Source data for moodupuu.eki.ee, the Estonian LLM leaderboard

A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.

Offline voice input keyboard & live subtitle tool for Android

Text and speech AI playground. The first version was vibe-coded with OpenAI Codex in the browser in ~10 days of 2 h/day sessions.

Rust re-implementation of OpenFST - library for constructing, combining, optimizing, and searching weighted finite-state transducers (FSTs). A Python binding is also available.

Bringing BERT into modernity via both architecture changes and scaling

Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces

APE Webclient

Offical FUTO Keyboard Issue Tracker and Source Mirror of https://gitlab.futo.org/keyboard/voiceinput

A very simple whisper Python FastAPI for OpenAI API, Android voice-typing (konele), Home Assistant (wyoming), and a voice-typing script on Linux and MacOS!

Documentation for the AI in a Box project

Offline voice input panel & keyboard with punctuation for Android.

Constrained Decoding for LLMs against JSON Schema

Self hosted high quality voice recognition for de-googled Android using whisper. Like Siri or OK Google.

An even smaller speech recognizer / force aligner

Eesti keele morfanalüsaator

Offline voice typing for Android

Kõnele service is an Android app that offers a speech-to-text service to other apps, in particular to Kõnele. It implements SpeechRecognizer, backed by an open source speech recognition server soft…

An open-source keyboard for Android which respects your privacy. Currently in beta.

Plausibility filtering with Grammatical Framework

Android Speech Recognition Service using Vosk/Kaldi and Mozilla DeepSpeech

Object detection using deep learning with Yolo, OpenCV and Python via Real Time Streaming Protocol (RTSP)

Brauseri laienduse loomine eestikeelse teksti dikteerimiseks kõnetuvastuse abil

Regex: generate matching and non matching strings based on regex pattern.

Estonian text-to-speech text normalization pipeline

Live Transcribe is an Android application that provides real-time captioning for people who are deaf or hard of hearing. This repository contains the Android client libraries for communicating with…

Modeling Composite Labels for Neural Morphological Tagging

Build `manylinux2014_x86_64` Python wheels for `pynini`, wrapping all its dependencies. This is a ServiceNow Research project that was started at Element AI.