Back to catalog

Aigiz Kunafin

A machine learning engineer who single-handedly released over a dozen open speech recognition and synthesis models and spell-checking tools for the Bashkir and Tatar languages.

About this project

Published 19 models and 13 datasets on Hugging Face for Bashkir and Tatar speech
Author of the tools bashspell, bashkort_translate_bot and bashkir-stress
Winner of the Enterprise RAG Challenge

Related projects

All projects in Author

Ilshat Säetov

AuthorLanguage project#Linguist#Language#Literature#Technology#Keyboard#Text recognition#Open sourceTatars

Associated member of CETOBaC at EHESS in Paris
Author of TATlit, a language model for literary Tatar
Author of an OCR model for Tatar Cyrillic and a macOS keyboard layout

Fastmorph

Language project#Language#Technology#Language model#Open sourceTatars

Created for the Written Tatar Language Corpus
Searches by word forms, lemmas, grammatical tags, and patterns
Supports distance constraints between words
Source code published under the GPL-3.0 license

Tweety Tatar 7B

Language project#Language#Technology#Language modelTatars

Created by an international multilingual-NLP research group
Adapted via trans-tokenization and fine-tuned on a Tatar corpus
The series also includes specialized model variants

Муэллиф