Google Translate Python API

 

Image by Christina Morillo from pexels.com
Images by Christina Morillo from pexels.com

There are many translation services, and Google's is one of the most commonly used services. Let's try out its Python API.

The package is googletrans. The documentation can be found at py-googletrans.pdf.

Supported Languages

import googletrans

print(googletrans.LANGUAGES)
print(len(googletrans.LANGUAGES))

lists 107 supported languages.


Language Detection

from googletrans import Translator

translator = Translator()
english_text = "Tyson Fury got up twice from the canvas to win it."
dt_en = translator.detect(english_text)
print(dt_en)

gives us Detected(lang=en, confidence=1)

translator = Translator()

japanese_text = "タイソンフューリーはそれを獲得するためにキャンバスから2回起きました."
dt_ja = translator.detect(japanese_text)
print(dt_ja)

gives us Detected(lang=ja, confidence=1)

These are too easy for googletrans :-) Let's try more complicated things.

translator = Translator()
mixed_text = (
    "タイソンフューリーはそれを獲得するためにキャンバスから2回起きました. Tyson Fury got up twice from the canvas to win it."
)
dt = translator.detect(mixed_text)
print(dt)

We provide Japanese and English statements and we get Detected(lang=ja, confidence=1). The Japanese language is detected with a full confidence score!

Let's reduce the Japanese statement to a few words.

translator = Translator()
mixed_text = "きました. Tyson Fury got up twice from the canvas to win it."
dt = translator.detect(mixed_text)
print(dt)

and we get Detected(lang=en, confidence=0.7228199). This is more logical.


Language Translation

Next, we look at this translation service.

translator = Translator()
japanese_text = "タイソンフューリーはそれを獲得するためにキャンバスから2回起きました."
tlr_ja = translator.translate(japanese_text)
print(tlr_ja)

By default, the destination translated language is en. And, we get good results.

Translated(src=ja, dest=en, text=Tyson Fury woke up twice from the canvas to win it., pronunciation=None, extra_data="{'translat...")

Let's test English to Japanese translation.

translator = Translator()
english_text = "Tyson Fury got up twice from the canvas to win it."
tlr_en = translator.translate(english_text, dest="ja")
print(tlr_en)

Once again, the result is good.

Translated(src=en, dest=ja, text=タイソンフューリーはそれを獲得するためにキャンバスから2回起きました。, pronunciation=Taisonfu~yūrī wa sore o kakutoku suru tame ni kyanbasu kara 2-kai okimashita., extra_data="{'translat...")

Let's use the list of words for translation.

translator = Translator()
list_words = ["こんにちは", "すみません"]
tlr_ja = translator.translate(list_words)
for tlr in tlr_ja:
    print(tlr)

And, we get a list of good results.

Translated(src=ja, dest=en, text=Hello, pronunciation=None, extra_data="{'translat...")
Translated(src=ja, dest=en, text=excuse me, pronunciation=None, extra_data="{'translat...")

Conclusion

Using these API is almost effortless. And the results are good.

I was using googletrans version 3.0.0, and it is not good as I ran into a bug. Please avoid this version.

Traceback (most recent call last):
  File "main.py", line 9, in <module>
    tlr_en = translator.translate(english_text, dest="ja")
  File "/Users/veseah/experiments/googletrans/.venv/lib/python3.8/site-packages/googletrans/client.py", line 182, in translate
    data = self._translate(text, dest, src, kwargs)
  File "/Users/veseah/experiments/googletrans/.venv/lib/python3.8/site-packages/googletrans/client.py", line 78, in _translate
    token = self.token_acquirer.do(text)
  File "/Users/veseah/experiments/googletrans/.venv/lib/python3.8/site-packages/googletrans/gtoken.py", line 194, in do
    self._update()
  File "/Users/veseah/experiments/googletrans/.venv/lib/python3.8/site-packages/googletrans/gtoken.py", line 62, in _update
    code = self.RE_TKK.search(r.text).group(1).replace('var ', '')
AttributeError: 'NoneType' object has no attribute 'group'



Comments

Post a Comment

Popular posts from this blog

Happy New Year, 2024 from DALL-E

Image
generated by DALL-E Wishing everyone a happy new year. Year 2023 is great for me because I learned much about OpenAI. I am involved in a live deployment with it, and involved in a handful of interesting user scenarios around it. On top of this, a copilot hackathon. The image above is generated by DALL-E and following is the code. 1. Dependencies python = "^3.10" pydantic-settings = "^2.1.0" openai = "^1.3.8" 2. Environment Parameters OPENAI_AZURE_ENDPOINT="<your azure openai endpoint>" AZURE_OPENAI_API_KEY="<your azure openai secret>" OPENAI_API_VERSION="2023-12-01-preview" OPENAI_DALLE_MODEL="dalle" Note: OPENAI_API_VERSION has to be 2023-12-01-preview otherwise you will get an exception openai.NotFoundError: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}} dalle  is the name of my dall-e-3 deployment model. You need to change it to
Read more

Bing Search as tool for OpenAI

Image
  Image from https://www.pexels.com/@skitterphoto/ Many times, we need to search for information in the web when we are working with OpenAI. One of the reasons is that the dataset for training for OpenAI is never up to date. For instance, the OpenAI GPT-4 Turbo has knowledge of events up to April 2023. Here is the Python implementation with Pydantic model. Dependencies python = "^3.10" pydantic-settings = "^2.1.0" pydantic = "^2.5.2" azure-cognitiveservices-search-websearch = "^2.0.0" Environment These are the environment parameters needed. Have the following in a .env file. azure_bing_search_endpoint="https://api.bing.microsoft.com" azure_bing_search_key="<key>" We look under "Keys and Endpoint" for these values. Pydantic Setting Model from pydantic_settings import BaseSettings class BingSearchSettings(BaseSettings): azure_bing_search_endpoint: str azure_bing_search_key: str class Config:
Read more

OpenAI: Functions Feature in 2023-07-01-preview API version

Image
  Image from https://www.pexels.com/@pavel-danilyuk/ One of the cool features of OpenAI version 2023-07-01 is its custom Functions feature. This feature is close to me because I am working on a project where we require OpenAI to generate JSON responses. We always want the generated JSON to be consistent, otherwise, we need to do some post-processing tasks to get the JSON object in the correct schema. In the blog, we observe the completion with and without this new feature. Development Setup python -m venv .venv poetry init poetry shell poetry add openai poetry add python-dotenv poetry add pydantic I am using Python version 3.11 Create .env file OPENAI_API_TYPE="azure" OPENAI_API_BASE="<OpenAI endpoint>" OPENAI_API_KEY="<OpenAI secret>" OPENAI_API_VERSION="2023-07-01-preview" OPENAI_DEPLOYMENT_ID="<deployment identifier>" Without OpenAI functions feature We use two sample texts for experimentation. We want to get the na
Read more