I realize that winners in this competition have either used mT5 or M2M models to get the best possible result. For that reason, I wrote this article in which I... See more

Hi all, The final leaderboard is postponed to 28 June as we are still reviewing code. All the best.

Using simple transformer seq2seq I have downloaded Helsinki-NLP/opus-mt-mul-en which work best in our case and using specific Seq2SeqArgs to set arguments of mo... See more

please tell me can i use gnmt model from google

Please are TPUs allowed? @amyflorida626Zindi

I quote:""" You may use pretrained models as long as they are openly available to everyone.The data used in this competition is the sole property of Zindi and t... See more

Is the scorer use_stemmer True or False?`RougeScorer(['rouge1'], use_stemmer=True)` or `RougeScorer(['rouge1'], use_stemmer=False)`

I don't understand this, but how some of the top 5 managed to get to that position with one or two submissions ?Is there a secret ingredient I'm unaware of ?

Hi Professionals,Kindly help with hint of fixing this... I'm training my model on Google Colab. Attempts made by me so far is to reduce the batch size, yet the... See more

Are we allowed to use services like Google Translate (https://pypi.org/project/deep-translator/) ?

What should our submission file look like, translated English sentences?

Hi all. I have been having this error. kindly help out.CUDA out of memory. Tried to allocate 150.00 MiB (GPU 0; 14.76 GiB total capacity; 13.52 GiB already allo... See more

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 t... See more

RuntimeError: CUDA out of memory. Tried to allocate 56.00 MiB (GPU 0; 15.90 GiB total capacity; 14.97 GiB already allocated; 57.75 MiB free; 15.06 GiB reserved... See more

Can the organizer's look into the scoring again? The competition is no fun with a broken metric

Hi,Are we still allowed to use JW300 yo-en data? (i'm confused because, in some other AI4D competition-Malwai news classification, it is not allowed). It will b... See more

Dear Zindians, We have re scored the leaderboard and we are using the NLTK BLEU library. We have also extended this challenge by 2 weeks. All the best and thank... See more

Hello Zindians!We’re really excited to be rolling out some changes to how the platform works, as always working to make this a better place for all of you to le... See more

Dear Zindi Team,I have seen that we are permitted to use data from JW300 can you give the Link

Dear Zindians, We are aware of the BLEU error and we are working on fixing it. Thank you for your patience.

I was in 2nd place with a score of 0.47xx, after I submit a new submission, it dropped me to the score of 0.1xx.

Hi all,this is a quick overview on the Zindi Package that we are trying to build and that is in testing now.==>CLICK HERE TO OPEN THE NOTEBOOK<==This pack... See more

Dear Zindians, We found a bug in the BLEU error metric. We are fixing it this week and will re-score the leaderboard by Monday.All the best, The Zindi Team

Anyone working with colab here?I keep on getting my sessions crashed even when i'd reduced batch size and training epoch.

Hello everyone, this is a message to @Johno or anyone else who's willing to write up a starter notebook for us beginners in this particular domain of ML. That w... See more