Hugging Face's logo
Alan Tseng's picture
22 5 12

Alan Tseng

agentlans
mondalsurojit's profile picture Jaswanth-0821's profile picture Mi6paulino's profile picture
Ā·

AI & ML interests

Small data, boring AI

Recent Activity

reacted to cesear64's post with šŸ§  29 minutes ago
Just published: how we built production Sango (Central African Republic) translation without fine-tuning, parallel corpus, or training compute. The method ā€” vocabulary-augmented prompting with a 581-entry native-speaker-verified lexicon ā€” generalizes to any of the ~2,000 African languages at the same data-poverty level. Recipe, dataset, and code template all included. šŸ“„ Blog: https://huggingface.co/blog/MEYNG/sangoai šŸ“¦ Dataset: https://huggingface.co/datasets/MEYNG/sango-vocabulary Would especially value feedback from anyone working on other low-resource African languages ā€” Ewondo, Lingala, Wolof next on our roadmap.
repliedto cesear64's post 29 minutes ago
Just published: how we built production Sango (Central African Republic) translation without fine-tuning, parallel corpus, or training compute. The method ā€” vocabulary-augmented prompting with a 581-entry native-speaker-verified lexicon ā€” generalizes to any of the ~2,000 African languages at the same data-poverty level. Recipe, dataset, and code template all included. šŸ“„ Blog: https://huggingface.co/blog/MEYNG/sangoai šŸ“¦ Dataset: https://huggingface.co/datasets/MEYNG/sango-vocabulary Would especially value feedback from anyone working on other low-resource African languages ā€” Ewondo, Lingala, Wolof next on our roadmap.
updated a model about 2 hours ago
agentlans/Qwen3.5-0.8B-wikipedia-conversation-generator
View all activity

Organizations

None yet