AI4D Yorùbá Machine Translation Challenge
$2,000 USD
Can you translate Yorùbá to English?
464 data scientists enrolled, 79 on the leaderboard
TranslationUnstructuredNLP
Nigeria
4 December 2020—30 May 2021
Ends in 20 days
Starter Notebook

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