Issues
- 0
- 0
Adding new languages to FLORES dataset
#66 opened by qunash - 0
- 0
The translations in Moroccan Arabic (ary_Arab) are just Modern Standard Arabic.
#64 opened by MedAymenF - 0
Standard Moroccan Tamazight mislabeled.
#63 opened by MedAymenF - 0
Wrong Text on Spanish Devset Line 536
#62 opened by sotwi - 1
The Cantonese (Yue Chinese, `yue_Hant`) data in FLORES-200 is not Cantonese at all
#61 opened by ayaka14732 - 0
- 1
- 3
Dataset Problem.
#58 opened by ShadowVicky - 0
- 3
- 4
Central Kurdish Problems
#50 opened by Sarchia - 3
Contribution: Kabyle Language
#51 opened by MohammedBelkacem - 0
Evaluation Script for all language pairs
#38 opened by alirezamshi-zz - 0
Could not reproduce FloresV1 BLEU scores
#43 opened by mnoukhov - 0
- 0
- 2
Scope for addition of New Language Bodo
#35 opened by sanjibnarzary - 0
Data Download is outdated
#32 opened by sonalsannigrahi - 0
Extra zero-width characters in the dataset
#31 opened by bact - 1
- 0
- 2
FLORES-101 benchmark and Alternative Spelling rules in some languages, using FLORES-101 for benchmarking embeddings models
#26 opened by Fikavec - 1
Submission to DynaBench does not show results
#28 opened by dannigt - 0
Question about the x->traditional Chinese
#27 opened by CSJianYang - 1
Evaluation of languages of the same family
#25 opened by jordimas - 4
- 1
Pashto Language does not have test set
#19 opened by ShaidaMuhammad - 5
Scripts to Scrape Data?
#6 opened by neubig - 2
- 1
- 0
- 2
Broken download link
#20 opened by berlino - 1
detokenize output
#21 opened by sonalsannigrahi - 2
How to replicate supervised NE-EN baseline?
#16 opened by j0ma - 5
ERROR in download-data.sh
#11 opened by nxphi47 - 3
Scripts for Back-translation?
#1 opened by ashim95 - 1
Can't Decompress ”commoncrawl.deduped.en.xz“.
#10 opened by zdou0830 - 4
- 7
Reproducing Fully Supervised Baseline
#7 opened by aw31 - 2
bad gateway for data downloading
#3 opened by amiktt - 0
how to get the monolingual corpus
#4 opened by cocaer - 2