AI & ML interests
None defined yet.
Recent Activity
View all activity
Articles
Article
Scaling Zero-Resource Vocabulary: A Data Pipeline for Sango
MEYNG
• 
cesear64
updated a
model 1 day ago
cesear64
updated a
model 2 days ago
cesear64
published 2
models 3 days ago
Post
4097
Just published: how we built production Sango (Central African Republic) translation without fine-tuning, parallel corpus, or training compute.
The method — vocabulary-augmented prompting with a 581-entry native-speaker-verified lexicon — generalizes to any of the ~2,000 African languages at the same data-poverty level. Recipe, dataset, and code template all included.
📄 Blog: https://huggingface.co/blog/MEYNG/sangoai
📦 Dataset: MEYNG/sango-vocabulary
Would especially value feedback from anyone working on other low-resource African languages — Ewondo, Lingala, Wolof next on our roadmap.
The method — vocabulary-augmented prompting with a 581-entry native-speaker-verified lexicon — generalizes to any of the ~2,000 African languages at the same data-poverty level. Recipe, dataset, and code template all included.
📄 Blog: https://huggingface.co/blog/MEYNG/sangoai
📦 Dataset: MEYNG/sango-vocabulary
Would especially value feedback from anyone working on other low-resource African languages — Ewondo, Lingala, Wolof next on our roadmap.
- 2 replies
Article
Vocabulary-Augmented Prompting for Sango — Production African Language AI Without a Parallel Corpus
MEYNG
• • 2 Article
Vocabulary-Augmented Prompting for Sango — Production African Language AI Without a Parallel Corpus
MEYNG
• cesear64
updated a
dataset 17 days ago
cesear64
published a
dataset about 2 months ago