# GitHub repos worth harvesting, from the API sweep + the four dataset docs.
GH_REPOS=[
 # multimodal / vision-language
 ("https://github.com/eftekhar-hossain/Bengali-Hateful-Memes","bengali_hateful_memes"),
 ("https://github.com/justaguyalways/ToxVidLM_ACL_2024","toxvidlm"),
 ("https://github.com/justaguyalways/Code-Mixed-Hinglish-Intervention-CIKM-2024","hinglish_intervention"),
 ("https://github.com/PraneethaBalanagu/Cyberbullying-Detection-in-Code-mixed-Memes-Using-Deep-Learning","codemix_memes"),
 # misinformation / fake news
 ("https://github.com/div5252/hindi-fake-news","hindi_fake_news"),
 ("https://github.com/BSAkash/Hindi-Fake-News-Detection-Dataset","hindi_fnd"),
 ("https://github.com/Piyush2912/FakeNewsDetectionHindiDataset","hindi_fnd2"),
 ("https://github.com/itsvaibhavsharmaji/Fake-News-Dataset-In-Hindi","hindi_fnd3"),
 ("https://github.com/HjH-Whu-CRC/Ax-to-Grind-Urdu","ax_to_grind"),
 ("https://github.com/MaazAmjad/Urdu-Fake-news-detection-FIRE2021","urdufake_fire2021"),
 # hate / hostility
 ("https://github.com/naurosromim/hate-speech-dataset-for-Bengali-social-media","bengali_hate_social"),
 ("https://github.com/Rafid-Mostafiz/Bengali-Hate-Speech-Dataset","bengali_hate2"),
 ("https://github.com/fatemafaria142/Bangla-Hate-Speech-Detection","bangla_hate3"),
 # code-mix / sentiment / NER
 ("https://github.com/mananjen/hinglish_sarcasm_dataset","hinglish_sarcasm"),
 ("https://github.com/20118/ACSA-Mix","acsa_mix"),
 ("https://github.com/shreyapatankar-commits/HINGLISH-SENTENCES","hinglish_sentences"),
 ("https://github.com/chandan5362/NER-on-Indic-Language-Dataset","indic_ner_gh"),
 ("https://github.com/pprithviraj-dev/hinglish-code-mixed-sentiment-analysis","hinglish_sent_gh"),
 # speech
 ("https://github.com/Nivedita5/Indic-TEDST","indic_tedst"),
 ("https://github.com/bala-ceg/doctor-patient-indic-speech-dataset","indic_doctor_speech"),
 # social / bias
 ("https://github.com/sohampoddar26/indian-transport-snam","indian_transport_snam"),
 ("https://github.com/AxleBlaze3/Covid_19_Tweets_with_Tagged_Needs","covid_tweets_needs"),
 ("https://github.com/debby123p/IndRegBias-A-Dataset-for-Studying-Indian-Regional-Biases-in-English-and-Code-Mixed-Languages","indregbias"),
]