Custom-Seq2Seq-Model-For-Machine-Translation | Custom Seq2Seq Model for Machine Translation | Translation library

Well, I did a workaround which solves my issue but doesn't solve the autodetect issue. Adding a second argument in the user input to include the "from_lang" fixes the issue.

I had a small search in pub.dev to check if there is any new lib to do this, but I didn't find it.

However, I recommend you use google API which receives the text and returns the language type.

You can check it in: google-detecting-language

A sample from the website you can check: body POST:

Textblob library uses Google API for translation functionality in the backend. Google has made some changes in the its API recently. Due to this reason TextBlob's translation feature has stopped working. I noticed that by making some minor changes in translate.py file (in your folder where all TextBlob files are located) as mentioned below, we can get rid of this error:

original code:

Your problem with pageData interface is the parent T is the same type required by the children. What you want is to open up the generic type to accommodate any record therefor allowing the children to define their own properties.

No, dot in a property name for interpolation is used as json dot notation. So if you want to keep "Hi {{first.name}}" in your translations, you need to pass in the t options like this: i18next.t('keyk', { first: { name: 'Jane' } })

Solution:

Your viewset is defined as:

You can build your own tokenizer following this tutorial https://www.tensorflow.org/text/guide/subwords_tokenizer

It is the exact same way they build the ted_hrlr_translate_pt_en_converter tokenizer in the transformers example, you just need to adjust it to your language.

I rewrote it for your case but didn't test it:

I think one possible answer to your dilemma is provided in this question: https://stackoverflow.com/questions/61523829/how-can-i-use-bert-fo-machine-translation#:~:text=BERT%20is%20not%20a%20machine%20translation%20model%2C%20BERT,there%20are%20doubts%20if%20it%20really%20pays%20off.

Practically with the output of BERT, you get a vectorized representation for each of your words. In essence, it is easier to use the output for other tasks, but trickier in the case of Machine Translation.

A good starting point of using a seq2seq model from the transformers library in the context of machine translation is the following: https://github.com/huggingface/notebooks/blob/master/examples/translation.ipynb.

The example above provides how to translate from English to Romanian.