AI4D Yorùbá Machine Translation Challenge
Helping Nigeria
$2 000 USD
Completed (almost 5 years ago)
Machine Translation
683 joined
84 active
Start
Dec 04, 20
Close
May 30, 21
Reveal
May 30, 21
Starter Notebook
Notebooks · 12 Apr 2021, 12:26 · 7
Hello Zindians
Maybe it is late but better late than never, i created a notebook based on encoder decoder models to translate Yoruba to English.
this is a link to the starter notebook https://github.com/Klaimohelmi/yoruba-to-english-neural-machine-translation
Good Luck
Hi Klai... thanks for this.
In running this:
model.fit_generator(generator = generate_batch(X_train, y_train, batch_size = batch_size),
steps_per_epoch = train_samples//batch_size,
epochs=epochs,
validation_data = generate_batch(X_test, y_test, batch_size = batch_size),
validation_steps = val_samples//batch_size)
Below is the error generated:
InvalidArgumentError: indices[127,0] = 15790 is not in [0, 15790) [[node model/embedding/embedding_lookup (defined at <ipython-input-43-a780c545a7a7>:5) ]] [Op:__inference_train_function_13820]
I tried checking StackOverflow but no familiar solution.
How do I go about this? Thanks
same error
I didn't get this error ! did u run the notebook on Kaggle ?
I ran the code on Google Colab
yes, i run it on kaggle
very strager !!! i run the notebook again and there is no error ! i added the data to the link maybe we don't have the same data or maybe there was updated !
I guess you need to check your vector representations..