A Kaldi recipe for training a hybrid DNN-HMM speech recognition model

Extract phone-level alignment and phonemic transcript from kaldi ali.*.gz files

Hyfforddi a defnyddio modelau adnabod lleferydd Cymraeg coqui-stt a KenLM // Train and use coqui-stt and KenLM based Welsh language speech recognition models.

Realtime internet radio stream speech recognition with Julius & ffmpeg

A kaldi recipe for modern standard arabic speech recognition

🎤 Voice Pipeline - Transforme voz em texto corrigido. Faster-Whisper + Gemma4, 100% offline.

Use kaldi pretrained nnet3 model to align individual sentences and get phone-level transcripts

Report of an end-to-end speech recognition task

This folder contains a solution for speech recognition and synthesis using the Microsoft Server Speech Platform Runtime (Version 11)

Speak right into your todo.txt with speedo. Set tags, priority, due dates directly from speech.

Resources for easily building ASR systems with Kaldi

A voice recorder and recording transmitter for Commbase

Open-set speech language identification https://arxiv.org/abs/2205.10397

Scripts para treino de modelos acústicos

A Kaldi-Recipe for Egyptian Arabic Speech Recognition

Adnabod lleferydd Cymraeg gyda Kaldi ASR | Welsh language speech recognition using Kaldi ASR

Provides easy access to the whisper.cpp application on snap-enabled OS distributions.

A voice recorder and recording transmitter for Commbase