YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Hi, I'm Tasal π
I'm an AI/NLP researcher building ZamAI β an open-source initiative to bring modern AI to the Pashto language. Pashto is spoken by 60β80 million people worldwide yet remains severely underrepresented in NLP research. I'm working to change that.
π What I'm Building
ZamAI is a full Pashto AI stack: language models, embeddings, translation, speech recognition, and the datasets that power them.
| Area | Flagship Repo |
|---|---|
| π£οΈ LLM (Chat) | ZamAI-LIama3-Pashto β LLaMA-3 8B fine-tuned for Pashto |
| π Embeddings | Multilingual-ZamAI-Embeddings β ps/ar/fa/ur/en |
| π Translation | ZamAI-Pashto-Translator β NLLB psβen |
| π€ Speech | ZamAI-Whisper-Pashto β Whisper ASR |
| π Sentiment | ZamAI-Sentiment-Pashto β RoBERTa classifier |
| π Dataset | ZamAi-Pashto-Datasets-V2 β 18K+ downloads |
| π¦ Mega Dataset | ZamAI-Pashto-Mega-Dataset β 1Mβ10M scale |
π€ Organization
Part of ZamAI-Pashto on Hugging Face.
π¬ Get in Touch
Working on low-resource language NLP? Open a discussion on any repo β contributions and dataset collaborations are very welcome.
"Ψ²Ω ΩΩΪ ΪΨ¨ΩΨ Ψ²Ω ΩΩΪ ΩΩΫΨͺ" β Our language, our identity.
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support