
Academic lab · Tallinn, Estonia
TalTech Language TechnologyTalTechNLP
The TalTech language technology lab publishing open Estonian speech recognition and translation models.
Tallinn, Estonia
- Type
- Academic lab
- Based in
- Tallinn, Estonia
- Featured projects
- 3
About
The Laboratory of Language Technology at Tallinn University of Technology develops speech and language technology for Estonian. Tanel Alumae leads related research.
Its general-purpose Estonian ASR is a Whisper-large-v2 fine-tune on about 1200 hours, reporting about 12 percent word error rate on Common Voice 11.
A Whisper fine-tune for Estonian-English-Russian speech translation was published in 2024, and children's speech recognition work in 2025.
Mission and ambitionsThe lab builds practical Estonian speech technology and shares models openly.
Known for
- 01
Estonian Whisper ASR
- 02
Estonian speech translation
- 03
TalTech Estonian Speech Dataset
Milestones
- 2023
Estonian Whisper large model update
Long-segment version dated 3 October.
- 2024
Estonian conversational speech translation
arXiv paper on fine-tuned end-to-end models.
- 2025
Children's speech recognition
SLaTE paper by Lilles, Mannik and Alumae.
Open source
Model with 33 likes on the Hub.
Model with 8 likes on the Hub.
- TalTechNLP/voxlingua107_wdsdataset
Dataset with 5 likes on the Hub.
Notable releases
Openness
Models and datasets are public on the TalTechNLP Hugging Face organisation.
People
- Tanel AlumäeResearcher, speech technology
Leads Estonian ASR and speech translation models.
Listed from the lab's own pages and public profiles.
Contact and community
Contact through the university website.
Sources
Compiled from the lab's public pages, Hugging Face and GitHub. Last checked 2026-11-17. Something wrong or out of date? Tell us on Discord.



