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

An communication aid for people with dysarthria exclusively for Tamil language.

Scripts para treino de modelos acústicos

HHM-based Arabic ASR using Kaldi engine

Forced alignment of Nda‘ Nda’ a Cameroonian language

End-to-End Arabic ASR using DeepSpeech engine

Resources for easily building ASR systems with Kaldi

This is now the official location of the Kaldi project.

BurrMill core

Dockerfile for kaldi-gstreamer-server.

Setup scripts for LumenVox Containers

Generate automated German subtitles using one of the three implemented machine learning generated language model.

To evaluate OpenAI's Whisper library for transcribing audio into text

A collection of various BASH scripts organised into subcategories. Most of these scripts were developed as assignments for the university's Systems & Networks Administration course. Others were developed to handle routine day-to-day tasks.

Playing with kaldi, try make myown recipes.

AUR (Arch Linux User Repository) package for the Murmure desktop app (based on upstream released sources) — Mirror of https://aur.archlinux.org/packages/murmure

This is now the official location of the Kaldi project.

An Indian English ASR system based on Hidden Markov Models (HMM) has been designed using Kaldi(Povey et al., 2011).