Tanel Alumäe

kaldi-gstreamer-server. Real-time full-duplex speech recognition server, based on the Kaldi toolkit and the GStreamer framwork.

kaldi-offline-transcriber. Offline transcription system for Estonian using Kaldi

gst-kaldi-nnet2-online. GStreamer plugin around Kaldi's online neural network decoder

ruby-pocketsphinx-server. Ruby-based web service for speech recognition, using the PocketSphinx gstreamer module

kiirkirjutaja. Python

online_speaker_change_detector. Online streaming speaker change detection model in Pytorch

kaldi-nnet-dur-model. Neural network phone duration model on top of the Kaldi speech recognition framework

sv_score_calibration. Score calibration for speaker verification

torch-xvectors-wav. Python

streaming-punctuator. Python

et-g2p. Grapheme to phoneme converter for Estonian

voxlingua107_sb. VoxLingua107 recipe for SpeechBrain

et-pocketsphinx-tutorial. Tutorial of Estonian speech recognition using PocketSphinx

pl-whisper-finetuner. Whisper finetuning with Pytorch Lightning

et-g2p-fst. FST-based rule-based grapheme-to-phoneme (and vice versa) converter for Estonian

voxceleb_weakly_supervised_segments. Speaker segmentations for the Voxceleb 1 and 2 datasets, generated using weakly supervised training

tsab. Transcribed Speech Archive Browser

kaldi-estonian-recipe. Recipe to train a general-purpose Estonian ASR system with all the bells and whistles (eventually)

simple_speech_llm. Train any LLM to support speech input

dictate.js. A small Javascript library for browser-based real-time speech recognition, which uses Recorderjs for audio capture, and a WebSocket connection to the Kaldi GStreamer server for speech recognition.

vosk-api. Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node

tts_preprocess_et. Preprocessing for Estonian text-to-speech

akurec-client. Java

kaldi-python. Python wrappers for Kaldi data

kaldi-align-server. Java

sinatra_speech_javaclient. Java

GST-Speech-API. Ruby

k6net6lke-benchmark. Eesti kõnetõlkeprojekti test-andmed ja skriptid

Automatic_Speech_Recognition. End-to-end Automatic Speech Recognition for Madarian and English in Tensorflow