README / README.md
openlimi's picture
Update README.md
5d74b7c verified
|
Raw History Blame Contribute Delete
880 Bytes
metadata
title: a
emoji: πŸš€
short_description: Open AI models and datasets for the Uzbek language.

Open Limi

We build and improve AI models for the Uzbek language, so that Uzbek speakers get the same quality of AI as speakers of any other major language.

What we do

  • πŸŽ™οΈ Speech Recognition (ASR) – accurate transcription for Uzbek
  • πŸ”Š Text-to-Speech (TTS) – natural, expressive Uzbek voices
  • 🌐 Translation & Speech-to-Speech – Uzbek ↔ English/Russian and more
  • πŸ’¬ Language Models – fine-tuned LLMs and embeddings for Uzbek
  • πŸ“Š Datasets & Benchmarks – clean, documented data and evaluation sets

Our approach

  1. Train new models where none exist.
  2. Fine-tune and improve existing open models for Uzbek.
  3. Release with clear model cards, benchmarks, and licenses.

Contact

🌐 Β· πŸ“§ openlimiuz@gmail.com Β· πŸ’Ό