TW)
Corsican (co)
Croatian (hr)
Czech (cs)
Danish (da)
Dutch (nl)
English (en)
Esperanto (eo)
Estonian (et)
Filipino (tl)
Finnish (fi)
French (fr)
Frisian (fy)
Galician (gl)
Georgian (ka)
German (de)
Greek (el)
Gujarati (gu)
Haitian Creole (ht)
Hausa (ha)
Hawaiian (haw)
Hebrew (iw)
Hindi (hi)
Hmong (hmn)
Hungarian (hu)
Icelandic (is)
Igbo (ig)
Indonesian (id)
Irish (ga)
Italian (it)
Japanese (ja)
Javanese (jw)
Kannada (kn)
Kazakh (kk)
Khmer (km)
Kinyarwanda (rw)
Korean (ko)
Kurdish (Kurmanji) (ku)
Kyrgyz (ky)
Lao (lo)
Latin (la)
Latvian (lv)
Lithuanian (lt)
Luxembourgish (lb)
Macedonian (mk)
Malagasy (mg)
Malay (ms)
Malayalam (ml)
Maltese (mt)
Maori (mi)
Marathi (mr)
Mongolian (mn)
Myanmar (Burmese) (my)
Nepali (ne)
Norwegian (no)
Odia (Oriya) (or)
Pashto (ps)
Persian (fa)
Polish (pl)
Portuguese (pt)
Punjabi (pa)
Romanian (ro)
Russian (ru)
Samoan (sm)
Scots Gaelic (gd)
Serbian (sr)
Sesotho (st)
Shona (sn)
Sindhi (sd)
Sinhala (si)
Slovak (sk)
Slovenian (sl)
Somali (so)
Spanish (es)
Sundanese (su)
Swahili (sw)
Swedish (sv)
Tajik (tg)
Tamil (ta)
Tatar (tt)
Telugu (te)
Thai (th)
Turkish (tr)
Turkmen (tk)
Ukrainian (uk)
Urdu (ur)
Uyghur (ug)
Uzbek (uz)
Vietnamese (vi)
Welsh (cy)
Xhosa (xh)
Yiddish (yi)
Yoruba (yo)
Zulu (zu)
Hebrew (he)
Chinese (Simplified) (zh)