How to solve text must be a valid text with maximum 5000 character, otherwise it cannot be translated

Question

I am using google translate api to translate some text.

The package is from deep_translator import GoogleTranslator.

However, every time it would return the error: --> text must be a valid text with maximum 5000 character, otherwise it cannot be translated

Does anyone know how to solve this? Is it possible to have a paid version of api to expand the maximum characters?

Thanks a lot!

Jalopy

Can you split the text into chunks and submit each chunk (eg. splitting at the closest paragraph with less than 5000 characters)? – Maynardmayne

The 5,000 character limit is per request. If you look at the Quotas page there is a 6,000,000 character per minute quota. So my suggestion is to break your text into chunks and make requests that way. – Solidary

Answer 1

You could split the text up in chunks in either words or sentences.

Using the NLTK module:

pip install nltk

import nltk
#nltk.download('popular') -- only need to do this once
x = '''I am using google translate api to translate some text.

The package is from deep_translator import GoogleTranslator.

However, every time it would return the error: --> text must be a valid text with maximum 5000 character, otherwise it cannot be translated

Does anyone know how to solve this? Is it possible to have a paid version of api to expand the maximum characters?

Thanks a lot!'''

x = nltk.tokenize.sent_tokenize(x)
for sentence in x:
    print(sentence) #send each sentence to translator

Aquacade